Parallel GPU implementation of iterative PCA algorithms.
Andrecut, M
2009-11-01
Principal component analysis (PCA) is a key statistical technique for multivariate data analysis. For large data sets, the common approach to PCA computation is based on the standard NIPALS-PCA algorithm, which unfortunately suffers from loss of orthogonality, and therefore its applicability is usually limited to the estimation of the first few components. Here we present an algorithm based on Gram-Schmidt orthogonalization (called GS-PCA), which eliminates this shortcoming of NIPALS-PCA. Also, we discuss the GPU (Graphics Processing Unit) parallel implementation of both NIPALS-PCA and GS-PCA algorithms. The numerical results show that the GPU parallel optimized versions, based on CUBLAS (NVIDIA), are substantially faster (up to 12 times) than the CPU optimized versions based on CBLAS (GNU Scientific Library).
Parallel GPU implementation of PWR reactor burnup
International Nuclear Information System (INIS)
Heimlich, A.; Silva, F.C.; Martinez, A.S.
2016-01-01
Highlights: • Three GPU algorithms used to evaluate the burn-up in a PWR reactor. • Exhibit speed improvement exceeding 200 times over the sequential. • The C++ container is expansible to accept new nuclides chains. - Abstract: This paper surveys three methods, implemented for multi-core CPU and graphic processor unit (GPU), to evaluate the fuel burn-up in a pressurized light water nuclear reactor (PWR) using the solutions of a large system of coupled ordinary differential equations. The reactor physics simulation of a PWR reactor spends a long execution time with burnup calculations, so performance improvement using GPU can imply in better core design and thus extended fuel life cycle. The results of this study exhibit speed improvement exceeding 200 times over the sequential solver, within 1% accuracy.
Murni, Bustamam, A.; Ernastuti, Handhika, T.; Kerami, D.
2017-07-01
Calculation of the matrix-vector multiplication in the real-world problems often involves large matrix with arbitrary size. Therefore, parallelization is needed to speed up the calculation process that usually takes a long time. Graph partitioning techniques that have been discussed in the previous studies cannot be used to complete the parallelized calculation of matrix-vector multiplication with arbitrary size. This is due to the assumption of graph partitioning techniques that can only solve the square and symmetric matrix. Hypergraph partitioning techniques will overcome the shortcomings of the graph partitioning technique. This paper addresses the efficient parallelization of matrix-vector multiplication through hypergraph partitioning techniques using CUDA GPU-based parallel computing. CUDA (compute unified device architecture) is a parallel computing platform and programming model that was created by NVIDIA and implemented by the GPU (graphics processing unit).
Parallel implementation of DNA sequences matching algorithms using PWM on GPU architecture.
Sharma, Rahul; Gupta, Nitin; Narang, Vipin; Mittal, Ankush
2011-01-01
Positional Weight Matrices (PWMs) are widely used in representation and detection of Transcription Factor Of Binding Sites (TFBSs) on DNA. We implement online PWM search algorithm over parallel architecture. A large PWM data can be processed on Graphic Processing Unit (GPU) systems in parallel which can help in matching sequences at a faster rate. Our method employs extensive usage of highly multithreaded architecture and shared memory of multi-cored GPU. An efficient use of shared memory is required to optimise parallel reduction in CUDA. Our optimised method has a speedup of 230-280x over linear implementation on GPU named GeForce GTX 280.
A GPU-paralleled implementation of an enhanced face recognition algorithm
Chen, Hao; Liu, Xiyang; Shao, Shuai; Zan, Jiguo
2013-03-01
Face recognition algorithm based on compressed sensing and sparse representation is hotly argued in these years. The scheme of this algorithm increases recognition rate as well as anti-noise capability. However, the computational cost is expensive and has become a main restricting factor for real world applications. In this paper, we introduce a GPU-accelerated hybrid variant of face recognition algorithm named parallel face recognition algorithm (pFRA). We describe here how to carry out parallel optimization design to take full advantage of many-core structure of a GPU. The pFRA is tested and compared with several other implementations under different data sample size. Finally, Our pFRA, implemented with NVIDIA GPU and Computer Unified Device Architecture (CUDA) programming model, achieves a significant speedup over the traditional CPU implementations.
Efficient parallel implementation of active appearance model fitting algorithm on GPU.
Wang, Jinwei; Ma, Xirong; Zhu, Yuanping; Sun, Jizhou
2014-01-01
The active appearance model (AAM) is one of the most powerful model-based object detecting and tracking methods which has been widely used in various situations. However, the high-dimensional texture representation causes very time-consuming computations, which makes the AAM difficult to apply to real-time systems. The emergence of modern graphics processing units (GPUs) that feature a many-core, fine-grained parallel architecture provides new and promising solutions to overcome the computational challenge. In this paper, we propose an efficient parallel implementation of the AAM fitting algorithm on GPUs. Our design idea is fine grain parallelism in which we distribute the texture data of the AAM, in pixels, to thousands of parallel GPU threads for processing, which makes the algorithm fit better into the GPU architecture. We implement our algorithm using the compute unified device architecture (CUDA) on the Nvidia's GTX 650 GPU, which has the latest Kepler architecture. To compare the performance of our algorithm with different data sizes, we built sixteen face AAM models of different dimensional textures. The experiment results show that our parallel AAM fitting algorithm can achieve real-time performance for videos even on very high-dimensional textures.
Efficient Parallel Implementation of Active Appearance Model Fitting Algorithm on GPU
Directory of Open Access Journals (Sweden)
Jinwei Wang
2014-01-01
Full Text Available The active appearance model (AAM is one of the most powerful model-based object detecting and tracking methods which has been widely used in various situations. However, the high-dimensional texture representation causes very time-consuming computations, which makes the AAM difficult to apply to real-time systems. The emergence of modern graphics processing units (GPUs that feature a many-core, fine-grained parallel architecture provides new and promising solutions to overcome the computational challenge. In this paper, we propose an efficient parallel implementation of the AAM fitting algorithm on GPUs. Our design idea is fine grain parallelism in which we distribute the texture data of the AAM, in pixels, to thousands of parallel GPU threads for processing, which makes the algorithm fit better into the GPU architecture. We implement our algorithm using the compute unified device architecture (CUDA on the Nvidia’s GTX 650 GPU, which has the latest Kepler architecture. To compare the performance of our algorithm with different data sizes, we built sixteen face AAM models of different dimensional textures. The experiment results show that our parallel AAM fitting algorithm can achieve real-time performance for videos even on very high-dimensional textures.
Implementation of GPU parallel equilibrium reconstruction for plasma control in EAST
Energy Technology Data Exchange (ETDEWEB)
Huang, Yao, E-mail: yaohuang@ipp.ac.cn [Institute of Plasma Physics, Chinese Academy of Sciences, Hefei (China); Xiao, B.J. [Institute of Plasma Physics, Chinese Academy of Sciences, Hefei (China); School of Nuclear Science & Technology, University of Science & Technology of China (China); Luo, Z.P.; Yuan, Q.P.; Pei, X.F. [Institute of Plasma Physics, Chinese Academy of Sciences, Hefei (China); Yue, X.N. [School of Nuclear Science & Technology, University of Science & Technology of China (China)
2016-11-15
Highlights: • We described parallel equilibrium reconstruction code P-EFIT running on GPU was integrated with EAST plasma control system. • Compared with RT-EFIT used in EAST, P-EFIT has better spatial resolution and full algorithm of EFIT per iteration. • With the data interface through RFM, 65 × 65 spatial grids P-EFIT can satisfy the accuracy and time feasibility requirements for plasma control. • Successful control using ISOFLUX/P-EFIT was established in the dedicated experiment during the EAST 2014 campaign. • This work is a stepping-stone towards versatile ISOFLUX/P-EFIT control, such as real-time equilibrium reconstruction with more diagnostics. - Abstract: Implementation of P-EFIT code for plasma control in EAST is described. P-EFIT is based on the EFIT framework, but built with the CUDA™ architecture to take advantage of massively parallel Graphical Processing Unit (GPU) cores to significantly accelerate the computation. 65 × 65 grid size P-EFIT can complete one reconstruction iteration in 300 μs, with one iteration strategy, it can satisfy the needs of real-time plasma shape control. Data interface between P-EFIT and PCS is realized and developed by transferring data through RFM. First application of P-EFIT to discharge control in EAST is described.
An improved non-uniformity correction algorithm and its GPU parallel implementation
Cheng, Kuanhong; Zhou, Huixin; Qin, Hanlin; Zhao, Dong; Qian, Kun; Rong, Shenghui
2018-05-01
The performance of SLP-THP based non-uniformity correction algorithm is seriously affected by the result of SLP filter, which always leads to image blurring and ghosting artifacts. To address this problem, an improved SLP-THP based non-uniformity correction method with curvature constraint was proposed. Here we put forward a new way to estimate spatial low frequency component. First, the details and contours of input image were obtained respectively by minimizing local Gaussian curvature and mean curvature of image surface. Then, the guided filter was utilized to combine these two parts together to get the estimate of spatial low frequency component. Finally, we brought this SLP component into SLP-THP method to achieve non-uniformity correction. The performance of proposed algorithm was verified by several real and simulated infrared image sequences. The experimental results indicated that the proposed algorithm can reduce the non-uniformity without detail losing. After that, a GPU based parallel implementation that runs 150 times faster than CPU was presented, which showed the proposed algorithm has great potential for real time application.
Bayer image parallel decoding based on GPU
Hu, Rihui; Xu, Zhiyong; Wei, Yuxing; Sun, Shaohua
2012-11-01
In the photoelectrical tracking system, Bayer image is decompressed in traditional method, which is CPU-based. However, it is too slow when the images become large, for example, 2K×2K×16bit. In order to accelerate the Bayer image decoding, this paper introduces a parallel speedup method for NVIDA's Graphics Processor Unit (GPU) which supports CUDA architecture. The decoding procedure can be divided into three parts: the first is serial part, the second is task-parallelism part, and the last is data-parallelism part including inverse quantization, inverse discrete wavelet transform (IDWT) as well as image post-processing part. For reducing the execution time, the task-parallelism part is optimized by OpenMP techniques. The data-parallelism part could advance its efficiency through executing on the GPU as CUDA parallel program. The optimization techniques include instruction optimization, shared memory access optimization, the access memory coalesced optimization and texture memory optimization. In particular, it can significantly speed up the IDWT by rewriting the 2D (Tow-dimensional) serial IDWT into 1D parallel IDWT. Through experimenting with 1K×1K×16bit Bayer image, data-parallelism part is 10 more times faster than CPU-based implementation. Finally, a CPU+GPU heterogeneous decompression system was designed. The experimental result shows that it could achieve 3 to 5 times speed increase compared to the CPU serial method.
Parallel generation of architecture on the GPU
Steinberger, Markus
2014-05-01
In this paper, we present a novel approach for the parallel evaluation of procedural shape grammars on the graphics processing unit (GPU). Unlike previous approaches that are either limited in the kind of shapes they allow, the amount of parallelism they can take advantage of, or both, our method supports state of the art procedural modeling including stochasticity and context-sensitivity. To increase parallelism, we explicitly express independence in the grammar, reduce inter-rule dependencies required for context-sensitive evaluation, and introduce intra-rule parallelism. Our rule scheduling scheme avoids unnecessary back and forth between CPU and GPU and reduces round trips to slow global memory by dynamically grouping rules in on-chip shared memory. Our GPU shape grammar implementation is multiple orders of magnitude faster than the standard in CPU-based rule evaluation, while offering equal expressive power. In comparison to the state of the art in GPU shape grammar derivation, our approach is nearly 50 times faster, while adding support for geometric context-sensitivity. © 2014 The Author(s) Computer Graphics Forum © 2014 The Eurographics Association and John Wiley & Sons Ltd. Published by John Wiley & Sons Ltd.
GPU Parallel Bundle Block Adjustment
Directory of Open Access Journals (Sweden)
ZHENG Maoteng
2017-09-01
Full Text Available To deal with massive data in photogrammetry, we introduce the GPU parallel computing technology. The preconditioned conjugate gradient and inexact Newton method are also applied to decrease the iteration times while solving the normal equation. A brand new workflow of bundle adjustment is developed to utilize GPU parallel computing technology. Our method can avoid the storage and inversion of the big normal matrix, and compute the normal matrix in real time. The proposed method can not only largely decrease the memory requirement of normal matrix, but also largely improve the efficiency of bundle adjustment. It also achieves the same accuracy as the conventional method. Preliminary experiment results show that the bundle adjustment of a dataset with about 4500 images and 9 million image points can be done in only 1.5 minutes while achieving sub-pixel accuracy.
GPU: the biggest key processor for AI and parallel processing
Baji, Toru
2017-07-01
Two types of processors exist in the market. One is the conventional CPU and the other is Graphic Processor Unit (GPU). Typical CPU is composed of 1 to 8 cores while GPU has thousands of cores. CPU is good for sequential processing, while GPU is good to accelerate software with heavy parallel executions. GPU was initially dedicated for 3D graphics. However from 2006, when GPU started to apply general-purpose cores, it was noticed that this architecture can be used as a general purpose massive-parallel processor. NVIDIA developed a software framework Compute Unified Device Architecture (CUDA) that make it possible to easily program the GPU for these application. With CUDA, GPU started to be used in workstations and supercomputers widely. Recently two key technologies are highlighted in the industry. The Artificial Intelligence (AI) and Autonomous Driving Cars. AI requires a massive parallel operation to train many-layers of neural networks. With CPU alone, it was impossible to finish the training in a practical time. The latest multi-GPU system with P100 makes it possible to finish the training in a few hours. For the autonomous driving cars, TOPS class of performance is required to implement perception, localization, path planning processing and again SoC with integrated GPU will play a key role there. In this paper, the evolution of the GPU which is one of the biggest commercial devices requiring state-of-the-art fabrication technology will be introduced. Also overview of the GPU demanding key application like the ones described above will be introduced.
Xu, Jincheng; Liu, Wei; Wang, Jin; Liu, Linong; Zhang, Jianfeng
2018-02-01
De-absorption pre-stack time migration (QPSTM) compensates for the absorption and dispersion of seismic waves by introducing an effective Q parameter, thereby making it an effective tool for 3D, high-resolution imaging of seismic data. Although the optimal aperture obtained via stationary-phase migration reduces the computational cost of 3D QPSTM and yields 3D stationary-phase QPSTM, the associated computational efficiency is still the main problem in the processing of 3D, high-resolution images for real large-scale seismic data. In the current paper, we proposed a division method for large-scale, 3D seismic data to optimize the performance of stationary-phase QPSTM on clusters of graphics processing units (GPU). Then, we designed an imaging point parallel strategy to achieve an optimal parallel computing performance. Afterward, we adopted an asynchronous double buffering scheme for multi-stream to perform the GPU/CPU parallel computing. Moreover, several key optimization strategies of computation and storage based on the compute unified device architecture (CUDA) were adopted to accelerate the 3D stationary-phase QPSTM algorithm. Compared with the initial GPU code, the implementation of the key optimization steps, including thread optimization, shared memory optimization, register optimization and special function units (SFU), greatly improved the efficiency. A numerical example employing real large-scale, 3D seismic data showed that our scheme is nearly 80 times faster than the CPU-QPSTM algorithm. Our GPU/CPU heterogeneous parallel computing framework significant reduces the computational cost and facilitates 3D high-resolution imaging for large-scale seismic data.
Parallelization and checkpointing of GPU applications through program transformation
Energy Technology Data Exchange (ETDEWEB)
Solano-Quinde, Lizandro Damian [Iowa State Univ., Ames, IA (United States)
2012-01-01
GPUs have emerged as a powerful tool for accelerating general-purpose applications. The availability of programming languages that makes writing general-purpose applications for running on GPUs tractable have consolidated GPUs as an alternative for accelerating general purpose applications. Among the areas that have benefited from GPU acceleration are: signal and image processing, computational fluid dynamics, quantum chemistry, and, in general, the High Performance Computing (HPC) Industry. In order to continue to exploit higher levels of parallelism with GPUs, multi-GPU systems are gaining popularity. In this context, single-GPU applications are parallelized for running in multi-GPU systems. Furthermore, multi-GPU systems help to solve the GPU memory limitation for applications with large application memory footprint. Parallelizing single-GPU applications has been approached by libraries that distribute the workload at runtime, however, they impose execution overhead and are not portable. On the other hand, on traditional CPU systems, parallelization has been approached through application transformation at pre-compile time, which enhances the application to distribute the workload at application level and does not have the issues of library-based approaches. Hence, a parallelization scheme for GPU systems based on application transformation is needed. Like any computing engine of today, reliability is also a concern in GPUs. GPUs are vulnerable to transient and permanent failures. Current checkpoint/restart techniques are not suitable for systems with GPUs. Checkpointing for GPU systems present new and interesting challenges, primarily due to the natural differences imposed by the hardware design, the memory subsystem architecture, the massive number of threads, and the limited amount of synchronization among threads. Therefore, a checkpoint/restart technique suitable for GPU systems is needed. The goal of this work is to exploit higher levels of parallelism and
cellGPU: Massively parallel simulations of dynamic vertex models
Sussman, Daniel M.
2017-10-01
Vertex models represent confluent tissue by polygonal or polyhedral tilings of space, with the individual cells interacting via force laws that depend on both the geometry of the cells and the topology of the tessellation. This dependence on the connectivity of the cellular network introduces several complications to performing molecular-dynamics-like simulations of vertex models, and in particular makes parallelizing the simulations difficult. cellGPU addresses this difficulty and lays the foundation for massively parallelized, GPU-based simulations of these models. This article discusses its implementation for a pair of two-dimensional models, and compares the typical performance that can be expected between running cellGPU entirely on the CPU versus its performance when running on a range of commercial and server-grade graphics cards. By implementing the calculation of topological changes and forces on cells in a highly parallelizable fashion, cellGPU enables researchers to simulate time- and length-scales previously inaccessible via existing single-threaded CPU implementations. Program Files doi:http://dx.doi.org/10.17632/6j2cj29t3r.1 Licensing provisions: MIT Programming language: CUDA/C++ Nature of problem: Simulations of off-lattice "vertex models" of cells, in which the interaction forces depend on both the geometry and the topology of the cellular aggregate. Solution method: Highly parallelized GPU-accelerated dynamical simulations in which the force calculations and the topological features can be handled on either the CPU or GPU. Additional comments: The code is hosted at https://gitlab.com/dmsussman/cellGPU, with documentation additionally maintained at http://dmsussman.gitlab.io/cellGPUdocumentation
Parallel fuzzy connected image segmentation on GPU.
Zhuge, Ying; Cao, Yong; Udupa, Jayaram K; Miller, Robert W
2011-07-01
Image segmentation techniques using fuzzy connectedness (FC) principles have shown their effectiveness in segmenting a variety of objects in several large applications. However, one challenge in these algorithms has been their excessive computational requirements when processing large image datasets. Nowadays, commodity graphics hardware provides a highly parallel computing environment. In this paper, the authors present a parallel fuzzy connected image segmentation algorithm implementation on NVIDIA's compute unified device Architecture (CUDA) platform for segmenting medical image data sets. In the FC algorithm, there are two major computational tasks: (i) computing the fuzzy affinity relations and (ii) computing the fuzzy connectedness relations. These two tasks are implemented as CUDA kernels and executed on GPU. A dramatic improvement in speed for both tasks is achieved as a result. Our experiments based on three data sets of small, medium, and large data size demonstrate the efficiency of the parallel algorithm, which achieves a speed-up factor of 24.4x, 18.1x, and 10.3x, correspondingly, for the three data sets on the NVIDIA Tesla C1060 over the implementation of the algorithm on CPU, and takes 0.25, 0.72, and 15.04 s, correspondingly, for the three data sets. The authors developed a parallel algorithm of the widely used fuzzy connected image segmentation method on the NVIDIA GPUs, which are far more cost- and speed-effective than both cluster of workstations and multiprocessing systems. A near-interactive speed of segmentation has been achieved, even for the large data set.
Parallel Optimization of 3D Cardiac Electrophysiological Model Using GPU
Directory of Open Access Journals (Sweden)
Yong Xia
2015-01-01
Full Text Available Large-scale 3D virtual heart model simulations are highly demanding in computational resources. This imposes a big challenge to the traditional computation resources based on CPU environment, which already cannot meet the requirement of the whole computation demands or are not easily available due to expensive costs. GPU as a parallel computing environment therefore provides an alternative to solve the large-scale computational problems of whole heart modeling. In this study, using a 3D sheep atrial model as a test bed, we developed a GPU-based simulation algorithm to simulate the conduction of electrical excitation waves in the 3D atria. In the GPU algorithm, a multicellular tissue model was split into two components: one is the single cell model (ordinary differential equation and the other is the diffusion term of the monodomain model (partial differential equation. Such a decoupling enabled realization of the GPU parallel algorithm. Furthermore, several optimization strategies were proposed based on the features of the virtual heart model, which enabled a 200-fold speedup as compared to a CPU implementation. In conclusion, an optimized GPU algorithm has been developed that provides an economic and powerful platform for 3D whole heart simulations.
GPU-based Parallel Application Design for Emerging Mobile Devices
Gupta, Kshitij
A revolution is underway in the computing world that is causing a fundamental paradigm shift in device capabilities and form-factor, with a move from well-established legacy desktop/laptop computers to mobile devices in varying sizes and shapes. Amongst all the tasks these devices must support, graphics has emerged as the 'killer app' for providing a fluid user interface and high-fidelity game rendering, effectively making the graphics processor (GPU) one of the key components in (present and future) mobile systems. By utilizing the GPU as a general-purpose parallel processor, this dissertation explores the GPU computing design space from an applications standpoint, in the mobile context, by focusing on key challenges presented by these devices---limited compute, memory bandwidth, and stringent power consumption requirements---while improving the overall application efficiency of the increasingly important speech recognition workload for mobile user interaction. We broadly partition trends in GPU computing into four major categories. We analyze hardware and programming model limitations in current-generation GPUs and detail an alternate programming style called Persistent Threads, identify four use case patterns, and propose minimal modifications that would be required for extending native support. We show how by manually extracting data locality and altering the speech recognition pipeline, we are able to achieve significant savings in memory bandwidth while simultaneously reducing the compute burden on GPU-like parallel processors. As we foresee GPU computing to evolve from its current 'co-processor' model into an independent 'applications processor' that is capable of executing complex work independently, we create an alternate application framework that enables the GPU to handle all control-flow dependencies autonomously at run-time while minimizing host involvement to just issuing commands, that facilitates an efficient application implementation. Finally, as
Parallel hyperbolic PDE simulation on clusters: Cell versus GPU
Rostrup, Scott; De Sterck, Hans
2010-12-01
:http://cpc.cs.qub.ac.uk/summaries/AEGY_v1_0.html Program obtainable from: CPC Program Library, Queen's University, Belfast, N. Ireland Licensing provisions: GPL v3 No. of lines in distributed program, including test data, etc.: 59 168 No. of bytes in distributed program, including test data, etc.: 453 409 Distribution format: tar.gz Programming language: C, CUDA Computer: Parallel Computing Clusters. Individual compute nodes may consist of x86 CPU, Cell processor, or x86 CPU with attached NVIDIA GPU accelerator. Operating system: Linux Has the code been vectorised or parallelized?: Yes. Tested on 1-128 x86 CPU cores, 1-32 Cell Processors, and 1-32 NVIDIA GPUs. RAM: Tested on Problems requiring up to 4 GB per compute node. Classification: 12 External routines: MPI, CUDA, IBM Cell SDK Nature of problem: MPI-parallel simulation of Shallow Water equations using high-resolution 2D hyperbolic equation solver on regular Cartesian grids for x86 CPU, Cell Processor, and NVIDIA GPU using CUDA. Solution method: SWsolver provides 3 implementations of a high-resolution 2D Shallow Water equation solver on regular Cartesian grids, for CPU, Cell Processor, and NVIDIA GPU. Each implementation uses MPI to divide work across a parallel computing cluster. Additional comments: Sub-program numdiff is used for the test run.
Parallel Computer System for 3D Visualization Stereo on GPU
Al-Oraiqat, Anas M.; Zori, Sergii A.
2018-03-01
This paper proposes the organization of a parallel computer system based on Graphic Processors Unit (GPU) for 3D stereo image synthesis. The development is based on the modified ray tracing method developed by the authors for fast search of tracing rays intersections with scene objects. The system allows significant increase in the productivity for the 3D stereo synthesis of photorealistic quality. The generalized procedure of 3D stereo image synthesis on the Graphics Processing Unit/Graphics Processing Clusters (GPU/GPC) is proposed. The efficiency of the proposed solutions by GPU implementation is compared with single-threaded and multithreaded implementations on the CPU. The achieved average acceleration in multi-thread implementation on the test GPU and CPU is about 7.5 and 1.6 times, respectively. Studying the influence of choosing the size and configuration of the computational Compute Unified Device Archi-tecture (CUDA) network on the computational speed shows the importance of their correct selection. The obtained experimental estimations can be significantly improved by new GPUs with a large number of processing cores and multiprocessors, as well as optimized configuration of the computing CUDA network.
GASPRNG: GPU accelerated scalable parallel random number generator library
Gao, Shuang; Peterson, Gregory D.
2013-04-01
Graphics processors represent a promising technology for accelerating computational science applications. Many computational science applications require fast and scalable random number generation with good statistical properties, so they use the Scalable Parallel Random Number Generators library (SPRNG). We present the GPU Accelerated SPRNG library (GASPRNG) to accelerate SPRNG in GPU-based high performance computing systems. GASPRNG includes code for a host CPU and CUDA code for execution on NVIDIA graphics processing units (GPUs) along with a programming interface to support various usage models for pseudorandom numbers and computational science applications executing on the CPU, GPU, or both. This paper describes the implementation approach used to produce high performance and also describes how to use the programming interface. The programming interface allows a user to be able to use GASPRNG the same way as SPRNG on traditional serial or parallel computers as well as to develop tightly coupled programs executing primarily on the GPU. We also describe how to install GASPRNG and use it. To help illustrate linking with GASPRNG, various demonstration codes are included for the different usage models. GASPRNG on a single GPU shows up to 280x speedup over SPRNG on a single CPU core and is able to scale for larger systems in the same manner as SPRNG. Because GASPRNG generates identical streams of pseudorandom numbers as SPRNG, users can be confident about the quality of GASPRNG for scalable computational science applications. Catalogue identifier: AEOI_v1_0 Program summary URL:http://cpc.cs.qub.ac.uk/summaries/AEOI_v1_0.html Program obtainable from: CPC Program Library, Queen’s University, Belfast, N. Ireland Licensing provisions: UTK license. No. of lines in distributed program, including test data, etc.: 167900 No. of bytes in distributed program, including test data, etc.: 1422058 Distribution format: tar.gz Programming language: C and CUDA. Computer: Any PC or
Overview of implementation of DARPA GPU program in SAIC
Braunreiter, Dennis; Furtek, Jeremy; Chen, Hai-Wen; Healy, Dennis
2008-04-01
This paper reviews the implementation of DARPA MTO STAP-BOY program for both Phase I and II conducted at Science Applications International Corporation (SAIC). The STAP-BOY program conducts fast covariance factorization and tuning techniques for space-time adaptive process (STAP) Algorithm Implementation on Graphics Processor unit (GPU) Architectures for Embedded Systems. The first part of our presentation on the DARPA STAP-BOY program will focus on GPU implementation and algorithm innovations for a prototype radar STAP algorithm. The STAP algorithm will be implemented on the GPU, using stream programming (from companies such as PeakStream, ATI Technologies' CTM, and NVIDIA) and traditional graphics APIs. This algorithm will include fast range adaptive STAP weight updates and beamforming applications, each of which has been modified to exploit the parallel nature of graphics architectures.
A multi-GPU implementation of a D2Q37 lattice Boltzmann code
Biferale, L.; Mantovani, F.; Pivanti, M.; Pozzati, F.; Sbragaglia, M.; Scagliarini, Andrea; Schifano, S.F.; Toschi, F.; Tripiccione, R.; Wyrzykowski, R.; Dongarra, J.; Karczewski, K.; Wasniewski, J.
2012-01-01
We describe a parallel implementation of a compressible Lattice Boltzmann code on a multi-GPU cluster based on Nvidia Fermi processors. We analyze how to optimize the algorithm for GP-GPU architectures, describe the implementation choices that we have adopted and compare our performance results with
GPU-Accelerated Parallel FDTD on Distributed Heterogeneous Platform
Directory of Open Access Journals (Sweden)
Ronglin Jiang
2014-01-01
Full Text Available This paper introduces a (finite difference time domain FDTD code written in Fortran and CUDA for realistic electromagnetic calculations with parallelization methods of Message Passing Interface (MPI and Open Multiprocessing (OpenMP. Since both Central Processing Unit (CPU and Graphics Processing Unit (GPU resources are utilized, a faster execution speed can be reached compared to a traditional pure GPU code. In our experiments, 64 NVIDIA TESLA K20m GPUs and 64 INTEL XEON E5-2670 CPUs are used to carry out the pure CPU, pure GPU, and CPU + GPU tests. Relative to the pure CPU calculations for the same problems, the speedup ratio achieved by CPU + GPU calculations is around 14. Compared to the pure GPU calculations for the same problems, the CPU + GPU calculations have 7.6%–13.2% performance improvement. Because of the small memory size of GPUs, the FDTD problem size is usually very small. However, this code can enlarge the maximum problem size by 25% without reducing the performance of traditional pure GPU code. Finally, using this code, a microstrip antenna array with 16×18 elements is calculated and the radiation patterns are compared with the ones of MoM. Results show that there is a well agreement between them.
Work-Efficient Parallel Skyline Computation for the GPU
DEFF Research Database (Denmark)
Bøgh, Kenneth Sejdenfaden; Chester, Sean; Assent, Ira
2015-01-01
offers the potential for parallelizing skyline computation across thousands of cores. However, attempts to port skyline algorithms to the GPU have prioritized throughput and failed to outperform sequential algorithms. In this paper, we introduce a new skyline algorithm, designed for the GPU, that uses...... a global, static partitioning scheme. With the partitioning, we can permit controlled branching to exploit transitive relationships and avoid most point-to-point comparisons. The result is a non-traditional GPU algorithm, SkyAlign, that prioritizes work-effciency and respectable throughput, rather than...
The development of GPU-based parallel PRNG for Monte Carlo applications in CUDA Fortran
Directory of Open Access Journals (Sweden)
Hamed Kargaran
2016-04-01
Full Text Available The implementation of Monte Carlo simulation on the CUDA Fortran requires a fast random number generation with good statistical properties on GPU. In this study, a GPU-based parallel pseudo random number generator (GPPRNG have been proposed to use in high performance computing systems. According to the type of GPU memory usage, GPU scheme is divided into two work modes including GLOBAL_MODE and SHARED_MODE. To generate parallel random numbers based on the independent sequence method, the combination of middle-square method and chaotic map along with the Xorshift PRNG have been employed. Implementation of our developed PPRNG on a single GPU showed a speedup of 150x and 470x (with respect to the speed of PRNG on a single CPU core for GLOBAL_MODE and SHARED_MODE, respectively. To evaluate the accuracy of our developed GPPRNG, its performance was compared to that of some other commercially available PPRNGs such as MATLAB, FORTRAN and Miller-Park algorithm through employing the specific standard tests. The results of this comparison showed that the developed GPPRNG in this study can be used as a fast and accurate tool for computational science applications.
The development of GPU-based parallel PRNG for Monte Carlo applications in CUDA Fortran
Energy Technology Data Exchange (ETDEWEB)
Kargaran, Hamed, E-mail: h-kargaran@sbu.ac.ir; Minuchehr, Abdolhamid; Zolfaghari, Ahmad [Department of nuclear engineering, Shahid Behesti University, Tehran, 1983969411 (Iran, Islamic Republic of)
2016-04-15
The implementation of Monte Carlo simulation on the CUDA Fortran requires a fast random number generation with good statistical properties on GPU. In this study, a GPU-based parallel pseudo random number generator (GPPRNG) have been proposed to use in high performance computing systems. According to the type of GPU memory usage, GPU scheme is divided into two work modes including GLOBAL-MODE and SHARED-MODE. To generate parallel random numbers based on the independent sequence method, the combination of middle-square method and chaotic map along with the Xorshift PRNG have been employed. Implementation of our developed PPRNG on a single GPU showed a speedup of 150x and 470x (with respect to the speed of PRNG on a single CPU core) for GLOBAL-MODE and SHARED-MODE, respectively. To evaluate the accuracy of our developed GPPRNG, its performance was compared to that of some other commercially available PPRNGs such as MATLAB, FORTRAN and Miller-Park algorithm through employing the specific standard tests. The results of this comparison showed that the developed GPPRNG in this study can be used as a fast and accurate tool for computational science applications.
Parallel fuzzy connected image segmentation on GPU
Zhuge, Ying; Cao, Yong; Udupa, Jayaram K.; Miller, Robert W.
2011-01-01
Purpose: Image segmentation techniques using fuzzy connectedness (FC) principles have shown their effectiveness in segmenting a variety of objects in several large applications. However, one challenge in these algorithms has been their excessive computational requirements when processing large image datasets. Nowadays, commodity graphics hardware provides a highly parallel computing environment. In this paper, the authors present a parallel fuzzy connected image segmentation algorithm impleme...
Parallel generation of architecture on the GPU
Steinberger, Markus; Kenzel, Michael; Kainz, Bernhard K.; Mü ller, Jö rg; Wonka, Peter; Schmalstieg, Dieter
2014-01-01
they can take advantage of, or both, our method supports state of the art procedural modeling including stochasticity and context-sensitivity. To increase parallelism, we explicitly express independence in the grammar, reduce inter-rule dependencies
GPU implementation of Bayesian neural network construction for data-intensive applications
International Nuclear Information System (INIS)
Perry, Michelle; Meyer-Baese, Anke; Prosper, Harrison B
2014-01-01
We describe a graphical processing unit (GPU) implementation of the Hybrid Markov Chain Monte Carlo (HMC) method for training Bayesian Neural Networks (BNN). Our implementation uses NVIDIA's parallel computing architecture, CUDA. We briefly review BNNs and the HMC method and we describe our implementations and give preliminary results.
2012-02-17
to be solved. Disclaimer: Reference herein to any specific commercial company , product, process, or service by trade name, trademark...data processing rather than data caching and control flow. To make use of this computational power, NVIDIA introduced a general purpose parallel...GPU implementations were run on an Intel Nehalem Xeon E5520 2.26GHz processor with an NVIDIA Tesla C2070 graphics card for varying numbers of
Directory of Open Access Journals (Sweden)
G Boroni
2017-03-01
Full Text Available Lattice Boltzmann Method (LBM has shown great potential in fluid simulations, but performance issues and difficulties to manage complex boundary conditions have hindered a wider application. The upcoming of Graphic Processing Units (GPU Computing offered a possible solution for the performance issue, and methods like the Immersed Boundary (IB algorithm proved to be a flexible solution to boundaries. Unfortunately, the implicit IB algorithm makes the LBM implementation in GPU a non-trivial task. This work presents a fully parallel GPU implementation of LBM in combination with IB. The fluid-boundary interaction is implemented via GPU kernels, using execution configurations and data structures specifically designed to accelerate each code execution. Simulations were validated against experimental and analytical data showing good agreement and improving the computational time. Substantial reductions of calculation rates were achieved, lowering down the required time to execute the same model in a CPU to about two magnitude orders.
Shen, Wenfeng; Wei, Daming; Xu, Weimin; Zhu, Xin; Yuan, Shizhong
2010-10-01
Biological computations like electrocardiological modelling and simulation usually require high-performance computing environments. This paper introduces an implementation of parallel computation for computer simulation of electrocardiograms (ECGs) in a personal computer environment with an Intel CPU of Core (TM) 2 Quad Q6600 and a GPU of Geforce 8800GT, with software support by OpenMP and CUDA. It was tested in three parallelization device setups: (a) a four-core CPU without a general-purpose GPU, (b) a general-purpose GPU plus 1 core of CPU, and (c) a four-core CPU plus a general-purpose GPU. To effectively take advantage of a multi-core CPU and a general-purpose GPU, an algorithm based on load-prediction dynamic scheduling was developed and applied to setting (c). In the simulation with 1600 time steps, the speedup of the parallel computation as compared to the serial computation was 3.9 in setting (a), 16.8 in setting (b), and 20.0 in setting (c). This study demonstrates that a current PC with a multi-core CPU and a general-purpose GPU provides a good environment for parallel computations in biological modelling and simulation studies. Copyright 2010 Elsevier Ireland Ltd. All rights reserved.
Parallelized Local Volatility Estimation Using GP-GPU Hardware Acceleration
Douglas, Craig C.
2010-01-01
We introduce an inverse problem for the local volatility model in option pricing. We solve the problem using the Levenberg-Marquardt algorithm and use the notion of the Fréchet derivative when calculating the Jacobian matrix. We analyze the existence of the Fréchet derivative and its numerical computation. To reduce the computational time of the inverse problem, a GP-GPU environment is considered for parallel computation. Numerical results confirm the validity and efficiency of the proposed method. ©2010 IEEE.
Directory of Open Access Journals (Sweden)
M. Huang
2015-09-01
Full Text Available The planetary boundary layer (PBL is the lowest part of the atmosphere and where its character is directly affected by its contact with the underlying planetary surface. The PBL is responsible for vertical sub-grid-scale fluxes due to eddy transport in the whole atmospheric column. It determines the flux profiles within the well-mixed boundary layer and the more stable layer above. It thus provides an evolutionary model of atmospheric temperature, moisture (including clouds, and horizontal momentum in the entire atmospheric column. For such purposes, several PBL models have been proposed and employed in the weather research and forecasting (WRF model of which the Yonsei University (YSU scheme is one. To expedite weather research and prediction, we have put tremendous effort into developing an accelerated implementation of the entire WRF model using graphics processing unit (GPU massive parallel computing architecture whilst maintaining its accuracy as compared to its central processing unit (CPU-based implementation. This paper presents our efficient GPU-based design on a WRF YSU PBL scheme. Using one NVIDIA Tesla K40 GPU, the GPU-based YSU PBL scheme achieves a speedup of 193× with respect to its CPU counterpart running on one CPU core, whereas the speedup for one CPU socket (4 cores with respect to 1 CPU core is only 3.5×. We can even boost the speedup to 360× with respect to 1 CPU core as two K40 GPUs are applied.
Implementation of collisions on GPU architecture in the Vorpal code
Leddy, Jarrod; Averkin, Sergey; Cowan, Ben; Sides, Scott; Werner, Greg; Cary, John
2017-10-01
The Vorpal code contains a variety of collision operators allowing for the simulation of plasmas containing multiple charge species interacting with neutrals, background gas, and EM fields. These existing algorithms have been improved and reimplemented to take advantage of the massive parallelization allowed by GPU architecture. The use of GPUs is most effective when algorithms are single-instruction multiple-data, so particle collisions are an ideal candidate for this parallelization technique due to their nature as a series of independent processes with the same underlying operation. This refactoring required data memory reorganization and careful consideration of device/host data allocation to minimize memory access and data communication per operation. Successful implementation has resulted in an order of magnitude increase in simulation speed for a test-case involving multiple binary collisions using the null collision method. Work supported by DARPA under contract W31P4Q-16-C-0009.
Cucheb: A GPU implementation of the filtered Lanczos procedure
Aurentz, Jared L.; Kalantzis, Vassilis; Saad, Yousef
2017-11-01
This paper describes the software package Cucheb, a GPU implementation of the filtered Lanczos procedure for the solution of large sparse symmetric eigenvalue problems. The filtered Lanczos procedure uses a carefully chosen polynomial spectral transformation to accelerate convergence of the Lanczos method when computing eigenvalues within a desired interval. This method has proven particularly effective for eigenvalue problems that arise in electronic structure calculations and density functional theory. We compare our implementation against an equivalent CPU implementation and show that using the GPU can reduce the computation time by more than a factor of 10. Program Summary Program title: Cucheb Program Files doi:http://dx.doi.org/10.17632/rjr9tzchmh.1 Licensing provisions: MIT Programming language: CUDA C/C++ Nature of problem: Electronic structure calculations require the computation of all eigenvalue-eigenvector pairs of a symmetric matrix that lie inside a user-defined real interval. Solution method: To compute all the eigenvalues within a given interval a polynomial spectral transformation is constructed that maps the desired eigenvalues of the original matrix to the exterior of the spectrum of the transformed matrix. The Lanczos method is then used to compute the desired eigenvectors of the transformed matrix, which are then used to recover the desired eigenvalues of the original matrix. The bulk of the operations are executed in parallel using a graphics processing unit (GPU). Runtime: Variable, depending on the number of eigenvalues sought and the size and sparsity of the matrix. Additional comments: Cucheb is compatible with CUDA Toolkit v7.0 or greater.
The performances of R GPU implementations of the GMRES method
Directory of Open Access Journals (Sweden)
Bogdan Oancea
2018-03-01
Full Text Available Although the performance of commodity computers has improved drastically with the introduction of multicore processors and GPU computing, the standard R distribution is still based on single-threaded model of computation, using only a small fraction of the computational power available now for most desktops and laptops. Modern statistical software packages rely on high performance implementations of the linear algebra routines there are at the core of several important leading edge statistical methods. In this paper we present a GPU implementation of the GMRES iterative method for solving linear systems. We compare the performance of this implementation with a pure single threaded version of the CPU. We also investigate the performance of our implementation using different GPU packages available now for R such as gmatrix, gputools or gpuR which are based on CUDA or OpenCL frameworks.
A Highly Parallel and Scalable Motion Estimation Algorithm with GPU for HEVC
Directory of Open Access Journals (Sweden)
Yun-gang Xue
2017-01-01
Full Text Available We propose a highly parallel and scalable motion estimation algorithm, named multilevel resolution motion estimation (MLRME for short, by combining the advantages of local full search and downsampling. By subsampling a video frame, a large amount of computation is saved. While using the local full-search method, it can exploit massive parallelism and make full use of the powerful modern many-core accelerators, such as GPU and Intel Xeon Phi. We implanted the proposed MLRME into HM12.0, and the experimental results showed that the encoding quality of the MLRME method is close to that of the fast motion estimation in HEVC, which declines by less than 1.5%. We also implemented the MLRME with CUDA, which obtained 30–60x speed-up compared to the serial algorithm on single CPU. Specifically, the parallel implementation of MLRME on a GTX 460 GPU can meet the real-time coding requirement with about 25 fps for the 2560×1600 video format, while, for 832×480, the performance is more than 100 fps.
Fast parallel tandem mass spectral library searching using GPU hardware acceleration.
Baumgardner, Lydia Ashleigh; Shanmugam, Avinash Kumar; Lam, Henry; Eng, Jimmy K; Martin, Daniel B
2011-06-03
Mass spectrometry-based proteomics is a maturing discipline of biologic research that is experiencing substantial growth. Instrumentation has steadily improved over time with the advent of faster and more sensitive instruments collecting ever larger data files. Consequently, the computational process of matching a peptide fragmentation pattern to its sequence, traditionally accomplished by sequence database searching and more recently also by spectral library searching, has become a bottleneck in many mass spectrometry experiments. In both of these methods, the main rate-limiting step is the comparison of an acquired spectrum with all potential matches from a spectral library or sequence database. This is a highly parallelizable process because the core computational element can be represented as a simple but arithmetically intense multiplication of two vectors. In this paper, we present a proof of concept project taking advantage of the massively parallel computing available on graphics processing units (GPUs) to distribute and accelerate the process of spectral assignment using spectral library searching. This program, which we have named FastPaSS (for Fast Parallelized Spectral Searching), is implemented in CUDA (Compute Unified Device Architecture) from NVIDIA, which allows direct access to the processors in an NVIDIA GPU. Our efforts demonstrate the feasibility of GPU computing for spectral assignment, through implementation of the validated spectral searching algorithm SpectraST in the CUDA environment.
A CFD Heterogeneous Parallel Solver Based on Collaborating CPU and GPU
Lai, Jianqi; Tian, Zhengyu; Li, Hua; Pan, Sha
2018-03-01
Since Graphic Processing Unit (GPU) has a strong ability of floating-point computation and memory bandwidth for data parallelism, it has been widely used in the areas of common computing such as molecular dynamics (MD), computational fluid dynamics (CFD) and so on. The emergence of compute unified device architecture (CUDA), which reduces the complexity of compiling program, brings the great opportunities to CFD. There are three different modes for parallel solution of NS equations: parallel solver based on CPU, parallel solver based on GPU and heterogeneous parallel solver based on collaborating CPU and GPU. As we can see, GPUs are relatively rich in compute capacity but poor in memory capacity and the CPUs do the opposite. We need to make full use of the GPUs and CPUs, so a CFD heterogeneous parallel solver based on collaborating CPU and GPU has been established. Three cases are presented to analyse the solver’s computational accuracy and heterogeneous parallel efficiency. The numerical results agree well with experiment results, which demonstrate that the heterogeneous parallel solver has high computational precision. The speedup on a single GPU is more than 40 for laminar flow, it decreases for turbulent flow, but it still can reach more than 20. What’s more, the speedup increases as the grid size becomes larger.
GPU-based parallel algorithm for blind image restoration using midfrequency-based methods
Xie, Lang; Luo, Yi-han; Bao, Qi-liang
2013-08-01
GPU-based general-purpose computing is a new branch of modern parallel computing, so the study of parallel algorithms specially designed for GPU hardware architecture is of great significance. In order to solve the problem of high computational complexity and poor real-time performance in blind image restoration, the midfrequency-based algorithm for blind image restoration was analyzed and improved in this paper. Furthermore, a midfrequency-based filtering method is also used to restore the image hardly with any recursion or iteration. Combining the algorithm with data intensiveness, data parallel computing and GPU execution model of single instruction and multiple threads, a new parallel midfrequency-based algorithm for blind image restoration is proposed in this paper, which is suitable for stream computing of GPU. In this algorithm, the GPU is utilized to accelerate the estimation of class-G point spread functions and midfrequency-based filtering. Aiming at better management of the GPU threads, the threads in a grid are scheduled according to the decomposition of the filtering data in frequency domain after the optimization of data access and the communication between the host and the device. The kernel parallelism structure is determined by the decomposition of the filtering data to ensure the transmission rate to get around the memory bandwidth limitation. The results show that, with the new algorithm, the operational speed is significantly increased and the real-time performance of image restoration is effectively improved, especially for high-resolution images.
Development of parallel GPU based algorithms for problems in nuclear area
International Nuclear Information System (INIS)
Almeida, Adino Americo Heimlich
2009-01-01
Graphics Processing Units (GPU) are high performance co-processors intended, originally, to improve the use and quality of computer graphics applications. Since researchers and practitioners realized the potential of using GPU for general purpose, their application has been extended to other fields out of computer graphics scope. The main objective of this work is to evaluate the impact of using GPU in two typical problems of Nuclear area. The neutron transport simulation using Monte Carlo method and solve heat equation in a bi-dimensional domain by finite differences method. To achieve this, we develop parallel algorithms for GPU and CPU in the two problems described above. The comparison showed that the GPU-based approach is faster than the CPU in a computer with two quad core processors, without precision loss. (author)
The GPU implementation of micro - Doppler period estimation
Yang, Liyuan; Wang, Junling; Bi, Ran
2018-03-01
Aiming at the problem that the computational complexity and the deficiency of real-time of the wideband radar echo signal, a program is designed to improve the performance of real-time extraction of micro-motion feature in this paper based on the CPU-GPU heterogeneous parallel structure. Firstly, we discuss the principle of the micro-Doppler effect generated by the rolling of the scattering points on the orbiting satellite, analyses how to use Kalman filter to compensate the translational motion of tumbling satellite and how to use the joint time-frequency analysis and inverse Radon transform to extract the micro-motion features from the echo after compensation. Secondly, the advantages of GPU in terms of real-time processing and the working principle of CPU-GPU heterogeneous parallelism are analysed, and a program flow based on GPU to extract the micro-motion feature from the radar echo signal of rolling satellite is designed. At the end of the article the results of extraction are given to verify the correctness of the program and algorithm.
A New Parallel Approach for Accelerating the GPU-Based Execution of Edge Detection Algorithms.
Emrani, Zahra; Bateni, Soroosh; Rabbani, Hossein
2017-01-01
Real-time image processing is used in a wide variety of applications like those in medical care and industrial processes. This technique in medical care has the ability to display important patient information graphi graphically, which can supplement and help the treatment process. Medical decisions made based on real-time images are more accurate and reliable. According to the recent researches, graphic processing unit (GPU) programming is a useful method for improving the speed and quality of medical image processing and is one of the ways of real-time image processing. Edge detection is an early stage in most of the image processing methods for the extraction of features and object segments from a raw image. The Canny method, Sobel and Prewitt filters, and the Roberts' Cross technique are some examples of edge detection algorithms that are widely used in image processing and machine vision. In this work, these algorithms are implemented using the Compute Unified Device Architecture (CUDA), Open Source Computer Vision (OpenCV), and Matrix Laboratory (MATLAB) platforms. An existing parallel method for Canny approach has been modified further to run in a fully parallel manner. This has been achieved by replacing the breadth- first search procedure with a parallel method. These algorithms have been compared by testing them on a database of optical coherence tomography images. The comparison of results shows that the proposed implementation of the Canny method on GPU using the CUDA platform improves the speed of execution by 2-100× compared to the central processing unit-based implementation using the OpenCV and MATLAB platforms.
Mobile Devices and GPU Parallelism in Ionospheric Data Processing
Mascharka, D.; Pankratius, V.
2015-12-01
Scientific data acquisition in the field is often constrained by data transfer backchannels to analysis environments. Geoscientists are therefore facing practical bottlenecks with increasing sensor density and variety. Mobile devices, such as smartphones and tablets, offer promising solutions to key problems in scientific data acquisition, pre-processing, and validation by providing advanced capabilities in the field. This is due to affordable network connectivity options and the increasing mobile computational power. This contribution exemplifies a scenario faced by scientists in the field and presents the "Mahali TEC Processing App" developed in the context of the NSF-funded Mahali project. Aimed at atmospheric science and the study of ionospheric Total Electron Content (TEC), this app is able to gather data from various dual-frequency GPS receivers. It demonstrates parsing of full-day RINEX files on mobile devices and on-the-fly computation of vertical TEC values based on satellite ephemeris models that are obtained from NASA. Our experiments show how parallel computing on the mobile device GPU enables fast processing and visualization of up to 2 million datapoints in real-time using OpenGL. GPS receiver bias is estimated through minimum TEC approximations that can be interactively adjusted by scientists in the graphical user interface. Scientists can also perform approximate computations for "quickviews" to reduce CPU processing time and memory consumption. In the final stage of our mobile processing pipeline, scientists can upload data to the cloud for further processing. Acknowledgements: The Mahali project (http://mahali.mit.edu) is funded by the NSF INSPIRE grant no. AGS-1343967 (PI: V. Pankratius). We would like to acknowledge our collaborators at Boston College, Virginia Tech, Johns Hopkins University, Colorado State University, as well as the support of UNAVCO for loans of dual-frequency GPS receivers for use in this project, and Intel for loans of
CUDA/GPU Technology : Parallel Programming For High Performance Scientific Computing
YUHENDRA; KUZE, Hiroaki; JOSAPHAT, Tetuko Sri Sumantyo
2009-01-01
[ABSTRACT]Graphics processing units (GP Us) originally designed for computer video cards have emerged as the most powerful chip in a high-performance workstation. In the high performance computation capabilities, graphic processing units (GPU) lead to much more powerful performance than conventional CPUs by means of parallel processing. In 2007, the birth of Compute Unified Device Architecture (CUDA) and CUDA-enabled GPUs by NVIDIA Corporation brought a revolution in the general purpose GPU a...
International Nuclear Information System (INIS)
Lee, Jin Pyo; Joo, Han Gyu
2010-01-01
In the thermo-fluid analysis code named CUPID, the linear system of pressure equations must be solved in each iteration step. The time for repeatedly solving the linear system can be quite significant because large sparse matrices of Rank more than 50,000 are involved and the diagonal dominance of the system is hardly hold. Therefore parallelization of the linear system solver is essential to reduce the computing time. Meanwhile, Graphics Processing Units (GPU) have been developed as highly parallel, multi-core processors for the global demand of high quality 3D graphics. If a suitable interface is provided, parallelization using GPU can be available to engineering computing. NVIDIA provides a Software Development Kit(SDK) named CUDA(Compute Unified Device Architecture) to code developers so that they can manage GPUs for parallelization using the C language. In this research, we implement parallel routines for the linear system solver using CUDA, and examine the performance of the parallelization. In the next section, we will describe the method of CUDA parallelization for the CUPID code, and then the performance of the CUDA parallelization will be discussed
GRay: A MASSIVELY PARALLEL GPU-BASED CODE FOR RAY TRACING IN RELATIVISTIC SPACETIMES
Energy Technology Data Exchange (ETDEWEB)
Chan, Chi-kwan; Psaltis, Dimitrios; Özel, Feryal [Department of Astronomy, University of Arizona, 933 N. Cherry Ave., Tucson, AZ 85721 (United States)
2013-11-01
We introduce GRay, a massively parallel integrator designed to trace the trajectories of billions of photons in a curved spacetime. This graphics-processing-unit (GPU)-based integrator employs the stream processing paradigm, is implemented in CUDA C/C++, and runs on nVidia graphics cards. The peak performance of GRay using single-precision floating-point arithmetic on a single GPU exceeds 300 GFLOP (or 1 ns per photon per time step). For a realistic problem, where the peak performance cannot be reached, GRay is two orders of magnitude faster than existing central-processing-unit-based ray-tracing codes. This performance enhancement allows more effective searches of large parameter spaces when comparing theoretical predictions of images, spectra, and light curves from the vicinities of compact objects to observations. GRay can also perform on-the-fly ray tracing within general relativistic magnetohydrodynamic algorithms that simulate accretion flows around compact objects. Making use of this algorithm, we calculate the properties of the shadows of Kerr black holes and the photon rings that surround them. We also provide accurate fitting formulae of their dependencies on black hole spin and observer inclination, which can be used to interpret upcoming observations of the black holes at the center of the Milky Way, as well as M87, with the Event Horizon Telescope.
GPU TECHNOLOGIES EMBODIED IN PARALLEL SOLVERS OF LINEAR ALGEBRAIC EQUATION SYSTEMS
Directory of Open Access Journals (Sweden)
Sidorov Alexander Vladimirovich
2012-10-01
Full Text Available The author reviews existing shareware solvers that are operated by graphical computer devices. The purpose of this review is to explore the opportunities and limitations of the above parallel solvers applicable for resolution of linear algebraic problems that arise at Research and Educational Centre of Computer Modeling at MSUCE, and Research and Engineering Centre STADYO. The author has explored new applications of the GPU in the PETSc suite and compared them with the results generated absent of the GPU. The research is performed within the CUSP library developed to resolve the problems of linear algebra through the application of GPU. The author has also reviewed the new MAGMA project which is analogous to LAPACK for the GPU.
Implementation and Comparison of the Lifting 5/3 and 9/7 Algorithms in MatLab on GPU
Directory of Open Access Journals (Sweden)
Randa Khemiri
2016-06-01
Full Text Available In order to accelerate the Discrete Wavelet Transform DWT, we have implemented and compared the lifting "Le Gall5/3" and "Cohen-Daubechies-Feauveau9/7" (CDF9/7 algorithms on a low cost NVIDIA’s GPU. The suggested implementation is realized in MatLab using the in-house parallel computation toolbox (PCT. Our experimental results indicate, that the speedup is proportional to the image size until it attains a maximum at 20482 pixels, beyond these values the curve decreases. The performance with GPU enhances above a factor of 2~3 compared with CPU.
Parallel computing in cluster of GPU applied to a problem of nuclear engineering
International Nuclear Information System (INIS)
Moraes, Sergio Ricardo S.; Heimlich, Adino; Resende, Pedro
2013-01-01
Cluster computing has been widely used as a low cost alternative for parallel processing in scientific applications. With the use of Message-Passing Interface (MPI) protocol development became even more accessible and widespread in the scientific community. A more recent trend is the use of Graphic Processing Unit (GPU), which is a powerful co-processor able to perform hundreds of instructions in parallel, reaching a capacity of hundreds of times the processing of a CPU. However, a standard PC does not allow, in general, more than two GPUs. Hence, it is proposed in this work development and evaluation of a hybrid low cost parallel approach to the solution to a nuclear engineering typical problem. The idea is to use clusters parallelism technology (MPI) together with GPU programming techniques (CUDA - Compute Unified Device Architecture) to simulate neutron transport through a slab using Monte Carlo method. By using a cluster comprised by four quad-core computers with 2 GPU each, it has been developed programs using MPI and CUDA technologies. Experiments, applying different configurations, from 1 to 8 GPUs has been performed and results were compared with the sequential (non-parallel) version. A speed up of about 2.000 times has been observed when comparing the 8-GPU with the sequential version. Results here presented are discussed and analyzed with the objective of outlining gains and possible limitations of the proposed approach. (author)
Energy Technology Data Exchange (ETDEWEB)
Almeida, Adino Americo Heimlich
2009-07-01
Graphics Processing Units (GPU) are high performance co-processors intended, originally, to improve the use and quality of computer graphics applications. Since researchers and practitioners realized the potential of using GPU for general purpose, their application has been extended to other fields out of computer graphics scope. The main objective of this work is to evaluate the impact of using GPU in two typical problems of Nuclear area. The neutron transport simulation using Monte Carlo method and solve heat equation in a bi-dimensional domain by finite differences method. To achieve this, we develop parallel algorithms for GPU and CPU in the two problems described above. The comparison showed that the GPU-based approach is faster than the CPU in a computer with two quad core processors, without precision loss. (author)
Streaming Parallel GPU Acceleration of Large-Scale filter-based Spiking Neural Networks
L.P. Slazynski (Leszek); S.M. Bohte (Sander)
2012-01-01
htmlabstractThe arrival of graphics processing (GPU) cards suitable for massively parallel computing promises a↵ordable large-scale neural network simulation previously only available at supercomputing facil- ities. While the raw numbers suggest that GPUs may outperform CPUs by at least an order of
A GPU Implementation of Local Search Operators for Symmetric Travelling Salesman Problem
Directory of Open Access Journals (Sweden)
Juraj Fosin
2013-06-01
Full Text Available The Travelling Salesman Problem (TSP is one of the most studied combinatorial optimization problem which is significant in many practical applications in transportation problems. The TSP problem is NP-hard problem and requires large computation power to be solved by the exact algorithms. In the past few years, fast development of general-purpose Graphics Processing Units (GPUs has brought huge improvement in decreasing the applications’ execution time. In this paper, we implement 2-opt and 3-opt local search operators for solving the TSP on the GPU using CUDA. The novelty presented in this paper is a new parallel iterated local search approach with 2-opt and 3-opt operators for symmetric TSP, optimized for the execution on GPUs. With our implementation large TSP problems (up to 85,900 cities can be solved using the GPU. We will show that our GPU implementation can be up to 20x faster without losing quality for all TSPlib problems as well as for our CRO TSP problem.
Comparison Of Hybrid Sorting Algorithms Implemented On Different Parallel Hardware Platforms
Directory of Open Access Journals (Sweden)
Dominik Zurek
2013-01-01
Full Text Available Sorting is a common problem in computer science. There are lot of well-known sorting algorithms created for sequential execution on a single processor. Recently, hardware platforms enable to create wide parallel algorithms. We have standard processors consist of multiple cores and hardware accelerators like GPU. The graphic cards with their parallel architecture give new possibility to speed up many algorithms. In this paper we describe results of implementation of a few different sorting algorithms on GPU cards and multicore processors. Then hybrid algorithm will be presented which consists of parts executed on both platforms, standard CPU and GPU.
Fast Simulation of Large-Scale Floods Based on GPU Parallel Computing
Directory of Open Access Journals (Sweden)
Qiang Liu
2018-05-01
Full Text Available Computing speed is a significant issue of large-scale flood simulations for real-time response to disaster prevention and mitigation. Even today, most of the large-scale flood simulations are generally run on supercomputers due to the massive amounts of data and computations necessary. In this work, a two-dimensional shallow water model based on an unstructured Godunov-type finite volume scheme was proposed for flood simulation. To realize a fast simulation of large-scale floods on a personal computer, a Graphics Processing Unit (GPU-based, high-performance computing method using the OpenACC application was adopted to parallelize the shallow water model. An unstructured data management method was presented to control the data transportation between the GPU and CPU (Central Processing Unit with minimum overhead, and then both computation and data were offloaded from the CPU to the GPU, which exploited the computational capability of the GPU as much as possible. The parallel model was validated using various benchmarks and real-world case studies. The results demonstrate that speed-ups of up to one order of magnitude can be achieved in comparison with the serial model. The proposed parallel model provides a fast and reliable tool with which to quickly assess flood hazards in large-scale areas and, thus, has a bright application prospect for dynamic inundation risk identification and disaster assessment.
Near real-time digital holographic microscope based on GPU parallel computing
Zhu, Gang; Zhao, Zhixiong; Wang, Huarui; Yang, Yan
2018-01-01
A transmission near real-time digital holographic microscope with in-line and off-axis light path is presented, in which the parallel computing technology based on compute unified device architecture (CUDA) and digital holographic microscopy are combined. Compared to other holographic microscopes, which have to implement reconstruction in multiple focal planes and are time-consuming the reconstruction speed of the near real-time digital holographic microscope can be greatly improved with the parallel computing technology based on CUDA, so it is especially suitable for measurements of particle field in micrometer and nanometer scale. Simulations and experiments show that the proposed transmission digital holographic microscope can accurately measure and display the velocity of particle field in micrometer scale, and the average velocity error is lower than 10%.With the graphic processing units(GPU), the computing time of the 100 reconstruction planes(512×512 grids) is lower than 120ms, while it is 4.9s using traditional reconstruction method by CPU. The reconstruction speed has been raised by 40 times. In other words, it can handle holograms at 8.3 frames per second and the near real-time measurement and display of particle velocity field are realized. The real-time three-dimensional reconstruction of particle velocity field is expected to achieve by further optimization of software and hardware. Keywords: digital holographic microscope,
A Parallel Algorithm for the Counting of Ellipses Present in Conglomerates Using GPU
Directory of Open Access Journals (Sweden)
Reyes Yam-Uicab
2018-01-01
Full Text Available Detecting and counting elliptical objects are an interesting problem in digital image processing. There are real-world applications of this problem in various disciplines. Solving this problem is harder when there is occlusion among the elliptical objects, since in general these objects are considered as part of the bigger object (conglomerate. The solution to this problem focusses on the detection and segmentation of the precise number of occluded elliptical objects, while omitting all noninteresting objects. There are a variety of computational approximations that focus on this problem; however, such approximations are not accurate when there is occlusion. This paper presents an algorithm designed to solve this problem, specifically, to detect, segment, and count elliptical objects of a specific size when these are in occlusion with other objects within the conglomerate. Our algorithm deals with a time-consuming combinatorial process. To optimize the execution time of our algorithm, we implemented a parallel GPU version with CUDA-C, which experimentally improved the detection of occluded objects, as well as lowering processing times compared to the sequential version of the method. Comparative test results with another method featured in literature showed improved detection of objects in occlusion when using the proposed parallel method.
Implementation of meso-scale radioactive dispersion model for GPU
Energy Technology Data Exchange (ETDEWEB)
Sunarko [National Nuclear Energy Agency of Indonesia (BATAN), Jakarta (Indonesia). Nuclear Energy Assessment Center; Suud, Zaki [Bandung Institute of Technology (ITB), Bandung (Indonesia). Physics Dept.
2017-05-15
Lagrangian Particle Dispersion Method (LPDM) is applied to model atmospheric dispersion of radioactive material in a meso-scale of a few tens of kilometers for site study purpose. Empirical relationships are used to determine the dispersion coefficient for various atmospheric stabilities. Diagnostic 3-D wind-field is solved based on data from one meteorological station using mass-conservation principle. Particles representing radioactive pollutant are dispersed in the wind-field as a point source. Time-integrated air concentration is calculated using kernel density estimator (KDE) in the lowest layer of the atmosphere. Parallel code is developed for GTX-660Ti GPU with a total of 1 344 scalar processors using CUDA. A test of 1-hour release discovers that linear speedup is achieved starting at 28 800 particles-per-hour (pph) up to about 20 x at 14 4000 pph. Another test simulating 6-hour release with 36 000 pph resulted in a speedup of about 60 x. Statistical analysis reveals that resulting grid doses are nearly identical in both CPU and GPU versions of the code.
GRAVIDY, a GPU modular, parallel direct-summation N-body integrator: dynamics with softening
Maureira-Fredes, Cristián; Amaro-Seoane, Pau
2018-01-01
A wide variety of outstanding problems in astrophysics involve the motion of a large number of particles under the force of gravity. These include the global evolution of globular clusters, tidal disruptions of stars by a massive black hole, the formation of protoplanets and sources of gravitational radiation. The direct-summation of N gravitational forces is a complex problem with no analytical solution and can only be tackled with approximations and numerical methods. To this end, the Hermite scheme is a widely used integration method. With different numerical techniques and special-purpose hardware, it can be used to speed up the calculations. But these methods tend to be computationally slow and cumbersome to work with. We present a new graphics processing unit (GPU), direct-summation N-body integrator written from scratch and based on this scheme, which includes relativistic corrections for sources of gravitational radiation. GRAVIDY has high modularity, allowing users to readily introduce new physics, it exploits available computational resources and will be maintained by regular updates. GRAVIDY can be used in parallel on multiple CPUs and GPUs, with a considerable speed-up benefit. The single-GPU version is between one and two orders of magnitude faster than the single-CPU version. A test run using four GPUs in parallel shows a speed-up factor of about 3 as compared to the single-GPU version. The conception and design of this first release is aimed at users with access to traditional parallel CPU clusters or computational nodes with one or a few GPU cards.
Yarovyi, Andrii A.; Timchenko, Leonid I.; Kozhemiako, Volodymyr P.; Kokriatskaia, Nataliya I.; Hamdi, Rami R.; Savchuk, Tamara O.; Kulyk, Oleksandr O.; Surtel, Wojciech; Amirgaliyev, Yedilkhan; Kashaganova, Gulzhan
2017-08-01
The paper deals with a problem of insufficient productivity of existing computer means for large image processing, which do not meet modern requirements posed by resource-intensive computing tasks of laser beam profiling. The research concentrated on one of the profiling problems, namely, real-time processing of spot images of the laser beam profile. Development of a theory of parallel-hierarchic transformation allowed to produce models for high-performance parallel-hierarchical processes, as well as algorithms and software for their implementation based on the GPU-oriented architecture using GPGPU technologies. The analyzed performance of suggested computerized tools for processing and classification of laser beam profile images allows to perform real-time processing of dynamic images of various sizes.
PIConGPU - A highly-scalable particle-in-cell implementation for GPU clusters
Energy Technology Data Exchange (ETDEWEB)
Bussmann, Michael; Burau, Heiko; Debus, Alexander; Huebl, Axel; Kluge, Thomas; Pausch, Richard; Schmeisser, Nils; Steiniger, Klaus; Widera, Rene; Wyderka, Nikolai; Schramm, Ulrich; Cowan, Thomas [HZDR, Dresden (Germany); Schneider, Benjamin [HZDR, Dresden (Germany); TU Dresden (Germany); Schmitt, Felix [NVIDIA, Austin, TX (United States); Grottel, Sebastian; Gumhold, Stefan [TU Dresden (Germany); Juckeland, Guido; Angel, Wolfgang [TU Dresden (Germany); ZIH, Dresden (Germany)
2013-07-01
PIConGPU can handle large-scale simulations of laser plasma and astrophysical plasma dynamics on GPU clusters with thousands of GPUs. High data throughput allows to conduct large parameter surveys but makes it necessary to rethink data analysis and look for new ways of analyzing large simulation data sets. The speedup seen on GPUs enables scientists to add physical effects to their code that up until recently have been too computationally demanding. We present recent results obtained with PIConGPU, discuss scaling behaviour, the most important building blocks of the code and new physics modules recently added. In addition we give an outlook on data analysis, resiliance and load balancing with PIConGPU.
Yu, Chaoyin; Yuan, Zhengwu; Wu, Yuanfeng
2017-10-01
Hyperspectral image unmixing is an important part of hyperspectral data analysis. The mixed pixel decomposition consists of two steps, endmember (the unique signatures of pure ground components) extraction and abundance (the proportion of each endmember in each pixel) estimation. Recently, a Discrete Particle Swarm Optimization algorithm (DPSO) was proposed for accurately extract endmembers with high optimal performance. However, the DPSO algorithm shows very high computational complexity, which makes the endmember extraction procedure very time consuming for hyperspectral image unmixing. Thus, in this paper, the DPSO endmember extraction algorithm was parallelized, implemented on the CUDA (GPU K20) platform, and evaluated by real hyperspectral remote sensing data. The experimental results show that with increasing the number of particles the parallelized version obtained much higher computing efficiency while maintain the same endmember exaction accuracy.
Big Data GPU-Driven Parallel Processing Spatial and Spatio-Temporal Clustering Algorithms
Konstantaras, Antonios; Skounakis, Emmanouil; Kilty, James-Alexander; Frantzeskakis, Theofanis; Maravelakis, Emmanuel
2016-04-01
Advances in graphics processing units' technology towards encompassing parallel architectures [1], comprised of thousands of cores and multiples of parallel threads, provide the foundation in terms of hardware for the rapid processing of various parallel applications regarding seismic big data analysis. Seismic data are normally stored as collections of vectors in massive matrices, growing rapidly in size as wider areas are covered, denser recording networks are being established and decades of data are being compiled together [2]. Yet, many processes regarding seismic data analysis are performed on each seismic event independently or as distinct tiles [3] of specific grouped seismic events within a much larger data set. Such processes, independent of one another can be performed in parallel narrowing down processing times drastically [1,3]. This research work presents the development and implementation of three parallel processing algorithms using Cuda C [4] for the investigation of potentially distinct seismic regions [5,6] present in the vicinity of the southern Hellenic seismic arc. The algorithms, programmed and executed in parallel comparatively, are the: fuzzy k-means clustering with expert knowledge [7] in assigning overall clusters' number; density-based clustering [8]; and a selves-developed spatio-temporal clustering algorithm encompassing expert [9] and empirical knowledge [10] for the specific area under investigation. Indexing terms: GPU parallel programming, Cuda C, heterogeneous processing, distinct seismic regions, parallel clustering algorithms, spatio-temporal clustering References [1] Kirk, D. and Hwu, W.: 'Programming massively parallel processors - A hands-on approach', 2nd Edition, Morgan Kaufman Publisher, 2013 [2] Konstantaras, A., Valianatos, F., Varley, M.R. and Makris, J.P.: 'Soft-Computing Modelling of Seismicity in the Southern Hellenic Arc', Geoscience and Remote Sensing Letters, vol. 5 (3), pp. 323-327, 2008 [3] Papadakis, S. and
GPU Implementation of High Rayleigh Number Three-Dimensional Mantle Convection
Sanchez, D. A.; Yuen, D. A.; Wright, G. B.; Barnett, G. A.
2010-12-01
Although we have entered the age of petascale computing, many factors are still prohibiting high-performance computing (HPC) from infiltrating all suitable scientific disciplines. For this reason and others, application of GPU to HPC is gaining traction in the scientific world. With its low price point, high performance potential, and competitive scalability, GPU has been an option well worth considering for the last few years. Moreover with the advent of NVIDIA's Fermi architecture, which brings ECC memory, better double-precision performance, and more RAM to GPU, there is a strong message of corporate support for GPU in HPC. However many doubts linger concerning the practicality of using GPU for scientific computing. In particular, GPU has a reputation for being difficult to program and suitable for only a small subset of problems. Although inroads have been made in addressing these concerns, for many scientists GPU still has hurdles to clear before becoming an acceptable choice. We explore the applicability of GPU to geophysics by implementing a three-dimensional, second-order finite-difference model of Rayleigh-Benard thermal convection on an NVIDIA GPU using C for CUDA. Our code reaches sufficient resolution, on the order of 500x500x250 evenly-spaced finite-difference gridpoints, on a single GPU. We make extensive use of highly optimized CUBLAS routines, allowing us to achieve performance on the order of O( 0.1 ) µs per timestep*gridpoint at this resolution. This performance has allowed us to study high Rayleigh number simulations, on the order of 2x10^7, on a single GPU.
Directory of Open Access Journals (Sweden)
Elise Cormie-Bowins
2012-10-01
Full Text Available We consider the problem of computing reachability probabilities: given a Markov chain, an initial state of the Markov chain, and a set of goal states of the Markov chain, what is the probability of reaching any of the goal states from the initial state? This problem can be reduced to solving a linear equation Ax = b for x, where A is a matrix and b is a vector. We consider two iterative methods to solve the linear equation: the Jacobi method and the biconjugate gradient stabilized (BiCGStab method. For both methods, a sequential and a parallel version have been implemented. The parallel versions have been implemented on the compute unified device architecture (CUDA so that they can be run on a NVIDIA graphics processing unit (GPU. From our experiments we conclude that as the size of the matrix increases, the CUDA implementations outperform the sequential implementations. Furthermore, the BiCGStab method performs better than the Jacobi method for dense matrices, whereas the Jacobi method does better for sparse ones. Since the reachability probabilities problem plays a key role in probabilistic model checking, we also compared the implementations for matrices obtained from a probabilistic model checker. Our experiments support the conjecture by Bosnacki et al. that the Jacobi method is superior to Krylov subspace methods, a class to which the BiCGStab method belongs, for probabilistic model checking.
Directory of Open Access Journals (Sweden)
B. Kumar
2016-06-01
Full Text Available Extended morphological profile (EMP is a good technique for extracting spectral-spatial information from the images but large size of hyperspectral images is an important concern for creating EMPs. However, with the availability of modern multi-core processors and commodity parallel processing systems like graphics processing units (GPUs at desktop level, parallel computing provides a viable option to significantly accelerate execution of such computations. In this paper, parallel implementation of an EMP based spectralspatial classification method for hyperspectral imagery is presented. The parallel implementation is done both on multi-core CPU and GPU. The impact of parallelization on speed up and classification accuracy is analyzed. For GPU, the implementation is done in compute unified device architecture (CUDA C. The experiments are carried out on two well-known hyperspectral images. It is observed from the experimental results that GPU implementation provides a speed up of about 7 times, while parallel implementation on multi-core CPU resulted in speed up of about 3 times. It is also observed that parallel implementation has no adverse impact on the classification accuracy.
GPU implementations of online track finding algorithms at PANDA
Energy Technology Data Exchange (ETDEWEB)
Herten, Andreas; Stockmanns, Tobias; Ritman, James [Institut fuer Kernphysik, Forschungszentrum Juelich GmbH (Germany); Adinetz, Andrew; Pleiter, Dirk [Juelich Supercomputing Centre, Forschungszentrum Juelich GmbH (Germany); Kraus, Jiri [NVIDIA GmbH (Germany); Collaboration: PANDA-Collaboration
2014-07-01
The PANDA experiment is a hadron physics experiment that will investigate antiproton annihilation in the charm quark mass region. The experiment is now being constructed as one of the main parts of the FAIR facility. At an event rate of 2 . 10{sup 7}/s a data rate of 200 GB/s is expected. A reduction of three orders of magnitude is required in order to save the data for further offline analysis. Since signal and background processes at PANDA have similar signatures, no hardware-level trigger is foreseen for the experiment. Instead, a fast online event filter is substituting this element. We investigate the possibility of using graphics processing units (GPUs) for the online tracking part of this task. Researched algorithms are a Hough Transform, a track finder involving Riemann surfaces, and the novel, PANDA-specific Triplet Finder. This talk shows selected advances in the implementations as well as performance evaluations of the GPU tracking algorithms to be used at the PANDA experiment.
Directory of Open Access Journals (Sweden)
Mathew G. Pelletier
2008-02-01
Full Text Available One of the main hurdles standing in the way of optimal cleaning of cotton lint isthe lack of sensing systems that can react fast enough to provide the control system withreal-time information as to the level of trash contamination of the cotton lint. This researchexamines the use of programmable graphic processing units (GPU as an alternative to thePCÃ¢Â€Â™s traditional use of the central processing unit (CPU. The use of the GPU, as analternative computation platform, allowed for the machine vision system to gain asignificant improvement in processing time. By improving the processing time, thisresearch seeks to address the lack of availability of rapid trash sensing systems and thusalleviate a situation in which the current systems view the cotton lint either well before, orafter, the cotton is cleaned. This extended lag/lead time that is currently imposed on thecotton trash cleaning control systems, is what is responsible for system operators utilizing avery large dead-band safety buffer in order to ensure that the cotton lint is not undercleaned.Unfortunately, the utilization of a large dead-band buffer results in the majority ofthe cotton lint being over-cleaned which in turn causes lint fiber-damage as well assignificant losses of the valuable lint due to the excessive use of cleaning machinery. Thisresearch estimates that upwards of a 30% reduction in lint loss could be gained through theuse of a tightly coupled trash sensor to the cleaning machinery control systems. Thisresearch seeks to improve processing times through the development of a new algorithm forcotton trash sensing that allows for implementation on a highly parallel architecture.Additionally, by moving the new parallel algorithm onto an alternative computing platform,the graphic processing unit Ã¢Â€ÂœGPUÃ¢Â€Â, for processing of the cotton trash images, a speed up ofover 6.5 times, over optimized code running on the PCÃ¢Â€Â™s central processing
Parallel, distributed and GPU computing technologies in single-particle electron microscopy.
Schmeisser, Martin; Heisen, Burkhard C; Luettich, Mario; Busche, Boris; Hauer, Florian; Koske, Tobias; Knauber, Karl-Heinz; Stark, Holger
2009-07-01
Most known methods for the determination of the structure of macromolecular complexes are limited or at least restricted at some point by their computational demands. Recent developments in information technology such as multicore, parallel and GPU processing can be used to overcome these limitations. In particular, graphics processing units (GPUs), which were originally developed for rendering real-time effects in computer games, are now ubiquitous and provide unprecedented computational power for scientific applications. Each parallel-processing paradigm alone can improve overall performance; the increased computational performance obtained by combining all paradigms, unleashing the full power of today's technology, makes certain applications feasible that were previously virtually impossible. In this article, state-of-the-art paradigms are introduced, the tools and infrastructure needed to apply these paradigms are presented and a state-of-the-art infrastructure and solution strategy for moving scientific applications to the next generation of computer hardware is outlined.
An optimization of a GPU-based parallel wind field module
International Nuclear Information System (INIS)
Pinheiro, André L.S.; Shirru, Roberto
2017-01-01
Atmospheric radionuclide dispersion systems (ARDS) are important tools to predict the impact of radioactive releases from Nuclear Power Plants and guide people evacuation from affected areas. Four modules comprise ARDS: Source Term, Wind Field, Plume Dispersion and Doses Calculations. The slowest is the Wind Field Module that was previously parallelized using the CUDA C language. The statement purpose of this work is to show the speedup gain with the optimization of the already parallel code of the GPU-based Wind Field module, based in WEST model (Extrapolated from Stability and Terrain). Due to the parallelization done in the wind field module, it was observed that some CUDA processors became idle, thus contributing to a reduction in speedup. It was proposed in this work a way of allocating these idle CUDA processors in order to increase the speedup. An acceleration of about 4 times can be seen in the comparative case study between the regular CUDA code and the optimized CUDA code. These results are quite motivating and point out that even after a parallelization of code, a parallel code optimization should be taken into account. (author)
An optimization of a GPU-based parallel wind field module
Energy Technology Data Exchange (ETDEWEB)
Pinheiro, André L.S.; Shirru, Roberto [Coordenacao de Pos-Graduacao e Pesquisa de Engenharia (PEN/COPPE/UFRJ), Rio de Janeiro, RJ (Brazil). Programa de Engenharia Nuclear; Pereira, Cláudio M.N.A., E-mail: apinheiro99@gmail.com, E-mail: schirru@lmp.ufrj.br, E-mail: cmnap@ien.gov.br [Instituto de Engenharia Nuclear (IEN/CNEN-RJ), Rio de Janeiro, RJ (Brazil)
2017-07-01
Atmospheric radionuclide dispersion systems (ARDS) are important tools to predict the impact of radioactive releases from Nuclear Power Plants and guide people evacuation from affected areas. Four modules comprise ARDS: Source Term, Wind Field, Plume Dispersion and Doses Calculations. The slowest is the Wind Field Module that was previously parallelized using the CUDA C language. The statement purpose of this work is to show the speedup gain with the optimization of the already parallel code of the GPU-based Wind Field module, based in WEST model (Extrapolated from Stability and Terrain). Due to the parallelization done in the wind field module, it was observed that some CUDA processors became idle, thus contributing to a reduction in speedup. It was proposed in this work a way of allocating these idle CUDA processors in order to increase the speedup. An acceleration of about 4 times can be seen in the comparative case study between the regular CUDA code and the optimized CUDA code. These results are quite motivating and point out that even after a parallelization of code, a parallel code optimization should be taken into account. (author)
Multi-GPU implementation of a VMAT treatment plan optimization algorithm
International Nuclear Information System (INIS)
Tian, Zhen; Folkerts, Michael; Tan, Jun; Jia, Xun; Jiang, Steve B.; Peng, Fei
2015-01-01
Purpose: Volumetric modulated arc therapy (VMAT) optimization is a computationally challenging problem due to its large data size, high degrees of freedom, and many hardware constraints. High-performance graphics processing units (GPUs) have been used to speed up the computations. However, GPU’s relatively small memory size cannot handle cases with a large dose-deposition coefficient (DDC) matrix in cases of, e.g., those with a large target size, multiple targets, multiple arcs, and/or small beamlet size. The main purpose of this paper is to report an implementation of a column-generation-based VMAT algorithm, previously developed in the authors’ group, on a multi-GPU platform to solve the memory limitation problem. While the column-generation-based VMAT algorithm has been previously developed, the GPU implementation details have not been reported. Hence, another purpose is to present detailed techniques employed for GPU implementation. The authors also would like to utilize this particular problem as an example problem to study the feasibility of using a multi-GPU platform to solve large-scale problems in medical physics. Methods: The column-generation approach generates VMAT apertures sequentially by solving a pricing problem (PP) and a master problem (MP) iteratively. In the authors’ method, the sparse DDC matrix is first stored on a CPU in coordinate list format (COO). On the GPU side, this matrix is split into four submatrices according to beam angles, which are stored on four GPUs in compressed sparse row format. Computation of beamlet price, the first step in PP, is accomplished using multi-GPUs. A fast inter-GPU data transfer scheme is accomplished using peer-to-peer access. The remaining steps of PP and MP problems are implemented on CPU or a single GPU due to their modest problem scale and computational loads. Barzilai and Borwein algorithm with a subspace step scheme is adopted here to solve the MP problem. A head and neck (H and N) cancer case is
Multi-GPU implementation of a VMAT treatment plan optimization algorithm
Energy Technology Data Exchange (ETDEWEB)
Tian, Zhen, E-mail: Zhen.Tian@UTSouthwestern.edu, E-mail: Xun.Jia@UTSouthwestern.edu, E-mail: Steve.Jiang@UTSouthwestern.edu; Folkerts, Michael; Tan, Jun; Jia, Xun, E-mail: Zhen.Tian@UTSouthwestern.edu, E-mail: Xun.Jia@UTSouthwestern.edu, E-mail: Steve.Jiang@UTSouthwestern.edu; Jiang, Steve B., E-mail: Zhen.Tian@UTSouthwestern.edu, E-mail: Xun.Jia@UTSouthwestern.edu, E-mail: Steve.Jiang@UTSouthwestern.edu [Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, Texas 75390 (United States); Peng, Fei [Computer Science Department, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213 (United States)
2015-06-15
Purpose: Volumetric modulated arc therapy (VMAT) optimization is a computationally challenging problem due to its large data size, high degrees of freedom, and many hardware constraints. High-performance graphics processing units (GPUs) have been used to speed up the computations. However, GPU’s relatively small memory size cannot handle cases with a large dose-deposition coefficient (DDC) matrix in cases of, e.g., those with a large target size, multiple targets, multiple arcs, and/or small beamlet size. The main purpose of this paper is to report an implementation of a column-generation-based VMAT algorithm, previously developed in the authors’ group, on a multi-GPU platform to solve the memory limitation problem. While the column-generation-based VMAT algorithm has been previously developed, the GPU implementation details have not been reported. Hence, another purpose is to present detailed techniques employed for GPU implementation. The authors also would like to utilize this particular problem as an example problem to study the feasibility of using a multi-GPU platform to solve large-scale problems in medical physics. Methods: The column-generation approach generates VMAT apertures sequentially by solving a pricing problem (PP) and a master problem (MP) iteratively. In the authors’ method, the sparse DDC matrix is first stored on a CPU in coordinate list format (COO). On the GPU side, this matrix is split into four submatrices according to beam angles, which are stored on four GPUs in compressed sparse row format. Computation of beamlet price, the first step in PP, is accomplished using multi-GPUs. A fast inter-GPU data transfer scheme is accomplished using peer-to-peer access. The remaining steps of PP and MP problems are implemented on CPU or a single GPU due to their modest problem scale and computational loads. Barzilai and Borwein algorithm with a subspace step scheme is adopted here to solve the MP problem. A head and neck (H and N) cancer case is
Cai, Yong; Cui, Xiangyang; Li, Guangyao; Liu, Wenyang
2018-04-01
The edge-smooth finite element method (ES-FEM) can improve the computational accuracy of triangular shell elements and the mesh partition efficiency of complex models. In this paper, an approach is developed to perform explicit finite element simulations of contact-impact problems with a graphical processing unit (GPU) using a special edge-smooth triangular shell element based on ES-FEM. Of critical importance for this problem is achieving finer-grained parallelism to enable efficient data loading and to minimize communication between the device and host. Four kinds of parallel strategies are then developed to efficiently solve these ES-FEM based shell element formulas, and various optimization methods are adopted to ensure aligned memory access. Special focus is dedicated to developing an approach for the parallel construction of edge systems. A parallel hierarchy-territory contact-searching algorithm (HITA) and a parallel penalty function calculation method are embedded in this parallel explicit algorithm. Finally, the program flow is well designed, and a GPU-based simulation system is developed, using Nvidia's CUDA. Several numerical examples are presented to illustrate the high quality of the results obtained with the proposed methods. In addition, the GPU-based parallel computation is shown to significantly reduce the computing time.
Parallelizing the QUDA Library for Multi-GPU Calculations in Lattice Quantum Chromodynamics
International Nuclear Information System (INIS)
Babich, Ronald; Clark, Michael; Joo, Balint
2010-01-01
Graphics Processing Units (GPUs) are having a transformational effect on numerical lattice quantum chromodynamics (LQCD) calculations of importance in nuclear and particle physics. The QUDA library provides a package of mixed precision sparse matrix linear solvers for LQCD applications, supporting single GPUs based on NVIDIA's Compute Unified Device Architecture (CUDA). This library, interfaced to the QDP++/Chroma framework for LQCD calculations, is currently in production use on the '9g' cluster at the Jefferson Laboratory, enabling unprecedented price/performance for a range of problems in LQCD. Nevertheless, memory constraints on current GPU devices limit the problem sizes that can be tackled. In this contribution we describe the parallelization of the QUDA library onto multiple GPUs using MPI, including strategies for the overlapping of communication and computation. We report on both weak and strong scaling for up to 32 GPUs interconnected by InfiniBand, on which we sustain in excess of 4 Tflops.
Parallelizing the QUDA Library for Multi-GPU Calculations in Lattice Quantum Chromodynamics
Energy Technology Data Exchange (ETDEWEB)
Ronald Babich, Michael Clark, Balint Joo
2010-11-01
Graphics Processing Units (GPUs) are having a transformational effect on numerical lattice quantum chromodynamics (LQCD) calculations of importance in nuclear and particle physics. The QUDA library provides a package of mixed precision sparse matrix linear solvers for LQCD applications, supporting single GPUs based on NVIDIA's Compute Unified Device Architecture (CUDA). This library, interfaced to the QDP++/Chroma framework for LQCD calculations, is currently in production use on the "9g" cluster at the Jefferson Laboratory, enabling unprecedented price/performance for a range of problems in LQCD. Nevertheless, memory constraints on current GPU devices limit the problem sizes that can be tackled. In this contribution we describe the parallelization of the QUDA library onto multiple GPUs using MPI, including strategies for the overlapping of communication and computation. We report on both weak and strong scaling for up to 32 GPUs interconnected by InfiniBand, on which we sustain in excess of 4 Tflops.
A massively parallel GPU-accelerated model for analysis of fully nonlinear free surface waves
DEFF Research Database (Denmark)
Engsig-Karup, Allan Peter; Madsen, Morten G.; Glimberg, Stefan Lemvig
2011-01-01
-storage flexible-order accurate finite difference method that is known to be efficient and scalable on a CPU core (single thread). To achieve parallel performance of the relatively complex numerical model, we investigate a new trend in high-performance computing where many-core GPUs are utilized as high......-throughput co-processors to the CPU. We describe and demonstrate how this approach makes it possible to do fast desktop computations for large nonlinear wave problems in numerical wave tanks (NWTs) with close to 50/100 million total grid points in double/ single precision with 4 GB global device memory...... available. A new code base has been developed in C++ and compute unified device architecture C and is found to improve the runtime more than an order in magnitude in double precision arithmetic for the same accuracy over an existing CPU (single thread) Fortran 90 code when executed on a single modern GPU...
Hou, Zhenlong; Huang, Danian
2017-09-01
In this paper, we make a study on the inversion of probability tomography (IPT) with gravity gradiometry data at first. The space resolution of the results is improved by multi-tensor joint inversion, depth weighting matrix and the other methods. Aiming at solving the problems brought by the big data in the exploration, we present the parallel algorithm and the performance analysis combining Compute Unified Device Architecture (CUDA) with Open Multi-Processing (OpenMP) based on Graphics Processing Unit (GPU) accelerating. In the test of the synthetic model and real data from Vinton Dome, we get the improved results. It is also proved that the improved inversion algorithm is effective and feasible. The performance of parallel algorithm we designed is better than the other ones with CUDA. The maximum speedup could be more than 200. In the performance analysis, multi-GPU speedup and multi-GPU efficiency are applied to analyze the scalability of the multi-GPU programs. The designed parallel algorithm is demonstrated to be able to process larger scale of data and the new analysis method is practical.
Parallel, distributed and GPU computing technologies in single-particle electron microscopy
International Nuclear Information System (INIS)
Schmeisser, Martin; Heisen, Burkhard C.; Luettich, Mario; Busche, Boris; Hauer, Florian; Koske, Tobias; Knauber, Karl-Heinz; Stark, Holger
2009-01-01
An introduction to the current paradigm shift towards concurrency in software. Most known methods for the determination of the structure of macromolecular complexes are limited or at least restricted at some point by their computational demands. Recent developments in information technology such as multicore, parallel and GPU processing can be used to overcome these limitations. In particular, graphics processing units (GPUs), which were originally developed for rendering real-time effects in computer games, are now ubiquitous and provide unprecedented computational power for scientific applications. Each parallel-processing paradigm alone can improve overall performance; the increased computational performance obtained by combining all paradigms, unleashing the full power of today’s technology, makes certain applications feasible that were previously virtually impossible. In this article, state-of-the-art paradigms are introduced, the tools and infrastructure needed to apply these paradigms are presented and a state-of-the-art infrastructure and solution strategy for moving scientific applications to the next generation of computer hardware is outlined
Directory of Open Access Journals (Sweden)
Paolo Cazzaniga
2014-01-01
high-performance computing solutions is motivated by the need of performing large numbers of in silico analysis to study the behavior of biological systems in different conditions, which necessitate a computing power that usually overtakes the capability of standard desktop computers. In this work we present coagSODA, a CUDA-powered computational tool that was purposely developed for the analysis of a large mechanistic model of the blood coagulation cascade (BCC, defined according to both mass-action kinetics and Hill functions. coagSODA allows the execution of parallel simulations of the dynamics of the BCC by automatically deriving the system of ordinary differential equations and then exploiting the numerical integration algorithm LSODA. We present the biological results achieved with a massive exploration of perturbed conditions of the BCC, carried out with one-dimensional and bi-dimensional parameter sweep analysis, and show that GPU-accelerated parallel simulations of this model can increase the computational performances up to a 181× speedup compared to the corresponding sequential simulations.
Implementation and optimization of ultrasound signal processing algorithms on mobile GPU
Kong, Woo Kyu; Lee, Wooyoul; Kim, Kyu Cheol; Yoo, Yangmo; Song, Tai-Kyong
2014-03-01
A general-purpose graphics processing unit (GPGPU) has been used for improving computing power in medical ultrasound imaging systems. Recently, a mobile GPU becomes powerful to deal with 3D games and videos at high frame rates on Full HD or HD resolution displays. This paper proposes the method to implement ultrasound signal processing on a mobile GPU available in the high-end smartphone (Galaxy S4, Samsung Electronics, Seoul, Korea) with programmable shaders on the OpenGL ES 2.0 platform. To maximize the performance of the mobile GPU, the optimization of shader design and load sharing between vertex and fragment shader was performed. The beamformed data were captured from a tissue mimicking phantom (Model 539 Multipurpose Phantom, ATS Laboratories, Inc., Bridgeport, CT, USA) by using a commercial ultrasound imaging system equipped with a research package (Ultrasonix Touch, Ultrasonix, Richmond, BC, Canada). The real-time performance is evaluated by frame rates while varying the range of signal processing blocks. The implementation method of ultrasound signal processing on OpenGL ES 2.0 was verified by analyzing PSNR with MATLAB gold standard that has the same signal path. CNR was also analyzed to verify the method. From the evaluations, the proposed mobile GPU-based processing method has no significant difference with the processing using MATLAB (i.e., PSNRe., 11.31). From the mobile GPU implementation, the frame rates of 57.6 Hz were achieved. The total execution time was 17.4 ms that was faster than the acquisition time (i.e., 34.4 ms). These results indicate that the mobile GPU-based processing method can support real-time ultrasound B-mode processing on the smartphone.
Shamonin, Denis P; Bron, Esther E; Lelieveldt, Boudewijn P F; Smits, Marion; Klein, Stefan; Staring, Marius
2013-01-01
Nonrigid image registration is an important, but time-consuming task in medical image analysis. In typical neuroimaging studies, multiple image registrations are performed, i.e., for atlas-based segmentation or template construction. Faster image registration routines would therefore be beneficial. In this paper we explore acceleration of the image registration package elastix by a combination of several techniques: (i) parallelization on the CPU, to speed up the cost function derivative calculation; (ii) parallelization on the GPU building on and extending the OpenCL framework from ITKv4, to speed up the Gaussian pyramid computation and the image resampling step; (iii) exploitation of certain properties of the B-spline transformation model; (iv) further software optimizations. The accelerated registration tool is employed in a study on diagnostic classification of Alzheimer's disease and cognitively normal controls based on T1-weighted MRI. We selected 299 participants from the publicly available Alzheimer's Disease Neuroimaging Initiative database. Classification is performed with a support vector machine based on gray matter volumes as a marker for atrophy. We evaluated two types of strategies (voxel-wise and region-wise) that heavily rely on nonrigid image registration. Parallelization and optimization resulted in an acceleration factor of 4-5x on an 8-core machine. Using OpenCL a speedup factor of 2 was realized for computation of the Gaussian pyramids, and 15-60 for the resampling step, for larger images. The voxel-wise and the region-wise classification methods had an area under the receiver operator characteristic curve of 88 and 90%, respectively, both for standard and accelerated registration. We conclude that the image registration package elastix was substantially accelerated, with nearly identical results to the non-optimized version. The new functionality will become available in the next release of elastix as open source under the BSD license.
Fast Parallel Image Registration on CPU and GPU for Diagnostic Classification of Alzheimer's Disease
Directory of Open Access Journals (Sweden)
Denis P Shamonin
2014-01-01
Full Text Available Nonrigid image registration is an important, but time-consuming taskin medical image analysis. In typical neuroimaging studies, multipleimage registrations are performed, i.e. for atlas-based segmentationor template construction. Faster image registration routines wouldtherefore be beneficial.In this paper we explore acceleration of the image registrationpackage elastix by a combination of several techniques: iparallelization on the CPU, to speed up the cost function derivativecalculation; ii parallelization on the GPU building on andextending the OpenCL framework from ITKv4, to speed up the Gaussianpyramid computation and the image resampling step; iii exploitationof certain properties of the B-spline transformation model; ivfurther software optimizations.The accelerated registration tool is employed in a study ondiagnostic classification of Alzheimer's disease and cognitivelynormal controls based on T1-weighted MRI. We selected 299participants from the publicly available Alzheimer's DiseaseNeuroimaging Initiative database. Classification is performed with asupport vector machine based on gray matter volumes as a marker foratrophy. We evaluated two types of strategies (voxel-wise andregion-wise that heavily rely on nonrigid image registration.Parallelization and optimization resulted in an acceleration factorof 4-5x on an 8-core machine. Using OpenCL a speedup factor of ~2was realized for computation of the Gaussian pyramids, and 15-60 forthe resampling step, for larger images. The voxel-wise and theregion-wise classification methods had an area under thereceiver operator characteristic curve of 88% and 90%,respectively, both for standard and accelerated registration.We conclude that the image registration package elastix wassubstantially accelerated, with nearly identical results to thenon-optimized version. The new functionality will become availablein the next release of elastix as open source under the BSD license.
Jiang, Hanyu; Ganesan, Narayan
2016-02-27
HMMER software suite is widely used for analysis of homologous protein and nucleotide sequences with high sensitivity. The latest version of hmmsearch in HMMER 3.x, utilizes heuristic-pipeline which consists of MSV/SSV (Multiple/Single ungapped Segment Viterbi) stage, P7Viterbi stage and the Forward scoring stage to accelerate homology detection. Since the latest version is highly optimized for performance on modern multi-core CPUs with SSE capabilities, only a few acceleration attempts report speedup. However, the most compute intensive tasks within the pipeline (viz., MSV/SSV and P7Viterbi stages) still stand to benefit from the computational capabilities of massively parallel processors. A Multi-Tiered Parallel Framework (CUDAMPF) implemented on CUDA-enabled GPUs presented here, offers a finer-grained parallelism for MSV/SSV and Viterbi algorithms. We couple SIMT (Single Instruction Multiple Threads) mechanism with SIMD (Single Instructions Multiple Data) video instructions with warp-synchronism to achieve high-throughput processing and eliminate thread idling. We also propose a hardware-aware optimal allocation scheme of scarce resources like on-chip memory and caches in order to boost performance and scalability of CUDAMPF. In addition, runtime compilation via NVRTC available with CUDA 7.0 is incorporated into the presented framework that not only helps unroll innermost loop to yield upto 2 to 3-fold speedup than static compilation but also enables dynamic loading and switching of kernels depending on the query model size, in order to achieve optimal performance. CUDAMPF is designed as a hardware-aware parallel framework for accelerating computational hotspots within the hmmsearch pipeline as well as other sequence alignment applications. It achieves significant speedup by exploiting hierarchical parallelism on single GPU and takes full advantage of limited resources based on their own performance features. In addition to exceeding performance of other
Performance of Сellular Automata-based Stream Ciphers in GPU Implementation
Directory of Open Access Journals (Sweden)
P. G. Klyucharev
2016-01-01
Full Text Available Earlier the author had developed methods to build high-performance generalized cellular automata-based symmetric ciphers, which allow obtaining the encryption algorithms that show extremely high performance in hardware implementation. However, their implementation based on the conventional microprocessors lacks high performance. The mere fact is quite common - it shows a scope of applications for these ciphers. Nevertheless, the use of graphic processors enables achieving an appropriate performance for a software implementation.The article is extension of a series of the articles, which study various aspects to construct and implement cryptographic algorithms based on the generalized cellular automata. The article is aimed at studying the capabilities to implement the GPU-based cryptographic algorithms under consideration.Representing a key generator, the implemented encryption algorithm comprises 2k generalized cellular automata. The cellular automata graphs are Ramanujan’s ones. The cells of produced k gamma streams alternate, thereby allowing the GPU capabilities to be better used.To implement was used OpenCL, as the most universal and platform-independent API. The software written in C ++ was designed so that the user could set various parameters, including the encryption key, the graph structure, the local communication function, various constants, etc. To test were used a variety of graphics processors (NVIDIA GTX 650; NVIDIA GTX 770; AMD R9 280X.Depending on operating conditions, and GPU used, a performance range is from 0.47 to 6.61 Gb / s, which is comparable to the performance of the countertypes.Thus, the article has demonstrated that using the GPU makes it is possible to provide efficient software implementation of stream ciphers based on the generalized cellular automata.This work was supported by the RFBR, the project №16-07-00542.
International Nuclear Information System (INIS)
Ding Yu; Qi Yujin; Zhang Xuezhu; Zhao Cuilan
2011-01-01
In this paper, we report the development of a high-performance image processing platform, which is based on CPU-GPU heterogeneous cluster. Currently, it consists of a Dell Precision T7500 and HP XW8600 workstations with parallel programming and runtime environment, using the message-passing interface (MPI) and CUDA (Compute Unified Device Architecture). We succeeded in developing parallel image processing techniques for 3D image reconstruction of X-ray micro-CT imaging. The results show that a GPU provides a computing efficiency of about 194 times faster than a single CPU, and the CPU-GPU clusters provides a computing efficiency of about 46 times faster than the CPU clusters. These meet the requirements of rapid 3D image reconstruction and real time image display. In conclusion, the use of CPU-GPU heterogeneous cluster is an effective way to build high-performance image processing platform. (authors)
Parallel implementation of geometric transformations
Energy Technology Data Exchange (ETDEWEB)
Clarke, K A; Ip, H H.S.
1982-10-01
An implementation of digitized picture rotation and magnification based on Weiman's algorithm is presented. In a programmable array machine routines to perform small transformations code efficiently. The method illustrates the interpolative nature of the algorithm. 6 references.
Computing treewidth on the GPU
Van Der Zanden, Tom C.; Bodlaender, Hans L.
2018-01-01
We present a parallel algorithm for computing the treewidth of a graph on a GPU. We implement this algorithm in OpenCL, and experimentally evaluate its performance. Our algorithm is based on an O∗(2n)-time algorithm that explores the elimination orderings of the graph using a Held-Karp like dynamic
Computing treewidth on the GPU
van der Zanden, T.C.; Bodlaender, Hans L.
2017-01-01
We present a parallel algorithm for computing the treewidth of a graph on a GPU. We implement this algorithm in OpenCL, and experimentally evaluate its performance. Our algorithm is based on an $O^*(2^{n})$-time algorithm that explores the elimination orderings of the graph using a Held-Karp like
Breast Cancer Image Segmentation Using K-Means Clustering Based on GPU Cuda Parallel Computing
Directory of Open Access Journals (Sweden)
Andika Elok Amalia
2018-02-01
Full Text Available Image processing technology is now widely used in the health area, one example is to help the radiologist to analyze the result of MRI (Magnetic Resonance Imaging, CT Scan and Mammography. Image segmentation is a process which is intended to obtain the objects contained in the image by dividing the image into several areas that have similarity attributes on an object with the aim of facilitating the analysis process. The increasing amount of patient data and larger image size are new challenges in segmentation process to use time efficiently while still keeping the process quality. Research on the segmentation of medical images have been done but still few that combine with parallel computing. In this research, K-Means clustering on the image of mammography result is implemented using two-way computation which are serial and parallel. The result shows that parallel computing gives faster average performance execution up to twofold.
a method of gravity and seismic sequential inversion and its GPU implementation
Liu, G.; Meng, X.
2011-12-01
In this abstract, we introduce a gravity and seismic sequential inversion method to invert for density and velocity together. For the gravity inversion, we use an iterative method based on correlation imaging algorithm; for the seismic inversion, we use the full waveform inversion. The link between the density and velocity is an empirical formula called Gardner equation, for large volumes of data, we use the GPU to accelerate the computation. For the gravity inversion method , we introduce a method based on correlation imaging algorithm,it is also a interative method, first we calculate the correlation imaging of the observed gravity anomaly, it is some value between -1 and +1, then we multiply this value with a little density ,this value become the initial density model. We get a forward reuslt with this initial model and also calculate the correaltion imaging of the misfit of observed data and the forward data, also multiply the correaltion imaging result a little density and add it to the initial model, then do the same procedure above , at last ,we can get a inversion density model. For the seismic inveron method ,we use a mothod base on the linearity of acoustic wave equation written in the frequency domain,with a intial velociy model, we can get a good velocity result. In the sequential inversion of gravity and seismic , we need a link formula to convert between density and velocity ,in our method , we use the Gardner equation. Driven by the insatiable market demand for real time, high-definition 3D images, the programmable NVIDIA Graphic Processing Unit (GPU) as co-processor of CPU has been developed for high performance computing. Compute Unified Device Architecture (CUDA) is a parallel programming model and software environment provided by NVIDIA designed to overcome the challenge of using traditional general purpose GPU while maintaining a low learn curve for programmers familiar with standard programming languages such as C. In our inversion processing
International Nuclear Information System (INIS)
Xu, Zuwei; Zhao, Haibo; Zheng, Chuguang
2015-01-01
This paper proposes a comprehensive framework for accelerating population balance-Monte Carlo (PBMC) simulation of particle coagulation dynamics. By combining Markov jump model, weighted majorant kernel and GPU (graphics processing unit) parallel computing, a significant gain in computational efficiency is achieved. The Markov jump model constructs a coagulation-rule matrix of differentially-weighted simulation particles, so as to capture the time evolution of particle size distribution with low statistical noise over the full size range and as far as possible to reduce the number of time loopings. Here three coagulation rules are highlighted and it is found that constructing appropriate coagulation rule provides a route to attain the compromise between accuracy and cost of PBMC methods. Further, in order to avoid double looping over all simulation particles when considering the two-particle events (typically, particle coagulation), the weighted majorant kernel is introduced to estimate the maximum coagulation rates being used for acceptance–rejection processes by single-looping over all particles, and meanwhile the mean time-step of coagulation event is estimated by summing the coagulation kernels of rejected and accepted particle pairs. The computational load of these fast differentially-weighted PBMC simulations (based on the Markov jump model) is reduced greatly to be proportional to the number of simulation particles in a zero-dimensional system (single cell). Finally, for a spatially inhomogeneous multi-dimensional (multi-cell) simulation, the proposed fast PBMC is performed in each cell, and multiple cells are parallel processed by multi-cores on a GPU that can implement the massively threaded data-parallel tasks to obtain remarkable speedup ratio (comparing with CPU computation, the speedup ratio of GPU parallel computing is as high as 200 in a case of 100 cells with 10 000 simulation particles per cell). These accelerating approaches of PBMC are
Murphy, Mark; Alley, Marcus; Demmel, James; Keutzer, Kurt; Vasanawala, Shreyas; Lustig, Michael
2012-01-01
We present ℓ1-SPIRiT, a simple algorithm for auto calibrating parallel imaging (acPI) and compressed sensing (CS) that permits an efficient implementation with clinically-feasible runtimes. We propose a CS objective function that minimizes cross-channel joint sparsity in the Wavelet domain. Our reconstruction minimizes this objective via iterative soft-thresholding, and integrates naturally with iterative Self-Consistent Parallel Imaging (SPIRiT). Like many iterative MRI reconstructions, ℓ1-SPIRiT’s image quality comes at a high computational cost. Excessively long runtimes are a barrier to the clinical use of any reconstruction approach, and thus we discuss our approach to efficiently parallelizing ℓ1-SPIRiT and to achieving clinically-feasible runtimes. We present parallelizations of ℓ1-SPIRiT for both multi-GPU systems and multi-core CPUs, and discuss the software optimization and parallelization decisions made in our implementation. The performance of these alternatives depends on the processor architecture, the size of the image matrix, and the number of parallel imaging channels. Fundamentally, achieving fast runtime requires the correct trade-off between cache usage and parallelization overheads. We demonstrate image quality via a case from our clinical experimentation, using a custom 3DFT Spoiled Gradient Echo (SPGR) sequence with up to 8× acceleration via poisson-disc undersampling in the two phase-encoded directions. PMID:22345529
International Nuclear Information System (INIS)
Kohno, R; Hotta, K; Nishioka, S; Matsubara, K; Tansho, R; Suzuki, T
2011-01-01
We implemented the simplified Monte Carlo (SMC) method on graphics processing unit (GPU) architecture under the computer-unified device architecture platform developed by NVIDIA. The GPU-based SMC was clinically applied for four patients with head and neck, lung, or prostate cancer. The results were compared to those obtained by a traditional CPU-based SMC with respect to the computation time and discrepancy. In the CPU- and GPU-based SMC calculations, the estimated mean statistical errors of the calculated doses in the planning target volume region were within 0.5% rms. The dose distributions calculated by the GPU- and CPU-based SMCs were similar, within statistical errors. The GPU-based SMC showed 12.30–16.00 times faster performance than the CPU-based SMC. The computation time per beam arrangement using the GPU-based SMC for the clinical cases ranged 9–67 s. The results demonstrate the successful application of the GPU-based SMC to a clinical proton treatment planning. (note)
Implementing Shared Memory Parallelism in MCBEND
Directory of Open Access Journals (Sweden)
Bird Adam
2017-01-01
Full Text Available MCBEND is a general purpose radiation transport Monte Carlo code from AMEC Foster Wheelers’s ANSWERS® Software Service. MCBEND is well established in the UK shielding community for radiation shielding and dosimetry assessments. The existing MCBEND parallel capability effectively involves running the same calculation on many processors. This works very well except when the memory requirements of a model restrict the number of instances of a calculation that will fit on a machine. To more effectively utilise parallel hardware OpenMP has been used to implement shared memory parallelism in MCBEND. This paper describes the reasoning behind the choice of OpenMP, notes some of the challenges of multi-threading an established code such as MCBEND and assesses the performance of the parallel method implemented in MCBEND.
A parallel implementation of 3D Zernike moment analysis
Berjón, Daniel; Arnaldo, Sergio; Morán, Francisco
2011-01-01
Zernike polynomials are a well known set of functions that find many applications in image or pattern characterization because they allow to construct shape descriptors that are invariant against translations, rotations or scale changes. The concepts behind them can be extended to higher dimension spaces, making them also fit to describe volumetric data. They have been less used than their properties might suggest due to their high computational cost. We present a parallel implementation of 3D Zernike moments analysis, written in C with CUDA extensions, which makes it practical to employ Zernike descriptors in interactive applications, yielding a performance of several frames per second in voxel datasets about 2003 in size. In our contribution, we describe the challenges of implementing 3D Zernike analysis in a general-purpose GPU. These include how to deal with numerical inaccuracies, due to the high precision demands of the algorithm, or how to deal with the high volume of input data so that it does not become a bottleneck for the system.
R-GPU : A reconfigurable GPU architecture
van den Braak, G.J.; Corporaal, H.
2016-01-01
Over the last decade, Graphics Processing Unit (GPU) architectures have evolved from a fixed-function graphics pipeline to a programmable, energy-efficient compute accelerator for massively parallel applications. The compute power arises from the GPU's Single Instruction/Multiple Threads
Fast neuromimetic object recognition using FPGA outperforms GPU implementations.
Orchard, Garrick; Martin, Jacob G; Vogelstein, R Jacob; Etienne-Cummings, Ralph
2013-08-01
Recognition of objects in still images has traditionally been regarded as a difficult computational problem. Although modern automated methods for visual object recognition have achieved steadily increasing recognition accuracy, even the most advanced computational vision approaches are unable to obtain performance equal to that of humans. This has led to the creation of many biologically inspired models of visual object recognition, among them the hierarchical model and X (HMAX) model. HMAX is traditionally known to achieve high accuracy in visual object recognition tasks at the expense of significant computational complexity. Increasing complexity, in turn, increases computation time, reducing the number of images that can be processed per unit time. In this paper we describe how the computationally intensive and biologically inspired HMAX model for visual object recognition can be modified for implementation on a commercial field-programmable aate Array, specifically the Xilinx Virtex 6 ML605 evaluation board with XC6VLX240T FPGA. We show that with minor modifications to the traditional HMAX model we can perform recognition on images of size 128 × 128 pixels at a rate of 190 images per second with a less than 1% loss in recognition accuracy in both binary and multiclass visual object recognition tasks.
GPU Accelerated Chemical Similarity Calculation for Compound Library Comparison
Ma, Chao; Wang, Lirong; Xie, Xiang-Qun
2012-01-01
Chemical similarity calculation plays an important role in compound library design, virtual screening, and “lead” optimization. In this manuscript, we present a novel GPU-accelerated algorithm for all-vs-all Tanimoto matrix calculation and nearest neighbor search. By taking advantage of multi-core GPU architecture and CUDA parallel programming technology, the algorithm is up to 39 times superior to the existing commercial software that runs on CPUs. Because of the utilization of intrinsic GPU instructions, this approach is nearly 10 times faster than existing GPU-accelerated sparse vector algorithm, when Unity fingerprints are used for Tanimoto calculation. The GPU program that implements this new method takes about 20 minutes to complete the calculation of Tanimoto coefficients between 32M PubChem compounds and 10K Active Probes compounds, i.e., 324G Tanimoto coefficients, on a 128-CUDA-core GPU. PMID:21692447
A task parallel implementation of fast multipole methods
Taura, Kenjiro; Nakashima, Jun; Yokota, Rio; Maruyama, Naoya
2012-01-01
This paper describes a task parallel implementation of ExaFMM, an open source implementation of fast multipole methods (FMM), using a lightweight task parallel library MassiveThreads. Although there have been many attempts on parallelizing FMM
Sailfish: A flexible multi-GPU implementation of the lattice Boltzmann method
Januszewski, M.; Kostur, M.
2014-09-01
We present Sailfish, an open source fluid simulation package implementing the lattice Boltzmann method (LBM) on modern Graphics Processing Units (GPUs) using CUDA/OpenCL. We take a novel approach to GPU code implementation and use run-time code generation techniques and a high level programming language (Python) to achieve state of the art performance, while allowing easy experimentation with different LBM models and tuning for various types of hardware. We discuss the general design principles of the code, scaling to multiple GPUs in a distributed environment, as well as the GPU implementation and optimization of many different LBM models, both single component (BGK, MRT, ELBM) and multicomponent (Shan-Chen, free energy). The paper also presents results of performance benchmarks spanning the last three NVIDIA GPU generations (Tesla, Fermi, Kepler), which we hope will be useful for researchers working with this type of hardware and similar codes. Catalogue identifier: AETA_v1_0 Program summary URL:http://cpc.cs.qub.ac.uk/summaries/AETA_v1_0.html Program obtainable from: CPC Program Library, Queen's University, Belfast, N. Ireland Licensing provisions: GNU Lesser General Public License, version 3 No. of lines in distributed program, including test data, etc.: 225864 No. of bytes in distributed program, including test data, etc.: 46861049 Distribution format: tar.gz Programming language: Python, CUDA C, OpenCL. Computer: Any with an OpenCL or CUDA-compliant GPU. Operating system: No limits (tested on Linux and Mac OS X). RAM: Hundreds of megabytes to tens of gigabytes for typical cases. Classification: 12, 6.5. External routines: PyCUDA/PyOpenCL, Numpy, Mako, ZeroMQ (for multi-GPU simulations), scipy, sympy Nature of problem: GPU-accelerated simulation of single- and multi-component fluid flows. Solution method: A wide range of relaxation models (LBGK, MRT, regularized LB, ELBM, Shan-Chen, free energy, free surface) and boundary conditions within the lattice
International Nuclear Information System (INIS)
Tavares, R S; Tsuzuki, M S G; Martins, T C
2012-01-01
Electrical Impedance Tomography (EIT) is an imaging technique that attempts to reconstruct the conductivity distribution inside an object from electrical currents and potentials applied and measured at its surface. The EIT reconstruction problem is approached as an optimization problem, where the difference between the simulated and measured distributions must be minimized. This optimization problem can be solved using Simulated Annealing (SA), but at a high computational cost. To reduce the computational load, it is possible to use an incomplete evaluation of the objective function. This algorithm showed to present an outside-in behavior, determining the impedance of the external elements first, similar to a layer striping algorithm. A new outside-in heuristic to make use of this property is proposed. It also presents the impact of using GPU for parallelizing matrix-vector multiplication and triangular solvers. Results with experimental data are presented. The outside-in heuristic showed to be faster when compared to the conventional SA algorithm.
Multi–GPU Implementation of Machine Learning Algorithm using CUDA and OpenCL
Directory of Open Access Journals (Sweden)
Jan Masek
2016-06-01
Full Text Available Using modern Graphic Processing Units (GPUs becomes very useful for computing complex and time consuming processes. GPUs provide high–performance computation capabilities with a good price. This paper deals with a multi–GPU OpenCL and CUDA implementations of k–Nearest Neighbor (k–NN algorithm. This work compares performances of OpenCLand CUDA implementations where each of them is suitable for different number of used attributes. The proposed CUDA algorithm achieves acceleration up to 880x in comparison witha single thread CPU version. The common k-NN was modified to be faster when the lower number of k neighbors is set. The performance of algorithm was verified with two GPUs dual-core NVIDIA GeForce GTX 690 and CPU Intel Core i7 3770 with 4.1 GHz frequency. The results of speed up were measured for one GPU, two GPUs, three and four GPUs. We performed several tests with data sets containing up to 4 million elements with various number of attributes.
Computation and parallel implementation for early vision
Gualtieri, J. Anthony
1990-01-01
The problem of early vision is to transform one or more retinal illuminance images-pixel arrays-to image representations built out of such primitive visual features such as edges, regions, disparities, and clusters. These transformed representations form the input to later vision stages that perform higher level vision tasks including matching and recognition. Researchers developed algorithms for: (1) edge finding in the scale space formulation; (2) correlation methods for computing matches between pairs of images; and (3) clustering of data by neural networks. These algorithms are formulated for parallel implementation of SIMD machines, such as the Massively Parallel Processor, a 128 x 128 array processor with 1024 bits of local memory per processor. For some cases, researchers can show speedups of three orders of magnitude over serial implementations.
Putnam, William M.
2011-01-01
Earth system models like the Goddard Earth Observing System model (GEOS-5) have been pushing the limits of large clusters of multi-core microprocessors, producing breath-taking fidelity in resolving cloud systems at a global scale. GPU computing presents an opportunity for improving the efficiency of these leading edge models. A GPU implementation of GEOS-5 will facilitate the use of cloud-system resolving resolutions in data assimilation and weather prediction, at resolutions near 3.5 km, improving our ability to extract detailed information from high-resolution satellite observations and ultimately produce better weather and climate predictions
Rueda, Antonio J.; Noguera, José M.; Luque, Adrián
2016-02-01
In recent years GPU computing has gained wide acceptance as a simple low-cost solution for speeding up computationally expensive processing in many scientific and engineering applications. However, in most cases accelerating a traditional CPU implementation for a GPU is a non-trivial task that requires a thorough refactorization of the code and specific optimizations that depend on the architecture of the device. OpenACC is a promising technology that aims at reducing the effort required to accelerate C/C++/Fortran code on an attached multicore device. Virtually with this technology the CPU code only has to be augmented with a few compiler directives to identify the areas to be accelerated and the way in which data has to be moved between the CPU and GPU. Its potential benefits are multiple: better code readability, less development time, lower risk of errors and less dependency on the underlying architecture and future evolution of the GPU technology. Our aim with this work is to evaluate the pros and cons of using OpenACC against native GPU implementations in computationally expensive hydrological applications, using the classic D8 algorithm of O'Callaghan and Mark for river network extraction as case-study. We implemented the flow accumulation step of this algorithm in CPU, using OpenACC and two different CUDA versions, comparing the length and complexity of the code and its performance with different datasets. We advance that although OpenACC can not match the performance of a CUDA optimized implementation (×3.5 slower in average), it provides a significant performance improvement against a CPU implementation (×2-6) with by far a simpler code and less implementation effort.
International Nuclear Information System (INIS)
Santos, Marcelo C. dos; Pereira, Claudio M.N.A.; Schirru, Roberto; Pinheiro, André; Coordenacao de Pos-Graduacao e Pesquisa de Engenharia
2017-01-01
Atmospheric radionuclide dispersion systems (ARDS) are essential mechanisms to predict the consequences of unexpected radioactive releases from nuclear power plants. Considering, that during an eventuality of an accident with a radioactive material release, an accurate forecast is vital to guide the evacuation plan of the possible affected areas. However, in order to predict the dispersion of the radioactive material and its impact on the environment, the model must process information about source term (radioactive materials released, activities and location), weather condition (wind, humidity and precipitation) and geographical characteristics (topography). Furthermore, ARDS is basically composed of 4 main modules: Source Term, Wind Field, Plume Dispersion and Doses Calculations. The Wind Field and Plume Dispersion modules are the ones that require a high computational performance to achieve accurate results within an acceptable time. Taking this into account, this work focuses on the development of a GPU-based parallel Plume Dispersion module, focusing on the radionuclide transport and diffusion calculations, which use a given wind field and a released source term as parameters. The program is being developed using the C ++ programming language, allied with CUDA libraries. In comparative case study between a parallel and sequential version of the slower function of the Plume Dispersion module, a speedup of 11.63 times could be observed. (author)
Energy Technology Data Exchange (ETDEWEB)
Santos, Marcelo C. dos; Pereira, Claudio M.N.A.; Schirru, Roberto; Pinheiro, André, E-mail: jovitamarcelo@gmail.com, E-mail: cmnap@ien.gov.br, E-mail: schirru@lmp.ufrj.br, E-mail: apinheiro99@gmail.com [Instituto de Engenharia Nuclear (IEN/CNEN-RJ), Rio de Janeiro, RJ (Brazil); Coordenacao de Pos-Graduacao e Pesquisa de Engenharia (COPPE/UFRJ), Rio de Janeiro, RJ (Brazil). Programa de Engenharia Nuclear
2017-07-01
Atmospheric radionuclide dispersion systems (ARDS) are essential mechanisms to predict the consequences of unexpected radioactive releases from nuclear power plants. Considering, that during an eventuality of an accident with a radioactive material release, an accurate forecast is vital to guide the evacuation plan of the possible affected areas. However, in order to predict the dispersion of the radioactive material and its impact on the environment, the model must process information about source term (radioactive materials released, activities and location), weather condition (wind, humidity and precipitation) and geographical characteristics (topography). Furthermore, ARDS is basically composed of 4 main modules: Source Term, Wind Field, Plume Dispersion and Doses Calculations. The Wind Field and Plume Dispersion modules are the ones that require a high computational performance to achieve accurate results within an acceptable time. Taking this into account, this work focuses on the development of a GPU-based parallel Plume Dispersion module, focusing on the radionuclide transport and diffusion calculations, which use a given wind field and a released source term as parameters. The program is being developed using the C ++ programming language, allied with CUDA libraries. In comparative case study between a parallel and sequential version of the slower function of the Plume Dispersion module, a speedup of 11.63 times could be observed. (author)
Lin, Hui; Liu, Tianyu; Su, Lin; Bednarz, Bryan; Caracappa, Peter; Xu, X. George
2017-09-01
Monte Carlo (MC) simulation is well recognized as the most accurate method for radiation dose calculations. For radiotherapy applications, accurate modelling of the source term, i.e. the clinical linear accelerator is critical to the simulation. The purpose of this paper is to perform source modelling and examine the accuracy and performance of the models on Intel Many Integrated Core coprocessors (aka Xeon Phi) and Nvidia GPU using ARCHER and explore the potential optimization methods. Phase Space-based source modelling for has been implemented. Good agreements were found in a tomotherapy prostate patient case and a TrueBeam breast case. From the aspect of performance, the whole simulation for prostate plan and breast plan cost about 173s and 73s with 1% statistical error.
Directory of Open Access Journals (Sweden)
Lin Hui
2017-01-01
Full Text Available Monte Carlo (MC simulation is well recognized as the most accurate method for radiation dose calculations. For radiotherapy applications, accurate modelling of the source term, i.e. the clinical linear accelerator is critical to the simulation. The purpose of this paper is to perform source modelling and examine the accuracy and performance of the models on Intel Many Integrated Core coprocessors (aka Xeon Phi and Nvidia GPU using ARCHER and explore the potential optimization methods. Phase Space-based source modelling for has been implemented. Good agreements were found in a tomotherapy prostate patient case and a TrueBeam breast case. From the aspect of performance, the whole simulation for prostate plan and breast plan cost about 173s and 73s with 1% statistical error.
NMF-mGPU: non-negative matrix factorization on multi-GPU systems.
Mejía-Roa, Edgardo; Tabas-Madrid, Daniel; Setoain, Javier; García, Carlos; Tirado, Francisco; Pascual-Montano, Alberto
2015-02-13
In the last few years, the Non-negative Matrix Factorization ( NMF ) technique has gained a great interest among the Bioinformatics community, since it is able to extract interpretable parts from high-dimensional datasets. However, the computing time required to process large data matrices may become impractical, even for a parallel application running on a multiprocessors cluster. In this paper, we present NMF-mGPU, an efficient and easy-to-use implementation of the NMF algorithm that takes advantage of the high computing performance delivered by Graphics-Processing Units ( GPUs ). Driven by the ever-growing demands from the video-games industry, graphics cards usually provided in PCs and laptops have evolved from simple graphics-drawing platforms into high-performance programmable systems that can be used as coprocessors for linear-algebra operations. However, these devices may have a limited amount of on-board memory, which is not considered by other NMF implementations on GPU. NMF-mGPU is based on CUDA ( Compute Unified Device Architecture ), the NVIDIA's framework for GPU computing. On devices with low memory available, large input matrices are blockwise transferred from the system's main memory to the GPU's memory, and processed accordingly. In addition, NMF-mGPU has been explicitly optimized for the different CUDA architectures. Finally, platforms with multiple GPUs can be synchronized through MPI ( Message Passing Interface ). In a four-GPU system, this implementation is about 120 times faster than a single conventional processor, and more than four times faster than a single GPU device (i.e., a super-linear speedup). Applications of GPUs in Bioinformatics are getting more and more attention due to their outstanding performance when compared to traditional processors. In addition, their relatively low price represents a highly cost-effective alternative to conventional clusters. In life sciences, this results in an excellent opportunity to facilitate the
Doulgerakis, Matthaios; Eggebrecht, Adam; Wojtkiewicz, Stanislaw; Culver, Joseph; Dehghani, Hamid
2017-12-01
Parameter recovery in diffuse optical tomography is a computationally expensive algorithm, especially when used for large and complex volumes, as in the case of human brain functional imaging. The modeling of light propagation, also known as the forward problem, is the computational bottleneck of the recovery algorithm, whereby the lack of a real-time solution is impeding practical and clinical applications. The objective of this work is the acceleration of the forward model, within a diffusion approximation-based finite-element modeling framework, employing parallelization to expedite the calculation of light propagation in realistic adult head models. The proposed methodology is applicable for modeling both continuous wave and frequency-domain systems with the results demonstrating a 10-fold speed increase when GPU architectures are available, while maintaining high accuracy. It is shown that, for a very high-resolution finite-element model of the adult human head with ∼600,000 nodes, consisting of heterogeneous layers, light propagation can be calculated at ∼0.25 s/excitation source. (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE).
Doulgerakis, Matthaios; Eggebrecht, Adam; Wojtkiewicz, Stanislaw; Culver, Joseph; Dehghani, Hamid
2017-12-01
Parameter recovery in diffuse optical tomography is a computationally expensive algorithm, especially when used for large and complex volumes, as in the case of human brain functional imaging. The modeling of light propagation, also known as the forward problem, is the computational bottleneck of the recovery algorithm, whereby the lack of a real-time solution is impeding practical and clinical applications. The objective of this work is the acceleration of the forward model, within a diffusion approximation-based finite-element modeling framework, employing parallelization to expedite the calculation of light propagation in realistic adult head models. The proposed methodology is applicable for modeling both continuous wave and frequency-domain systems with the results demonstrating a 10-fold speed increase when GPU architectures are available, while maintaining high accuracy. It is shown that, for a very high-resolution finite-element model of the adult human head with ˜600,000 nodes, consisting of heterogeneous layers, light propagation can be calculated at ˜0.25 s/excitation source.
Implementation and Optimization of GPU-Based Static State Security Analysis in Power Systems
Directory of Open Access Journals (Sweden)
Yong Chen
2017-01-01
Full Text Available Static state security analysis (SSSA is one of the most important computations to check whether a power system is in normal and secure operating state. It is a challenge to satisfy real-time requirements with CPU-based concurrent methods due to the intensive computations. A sensitivity analysis-based method with Graphics processing unit (GPU is proposed for power systems, which can reduce calculation time by 40% compared to the execution on a 4-core CPU. The proposed method involves load flow analysis and sensitivity analysis. In load flow analysis, a multifrontal method for sparse LU factorization is explored on GPU through dynamic frontal task scheduling between CPU and GPU. The varying matrix operations during sensitivity analysis on GPU are highly optimized in this study. The results of performance evaluations show that the proposed GPU-based SSSA with optimized matrix operations can achieve a significant reduction in computation time.
Efficient implementation of the many-body Reactive Bond Order (REBO) potential on GPU
Energy Technology Data Exchange (ETDEWEB)
Trędak, Przemysław, E-mail: przemyslaw.tredak@fuw.edu.pl [Faculty of Physics, University of Warsaw, ul. Pasteura 5, 02-093 Warsaw (Poland); Rudnicki, Witold R. [Institute of Informatics, University of Białystok, ul. Konstantego Ciołkowskiego 1M, 15-245 Białystok (Poland); Interdisciplinary Centre for Mathematical and Computational Modelling, University of Warsaw, ul. Pawińskiego 5a, 02-106 Warsaw (Poland); Majewski, Jacek A. [Faculty of Physics, University of Warsaw, ul. Pasteura 5, 02-093 Warsaw (Poland)
2016-09-15
The second generation Reactive Bond Order (REBO) empirical potential is commonly used to accurately model a wide range hydrocarbon materials. It is also extensible to other atom types and interactions. REBO potential assumes complex multi-body interaction model, that is difficult to represent efficiently in the SIMD or SIMT programming model. Hence, despite its importance, no efficient GPGPU implementation has been developed for this potential. Here we present a detailed description of a highly efficient GPGPU implementation of molecular dynamics algorithm using REBO potential. The presented algorithm takes advantage of rarely used properties of the SIMT architecture of a modern GPU to solve difficult synchronizations issues that arise in computations of multi-body potential. Techniques developed for this problem may be also used to achieve efficient solutions of different problems. The performance of proposed algorithm is assessed using a range of model systems. It is compared to highly optimized CPU implementation (both single core and OpenMP) available in LAMMPS package. These experiments show up to 6x improvement in forces computation time using single processor of the NVIDIA Tesla K80 compared to high end 16-core Intel Xeon processor.
Portable implementation model for CFD simulations. Application to hybrid CPU/GPU supercomputers
Oyarzun, Guillermo; Borrell, Ricard; Gorobets, Andrey; Oliva, Assensi
2017-10-01
Nowadays, high performance computing (HPC) systems experience a disruptive moment with a variety of novel architectures and frameworks, without any clarity of which one is going to prevail. In this context, the portability of codes across different architectures is of major importance. This paper presents a portable implementation model based on an algebraic operational approach for direct numerical simulation (DNS) and large eddy simulation (LES) of incompressible turbulent flows using unstructured hybrid meshes. The strategy proposed consists in representing the whole time-integration algorithm using only three basic algebraic operations: sparse matrix-vector product, a linear combination of vectors and dot product. The main idea is based on decomposing the nonlinear operators into a concatenation of two SpMV operations. This provides high modularity and portability. An exhaustive analysis of the proposed implementation for hybrid CPU/GPU supercomputers has been conducted with tests using up to 128 GPUs. The main objective consists in understanding the challenges of implementing CFD codes on new architectures.
Solving global optimization problems on GPU cluster
Energy Technology Data Exchange (ETDEWEB)
Barkalov, Konstantin; Gergel, Victor; Lebedev, Ilya [Lobachevsky State University of Nizhni Novgorod, Gagarin Avenue 23, 603950 Nizhni Novgorod (Russian Federation)
2016-06-08
The paper contains the results of investigation of a parallel global optimization algorithm combined with a dimension reduction scheme. This allows solving multidimensional problems by means of reducing to data-independent subproblems with smaller dimension solved in parallel. The new element implemented in the research consists in using several graphic accelerators at different computing nodes. The paper also includes results of solving problems of well-known multiextremal test class GKLS on Lobachevsky supercomputer using tens of thousands of GPU cores.
A GPU implementation of a track-repeating algorithm for proton radiotherapy dose calculations
International Nuclear Information System (INIS)
Yepes, Pablo P; Mirkovic, Dragan; Taddei, Phillip J
2010-01-01
An essential component in proton radiotherapy is the algorithm to calculate the radiation dose to be delivered to the patient. The most common dose algorithms are fast but they are approximate analytical approaches. However their level of accuracy is not always satisfactory, especially for heterogeneous anatomical areas, like the thorax. Monte Carlo techniques provide superior accuracy; however, they often require large computation resources, which render them impractical for routine clinical use. Track-repeating algorithms, for example the fast dose calculator, have shown promise for achieving the accuracy of Monte Carlo simulations for proton radiotherapy dose calculations in a fraction of the computation time. We report on the implementation of the fast dose calculator for proton radiotherapy on a card equipped with graphics processor units (GPUs) rather than on a central processing unit architecture. This implementation reproduces the full Monte Carlo and CPU-based track-repeating dose calculations within 2%, while achieving a statistical uncertainty of 2% in less than 1 min utilizing one single GPU card, which should allow real-time accurate dose calculations.
Implementation and performance of parallelized elegant
International Nuclear Information System (INIS)
Wang, Y.; Borland, M.
2008-01-01
The program elegant is widely used for design and modeling of linacs for free-electron lasers and energy recovery linacs, as well as storage rings and other applications. As part of a multi-year effort, we have parallelized many aspects of the code, including single-particle dynamics, wakefields, and coherent synchrotron radiation. We report on the approach used for gradual parallelization, which proved very beneficial in getting parallel features into the hands of users quickly. We also report details of parallelization of collective effects. Finally, we discuss performance of the parallelized code in various applications.
A Parallel Algebraic Multigrid Solver on Graphics Processing Units
Haase, Gundolf
2010-01-01
The paper presents a multi-GPU implementation of the preconditioned conjugate gradient algorithm with an algebraic multigrid preconditioner (PCG-AMG) for an elliptic model problem on a 3D unstructured grid. An efficient parallel sparse matrix-vector multiplication scheme underlying the PCG-AMG algorithm is presented for the many-core GPU architecture. A performance comparison of the parallel solver shows that a singe Nvidia Tesla C1060 GPU board delivers the performance of a sixteen node Infiniband cluster and a multi-GPU configuration with eight GPUs is about 100 times faster than a typical server CPU core. © 2010 Springer-Verlag.
Implementations of BLAST for parallel computers.
Jülich, A
1995-02-01
The BLAST sequence comparison programs have been ported to a variety of parallel computers-the shared memory machine Cray Y-MP 8/864 and the distributed memory architectures Intel iPSC/860 and nCUBE. Additionally, the programs were ported to run on workstation clusters. We explain the parallelization techniques and consider the pros and cons of these methods. The BLAST programs are very well suited for parallelization for a moderate number of processors. We illustrate our results using the program blastp as an example. As input data for blastp, a 799 residue protein query sequence and the protein database PIR were used.
2015-06-01
implementation of the direct interaction called particle-to-particle kernel for a shared-memory single GPU device using the Compute Unified Device Architecture ...GPU-defined P2P kernel we developed using the Compute Unified Device Architecture (CUDA).9 A brief outline of the rest of this work follows. The...Employed The computing environment used for this work is a 64-node heterogeneous cluster consisting of 48 IBM dx360M4 nodes, each with one Intel Phi
Event- and Time-Driven Techniques Using Parallel CPU-GPU Co-processing for Spiking Neural Networks.
Naveros, Francisco; Garrido, Jesus A; Carrillo, Richard R; Ros, Eduardo; Luque, Niceto R
2017-01-01
Modeling and simulating the neural structures which make up our central neural system is instrumental for deciphering the computational neural cues beneath. Higher levels of biological plausibility usually impose higher levels of complexity in mathematical modeling, from neural to behavioral levels. This paper focuses on overcoming the simulation problems (accuracy and performance) derived from using higher levels of mathematical complexity at a neural level. This study proposes different techniques for simulating neural models that hold incremental levels of mathematical complexity: leaky integrate-and-fire (LIF), adaptive exponential integrate-and-fire (AdEx), and Hodgkin-Huxley (HH) neural models (ranged from low to high neural complexity). The studied techniques are classified into two main families depending on how the neural-model dynamic evaluation is computed: the event-driven or the time-driven families. Whilst event-driven techniques pre-compile and store the neural dynamics within look-up tables, time-driven techniques compute the neural dynamics iteratively during the simulation time. We propose two modifications for the event-driven family: a look-up table recombination to better cope with the incremental neural complexity together with a better handling of the synchronous input activity. Regarding the time-driven family, we propose a modification in computing the neural dynamics: the bi-fixed-step integration method. This method automatically adjusts the simulation step size to better cope with the stiffness of the neural model dynamics running in CPU platforms. One version of this method is also implemented for hybrid CPU-GPU platforms. Finally, we analyze how the performance and accuracy of these modifications evolve with increasing levels of neural complexity. We also demonstrate how the proposed modifications which constitute the main contribution of this study systematically outperform the traditional event- and time-driven techniques under
Real-Time GPU Implementation of Transverse Oscillation Vector Velocity Flow Imaging
DEFF Research Database (Denmark)
Bradway, David; Pihl, Michael Johannes; Krebs, Andreas
2014-01-01
Rapid estimation of blood velocity and visualization of complex flow patterns are important for clinical use of diagnostic ultrasound. This paper presents real-time processing for two-dimensional (2-D) vector flow imaging which utilizes an off-the-shelf graphics processing unit (GPU). In this work...... vector flow acquisition takes 2.3 milliseconds seconds on an Advanced Micro Devices Radeon HD 7850 GPU card. The detected velocities are accurate to within the precision limit of the output format of the display routine. Because this tool was developed as a module external to the scanner’s built...
Comparison of image sharpness metrics and real-time sharpening methods with GPU implementations
CSIR Research Space (South Africa)
De Villiers, Johan P
2010-06-01
Full Text Available , and not in trying to adjust the image to some fixed sharpness value. With the advent of the increased progammability of Graphics Pro- cessing Units (GPU) and their seemingly ever increasing number of processor cores (the dual-GPU NVidia GTX295 has 480 cores...) Quadro MDS 140M 16 400 64 700 ATI HD 2400XT 40 800 64 700 NVidia 9600GT 64 650 256 900 NVidia GTX280 240 602 512 1107 2 Metric descriptions Three metrics are used to evaluate images for sharpness. The first two are a measure of how much information...
GPU Computing For Particle Tracking
International Nuclear Information System (INIS)
Nishimura, Hiroshi; Song, Kai; Muriki, Krishna; Sun, Changchun; James, Susan; Qin, Yong
2011-01-01
This is a feasibility study of using a modern Graphics Processing Unit (GPU) to parallelize the accelerator particle tracking code. To demonstrate the massive parallelization features provided by GPU computing, a simplified TracyGPU program is developed for dynamic aperture calculation. Performances, issues, and challenges from introducing GPU are also discussed. General purpose Computation on Graphics Processing Units (GPGPU) bring massive parallel computing capabilities to numerical calculation. However, the unique architecture of GPU requires a comprehensive understanding of the hardware and programming model to be able to well optimize existing applications. In the field of accelerator physics, the dynamic aperture calculation of a storage ring, which is often the most time consuming part of the accelerator modeling and simulation, can benefit from GPU due to its embarrassingly parallel feature, which fits well with the GPU programming model. In this paper, we use the Tesla C2050 GPU which consists of 14 multi-processois (MP) with 32 cores on each MP, therefore a total of 448 cores, to host thousands ot threads dynamically. Thread is a logical execution unit of the program on GPU. In the GPU programming model, threads are grouped into a collection of blocks Within each block, multiple threads share the same code, and up to 48 KB of shared memory. Multiple thread blocks form a grid, which is executed as a GPU kernel. A simplified code that is a subset of Tracy++ (2) is developed to demonstrate the possibility of using GPU to speed up the dynamic aperture calculation by having each thread track a particle.
Synergia CUDA: GPU-accelerated accelerator modeling package
International Nuclear Information System (INIS)
Lu, Q; Amundson, J
2014-01-01
Synergia is a parallel, 3-dimensional space-charge particle-in-cell accelerator modeling code. We present our work porting the purely MPI-based version of the code to a hybrid of CPU and GPU computing kernels. The hybrid code uses the CUDA platform in the same framework as the pure MPI solution. We have implemented a lock-free collaborative charge-deposition algorithm for the GPU, as well as other optimizations, including local communication avoidance for GPUs, a customized FFT, and fine-tuned memory access patterns. On a small GPU cluster (up to 4 Tesla C1070 GPUs), our benchmarks exhibit both superior peak performance and better scaling than a CPU cluster with 16 nodes and 128 cores. We also compare the code performance on different GPU architectures, including C1070 Tesla and K20 Kepler.
IMPLEMENTATION OF SERIAL AND PARALLEL BUBBLE SORT ON FPGA
Directory of Open Access Journals (Sweden)
Dwi Marhaendro Jati Purnomo
2016-06-01
Full Text Available Sorting is common process in computational world. Its utilization are on many fields from research to industry. There are many sorting algorithm in nowadays. One of the simplest yet powerful is bubble sort. In this study, bubble sort is implemented on FPGA. The implementation was taken on serial and parallel approach. Serial and parallel bubble sort then compared by means of its memory, execution time, and utility which comprises slices and LUTs. The experiments show that serial bubble sort required smaller memory as well as utility compared to parallel bubble sort. Meanwhile, parallel bubble sort performed faster than serial bubble sort
A task parallel implementation of fast multipole methods
Taura, Kenjiro
2012-11-01
This paper describes a task parallel implementation of ExaFMM, an open source implementation of fast multipole methods (FMM), using a lightweight task parallel library MassiveThreads. Although there have been many attempts on parallelizing FMM, experiences have almost exclusively been limited to formulation based on flat homogeneous parallel loops. FMM in fact contains operations that cannot be readily expressed in such conventional but restrictive models. We show that task parallelism, or parallel recursions in particular, allows us to parallelize all operations of FMM naturally and scalably. Moreover it allows us to parallelize a \\'\\'mutual interaction\\'\\' for force/potential evaluation, which is roughly twice as efficient as a more conventional, unidirectional force/potential evaluation. The net result is an open source FMM that is clearly among the fastest single node implementations, including those on GPUs; with a million particles on a 32 cores Sandy Bridge 2.20GHz node, it completes a single time step including tree construction and force/potential evaluation in 65 milliseconds. The study clearly showcases both programmability and performance benefits of flexible parallel constructs over more monolithic parallel loops. © 2012 IEEE.
Real-Time Incompressible Fluid Simulation on the GPU
Directory of Open Access Journals (Sweden)
Xiao Nie
2015-01-01
Full Text Available We present a parallel framework for simulating incompressible fluids with predictive-corrective incompressible smoothed particle hydrodynamics (PCISPH on the GPU in real time. To this end, we propose an efficient GPU streaming pipeline to map the entire computational task onto the GPU, fully exploiting the massive computational power of state-of-the-art GPUs. In PCISPH-based simulations, neighbor search is the major performance obstacle because this process is performed several times at each time step. To eliminate this bottleneck, an efficient parallel sorting method for this time-consuming step is introduced. Moreover, we discuss several optimization techniques including using fast on-chip shared memory to avoid global memory bandwidth limitations and thus further improve performance on modern GPU hardware. With our framework, the realism of real-time fluid simulation is significantly improved since our method enforces incompressibility constraint which is typically ignored due to efficiency reason in previous GPU-based SPH methods. The performance results illustrate that our approach can efficiently simulate realistic incompressible fluid in real time and results in a speed-up factor of up to 23 on a high-end NVIDIA GPU in comparison to single-threaded CPU-based implementation.
Implementation of a high performance parallel finite element micromagnetics package
International Nuclear Information System (INIS)
Scholz, W.; Suess, D.; Dittrich, R.; Schrefl, T.; Tsiantos, V.; Forster, H.; Fidler, J.
2004-01-01
A new high performance scalable parallel finite element micromagnetics package has been implemented. It includes solvers for static energy minimization, time integration of the Landau-Lifshitz-Gilbert equation, and the nudged elastic band method
An implementation of the direct-forcing immersed boundary method using GPU power
Directory of Open Access Journals (Sweden)
Bulent Tutkun
2017-01-01
Full Text Available A graphics processing unit (GPU is utilized to apply the direct-forcing immersed boundary method. The code running on the GPU is generated with the help of the Compute Unified Device Architecture (CUDA. The first and second spatial derivatives of the incompressible Navier-Stokes equations are discretized by the sixth-order central compact finite-difference schemes. Two flow fields are simulated. The first test case is the simulated flow around a square cylinder, with the results providing good estimations of the wake region mechanics and vortex shedding. The second test case is the simulated flow around a circular cylinder. This case was selected to better understand the effects of sharp corners on the force coefficients. It was observed that the estimation of the force coefficients did not result in any troubles in the case of a circular cylinder. Additionally, the performance values obtained for the calculation time for the solution of the Poisson equation are compared with the values for other CPUs and GPUs from the literature. Consequently, approximately 3× and 20× speedups are achieved in comparison with GPU (using CUSP library and CPU, respectively. CUSP is an open-source library for sparse linear algebra and graph computations on CUDA.
Implementation of Serial and Parallel Bubble Sort on Fpga
Purnomo, Dwi Marhaendro Jati; Arinaldi, Ahmad; Priyantini, Dwi Teguh; Wibisono, Ari; Febrian, Andreas
2016-01-01
Sorting is common process in computational world. Its utilization are on many fields from research to industry. There are many sorting algorithm in nowadays. One of the simplest yet powerful is bubble sort. In this study, bubble sort is implemented on FPGA. The implementation was taken on serial and parallel approach. Serial and parallel bubble sort then compared by means of its memory, execution time, and utility which comprises slices and LUTs. The experiments show that serial bubble sort r...
Parallel and vector implementation of APROS simulator code
International Nuclear Information System (INIS)
Niemi, J.; Tommiska, J.
1990-01-01
In this paper the vector and parallel processing implementation of a general purpose simulator code is discussed. In this code the utilization of vector processing is straightforward. In addition to the loop level parallel processing, the functional decomposition and the domain decomposition have been considered. Results represented for a PWR-plant simulation illustrate the potential speed-up factors of the alternatives. It turns out that the loop level parallelism and the domain decomposition are the most promising alternative to employ the parallel processing. (author)
Implementation of a parallel version of a regional climate model
Energy Technology Data Exchange (ETDEWEB)
Gerstengarbe, F.W. [ed.; Kuecken, M. [Potsdam-Institut fuer Klimafolgenforschung (PIK), Potsdam (Germany); Schaettler, U. [Deutscher Wetterdienst, Offenbach am Main (Germany). Geschaeftsbereich Forschung und Entwicklung
1997-10-01
A regional climate model developed by the Max Planck Institute for Meterology and the German Climate Computing Centre in Hamburg based on the `Europa` and `Deutschland` models of the German Weather Service has been parallelized and implemented on the IBM RS/6000 SP computer system of the Potsdam Institute for Climate Impact Research including parallel input/output processing, the explicit Eulerian time-step, the semi-implicit corrections, the normal-mode initialization and the physical parameterizations of the German Weather Service. The implementation utilizes Fortran 90 and the Message Passing Interface. The parallelization strategy used is a 2D domain decomposition. This report describes the parallelization strategy, the parallel I/O organization, the influence of different domain decomposition approaches for static and dynamic load imbalances and first numerical results. (orig.)
Acceleration for 2D time-domain elastic full waveform inversion using a single GPU card
Jiang, Jinpeng; Zhu, Peimin
2018-05-01
Full waveform inversion (FWI) is a challenging procedure due to the high computational cost related to the modeling, especially for the elastic case. The graphics processing unit (GPU) has become a popular device for the high-performance computing (HPC). To reduce the long computation time, we design and implement the GPU-based 2D elastic FWI (EFWI) in time domain using a single GPU card. We parallelize the forward modeling and gradient calculations using the CUDA programming language. To overcome the limitation of relatively small global memory on GPU, the boundary saving strategy is exploited to reconstruct the forward wavefield. Moreover, the L-BFGS optimization method used in the inversion increases the convergence of the misfit function. A multiscale inversion strategy is performed in the workflow to obtain the accurate inversion results. In our tests, the GPU-based implementations using a single GPU device achieve >15 times speedup in forward modeling, and about 12 times speedup in gradient calculation, compared with the eight-core CPU implementations optimized by OpenMP. The test results from the GPU implementations are verified to have enough accuracy by comparing the results obtained from the CPU implementations.
CSIR Research Space (South Africa)
Govender, Nicolin
2015-09-01
Full Text Available consideration due to the architectural differences between CPU and GPU platforms. This paper describes the DEM algorithms and heuristics that are optimized for the parallel NVIDIA Kepler GPU architecture in detail. This includes a GPU optimized collision...
Advantages of GPU technology in DFT calculations of intercalated graphene
Pešić, J.; Gajić, R.
2014-09-01
Over the past few years, the expansion of general-purpose graphic-processing unit (GPGPU) technology has had a great impact on computational science. GPGPU is the utilization of a graphics-processing unit (GPU) to perform calculations in applications usually handled by the central processing unit (CPU). Use of GPGPUs as a way to increase computational power in the material sciences has significantly decreased computational costs in already highly demanding calculations. A level of the acceleration and parallelization depends on the problem itself. Some problems can benefit from GPU acceleration and parallelization, such as the finite-difference time-domain algorithm (FTDT) and density-functional theory (DFT), while others cannot take advantage of these modern technologies. A number of GPU-supported applications had emerged in the past several years (www.nvidia.com/object/gpu-applications.html). Quantum Espresso (QE) is reported as an integrated suite of open source computer codes for electronic-structure calculations and materials modeling at the nano-scale. It is based on DFT, the use of a plane-waves basis and a pseudopotential approach. Since the QE 5.0 version, it has been implemented as a plug-in component for standard QE packages that allows exploiting the capabilities of Nvidia GPU graphic cards (www.qe-forge.org/gf/proj). In this study, we have examined the impact of the usage of GPU acceleration and parallelization on the numerical performance of DFT calculations. Graphene has been attracting attention worldwide and has already shown some remarkable properties. We have studied an intercalated graphene, using the QE package PHonon, which employs GPU. The term ‘intercalation’ refers to a process whereby foreign adatoms are inserted onto a graphene lattice. In addition, by intercalating different atoms between graphene layers, it is possible to tune their physical properties. Our experiments have shown there are benefits from using GPUs, and we reached an
Advantages of GPU technology in DFT calculations of intercalated graphene
International Nuclear Information System (INIS)
Pešić, J; Gajić, R
2014-01-01
Over the past few years, the expansion of general-purpose graphic-processing unit (GPGPU) technology has had a great impact on computational science. GPGPU is the utilization of a graphics-processing unit (GPU) to perform calculations in applications usually handled by the central processing unit (CPU). Use of GPGPUs as a way to increase computational power in the material sciences has significantly decreased computational costs in already highly demanding calculations. A level of the acceleration and parallelization depends on the problem itself. Some problems can benefit from GPU acceleration and parallelization, such as the finite-difference time-domain algorithm (FTDT) and density-functional theory (DFT), while others cannot take advantage of these modern technologies. A number of GPU-supported applications had emerged in the past several years (www.nvidia.com/object/gpu-applications.html). Quantum Espresso (QE) is reported as an integrated suite of open source computer codes for electronic-structure calculations and materials modeling at the nano-scale. It is based on DFT, the use of a plane-waves basis and a pseudopotential approach. Since the QE 5.0 version, it has been implemented as a plug-in component for standard QE packages that allows exploiting the capabilities of Nvidia GPU graphic cards (www.qe-forge.org/gf/proj). In this study, we have examined the impact of the usage of GPU acceleration and parallelization on the numerical performance of DFT calculations. Graphene has been attracting attention worldwide and has already shown some remarkable properties. We have studied an intercalated graphene, using the QE package PHonon, which employs GPU. The term ‘intercalation’ refers to a process whereby foreign adatoms are inserted onto a graphene lattice. In addition, by intercalating different atoms between graphene layers, it is possible to tune their physical properties. Our experiments have shown there are benefits from using GPUs, and we reached an
Wang, Jin; Zhang, Cao; Katz, Joseph
2016-11-01
A PIV based method to reconstruct the volumetric pressure field by direct integration of the 3D material acceleration directions has been developed. Extending the 2D virtual-boundary omni-directional method (Omni2D, Liu & Katz, 2013), the new 3D parallel-line omni-directional method (Omni3D) integrates the material acceleration along parallel lines aligned in multiple directions. Their angles are set by a spherical virtual grid. The integration is parallelized on a Tesla K40c GPU, which reduced the computing time from three hours to one minute for a single realization. To validate its performance, this method is utilized to calculate the 3D pressure fields in isotropic turbulence and channel flow using the JHU DNS Databases (http://turbulence.pha.jhu.edu). Both integration of the DNS acceleration as well as acceleration from synthetic 3D particles are tested. Results are compared to other method, e.g. solution to the Pressure Poisson Equation (e.g. PPE, Ghaemi et al., 2012) with Bernoulli based Dirichlet boundary conditions, and the Omni2D method. The error in Omni3D prediction is uniformly low, and its sensitivity to acceleration errors is local. It agrees with the PPE/Bernoulli prediction away from the Dirichlet boundary. The Omni3D method is also applied to experimental data obtained using tomographic PIV, and results are correlated with deformation of a compliant wall. ONR.
Czech Academy of Sciences Publication Activity Database
Bauer, Petr; Klement, V.; Oberhuber, T.; Žabka, V.
2016-01-01
Roč. 200, March (2016), s. 50-56 ISSN 0010-4655 R&D Projects: GA ČR GB14-36566G Institutional support: RVO:61388998 Keywords : Navier–Stokes equations * mixed finite elements * multigrid * Vanka-type smoothers * Gauss–Seidel * red–black coloring * parallelization * GPU Subject RIV: BK - Fluid Dynamics Impact factor: 3.936, year: 2016
Comparison of multihardware parallel implementations for a phase unwrapping algorithm
Hernandez-Lopez, Francisco Javier; Rivera, Mariano; Salazar-Garibay, Adan; Legarda-Sáenz, Ricardo
2018-04-01
Phase unwrapping is an important problem in the areas of optical metrology, synthetic aperture radar (SAR) image analysis, and magnetic resonance imaging (MRI) analysis. These images are becoming larger in size and, particularly, the availability and need for processing of SAR and MRI data have increased significantly with the acquisition of remote sensing data and the popularization of magnetic resonators in clinical diagnosis. Therefore, it is important to develop faster and accurate phase unwrapping algorithms. We propose a parallel multigrid algorithm of a phase unwrapping method named accumulation of residual maps, which builds on a serial algorithm that consists of the minimization of a cost function; minimization achieved by means of a serial Gauss-Seidel kind algorithm. Our algorithm also optimizes the original cost function, but unlike the original work, our algorithm is a parallel Jacobi class with alternated minimizations. This strategy is known as the chessboard type, where red pixels can be updated in parallel at same iteration since they are independent. Similarly, black pixels can be updated in parallel in an alternating iteration. We present parallel implementations of our algorithm for different parallel multicore architecture such as CPU-multicore, Xeon Phi coprocessor, and Nvidia graphics processing unit. In all the cases, we obtain a superior performance of our parallel algorithm when compared with the original serial version. In addition, we present a detailed comparative performance of the developed parallel versions.
How General-Purpose can a GPU be?
Directory of Open Access Journals (Sweden)
Philip Machanick
2015-12-01
Full Text Available The use of graphics processing units (GPUs in general-purpose computation (GPGPU is a growing field. GPU instruction sets, while implementing a graphics pipeline, draw from a range of single instruction multiple datastream (SIMD architectures characteristic of the heyday of supercomputers. Yet only one of these SIMD instruction sets has been of application on a wide enough range of problems to survive the era when the full range of supercomputer design variants was being explored: vector instructions. This paper proposes a reconceptualization of the GPU as a multicore design with minimal exotic modes of parallelism so as to make GPGPU truly general.
Many-Body Mean-Field Equations: Parallel implementation
International Nuclear Information System (INIS)
Vallieres, M.; Umar, S.; Chinn, C.; Strayer, M.
1993-01-01
We describe the implementation of Hartree-Fock Many-Body Mean-Field Equations on a Parallel Intel iPSC/860 hypercube. We first discuss the Nuclear Mean-Field approach in physical terms. Then we describe our parallel implementation of this approach on the Intel iPSC/860 hypercube. We discuss and compare the advantages and disadvantages of the domain partition versus the Hilbert space partition for this problem. We conclude by discussing some timing experiments on various computing platforms
Fully 3D GPU PET reconstruction
Energy Technology Data Exchange (ETDEWEB)
Herraiz, J.L., E-mail: joaquin@nuclear.fis.ucm.es [Grupo de Fisica Nuclear, Departmento Fisica Atomica, Molecular y Nuclear, Universidad Complutense de Madrid (Spain); Espana, S. [Department of Radiation Oncology, Massachusetts General Hospital and Harvard Medical School, Boston, MA (United States); Cal-Gonzalez, J. [Grupo de Fisica Nuclear, Departmento Fisica Atomica, Molecular y Nuclear, Universidad Complutense de Madrid (Spain); Vaquero, J.J. [Departmento de Bioingenieria e Ingenieria Espacial, Universidad Carlos III, Madrid (Spain); Desco, M. [Departmento de Bioingenieria e Ingenieria Espacial, Universidad Carlos III, Madrid (Spain); Unidad de Medicina y Cirugia Experimental, Hospital General Universitario Gregorio Maranon, Madrid (Spain); Udias, J.M. [Grupo de Fisica Nuclear, Departmento Fisica Atomica, Molecular y Nuclear, Universidad Complutense de Madrid (Spain)
2011-08-21
Fully 3D iterative tomographic image reconstruction is computationally very demanding. Graphics Processing Unit (GPU) has been proposed for many years as potential accelerators in complex scientific problems, but it has not been used until the recent advances in the programmability of GPUs that the best available reconstruction codes have started to be implemented to be run on GPUs. This work presents a GPU-based fully 3D PET iterative reconstruction software. This new code may reconstruct sinogram data from several commercially available PET scanners. The most important and time-consuming parts of the code, the forward and backward projection operations, are based on an accurate model of the scanner obtained with the Monte Carlo code PeneloPET and they have been massively parallelized on the GPU. For the PET scanners considered, the GPU-based code is more than 70 times faster than a similar code running on a single core of a fast CPU, obtaining in both cases the same images. The code has been designed to be easily adapted to reconstruct sinograms from any other PET scanner, including scanner prototypes.
Fully 3D GPU PET reconstruction
International Nuclear Information System (INIS)
Herraiz, J.L.; Espana, S.; Cal-Gonzalez, J.; Vaquero, J.J.; Desco, M.; Udias, J.M.
2011-01-01
Fully 3D iterative tomographic image reconstruction is computationally very demanding. Graphics Processing Unit (GPU) has been proposed for many years as potential accelerators in complex scientific problems, but it has not been used until the recent advances in the programmability of GPUs that the best available reconstruction codes have started to be implemented to be run on GPUs. This work presents a GPU-based fully 3D PET iterative reconstruction software. This new code may reconstruct sinogram data from several commercially available PET scanners. The most important and time-consuming parts of the code, the forward and backward projection operations, are based on an accurate model of the scanner obtained with the Monte Carlo code PeneloPET and they have been massively parallelized on the GPU. For the PET scanners considered, the GPU-based code is more than 70 times faster than a similar code running on a single core of a fast CPU, obtaining in both cases the same images. The code has been designed to be easily adapted to reconstruct sinograms from any other PET scanner, including scanner prototypes.
High Performance Processing and Analysis of Geospatial Data Using CUDA on GPU
Directory of Open Access Journals (Sweden)
STOJANOVIC, N.
2014-11-01
Full Text Available In this paper, the high-performance processing of massive geospatial data on many-core GPU (Graphic Processing Unit is presented. We use CUDA (Compute Unified Device Architecture programming framework to implement parallel processing of common Geographic Information Systems (GIS algorithms, such as viewshed analysis and map-matching. Experimental evaluation indicates the improvement in performance with respect to CPU-based solutions and shows feasibility of using GPU and CUDA for parallel implementation of GIS algorithms over large-scale geospatial datasets.
Incompressible SPH (ISPH) with fast Poisson solver on a GPU
Chow, Alex D.; Rogers, Benedict D.; Lind, Steven J.; Stansby, Peter K.
2018-05-01
This paper presents a fast incompressible SPH (ISPH) solver implemented to run entirely on a graphics processing unit (GPU) capable of simulating several millions of particles in three dimensions on a single GPU. The ISPH algorithm is implemented by converting the highly optimised open-source weakly-compressible SPH (WCSPH) code DualSPHysics to run ISPH on the GPU, combining it with the open-source linear algebra library ViennaCL for fast solutions of the pressure Poisson equation (PPE). Several challenges are addressed with this research: constructing a PPE matrix every timestep on the GPU for moving particles, optimising the limited GPU memory, and exploiting fast matrix solvers. The ISPH pressure projection algorithm is implemented as 4 separate stages, each with a particle sweep, including an algorithm for the population of the PPE matrix suitable for the GPU, and mixed precision storage methods. An accurate and robust ISPH boundary condition ideal for parallel processing is also established by adapting an existing WCSPH boundary condition for ISPH. A variety of validation cases are presented: an impulsively started plate, incompressible flow around a moving square in a box, and dambreaks (2-D and 3-D) which demonstrate the accuracy, flexibility, and speed of the methodology. Fragmentation of the free surface is shown to influence the performance of matrix preconditioners and therefore the PPE matrix solution time. The Jacobi preconditioner demonstrates robustness and reliability in the presence of fragmented flows. For a dambreak simulation, GPU speed ups demonstrate up to 10-18 times and 1.1-4.5 times compared to single-threaded and 16-threaded CPU run times respectively.
A portable implementation of ARPACK for distributed memory parallel architectures
Energy Technology Data Exchange (ETDEWEB)
Maschhoff, K.J.; Sorensen, D.C.
1996-12-31
ARPACK is a package of Fortran 77 subroutines which implement the Implicitly Restarted Arnoldi Method used for solving large sparse eigenvalue problems. A parallel implementation of ARPACK is presented which is portable across a wide range of distributed memory platforms and requires minimal changes to the serial code. The communication layers used for message passing are the Basic Linear Algebra Communication Subprograms (BLACS) developed for the ScaLAPACK project and Message Passing Interface(MPI).
International Nuclear Information System (INIS)
Baron, E.; Hauschildt, Peter H.
1998-01-01
We describe an important addition to the parallel implementation of our generalized nonlocal thermodynamic equilibrium (NLTE) stellar atmosphere and radiative transfer computer program PHOENIX. In a previous paper in this series we described data and task parallel algorithms we have developed for radiative transfer, spectral line opacity, and NLTE opacity and rate calculations. These algorithms divided the work spatially or by spectral lines, that is, distributing the radial zones, individual spectral lines, or characteristic rays among different processors and employ, in addition, task parallelism for logically independent functions (such as atomic and molecular line opacities). For finite, monotonic velocity fields, the radiative transfer equation is an initial value problem in wavelength, and hence each wavelength point depends upon the previous one. However, for sophisticated NLTE models of both static and moving atmospheres needed to accurately describe, e.g., novae and supernovae, the number of wavelength points is very large (200,000 - 300,000) and hence parallelization over wavelength can lead both to considerable speedup in calculation time and the ability to make use of the aggregate memory available on massively parallel supercomputers. Here, we describe an implementation of a pipelined design for the wavelength parallelization of PHOENIX, where the necessary data from the processor working on a previous wavelength point is sent to the processor working on the succeeding wavelength point as soon as it is known. Our implementation uses a MIMD design based on a relatively small number of standard message passing interface (MPI) library calls and is fully portable between serial and parallel computers. copyright 1998 The American Astronomical Society
Implementing parallel elliptic solver on a Beowulf cluster
Directory of Open Access Journals (Sweden)
Marcin Paprzycki
1999-12-01
Full Text Available In a recent paper cite{zara} a parallel direct solver for the linear systems arising from elliptic partial differential equations has been proposed. The aim of this note is to present the initial evaluation of the performance characteristics of this algorithm on Beowulf-type cluster. In this context the performance of PVM and MPI based implementations is compared.
International Nuclear Information System (INIS)
Priimak, Dmitri
2014-01-01
We present a finite difference numerical algorithm for solving two dimensional spatially homogeneous Boltzmann transport equation which describes electron transport in a semiconductor superlattice subject to crossed time dependent electric and constant magnetic fields. The algorithm is implemented both in C language targeted to CPU and in CUDA C language targeted to commodity NVidia GPU. We compare performances and merits of one implementation versus another and discuss various software optimisation techniques
Energy Technology Data Exchange (ETDEWEB)
Priimak, Dmitri
2014-12-01
We present a finite difference numerical algorithm for solving two dimensional spatially homogeneous Boltzmann transport equation which describes electron transport in a semiconductor superlattice subject to crossed time dependent electric and constant magnetic fields. The algorithm is implemented both in C language targeted to CPU and in CUDA C language targeted to commodity NVidia GPU. We compare performances and merits of one implementation versus another and discuss various software optimisation techniques.
CSIR Research Space (South Africa)
Duvenhage, B
2010-06-01
Full Text Available rate of 15 fps at an image and ROI size of 640 480 pixels. This result was measured on an NVidia Tesla C870 GPU with about half as many processor cores as the GeForce GTX285 GPU. Marzat, et al. however estimate that their execu- tion times would...
A scalable implementation of RI-SCF on parallel computers
International Nuclear Information System (INIS)
Fruechtl, H.A.; Kendall, R.A.; Harrison, R.J.
1996-01-01
In order to avoid the integral bottleneck of conventional SCF calculations, the Resolution of the Identity (RI) method is used to obtain an approximate solution to the Hartree-Fock equations. In this approximation only three-center integrals are needed to build the Fock matrix. It has been implemented as part of the NWChem package of portable and scalable ab initio programs for parallel computers. Utilizing the V-approximation, both the Coulomb and exchange contribution to the Fock matrix can be calculated from a transformed set of three-center integrals which have to be precalculated and stored. A distributed in-core method as well as a disk based implementation have been programmed. Details of the implementation as well as the parallel programming tools used are described. We also give results and timings from benchmark calculations
GPU Computing Gems Emerald Edition
Hwu, Wen-mei W
2011-01-01
".the perfect companion to Programming Massively Parallel Processors by Hwu & Kirk." -Nicolas Pinto, Research Scientist at Harvard & MIT, NVIDIA Fellow 2009-2010 Graphics processing units (GPUs) can do much more than render graphics. Scientists and researchers increasingly look to GPUs to improve the efficiency and performance of computationally-intensive experiments across a range of disciplines. GPU Computing Gems: Emerald Edition brings their techniques to you, showcasing GPU-based solutions including: Black hole simulations with CUDA GPU-accelerated computation and interactive display of
Parallel implementations of 2D explicit Euler solvers
International Nuclear Information System (INIS)
Giraud, L.; Manzini, G.
1996-01-01
In this work we present a subdomain partitioning strategy applied to an explicit high-resolution Euler solver. We describe the design of a portable parallel multi-domain code suitable for parallel environments. We present several implementations on a representative range of MlMD computers that include shared memory multiprocessors, distributed virtual shared memory computers, as well as networks of workstations. Computational results are given to illustrate the efficiency, the scalability, and the limitations of the different approaches. We discuss also the effect of the communication protocol on the optimal domain partitioning strategy for the distributed memory computers
Efficient parallel implementations of approximation algorithms for guarding 1.5D terrains
Directory of Open Access Journals (Sweden)
Goran Martinović
2015-03-01
Full Text Available In the 1.5D terrain guarding problem, an x-monotone polygonal line is dened by k vertices and a G set of terrain points, i.e. guards, and a N set of terrain points which guards are to observe (guard. This involves a weighted version of the guarding problem where guards G have weights. The goal is to determine a minimum weight subset of G to cover all the points in N, including a version where points from N have demands. Furthermore, another goal is to determine the smallest subset of G, such that every point in N is observed by the required number of guards. Both problems are NP-hard and have a factor 5 approximation [3, 4]. This paper will show that if the (1+ϵ-approximate solver for the corresponding linear program is a computer, for any ϵ > 0, an extra 1+ϵ factor will appear in the final approximation factor for both problems. A comparison will be carried out the parallel implementation based on GPU and CPU threads with the Gurobi solver, leading to the conclusion that the respective algorithm outperforms the Gurobi solver on large and dense inputs typically by one order of magnitude.
Medical image processing on the GPU - past, present and future.
Eklund, Anders; Dufort, Paul; Forsberg, Daniel; LaConte, Stephen M
2013-12-01
Graphics processing units (GPUs) are used today in a wide range of applications, mainly because they can dramatically accelerate parallel computing, are affordable and energy efficient. In the field of medical imaging, GPUs are in some cases crucial for enabling practical use of computationally demanding algorithms. This review presents the past and present work on GPU accelerated medical image processing, and is meant to serve as an overview and introduction to existing GPU implementations. The review covers GPU acceleration of basic image processing operations (filtering, interpolation, histogram estimation and distance transforms), the most commonly used algorithms in medical imaging (image registration, image segmentation and image denoising) and algorithms that are specific to individual modalities (CT, PET, SPECT, MRI, fMRI, DTI, ultrasound, optical imaging and microscopy). The review ends by highlighting some future possibilities and challenges. Copyright © 2013 Elsevier B.V. All rights reserved.
Parallel Sequential Monte Carlo for Efficient Density Combination: The Deco Matlab Toolbox
DEFF Research Database (Denmark)
Casarin, Roberto; Grassi, Stefano; Ravazzolo, Francesco
This paper presents the Matlab package DeCo (Density Combination) which is based on the paper by Billio et al. (2013) where a constructive Bayesian approach is presented for combining predictive densities originating from different models or other sources of information. The combination weights...... for standard CPU computing and for Graphical Process Unit (GPU) parallel computing. For the GPU implementation we use the Matlab parallel computing toolbox and show how to use General Purposes GPU computing almost effortless. This GPU implementation comes with a speed up of the execution time up to seventy...... times compared to a standard CPU Matlab implementation on a multicore CPU. We show the use of the package and the computational gain of the GPU version, through some simulation experiments and empirical applications....
Lin, Mingpei; Xu, Ming; Fu, Xiaoyu
2017-05-01
Currently, a tremendous amount of space debris in Earth's orbit imperils operational spacecraft. It is essential to undertake risk assessments of collisions and predict dangerous encounters in space. However, collision predictions for an enormous amount of space debris give rise to large-scale computations. In this paper, a parallel algorithm is established on the Compute Unified Device Architecture (CUDA) platform of NVIDIA Corporation for collision prediction. According to the parallel structure of NVIDIA graphics processors, a block decomposition strategy is adopted in the algorithm. Space debris is divided into batches, and the computation and data transfer operations of adjacent batches overlap. As a consequence, the latency to access shared memory during the entire computing process is significantly reduced, and a higher computing speed is reached. Theoretically, a simulation of collision prediction for space debris of any amount and for any time span can be executed. To verify this algorithm, a simulation example including 1382 pieces of debris, whose operational time scales vary from 1 min to 3 days, is conducted on Tesla C2075 of NVIDIA. The simulation results demonstrate that with the same computational accuracy as that of a CPU, the computing speed of the parallel algorithm on a GPU is 30 times that on a CPU. Based on this algorithm, collision prediction of over 150 Chinese spacecraft for a time span of 3 days can be completed in less than 3 h on a single computer, which meets the timeliness requirement of the initial screening task. Furthermore, the algorithm can be adapted for multiple tasks, including particle filtration, constellation design, and Monte-Carlo simulation of an orbital computation.
Computationally efficient implementation of combustion chemistry in parallel PDF calculations
International Nuclear Information System (INIS)
Lu Liuyan; Lantz, Steven R.; Ren Zhuyin; Pope, Stephen B.
2009-01-01
In parallel calculations of combustion processes with realistic chemistry, the serial in situ adaptive tabulation (ISAT) algorithm [S.B. Pope, Computationally efficient implementation of combustion chemistry using in situ adaptive tabulation, Combustion Theory and Modelling, 1 (1997) 41-63; L. Lu, S.B. Pope, An improved algorithm for in situ adaptive tabulation, Journal of Computational Physics 228 (2009) 361-386] substantially speeds up the chemistry calculations on each processor. To improve the parallel efficiency of large ensembles of such calculations in parallel computations, in this work, the ISAT algorithm is extended to the multi-processor environment, with the aim of minimizing the wall clock time required for the whole ensemble. Parallel ISAT strategies are developed by combining the existing serial ISAT algorithm with different distribution strategies, namely purely local processing (PLP), uniformly random distribution (URAN), and preferential distribution (PREF). The distribution strategies enable the queued load redistribution of chemistry calculations among processors using message passing. They are implemented in the software x2f m pi, which is a Fortran 95 library for facilitating many parallel evaluations of a general vector function. The relative performance of the parallel ISAT strategies is investigated in different computational regimes via the PDF calculations of multiple partially stirred reactors burning methane/air mixtures. The results show that the performance of ISAT with a fixed distribution strategy strongly depends on certain computational regimes, based on how much memory is available and how much overlap exists between tabulated information on different processors. No one fixed strategy consistently achieves good performance in all the regimes. Therefore, an adaptive distribution strategy, which blends PLP, URAN and PREF, is devised and implemented. It yields consistently good performance in all regimes. In the adaptive parallel
Sequential and parallel image restoration: neural network implementations.
Figueiredo, M T; Leitao, J N
1994-01-01
Sequential and parallel image restoration algorithms and their implementations on neural networks are proposed. For images degraded by linear blur and contaminated by additive white Gaussian noise, maximum a posteriori (MAP) estimation and regularization theory lead to the same high dimension convex optimization problem. The commonly adopted strategy (in using neural networks for image restoration) is to map the objective function of the optimization problem into the energy of a predefined network, taking advantage of its energy minimization properties. Departing from this approach, we propose neural implementations of iterative minimization algorithms which are first proved to converge. The developed schemes are based on modified Hopfield (1985) networks of graded elements, with both sequential and parallel updating schedules. An algorithm supported on a fully standard Hopfield network (binary elements and zero autoconnections) is also considered. Robustness with respect to finite numerical precision is studied, and examples with real images are presented.
A parallel implementation of 3D Zernike moment analysis
Berjón Díez, Daniel; Arnaldo Duart, Sergio; Morán Burgos, Francisco
2011-01-01
Zernike polynomials are a well known set of functions that find many applications in image or pattern characterization because they allow to construct shape descriptors that are invariant against translations, rotations or scale changes. The concepts behind them can be extended to higher dimension spaces, making them also fit to describe volumetric data. They have been less used than their properties might suggest due to their high computational cost. We present a parallel implementation of 3...
Algorithm of parallel: hierarchical transformation and its implementation on FPGA
Timchenko, Leonid I.; Petrovskiy, Mykola S.; Kokryatskay, Natalia I.; Barylo, Alexander S.; Dembitska, Sofia V.; Stepanikuk, Dmytro S.; Suleimenov, Batyrbek; Zyska, Tomasz; Uvaysova, Svetlana; Shedreyeva, Indira
2017-08-01
In this paper considers the algorithm of laser beam spots image classification in atmospheric-optical transmission systems. It discusses the need for images filtering using adaptive methods, using, for example, parallel-hierarchical networks. The article also highlights the need to create high-speed memory devices for such networks. Implementation and simulation results of the developed method based on the PLD are demonstrated, which shows that the presented method gives 15-20% better prediction results than similar methods.
Implementing Parallel Google Map-Reduce in Eden
DEFF Research Database (Denmark)
Berthold, Jost; Dieterle, Mischa; Loogen, Rita
2009-01-01
Recent publications have emphasised map-reduce as a general programming model (labelled Google map-reduce), and described existing high-performance implementations for large data sets. We present two parallel implementations for this Google map-reduce skeleton, one following earlier work, and one...... of the Google map-reduce skeleton in usage and performance, and deliver runtime analyses for example applications. Although very flexible, the Google map-reduce skeleton is often too general, and typical examples reveal a better runtime behaviour using alternative skeletons....
GPU Lossless Hyperspectral Data Compression System for Space Applications
Keymeulen, Didier; Aranki, Nazeeh; Hopson, Ben; Kiely, Aaron; Klimesh, Matthew; Benkrid, Khaled
2012-01-01
On-board lossless hyperspectral data compression reduces data volume in order to meet NASA and DoD limited downlink capabilities. At JPL, a novel, adaptive and predictive technique for lossless compression of hyperspectral data, named the Fast Lossless (FL) algorithm, was recently developed. This technique uses an adaptive filtering method and achieves state-of-the-art performance in both compression effectiveness and low complexity. Because of its outstanding performance and suitability for real-time onboard hardware implementation, the FL compressor is being formalized as the emerging CCSDS Standard for Lossless Multispectral & Hyperspectral image compression. The FL compressor is well-suited for parallel hardware implementation. A GPU hardware implementation was developed for FL targeting the current state-of-the-art GPUs from NVIDIA(Trademark). The GPU implementation on a NVIDIA(Trademark) GeForce(Trademark) GTX 580 achieves a throughput performance of 583.08 Mbits/sec (44.85 MSamples/sec) and an acceleration of at least 6 times a software implementation running on a 3.47 GHz single core Intel(Trademark) Xeon(Trademark) processor. This paper describes the design and implementation of the FL algorithm on the GPU. The massively parallel implementation will provide in the future a fast and practical real-time solution for airborne and space applications.
A. Agbaria (Adnan); D. Minor (David); N. Peterfreund (Natan); E. Rozenberg (Eyal); O. Rosenberg (Ofer); Huawei Research
2016-01-01
textabstractExisting work on accelerating analytic DB query processing with (discrete) GPUs fails to fully realize their potential for speedup through parallelism: Published results do not achieve significant speedup over more performant CPU-only DBMSes when processing complete queries. This
GPU accelerated manifold correction method for spinning compact binaries
Ran, Chong-xi; Liu, Song; Zhong, Shuang-ying
2018-04-01
The graphics processing unit (GPU) acceleration of the manifold correction algorithm based on the compute unified device architecture (CUDA) technology is designed to simulate the dynamic evolution of the Post-Newtonian (PN) Hamiltonian formulation of spinning compact binaries. The feasibility and the efficiency of parallel computation on GPU have been confirmed by various numerical experiments. The numerical comparisons show that the accuracy on GPU execution of manifold corrections method has a good agreement with the execution of codes on merely central processing unit (CPU-based) method. The acceleration ability when the codes are implemented on GPU can increase enormously through the use of shared memory and register optimization techniques without additional hardware costs, implying that the speedup is nearly 13 times as compared with the codes executed on CPU for phase space scan (including 314 × 314 orbits). In addition, GPU-accelerated manifold correction method is used to numerically study how dynamics are affected by the spin-induced quadrupole-monopole interaction for black hole binary system.
GPU-accelerated Gibbs ensemble Monte Carlo simulations of Lennard-Jonesium
Mick, Jason; Hailat, Eyad; Russo, Vincent; Rushaidat, Kamel; Schwiebert, Loren; Potoff, Jeffrey
2013-12-01
This work describes an implementation of canonical and Gibbs ensemble Monte Carlo simulations on graphics processing units (GPUs). The pair-wise energy calculations, which consume the majority of the computational effort, are parallelized using the energetic decomposition algorithm. While energetic decomposition is relatively inefficient for traditional CPU-bound codes, the algorithm is ideally suited to the architecture of the GPU. The performance of the CPU and GPU codes are assessed for a variety of CPU and GPU combinations for systems containing between 512 and 131,072 particles. For a system of 131,072 particles, the GPU-enabled canonical and Gibbs ensemble codes were 10.3 and 29.1 times faster (GTX 480 GPU vs. i5-2500K CPU), respectively, than an optimized serial CPU-bound code. Due to overhead from memory transfers from system RAM to the GPU, the CPU code was slightly faster than the GPU code for simulations containing less than 600 particles. The critical temperature Tc∗=1.312(2) and density ρc∗=0.316(3) were determined for the tail corrected Lennard-Jones potential from simulations of 10,000 particle systems, and found to be in exact agreement with prior mixed field finite-size scaling calculations [J.J. Potoff, A.Z. Panagiotopoulos, J. Chem. Phys. 109 (1998) 10914].
Implementation of a Parallel Protein Structure Alignment Service on Cloud
Directory of Open Access Journals (Sweden)
Che-Lun Hung
2013-01-01
Full Text Available Protein structure alignment has become an important strategy by which to identify evolutionary relationships between protein sequences. Several alignment tools are currently available for online comparison of protein structures. In this paper, we propose a parallel protein structure alignment service based on the Hadoop distribution framework. This service includes a protein structure alignment algorithm, a refinement algorithm, and a MapReduce programming model. The refinement algorithm refines the result of alignment. To process vast numbers of protein structures in parallel, the alignment and refinement algorithms are implemented using MapReduce. We analyzed and compared the structure alignments produced by different methods using a dataset randomly selected from the PDB database. The experimental results verify that the proposed algorithm refines the resulting alignments more accurately than existing algorithms. Meanwhile, the computational performance of the proposed service is proportional to the number of processors used in our cloud platform.
A high performance GPU implementation of Surface Energy Balance System (SEBS) based on CUDA-C
Abouali, Mohammad; Timmermans, J.; Castillo, Jose E.; Su, Zhongbo
2013-01-01
This paper introduces a new implementation of the Surface Energy Balance System (SEBS) algorithm harnessing the many cores available on Graphics Processing Units (GPUs). This new implementation uses Compute Unified Device Architecture C (CUDA-C) programming model and is designed to be executed on a
A real-time spike sorting method based on the embedded GPU.
Zelan Yang; Kedi Xu; Xiang Tian; Shaomin Zhang; Xiaoxiang Zheng
2017-07-01
Microelectrode arrays with hundreds of channels have been widely used to acquire neuron population signals in neuroscience studies. Online spike sorting is becoming one of the most important challenges for high-throughput neural signal acquisition systems. Graphic processing unit (GPU) with high parallel computing capability might provide an alternative solution for increasing real-time computational demands on spike sorting. This study reported a method of real-time spike sorting through computing unified device architecture (CUDA) which was implemented on an embedded GPU (NVIDIA JETSON Tegra K1, TK1). The sorting approach is based on the principal component analysis (PCA) and K-means. By analyzing the parallelism of each process, the method was further optimized in the thread memory model of GPU. Our results showed that the GPU-based classifier on TK1 is 37.92 times faster than the MATLAB-based classifier on PC while their accuracies were the same with each other. The high-performance computing features of embedded GPU demonstrated in our studies suggested that the embedded GPU provide a promising platform for the real-time neural signal processing.
DEFF Research Database (Denmark)
Damkjær, Jesper; Erleben, Kenny
2009-01-01
and a simultaneous descend in the tandem traversal. The data structure design and traversal are highly specialized for exploiting the parallel threads in the NVIDIA GPUs. As proof-of-concept we demonstrate a GPU implementation for a multibody dynamics simulation, showing an approximate speedup factor of up to 8...
Development of a GPU-accelerated MIKE 21 Solver for Water Wave Dynamics
DEFF Research Database (Denmark)
Aackermann, Peter Edward; Pedersen, Peter Juhler Dinesen; Engsig-Karup, Allan Peter
2013-01-01
With encouragement by the company DHI are the aim of this B.Sc. thesis1 to investigate, whether if it is possible to accelerate the simulation speed of DHIs commercial product MIKE 21 HD, by formulating a parallel solution scheme and implementing it to be executed on a CUDA-enabled GPU (massive...
Efficient two-level preconditionined conjugate gradient method on the GPU
Gupta, R.; Van Gijzen, M.B.; Vuik, K.
2011-01-01
We present an implementation of Two-Level Preconditioned Conjugate Gradient Method for the GPU. We investigate a Truncated Neumann Series based preconditioner in combination with deflation and compare it with Block Incomplete Cholesky schemes. This combination exhibits fine-grain parallelism and
Hallock, Michael J; Stone, John E; Roberts, Elijah; Fry, Corey; Luthey-Schulten, Zaida
2014-05-01
Simulation of in vivo cellular processes with the reaction-diffusion master equation (RDME) is a computationally expensive task. Our previous software enabled simulation of inhomogeneous biochemical systems for small bacteria over long time scales using the MPD-RDME method on a single GPU. Simulations of larger eukaryotic systems exceed the on-board memory capacity of individual GPUs, and long time simulations of modest-sized cells such as yeast are impractical on a single GPU. We present a new multi-GPU parallel implementation of the MPD-RDME method based on a spatial decomposition approach that supports dynamic load balancing for workstations containing GPUs of varying performance and memory capacity. We take advantage of high-performance features of CUDA for peer-to-peer GPU memory transfers and evaluate the performance of our algorithms on state-of-the-art GPU devices. We present parallel e ciency and performance results for simulations using multiple GPUs as system size, particle counts, and number of reactions grow. We also demonstrate multi-GPU performance in simulations of the Min protein system in E. coli . Moreover, our multi-GPU decomposition and load balancing approach can be generalized to other lattice-based problems.
GPU-accelerated adjoint algorithmic differentiation
Gremse, Felix; Höfter, Andreas; Razik, Lukas; Kiessling, Fabian; Naumann, Uwe
2016-03-01
Many scientific problems such as classifier training or medical image reconstruction can be expressed as minimization of differentiable real-valued cost functions and solved with iterative gradient-based methods. Adjoint algorithmic differentiation (AAD) enables automated computation of gradients of such cost functions implemented as computer programs. To backpropagate adjoint derivatives, excessive memory is potentially required to store the intermediate partial derivatives on a dedicated data structure, referred to as the ;tape;. Parallelization is difficult because threads need to synchronize their accesses during taping and backpropagation. This situation is aggravated for many-core architectures, such as Graphics Processing Units (GPUs), because of the large number of light-weight threads and the limited memory size in general as well as per thread. We show how these limitations can be mediated if the cost function is expressed using GPU-accelerated vector and matrix operations which are recognized as intrinsic functions by our AAD software. We compare this approach with naive and vectorized implementations for CPUs. We use four increasingly complex cost functions to evaluate the performance with respect to memory consumption and gradient computation times. Using vectorization, CPU and GPU memory consumption could be substantially reduced compared to the naive reference implementation, in some cases even by an order of complexity. The vectorization allowed usage of optimized parallel libraries during forward and reverse passes which resulted in high speedups for the vectorized CPU version compared to the naive reference implementation. The GPU version achieved an additional speedup of 7.5 ± 4.4, showing that the processing power of GPUs can be utilized for AAD using this concept. Furthermore, we show how this software can be systematically extended for more complex problems such as nonlinear absorption reconstruction for fluorescence-mediated tomography.
Directory of Open Access Journals (Sweden)
Christley Scott
2010-08-01
Full Text Available Abstract Background Simulation of sophisticated biological models requires considerable computational power. These models typically integrate together numerous biological phenomena such as spatially-explicit heterogeneous cells, cell-cell interactions, cell-environment interactions and intracellular gene networks. The recent advent of programming for graphical processing units (GPU opens up the possibility of developing more integrative, detailed and predictive biological models while at the same time decreasing the computational cost to simulate those models. Results We construct a 3D model of epidermal development and provide a set of GPU algorithms that executes significantly faster than sequential central processing unit (CPU code. We provide a parallel implementation of the subcellular element method for individual cells residing in a lattice-free spatial environment. Each cell in our epidermal model includes an internal gene network, which integrates cellular interaction of Notch signaling together with environmental interaction of basement membrane adhesion, to specify cellular state and behaviors such as growth and division. We take a pedagogical approach to describing how modeling methods are efficiently implemented on the GPU including memory layout of data structures and functional decomposition. We discuss various programmatic issues and provide a set of design guidelines for GPU programming that are instructive to avoid common pitfalls as well as to extract performance from the GPU architecture. Conclusions We demonstrate that GPU algorithms represent a significant technological advance for the simulation of complex biological models. We further demonstrate with our epidermal model that the integration of multiple complex modeling methods for heterogeneous multicellular biological processes is both feasible and computationally tractable using this new technology. We hope that the provided algorithms and source code will be a
Implementation of PHENIX trigger algorithms on massively parallel computers
International Nuclear Information System (INIS)
Petridis, A.N.; Wohn, F.K.
1995-01-01
The event selection requirements of contemporary high energy and nuclear physics experiments are met by the introduction of on-line trigger algorithms which identify potentially interesting events and reduce the data acquisition rate to levels that are manageable by the electronics. Such algorithms being parallel in nature can be simulated off-line using massively parallel computers. The PHENIX experiment intends to investigate the possible existence of a new phase of matter called the quark gluon plasma which has been theorized to have existed in very early stages of the evolution of the universe by studying collisions of heavy nuclei at ultra-relativistic energies. Such interactions can also reveal important information regarding the structure of the nucleus and mandate a thorough investigation of the simpler proton-nucleus collisions at the same energies. The complexity of PHENIX events and the need to analyze and also simulate them at rates similar to the data collection ones imposes enormous computation demands. This work is a first effort to implement PHENIX trigger algorithms on parallel computers and to study the feasibility of using such machines to run the complex programs necessary for the simulation of the PHENIX detector response. Fine and coarse grain approaches have been studied and evaluated. Depending on the application the performance of a massively parallel computer can be much better or much worse than that of a serial workstation. A comparison between single instruction and multiple instruction computers is also made and possible applications of the single instruction machines to high energy and nuclear physics experiments are outlined. copyright 1995 American Institute of Physics
Aalto, R. E.; Lauer, J. W.; Darby, S. E.; Best, J.; Dietrich, W. E.
2015-12-01
During glacial-marine transgressions vast volumes of sediment are deposited due to the infilling of lowland fluvial systems and shallow shelves, material that is removed during ensuing regressions. Modelling these processes would illuminate system morphodynamics, fluxes, and 'complexity' in response to base level change, yet such problems are computationally formidable. Environmental systems are characterized by strong interconnectivity, yet traditional supercomputers have slow inter-node communication -- whereas rapidly advancing Graphics Processing Unit (GPU) technology offers vastly higher (>100x) bandwidths. GULLEM (GpU-accelerated Lowland Landscape Evolution Model) employs massively parallel code to simulate coupled fluvial-landscape evolution for complex lowland river systems over large temporal and spatial scales. GULLEM models the accommodation space carved/infilled by representing a range of geomorphic processes, including: river & tributary incision within a multi-directional flow regime, non-linear diffusion, glacial-isostatic flexure, hydraulic geometry, tectonic deformation, sediment production, transport & deposition, and full 3D tracking of all resulting stratigraphy. Model results concur with the Holocene dynamics of the Fly River, PNG -- as documented with dated cores, sonar imaging of floodbasin stratigraphy, and the observations of topographic remnants from LGM conditions. Other supporting research was conducted along the Mekong River, the largest fluvial system of the Sunda Shelf. These and other field data provide tantalizing empirical glimpses into the lowland landscapes of large rivers during glacial-interglacial transitions, observations that can be explored with this powerful numerical model. GULLEM affords estimates for the timing and flux budgets within the Fly and Sunda Systems, illustrating complex internal system responses to the external forcing of sea level and climate. Furthermore, GULLEM can be applied to most ANY fluvial system to
FastGCN: a GPU accelerated tool for fast gene co-expression networks.
Directory of Open Access Journals (Sweden)
Meimei Liang
Full Text Available Gene co-expression networks comprise one type of valuable biological networks. Many methods and tools have been published to construct gene co-expression networks; however, most of these tools and methods are inconvenient and time consuming for large datasets. We have developed a user-friendly, accelerated and optimized tool for constructing gene co-expression networks that can fully harness the parallel nature of GPU (Graphic Processing Unit architectures. Genetic entropies were exploited to filter out genes with no or small expression changes in the raw data preprocessing step. Pearson correlation coefficients were then calculated. After that, we normalized these coefficients and employed the False Discovery Rate to control the multiple tests. At last, modules identification was conducted to construct the co-expression networks. All of these calculations were implemented on a GPU. We also compressed the coefficient matrix to save space. We compared the performance of the GPU implementation with those of multi-core CPU implementations with 16 CPU threads, single-thread C/C++ implementation and single-thread R implementation. Our results show that GPU implementation largely outperforms single-thread C/C++ implementation and single-thread R implementation, and GPU implementation outperforms multi-core CPU implementation when the number of genes increases. With the test dataset containing 16,000 genes and 590 individuals, we can achieve greater than 63 times the speed using a GPU implementation compared with a single-thread R implementation when 50 percent of genes were filtered out and about 80 times the speed when no genes were filtered out.
Implementation of the CA-CFAR algorithm for pulsed-doppler radar on a GPU architecture
CSIR Research Space (South Africa)
Venter, CJ
2011-12-01
Full Text Available /republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Implementation of the CA-CFAR Algorithm for Pulsed...
Status of parallel Python-based implementation of UEDGE
Umansky, M. V.; Pankin, A. Y.; Rognlien, T. D.; Dimits, A. M.; Friedman, A.; Joseph, I.
2017-10-01
The tokamak edge transport code UEDGE has long used the code-development and run-time framework Basis. However, with the support for Basis expected to terminate in the coming years, and with the advent of the modern numerical language Python, it has become desirable to move UEDGE to Python, to ensure its long-term viability. Our new Python-based UEDGE implementation takes advantage of the portable build system developed for FACETS. The new implementation gives access to Python's graphical libraries and numerical packages for pre- and post-processing, and support of HDF5 simplifies exchanging data. The older serial version of UEDGE has used for time-stepping the Newton-Krylov solver NKSOL. The renovated implementation uses backward Euler discretization with nonlinear solvers from PETSc, which has the promise to significantly improve the UEDGE parallel performance. We will report on assessment of some of the extended UEDGE capabilities emerging in the new implementation, and will discuss the future directions. Work performed for U.S. DOE by LLNL under contract DE-AC52-07NA27344.
International Nuclear Information System (INIS)
Ammazzalorso, F; Jelen, U; Bednarz, T
2014-01-01
We demonstrate acceleration on graphic processing units (GPU) of automatic identification of robust particle therapy beam setups, minimizing negative dosimetric effects of Bragg peak displacement caused by treatment-time patient positioning errors. Our particle therapy research toolkit, RobuR, was extended with OpenCL support and used to implement calculation on GPU of the Port Homogeneity Index, a metric scoring irradiation port robustness through analysis of tissue density patterns prior to dose optimization and computation. Results were benchmarked against an independent native CPU implementation. Numerical results were in agreement between the GPU implementation and native CPU implementation. For 10 skull base cases, the GPU-accelerated implementation was employed to select beam setups for proton and carbon ion treatment plans, which proved to be dosimetrically robust, when recomputed in presence of various simulated positioning errors. From the point of view of performance, average running time on the GPU decreased by at least one order of magnitude compared to the CPU, rendering the GPU-accelerated analysis a feasible step in a clinical treatment planning interactive session. In conclusion, selection of robust particle therapy beam setups can be effectively accelerated on a GPU and become an unintrusive part of the particle therapy treatment planning workflow. Additionally, the speed gain opens new usage scenarios, like interactive analysis manipulation (e.g. constraining of some setup) and re-execution. Finally, through OpenCL portable parallelism, the new implementation is suitable also for CPU-only use, taking advantage of multiple cores, and can potentially exploit types of accelerators other than GPUs.
Ammazzalorso, F.; Bednarz, T.; Jelen, U.
2014-03-01
We demonstrate acceleration on graphic processing units (GPU) of automatic identification of robust particle therapy beam setups, minimizing negative dosimetric effects of Bragg peak displacement caused by treatment-time patient positioning errors. Our particle therapy research toolkit, RobuR, was extended with OpenCL support and used to implement calculation on GPU of the Port Homogeneity Index, a metric scoring irradiation port robustness through analysis of tissue density patterns prior to dose optimization and computation. Results were benchmarked against an independent native CPU implementation. Numerical results were in agreement between the GPU implementation and native CPU implementation. For 10 skull base cases, the GPU-accelerated implementation was employed to select beam setups for proton and carbon ion treatment plans, which proved to be dosimetrically robust, when recomputed in presence of various simulated positioning errors. From the point of view of performance, average running time on the GPU decreased by at least one order of magnitude compared to the CPU, rendering the GPU-accelerated analysis a feasible step in a clinical treatment planning interactive session. In conclusion, selection of robust particle therapy beam setups can be effectively accelerated on a GPU and become an unintrusive part of the particle therapy treatment planning workflow. Additionally, the speed gain opens new usage scenarios, like interactive analysis manipulation (e.g. constraining of some setup) and re-execution. Finally, through OpenCL portable parallelism, the new implementation is suitable also for CPU-only use, taking advantage of multiple cores, and can potentially exploit types of accelerators other than GPUs.
Cluster implementation for parallel computation within MATLAB software environment
International Nuclear Information System (INIS)
Santana, Antonio O. de; Dantas, Carlos C.; Charamba, Luiz G. da R.; Souza Neto, Wilson F. de; Melo, Silvio B. Melo; Lima, Emerson A. de O.
2013-01-01
A cluster for parallel computation with MATLAB software the COCGT - Cluster for Optimizing Computing in Gamma ray Transmission methods, is implemented. The implementation correspond to creation of a local net of computers, facilities and configurations of software, as well as the accomplishment of cluster tests for determine and optimizing of performance in the data processing. The COCGT implementation was required by data computation from gamma transmission measurements applied to fluid dynamic and tomography reconstruction in a FCC-Fluid Catalytic Cracking cold pilot unity, and simulation data as well. As an initial test the determination of SVD - Singular Values Decomposition - of random matrix with dimension (n , n), n=1000, using the Girco's law modified, revealed that COCGT was faster in comparison to the literature [1] cluster, which is similar and operates at the same conditions. Solution of a system of linear equations provided a new test for the COCGT performance by processing a square matrix with n=10000, computing time was 27 s and for square matrix with n=12000, computation time was 45 s. For determination of the cluster behavior in relation to 'parfor' (parallel for-loop) and 'spmd' (single program multiple data), two codes were used containing those two commands and the same problem: determination of SVD of a square matrix with n= 1000. The execution of codes by means of COCGT proved: 1) for the code with 'parfor', the performance improved with the labs number from 1 to 8 labs; 2) for the code 'spmd', just 1 lab (core) was enough to process and give results in less than 1 s. In similar situation, with the difference that now the SVD will be determined from square matrix with n1500, for code with 'parfor', and n=7000, for code with 'spmd'. That results take to conclusions: 1) for the code with 'parfor', the behavior was the same already described above; 2) for code with 'spmd', the same besides having produced a larger performance, it supports a
International Nuclear Information System (INIS)
Modiri, A; Hagan, A; Gu, X; Sawant, A
2015-01-01
Purpose 4D-IMRT planning, combined with dynamic MLC tracking delivery, utilizes the temporal dimension as an additional degree of freedom to achieve improved OAR-sparing. The computational complexity for such optimization increases exponentially with increase in dimensionality. In order to accomplish this task in a clinically-feasible time frame, we present an initial implementation of GPU-based 4D-IMRT planning based on particle swarm optimization (PSO). Methods The target and normal structures were manually contoured on ten phases of a 4DCT scan of a NSCLC patient with a 54cm3 right-lower-lobe tumor (1.5cm motion). Corresponding ten 3D-IMRT plans were created in the Eclipse treatment planning system (Ver-13.6). A vendor-provided scripting interface was used to export 3D-dose matrices corresponding to each control point (10 phases × 9 beams × 166 control points = 14,940), which served as input to PSO. The optimization task was to iteratively adjust the weights of each control point and scale the corresponding dose matrices. In order to handle the large amount of data in GPU memory, dose matrices were sparsified and placed in contiguous memory blocks with the 14,940 weight-variables. PSO was implemented on CPU (dual-Xeon, 3.1GHz) and GPU (dual-K20 Tesla, 2496 cores, 3.52Tflops, each) platforms. NiftyReg, an open-source deformable image registration package, was used to calculate the summed dose. Results The 4D-PSO plan yielded PTV coverage comparable to the clinical ITV-based plan and significantly higher OAR-sparing, as follows: lung Dmean=33%; lung V20=27%; spinal cord Dmax=26%; esophagus Dmax=42%; heart Dmax=0%; heart Dmean=47%. The GPU-PSO processing time for 14940 variables and 7 PSO-particles was 41% that of CPU-PSO (199 vs. 488 minutes). Conclusion Truly 4D-IMRT planning can yield significant OAR dose-sparing while preserving PTV coverage. The corresponding optimization problem is large-scale, non-convex and computationally rigorous. Our initial results
Energy Technology Data Exchange (ETDEWEB)
Modiri, A; Hagan, A; Gu, X; Sawant, A [UT Southwestern Medical Center, Dallas, TX (United States)
2015-06-15
Purpose 4D-IMRT planning, combined with dynamic MLC tracking delivery, utilizes the temporal dimension as an additional degree of freedom to achieve improved OAR-sparing. The computational complexity for such optimization increases exponentially with increase in dimensionality. In order to accomplish this task in a clinically-feasible time frame, we present an initial implementation of GPU-based 4D-IMRT planning based on particle swarm optimization (PSO). Methods The target and normal structures were manually contoured on ten phases of a 4DCT scan of a NSCLC patient with a 54cm3 right-lower-lobe tumor (1.5cm motion). Corresponding ten 3D-IMRT plans were created in the Eclipse treatment planning system (Ver-13.6). A vendor-provided scripting interface was used to export 3D-dose matrices corresponding to each control point (10 phases × 9 beams × 166 control points = 14,940), which served as input to PSO. The optimization task was to iteratively adjust the weights of each control point and scale the corresponding dose matrices. In order to handle the large amount of data in GPU memory, dose matrices were sparsified and placed in contiguous memory blocks with the 14,940 weight-variables. PSO was implemented on CPU (dual-Xeon, 3.1GHz) and GPU (dual-K20 Tesla, 2496 cores, 3.52Tflops, each) platforms. NiftyReg, an open-source deformable image registration package, was used to calculate the summed dose. Results The 4D-PSO plan yielded PTV coverage comparable to the clinical ITV-based plan and significantly higher OAR-sparing, as follows: lung Dmean=33%; lung V20=27%; spinal cord Dmax=26%; esophagus Dmax=42%; heart Dmax=0%; heart Dmean=47%. The GPU-PSO processing time for 14940 variables and 7 PSO-particles was 41% that of CPU-PSO (199 vs. 488 minutes). Conclusion Truly 4D-IMRT planning can yield significant OAR dose-sparing while preserving PTV coverage. The corresponding optimization problem is large-scale, non-convex and computationally rigorous. Our initial results
Ramses-GPU: Second order MUSCL-Handcock finite volume fluid solver
Kestener, Pierre
2017-10-01
RamsesGPU is a reimplementation of RAMSES (ascl:1011.007) which drops the adaptive mesh refinement (AMR) features to optimize 3D uniform grid algorithms for modern graphics processor units (GPU) to provide an efficient software package for astrophysics applications that do not need AMR features but do require a very large number of integration time steps. RamsesGPU provides an very efficient C++/CUDA/MPI software implementation of a second order MUSCL-Handcock finite volume fluid solver for compressible hydrodynamics as a magnetohydrodynamics solver based on the constraint transport technique. Other useful modules includes static gravity, dissipative terms (viscosity, resistivity), and forcing source term for turbulence studies, and special care was taken to enhance parallel input/output performance by using state-of-the-art libraries such as HDF5 and parallel-netcdf.
High Performance Implementation of 3D Convolutional Neural Networks on a GPU
Wang, Zelong; Wen, Mei; Zhang, Chunyuan; Wang, Yijie
2017-01-01
Convolutional neural networks have proven to be highly successful in applications such as image classification, object tracking, and many other tasks based on 2D inputs. Recently, researchers have started to apply convolutional neural networks to video classification, which constitutes a 3D input and requires far larger amounts of memory and much more computation. FFT based methods can reduce the amount of computation, but this generally comes at the cost of an increased memory requirement. On the other hand, the Winograd Minimal Filtering Algorithm (WMFA) can reduce the number of operations required and thus can speed up the computation, without increasing the required memory. This strategy was shown to be successful for 2D neural networks. We implement the algorithm for 3D convolutional neural networks and apply it to a popular 3D convolutional neural network which is used to classify videos and compare it to cuDNN. For our highly optimized implementation of the algorithm, we observe a twofold speedup for most of the 3D convolution layers of our test network compared to the cuDNN version. PMID:29250109
High Performance Implementation of 3D Convolutional Neural Networks on a GPU.
Lan, Qiang; Wang, Zelong; Wen, Mei; Zhang, Chunyuan; Wang, Yijie
2017-01-01
Convolutional neural networks have proven to be highly successful in applications such as image classification, object tracking, and many other tasks based on 2D inputs. Recently, researchers have started to apply convolutional neural networks to video classification, which constitutes a 3D input and requires far larger amounts of memory and much more computation. FFT based methods can reduce the amount of computation, but this generally comes at the cost of an increased memory requirement. On the other hand, the Winograd Minimal Filtering Algorithm (WMFA) can reduce the number of operations required and thus can speed up the computation, without increasing the required memory. This strategy was shown to be successful for 2D neural networks. We implement the algorithm for 3D convolutional neural networks and apply it to a popular 3D convolutional neural network which is used to classify videos and compare it to cuDNN. For our highly optimized implementation of the algorithm, we observe a twofold speedup for most of the 3D convolution layers of our test network compared to the cuDNN version.
Vectorization, parallelization and implementation of Quantum molecular dynamics codes (QQQF, MONTEV)
Energy Technology Data Exchange (ETDEWEB)
Kato, Kaori [High Energy Accelerator Research Organization, Tsukuba, Ibaraki (Japan); Kunugi, Tomoaki; Kotake, Susumu; Shibahara, Masahiko
1998-03-01
This report describes parallelization, vectorization and implementation for two simulation codes, Quantum molecular dynamics simulation code QQQF and Photon montecalro molecular dynamics simulation code MONTEV, that have been developed for the analysis of the thermalization of photon energies in the molecule or materials. QQQF has been vectorized and parallelized on Fujitsu VPP and has been implemented from VPP to Intel Paragon XP/S and parallelized. MONTEV has been implemented from VPP to Paragon and parallelized. (author)
International Nuclear Information System (INIS)
Renaud, M; Seuntjens, J; Roberge, D
2014-01-01
Purpose: Assessing the performance and uncertainty of a pre-calculated Monte Carlo (PMC) algorithm for proton and electron transport running on graphics processing units (GPU). While PMC methods have been described in the past, an explicit quantification of the latent uncertainty arising from recycling a limited number of tracks in the pre-generated track bank is missing from the literature. With a proper uncertainty analysis, an optimal pre-generated track bank size can be selected for a desired dose calculation uncertainty. Methods: Particle tracks were pre-generated for electrons and protons using EGSnrc and GEANT4, respectively. The PMC algorithm for track transport was implemented on the CUDA programming framework. GPU-PMC dose distributions were compared to benchmark dose distributions simulated using general-purpose MC codes in the same conditions. A latent uncertainty analysis was performed by comparing GPUPMC dose values to a “ground truth” benchmark while varying the track bank size and primary particle histories. Results: GPU-PMC dose distributions and benchmark doses were within 1% of each other in voxels with dose greater than 50% of Dmax. In proton calculations, a submillimeter distance-to-agreement error was observed at the Bragg Peak. Latent uncertainty followed a Poisson distribution with the number of tracks per energy (TPE) and a track bank of 20,000 TPE produced a latent uncertainty of approximately 1%. Efficiency analysis showed a 937× and 508× gain over a single processor core running DOSXYZnrc for 16 MeV electrons in water and bone, respectively. Conclusion: The GPU-PMC method can calculate dose distributions for electrons and protons to a statistical uncertainty below 1%. The track bank size necessary to achieve an optimal efficiency can be tuned based on the desired uncertainty. Coupled with a model to calculate dose contributions from uncharged particles, GPU-PMC is a candidate for inverse planning of modulated electron radiotherapy
2017-08-01
used for its GPU computing capability during the experiment. It has Nvidia Tesla K40 GPU accelerators containing 32 GPU nodes consisting of 1024...cores. CUDA is a parallel computing platform and application programming interface (API) model that was created and designed by Nvidia to give direct...Agricultural and Forest Meteorology. 1995:76:277–291, ISSN 0168-1923. 3. GPU vs. CPU? What is GPU computing? Santa Clara (CA): Nvidia Corporation; 2017
Energy Technology Data Exchange (ETDEWEB)
Brabec, Jiri; Pittner, Jiri; van Dam, Hubertus JJ; Apra, Edoardo; Kowalski, Karol
2012-02-01
A novel algorithm for implementing general type of multireference coupled-cluster (MRCC) theory based on the Jeziorski-Monkhorst exponential Ansatz [B. Jeziorski, H.J. Monkhorst, Phys. Rev. A 24, 1668 (1981)] is introduced. The proposed algorithm utilizes processor groups to calculate the equations for the MRCC amplitudes. In the basic formulation each processor group constructs the equations related to a specific subset of references. By flexible choice of processor groups and subset of reference-specific sufficiency conditions designated to a given group one can assure optimum utilization of available computing resources. The performance of this algorithm is illustrated on the examples of the Brillouin-Wigner and Mukherjee MRCC methods with singles and doubles (BW-MRCCSD and Mk-MRCCSD). A significant improvement in scalability and in reduction of time to solution is reported with respect to recently reported parallel implementation of the BW-MRCCSD formalism [J.Brabec, H.J.J. van Dam, K. Kowalski, J. Pittner, Chem. Phys. Lett. 514, 347 (2011)].
Yang, Lin; Zhang, Feng; Wang, Cai-Zhuang; Ho, Kai-Ming; Travesset, Alex
2018-04-01
We present an implementation of EAM and FS interatomic potentials, which are widely used in simulating metallic systems, in HOOMD-blue, a software designed to perform classical molecular dynamics simulations using GPU accelerations. We first discuss the details of our implementation and then report extensive benchmark tests. We demonstrate that single-precision floating point operations efficiently implemented on GPUs can produce sufficient accuracy when compared against double-precision codes, as demonstrated in test simulations of calculations of the glass-transition temperature of Cu64.5Zr35.5, and pair correlation function g (r) of liquid Ni3Al. Our code scales well with the size of the simulating system on NVIDIA Tesla M40 and P100 GPUs. Compared with another popular software LAMMPS running on 32 cores of AMD Opteron 6220 processors, the GPU/CPU performance ratio can reach as high as 4.6. The source code can be accessed through the HOOMD-blue web page for free by any interested user.
Fast Simulation of Dynamic Ultrasound Images Using the GPU.
Storve, Sigurd; Torp, Hans
2017-10-01
Simulated ultrasound data is a valuable tool for development and validation of quantitative image analysis methods in echocardiography. Unfortunately, simulation time can become prohibitive for phantoms consisting of a large number of point scatterers. The COLE algorithm by Gao et al. is a fast convolution-based simulator that trades simulation accuracy for improved speed. We present highly efficient parallelized CPU and GPU implementations of the COLE algorithm with an emphasis on dynamic simulations involving moving point scatterers. We argue that it is crucial to minimize the amount of data transfers from the CPU to achieve good performance on the GPU. We achieve this by storing the complete trajectories of the dynamic point scatterers as spline curves in the GPU memory. This leads to good efficiency when simulating sequences consisting of a large number of frames, such as B-mode and tissue Doppler data for a full cardiac cycle. In addition, we propose a phase-based subsample delay technique that efficiently eliminates flickering artifacts seen in B-mode sequences when COLE is used without enough temporal oversampling. To assess the performance, we used a laptop computer and a desktop computer, each equipped with a multicore Intel CPU and an NVIDIA GPU. Running the simulator on a high-end TITAN X GPU, we observed two orders of magnitude speedup compared to the parallel CPU version, three orders of magnitude speedup compared to simulation times reported by Gao et al. in their paper on COLE, and a speedup of 27000 times compared to the multithreaded version of Field II, using numbers reported in a paper by Jensen. We hope that by releasing the simulator as an open-source project we will encourage its use and further development.
GPU accelerated population annealing algorithm
Barash, Lev Yu.; Weigel, Martin; Borovský, Michal; Janke, Wolfhard; Shchur, Lev N.
2017-11-01
Population annealing is a promising recent approach for Monte Carlo simulations in statistical physics, in particular for the simulation of systems with complex free-energy landscapes. It is a hybrid method, combining importance sampling through Markov chains with elements of sequential Monte Carlo in the form of population control. While it appears to provide algorithmic capabilities for the simulation of such systems that are roughly comparable to those of more established approaches such as parallel tempering, it is intrinsically much more suitable for massively parallel computing. Here, we tap into this structural advantage and present a highly optimized implementation of the population annealing algorithm on GPUs that promises speed-ups of several orders of magnitude as compared to a serial implementation on CPUs. While the sample code is for simulations of the 2D ferromagnetic Ising model, it should be easily adapted for simulations of other spin models, including disordered systems. Our code includes implementations of some advanced algorithmic features that have only recently been suggested, namely the automatic adaptation of temperature steps and a multi-histogram analysis of the data at different temperatures. Program Files doi:http://dx.doi.org/10.17632/sgzt4b7b3m.1 Licensing provisions: Creative Commons Attribution license (CC BY 4.0) Programming language: C, CUDA External routines/libraries: NVIDIA CUDA Toolkit 6.5 or newer Nature of problem: The program calculates the internal energy, specific heat, several magnetization moments, entropy and free energy of the 2D Ising model on square lattices of edge length L with periodic boundary conditions as a function of inverse temperature β. Solution method: The code uses population annealing, a hybrid method combining Markov chain updates with population control. The code is implemented for NVIDIA GPUs using the CUDA language and employs advanced techniques such as multi-spin coding, adaptive temperature
Deng, Liang; Bai, Hanli; Wang, Fang; Xu, Qingxin
2016-06-01
CPU/GPU computing allows scientists to tremendously accelerate their numerical codes. In this paper, we port and optimize a double precision alternating direction implicit (ADI) solver for three-dimensional compressible Navier-Stokes equations from our in-house Computational Fluid Dynamics (CFD) software on heterogeneous platform. First, we implement a full GPU version of the ADI solver to remove a lot of redundant data transfers between CPU and GPU, and then design two fine-grain schemes, namely “one-thread-one-point” and “one-thread-one-line”, to maximize the performance. Second, we present a dual-level parallelization scheme using the CPU/GPU collaborative model to exploit the computational resources of both multi-core CPUs and many-core GPUs within the heterogeneous platform. Finally, considering the fact that memory on a single node becomes inadequate when the simulation size grows, we present a tri-level hybrid programming pattern MPI-OpenMP-CUDA that merges fine-grain parallelism using OpenMP and CUDA threads with coarse-grain parallelism using MPI for inter-node communication. We also propose a strategy to overlap the computation with communication using the advanced features of CUDA and MPI programming. We obtain speedups of 6.0 for the ADI solver on one Tesla M2050 GPU in contrast to two Xeon X5670 CPUs. Scalability tests show that our implementation can offer significant performance improvement on heterogeneous platform.
PIConGPU - How to build one of the fastest GPU particle-in-cell codes in the world
Energy Technology Data Exchange (ETDEWEB)
Burau, Heiko; Debus, Alexander; Helm, Anton; Huebl, Axel; Kluge, Thomas; Widera, Rene; Bussmann, Michael; Schramm, Ulrich; Cowan, Thomas [HZDR, Dresden (Germany); Juckeland, Guido; Nagel, Wolfgang [TU Dresden (Germany); ZIH, Dresden (Germany); Schmitt, Felix [NVIDIA (United States)
2013-07-01
We present the algorithmic building blocks of PIConGPU, one of the fastest implementations of the particle-in-cell algortihm on GPU clusters. PIConGPU is a highly-scalable, 3D3V electromagnetic PIC code that is used in laser plasma and astrophysical plasma simulations.
Staring, M.; Al-Ars, Z.; Berendsen, Floris; Angelini, Elsa D.; Landman, Bennett A.
2018-01-01
Currently, non-rigid image registration algorithms are too computationally intensive to use in time-critical applications. Existing implementations that focus on speed typically address this by either parallelization on GPU-hardware, or by introducing methodically novel techniques into
Porting AMG2013 to Heterogeneous CPU+GPU Nodes
Energy Technology Data Exchange (ETDEWEB)
Samfass, Philipp [Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
2017-01-26
LLNL's future advanced technology system SIERRA will feature heterogeneous compute nodes that consist of IBM PowerV9 CPUs and NVIDIA Volta GPUs. Conceptually, the motivation for such an architecture is quite straightforward: While GPUs are optimized for throughput on massively parallel workloads, CPUs strive to minimize latency for rather sequential operations. Yet, making optimal use of heterogeneous architectures raises new challenges for the development of scalable parallel software, e.g., with respect to work distribution. Porting LLNL's parallel numerical libraries to upcoming heterogeneous CPU+GPU architectures is therefore a critical factor for ensuring LLNL's future success in ful lling its national mission. One of these libraries, called HYPRE, provides parallel solvers and precondi- tioners for large, sparse linear systems of equations. In the context of this intern- ship project, I consider AMG2013 which is a proxy application for major parts of HYPRE that implements a benchmark for setting up and solving di erent systems of linear equations. In the following, I describe in detail how I ported multiple parts of AMG2013 to the GPU (Section 2) and present results for di erent experiments that demonstrate a successful parallel implementation on the heterogeneous ma- chines surface and ray (Section 3). In Section 4, I give guidelines on how my code should be used. Finally, I conclude and give an outlook for future work (Section 5).
GPU accelerated generation of digitally reconstructed radiographs for 2-D/3-D image registration.
Dorgham, Osama M; Laycock, Stephen D; Fisher, Mark H
2012-09-01
Recent advances in programming languages for graphics processing units (GPUs) provide developers with a convenient way of implementing applications which can be executed on the CPU and GPU interchangeably. GPUs are becoming relatively cheap, powerful, and widely available hardware components, which can be used to perform intensive calculations. The last decade of hardware performance developments shows that GPU-based computation is progressing significantly faster than CPU-based computation, particularly if one considers the execution of highly parallelisable algorithms. Future predictions illustrate that this trend is likely to continue. In this paper, we introduce a way of accelerating 2-D/3-D image registration by developing a hybrid system which executes on the CPU and utilizes the GPU for parallelizing the generation of digitally reconstructed radiographs (DRRs). Based on the advancements of the GPU over the CPU, it is timely to exploit the benefits of many-core GPU technology by developing algorithms for DRR generation. Although some previous work has investigated the rendering of DRRs using the GPU, this paper investigates approximations which reduce the computational overhead while still maintaining a quality consistent with that needed for 2-D/3-D registration with sufficient accuracy to be clinically acceptable in certain applications of radiation oncology. Furthermore, by comparing implementations of 2-D/3-D registration on the CPU and GPU, we investigate current performance and propose an optimal framework for PC implementations addressing the rigid registration problem. Using this framework, we are able to render DRR images from a 256×256×133 CT volume in ~24 ms using an NVidia GeForce 8800 GTX and in ~2 ms using NVidia GeForce GTX 580. In addition to applications requiring fast automatic patient setup, these levels of performance suggest image-guided radiation therapy at video frame rates is technically feasible using relatively low cost PC
An Implementation and Parallelization of the Scale Space Meshing Algorithm
Directory of Open Access Journals (Sweden)
Julie Digne
2015-11-01
Full Text Available Creating an interpolating mesh from an unorganized set of oriented points is a difficult problemwhich is often overlooked. Most methods focus indeed on building a watertight smoothed meshby defining some function whose zero level set is the surface of the object. However in some casesit is crucial to build a mesh that interpolates the points and does not fill the acquisition holes:either because the data are sparse and trying to fill the holes would create spurious artifactsor because the goal is to explore visually the data exactly as they were acquired without anysmoothing process. In this paper we detail a parallel implementation of the Scale-Space Meshingalgorithm, which builds on the scale-space framework for reconstructing a high precision meshfrom an input oriented point set. This algorithm first smoothes the point set, producing asingularity free shape. It then uses a standard mesh reconstruction technique, the Ball PivotingAlgorithm, to build a mesh from the smoothed point set. The final step consists in back-projecting the mesh built on the smoothed positions onto the original point set. The result ofthis process is an interpolating, hole-preserving surface mesh reconstruction.
Energy Technology Data Exchange (ETDEWEB)
Wu, Meng; Fessler, Jeffrey A. [Michigan Univ., Ann Arbor, MI (United States). Dept. of Electrical Engineering and Computer Science
2011-07-01
Iterative 3D image reconstruction methods can improve image quality over conventional filtered back projection (FBP) in X-ray computed tomography. However, high computational costs deter the routine use of iterative reconstruction clinically. The separable footprint method for forward and back-projection simplifies the integrals over a detector cell in a way that is quite accurate and also has a relatively efficient CPU implementation. In this project, we implemented the separable footprints method for both forward and backward projection on a graphics processing unit (GPU) with NVDIA's parallel computing architecture (CUDA). This paper describes our GPU kernels for the separable footprint method and simulation results. (orig.)
The gputools package enables GPU computing in R.
Buckner, Joshua; Wilson, Justin; Seligman, Mark; Athey, Brian; Watson, Stanley; Meng, Fan
2010-01-01
By default, the R statistical environment does not make use of parallelism. Researchers may resort to expensive solutions such as cluster hardware for large analysis tasks. Graphics processing units (GPUs) provide an inexpensive and computationally powerful alternative. Using R and the CUDA toolkit from Nvidia, we have implemented several functions commonly used in microarray gene expression analysis for GPU-equipped computers. R users can take advantage of the better performance provided by an Nvidia GPU. The package is available from CRAN, the R project's repository of packages, at http://cran.r-project.org/web/packages/gputools More information about our gputools R package is available at http://brainarray.mbni.med.umich.edu/brainarray/Rgpgpu
GPU accelerated FDTD solver and its application in MRI.
Chi, J; Liu, F; Jin, J; Mason, D G; Crozier, S
2010-01-01
The finite difference time domain (FDTD) method is a popular technique for computational electromagnetics (CEM). The large computational power often required, however, has been a limiting factor for its applications. In this paper, we will present a graphics processing unit (GPU)-based parallel FDTD solver and its successful application to the investigation of a novel B1 shimming scheme for high-field magnetic resonance imaging (MRI). The optimized shimming scheme exhibits considerably improved transmit B(1) profiles. The GPU implementation dramatically shortened the runtime of FDTD simulation of electromagnetic field compared with its CPU counterpart. The acceleration in runtime has made such investigation possible, and will pave the way for other studies of large-scale computational electromagnetic problems in modern MRI which were previously impractical.
Directory of Open Access Journals (Sweden)
Hee-Min Choi
2015-06-01
Full Text Available An accelerated spatial redundancy-based novel-look-up-table (A-SR-NLUT method based on a new concept of the N-point one-dimensional sub-principal fringe pattern (N-point1-D sub-PFP is implemented on a graphics processing unit (GPU for fast calculation of computer-generated holograms (CGHs of three-dimensional (3-Dobjects. Since the proposed method can generate the N-point two-dimensional (2-D PFPs for CGH calculation from the pre-stored N-point 1-D PFPs, the loading time of the N-point PFPs on the GPU can be dramatically reduced, which results in a great increase of the computational speed of the proposed method. Experimental results confirm that the average calculation time for one-object point has been reduced by 49.6% and 55.4% compared to those of the conventional 2-D SR-NLUT methods for each case of the 2-point and 3-point SR maps, respectively.
Huang, Fang; Liu, Dingsheng; Tan, Xicheng; Wang, Jian; Chen, Yunping; He, Binbin
2011-04-01
To design and implement an open-source parallel GIS (OP-GIS) based on a Linux cluster, the parallel inverse distance weighting (IDW) interpolation algorithm has been chosen as an example to explore the working model and the principle of algorithm parallel pattern (APP), one of the parallelization patterns for OP-GIS. Based on an analysis of the serial IDW interpolation algorithm of GRASS GIS, this paper has proposed and designed a specific parallel IDW interpolation algorithm, incorporating both single process, multiple data (SPMD) and master/slave (M/S) programming modes. The main steps of the parallel IDW interpolation algorithm are: (1) the master node packages the related information, and then broadcasts it to the slave nodes; (2) each node calculates its assigned data extent along one row using the serial algorithm; (3) the master node gathers the data from all nodes; and (4) iterations continue until all rows have been processed, after which the results are outputted. According to the experiments performed in the course of this work, the parallel IDW interpolation algorithm can attain an efficiency greater than 0.93 compared with similar algorithms, which indicates that the parallel algorithm can greatly reduce processing time and maximize speed and performance.
SU-E-T-395: Multi-GPU-Based VMAT Treatment Plan Optimization Using a Column-Generation Approach
International Nuclear Information System (INIS)
Tian, Z; Shi, F; Jia, X; Jiang, S; Peng, F
2014-01-01
Purpose: GPU has been employed to speed up VMAT optimizations from hours to minutes. However, its limited memory capacity makes it difficult to handle cases with a huge dose-deposition-coefficient (DDC) matrix, e.g. those with a large target size, multiple arcs, small beam angle intervals and/or small beamlet size. We propose multi-GPU-based VMAT optimization to solve this memory issue to make GPU-based VMAT more practical for clinical use. Methods: Our column-generation-based method generates apertures sequentially by iteratively searching for an optimal feasible aperture (referred as pricing problem, PP) and optimizing aperture intensities (referred as master problem, MP). The PP requires access to the large DDC matrix, which is implemented on a multi-GPU system. Each GPU stores a DDC sub-matrix corresponding to one fraction of beam angles and is only responsible for calculation related to those angles. Broadcast and parallel reduction schemes are adopted for inter-GPU data transfer. MP is a relatively small-scale problem and is implemented on one GPU. One headand- neck cancer case was used for test. Three different strategies for VMAT optimization on single GPU were also implemented for comparison: (S1) truncating DDC matrix to ignore its small value entries for optimization; (S2) transferring DDC matrix part by part to GPU during optimizations whenever needed; (S3) moving DDC matrix related calculation onto CPU. Results: Our multi-GPU-based implementation reaches a good plan within 1 minute. Although S1 was 10 seconds faster than our method, the obtained plan quality is worse. Both S2 and S3 handle the full DDC matrix and hence yield the same plan as in our method. However, the computation time is longer, namely 4 minutes and 30 minutes, respectively. Conclusion: Our multi-GPU-based VMAT optimization can effectively solve the limited memory issue with good plan quality and high efficiency, making GPUbased ultra-fast VMAT planning practical for real clinical use
SU-E-T-395: Multi-GPU-Based VMAT Treatment Plan Optimization Using a Column-Generation Approach
Energy Technology Data Exchange (ETDEWEB)
Tian, Z; Shi, F; Jia, X; Jiang, S [UT Southwestern Medical Ctr at Dallas, Dallas, TX (United States); Peng, F [Carnegie Mellon University, Pittsburgh, PA (United States)
2014-06-01
Purpose: GPU has been employed to speed up VMAT optimizations from hours to minutes. However, its limited memory capacity makes it difficult to handle cases with a huge dose-deposition-coefficient (DDC) matrix, e.g. those with a large target size, multiple arcs, small beam angle intervals and/or small beamlet size. We propose multi-GPU-based VMAT optimization to solve this memory issue to make GPU-based VMAT more practical for clinical use. Methods: Our column-generation-based method generates apertures sequentially by iteratively searching for an optimal feasible aperture (referred as pricing problem, PP) and optimizing aperture intensities (referred as master problem, MP). The PP requires access to the large DDC matrix, which is implemented on a multi-GPU system. Each GPU stores a DDC sub-matrix corresponding to one fraction of beam angles and is only responsible for calculation related to those angles. Broadcast and parallel reduction schemes are adopted for inter-GPU data transfer. MP is a relatively small-scale problem and is implemented on one GPU. One headand- neck cancer case was used for test. Three different strategies for VMAT optimization on single GPU were also implemented for comparison: (S1) truncating DDC matrix to ignore its small value entries for optimization; (S2) transferring DDC matrix part by part to GPU during optimizations whenever needed; (S3) moving DDC matrix related calculation onto CPU. Results: Our multi-GPU-based implementation reaches a good plan within 1 minute. Although S1 was 10 seconds faster than our method, the obtained plan quality is worse. Both S2 and S3 handle the full DDC matrix and hence yield the same plan as in our method. However, the computation time is longer, namely 4 minutes and 30 minutes, respectively. Conclusion: Our multi-GPU-based VMAT optimization can effectively solve the limited memory issue with good plan quality and high efficiency, making GPUbased ultra-fast VMAT planning practical for real clinical use.
MASSIVELY PARALLEL LATENT SEMANTIC ANALYSES USING A GRAPHICS PROCESSING UNIT
Energy Technology Data Exchange (ETDEWEB)
Cavanagh, J.; Cui, S.
2009-01-01
Latent Semantic Analysis (LSA) aims to reduce the dimensions of large term-document datasets using Singular Value Decomposition. However, with the ever-expanding size of datasets, current implementations are not fast enough to quickly and easily compute the results on a standard PC. A graphics processing unit (GPU) can solve some highly parallel problems much faster than a traditional sequential processor or central processing unit (CPU). Thus, a deployable system using a GPU to speed up large-scale LSA processes would be a much more effective choice (in terms of cost/performance ratio) than using a PC cluster. Due to the GPU’s application-specifi c architecture, harnessing the GPU’s computational prowess for LSA is a great challenge. We presented a parallel LSA implementation on the GPU, using NVIDIA® Compute Unifi ed Device Architecture and Compute Unifi ed Basic Linear Algebra Subprograms software. The performance of this implementation is compared to traditional LSA implementation on a CPU using an optimized Basic Linear Algebra Subprograms library. After implementation, we discovered that the GPU version of the algorithm was twice as fast for large matrices (1 000x1 000 and above) that had dimensions not divisible by 16. For large matrices that did have dimensions divisible by 16, the GPU algorithm ran fi ve to six times faster than the CPU version. The large variation is due to architectural benefi ts of the GPU for matrices divisible by 16. It should be noted that the overall speeds for the CPU version did not vary from relative normal when the matrix dimensions were divisible by 16. Further research is needed in order to produce a fully implementable version of LSA. With that in mind, the research we presented shows that the GPU is a viable option for increasing the speed of LSA, in terms of cost/performance ratio.
International Nuclear Information System (INIS)
Bastiens, K.; Lemahieu, I.
1994-01-01
The application of a maximum entropy reconstruction algorithm to PET images requires a lot of computing resources. A parallel implementation could seriously reduce the execution time. However, programming a parallel application is still a non trivial task, needing specialized people. In this paper a programming environment based on a visual programming language is used for a parallel implementation of the reconstruction algorithm. This programming environment allows less experienced programmers to use the performance of multiprocessor systems. (authors)
Energy Technology Data Exchange (ETDEWEB)
Bastiens, K; Lemahieu, I [University of Ghent - ELIS Department, St. Pietersnieuwstraat 41, B-9000 Ghent (Belgium)
1994-12-31
The application of a maximum entropy reconstruction algorithm to PET images requires a lot of computing resources. A parallel implementation could seriously reduce the execution time. However, programming a parallel application is still a non trivial task, needing specialized people. In this paper a programming environment based on a visual programming language is used for a parallel implementation of the reconstruction algorithm. This programming environment allows less experienced programmers to use the performance of multiprocessor systems. (authors). 8 refs, 3 figs, 1 tab.
Weigel, Martin
2011-09-01
Over the last couple of years it has been realized that the vast computational power of graphics processing units (GPUs) could be harvested for purposes other than the video game industry. This power, which at least nominally exceeds that of current CPUs by large factors, results from the relative simplicity of the GPU architectures as compared to CPUs, combined with a large number of parallel processing units on a single chip. To benefit from this setup for general computing purposes, the problems at hand need to be prepared in a way to profit from the inherent parallelism and hierarchical structure of memory accesses. In this contribution I discuss the performance potential for simulating spin models, such as the Ising model, on GPU as compared to conventional simulations on CPU.
Graphics Processing Unit Enhanced Parallel Document Flocking Clustering
Energy Technology Data Exchange (ETDEWEB)
Cui, Xiaohui [ORNL; Potok, Thomas E [ORNL; ST Charles, Jesse Lee [ORNL
2010-01-01
Analyzing and clustering documents is a complex problem. One explored method of solving this problem borrows from nature, imitating the flocking behavior of birds. One limitation of this method of document clustering is its complexity O(n2). As the number of documents grows, it becomes increasingly difficult to generate results in a reasonable amount of time. In the last few years, the graphics processing unit (GPU) has received attention for its ability to solve highly-parallel and semi-parallel problems much faster than the traditional sequential processor. In this paper, we have conducted research to exploit this archi- tecture and apply its strengths to the flocking based document clustering problem. Using the CUDA platform from NVIDIA, we developed a doc- ument flocking implementation to be run on the NVIDIA GEFORCE GPU. Performance gains ranged from thirty-six to nearly sixty times improvement of the GPU over the CPU implementation.
Moving-Target Position Estimation Using GPU-Based Particle Filter for IoT Sensing Applications
Directory of Open Access Journals (Sweden)
Seongseop Kim
2017-11-01
Full Text Available A particle filter (PF has been introduced for effective position estimation of moving targets for non-Gaussian and nonlinear systems. The time difference of arrival (TDOA method using acoustic sensor array has normally been used to for estimation by concealing the location of a moving target, especially underwater. In this paper, we propose a GPU -based acceleration of target position estimation using a PF and propose an efficient system and software architecture. The proposed graphic processing unit (GPU-based algorithm has more advantages in applying PF signal processing to a target system, which consists of large-scale Internet of Things (IoT-driven sensors because of the parallelization which is scalable. For the TDOA measurement from the acoustic sensor array, we use the generalized cross correlation phase transform (GCC-PHAT method to obtain the correlation coefficient of the signal using Fast Fourier Transform (FFT, and we try to accelerate the calculations of GCC-PHAT based TDOA measurements using FFT with GPU compute unified device architecture (CUDA. The proposed approach utilizes a parallelization method in the target position estimation algorithm using GPU-based PF processing. In addition, it could efficiently estimate sudden movement change of the target using GPU-based parallel computing which also can be used for multiple target tracking. It also provides scalability in extending the detection algorithm according to the increase of the number of sensors. Therefore, the proposed architecture can be applied in IoT sensing applications with a large number of sensors. The target estimation algorithm was verified using MATLAB and implemented using GPU CUDA. We implemented the proposed signal processing acceleration system using target GPU to analyze in terms of execution time. The execution time of the algorithm is reduced by 55% from to the CPU standalone operation in target embedded board, NVIDIA Jetson TX1. Also, to apply large
Distributed GPU Computing in GIScience
Jiang, Y.; Yang, C.; Huang, Q.; Li, J.; Sun, M.
2013-12-01
Geoscientists strived to discover potential principles and patterns hidden inside ever-growing Big Data for scientific discoveries. To better achieve this objective, more capable computing resources are required to process, analyze and visualize Big Data (Ferreira et al., 2003; Li et al., 2013). Current CPU-based computing techniques cannot promptly meet the computing challenges caused by increasing amount of datasets from different domains, such as social media, earth observation, environmental sensing (Li et al., 2013). Meanwhile CPU-based computing resources structured as cluster or supercomputer is costly. In the past several years with GPU-based technology matured in both the capability and performance, GPU-based computing has emerged as a new computing paradigm. Compare to traditional computing microprocessor, the modern GPU, as a compelling alternative microprocessor, has outstanding high parallel processing capability with cost-effectiveness and efficiency(Owens et al., 2008), although it is initially designed for graphical rendering in visualization pipe. This presentation reports a distributed GPU computing framework for integrating GPU-based computing within distributed environment. Within this framework, 1) for each single computer, computing resources of both GPU-based and CPU-based can be fully utilized to improve the performance of visualizing and processing Big Data; 2) within a network environment, a variety of computers can be used to build up a virtual super computer to support CPU-based and GPU-based computing in distributed computing environment; 3) GPUs, as a specific graphic targeted device, are used to greatly improve the rendering efficiency in distributed geo-visualization, especially for 3D/4D visualization. Key words: Geovisualization, GIScience, Spatiotemporal Studies Reference : 1. Ferreira de Oliveira, M. C., & Levkowitz, H. (2003). From visual data exploration to visual data mining: A survey. Visualization and Computer Graphics, IEEE
Comparing and Optimising Parallel Haskell Implementations for Multicore Machines
DEFF Research Database (Denmark)
Berthold, Jost; Marlow, Simon; Hammond, Kevin
2009-01-01
In this paper, we investigate the differences and tradeoffs imposed by two parallel Haskell dialects running on multicore machines. GpH and Eden are both constructed using the highly-optimising sequential GHC compiler, and share thread scheduling, and other elements, from a common code base. The ...
Adaptive-Multilevel BDDC and its parallel implementation
Czech Academy of Sciences Publication Activity Database
Sousedík, Bedřich; Šístek, Jakub; Mandel, J.
2013-01-01
Roč. 95, č. 12 (2013), s. 1087-1119 ISSN 0010-485X R&D Projects: GA ČR GA106/08/0403 Institutional support: RVO:61388998 ; RVO:67985840 Keywords : BDDC * parallel algorithms * domain decomposition Subject RIV: JC - Computer Hardware ; Software; BA - General Mathematics (MU-W) Impact factor: 1.055, year: 2013
Analysis and implementation of LLC-T series parallel resonant ...
African Journals Online (AJOL)
A prototype 300 W, 100 kHz converter is designed and built to experimentally demonstrate, dynamic and steady state performance for the LLC-T series parallel resonant converter. A comparative study is performed between experimental results and the simulation studies. The analysis shows that the output of converter is ...
LDPC Decoding on GPU for Mobile Device
Directory of Open Access Journals (Sweden)
Yiqin Lu
2016-01-01
Full Text Available A flexible software LDPC decoder that exploits data parallelism for simultaneous multicode words decoding on the mobile device is proposed in this paper, supported by multithreading on OpenCL based graphics processing units. By dividing the check matrix into several parts to make full use of both the local memory and private memory on GPU and properly modify the code capacity each time, our implementation on a mobile phone shows throughputs above 100 Mbps and delay is less than 1.6 millisecond in decoding, which make high-speed communication like video calling possible. To realize efficient software LDPC decoding on the mobile device, the LDPC decoding feature on communication baseband chip should be replaced to save the cost and make it easier to upgrade decoder to be compatible with a variety of channel access schemes.
Travel Software using GPU Hardware
Szalwinski, Chris M; Dimov, Veliko Atanasov; CERN. Geneva. ATS Department
2015-01-01
Travel is the main multi-particle tracking code being used at CERN for the beam dynamics calculations through hadron and ion linear accelerators. It uses two routines for the calculation of space charge forces, namely, rings of charges and point-to-point. This report presents the studies to improve the performance of Travel using GPU hardware. The studies showed that the performance of Travel with the point-to-point simulations of space-charge effects can be speeded up at least 72 times using current GPU hardware. Simple recompilation of the source code using an Intel compiler can improve performance at least 4 times without GPU support. The limited memory of the GPU is the bottleneck. Two algorithms were investigated on this point: repeated computation and tiling. The repeating computation algorithm is simpler and is the currently recommended solution. The tiling algorithm was more complicated and degraded performance. Both build and test instructions for the parallelized version of the software are inclu...
GPU-based large-scale visualization
Hadwiger, Markus
2013-11-19
Recent advances in image and volume acquisition as well as computational advances in simulation have led to an explosion of the amount of data that must be visualized and analyzed. Modern techniques combine the parallel processing power of GPUs with out-of-core methods and data streaming to enable the interactive visualization of giga- and terabytes of image and volume data. A major enabler for interactivity is making both the computational and the visualization effort proportional to the amount of data that is actually visible on screen, decoupling it from the full data size. This leads to powerful display-aware multi-resolution techniques that enable the visualization of data of almost arbitrary size. The course consists of two major parts: An introductory part that progresses from fundamentals to modern techniques, and a more advanced part that discusses details of ray-guided volume rendering, novel data structures for display-aware visualization and processing, and the remote visualization of large online data collections. You will learn how to develop efficient GPU data structures and large-scale visualizations, implement out-of-core strategies and concepts such as virtual texturing that have only been employed recently, as well as how to use modern multi-resolution representations. These approaches reduce the GPU memory requirements of extremely large data to a working set size that fits into current GPUs. You will learn how to perform ray-casting of volume data of almost arbitrary size and how to render and process gigapixel images using scalable, display-aware techniques. We will describe custom virtual texturing architectures as well as recent hardware developments in this area. We will also describe client/server systems for distributed visualization, on-demand data processing and streaming, and remote visualization. We will describe implementations using OpenGL as well as CUDA, exploiting parallelism on GPUs combined with additional asynchronous
International Nuclear Information System (INIS)
Li Hanyu; Zhou Haijing; Dong Zhiwei; Liao Cheng; Chang Lei; Cao Xiaolin; Xiao Li
2010-01-01
A large-scale parallel electromagnetic field simulation program JEMS-FDTD(J Electromagnetic Solver-Finite Difference Time Domain) is designed and implemented on JASMIN (J parallel Adaptive Structured Mesh applications INfrastructure). This program can simulate propagation, radiation, couple of electromagnetic field by solving Maxwell equations on structured mesh explicitly with FDTD method. JEMS-FDTD is able to simulate billion-mesh-scale problems on thousands of processors. In this article, the program is verified by simulating the radiation of an electric dipole. A beam waveguide is simulated to demonstrate the capability of large scale parallel computation. A parallel performance test indicates that a high parallel efficiency is obtained. (authors)
A parallel implementation of 3-d CT image reconstruction on a hypercube multiprocessor
International Nuclear Information System (INIS)
Chen, C.M.; Lee, S.Y.; Cho, Z.H.
1990-01-01
In this paper, the authors describe how image reconstruction in computerized tomography (CT) can be parallelized on a message-passing multiprocessor. In particular, the results obtained from parallel implementation of 3-D CT image reconstruction for parallel beam geometries on the Intel hypercube, iPSC/2, are presented. A two stage pipelining approach is employed for filtering (convolution) and backprojection. The conventional sequential convolution algorithm is modified such that the symmetry of the filter kernel is fully utilized for parallelization. In the backprojection stage, the 3-D incremental algorithm, the authors' recently developed backprojection scheme which is shown to be faster than conventional algorithm, is parallelized
Uso de tarjetas GPU para acelerar el procesado de señales
Amat Sanz, David
2017-01-01
This Bachelor's Degree Final Project aims to analyze and implement another way to process digital signals, improving their performance and speed of execution. DSP and FPGA are the most commonly used elements for any kind of signal processing. This project focuses on the use of graphics cards (GPU) to exploit to the maximum the parallelism that is available today. Current processors (CPUs) have a few cores and work sequentially which can be very time consuming if large amounts of data are bein...
Large Scale Simulations of the Euler Equations on GPU Clusters
Liebmann, Manfred
2010-08-01
The paper investigates the scalability of a parallel Euler solver, using the Vijayasundaram method, on a GPU cluster with 32 Nvidia Geforce GTX 295 boards. The aim of this research is to enable large scale fluid dynamics simulations with up to one billion elements. We investigate communication protocols for the GPU cluster to compensate for the slow Gigabit Ethernet network between the GPU compute nodes and to maintain overall efficiency. A diesel engine intake-port and a nozzle, meshed in different resolutions, give good real world examples for the scalability tests on the GPU cluster. © 2010 IEEE.
Parallel processing implementation for the coupled transport of photons and electrons using OpenMP
Doerner, Edgardo
2016-05-01
In this work the use of OpenMP to implement the parallel processing of the Monte Carlo (MC) simulation of the coupled transport for photons and electrons is presented. This implementation was carried out using a modified EGSnrc platform which enables the use of the Microsoft Visual Studio 2013 (VS2013) environment, together with the developing tools available in the Intel Parallel Studio XE 2015 (XE2015). The performance study of this new implementation was carried out in a desktop PC with a multi-core CPU, taking as a reference the performance of the original platform. The results were satisfactory, both in terms of scalability as parallelization efficiency.
Quick plasma equilibrium reconstruction based on GPU
International Nuclear Information System (INIS)
Xiao Bingjia; Huang, Y.; Luo, Z.P.; Yuan, Q.P.; Lao, L.
2014-01-01
A parallel code named P-EFIT which could complete an equilibrium reconstruction iteration in 250 μs is described. It is built with the CUDA TM architecture by using Graphical Processing Unit (GPU). It is described for the optimization of middle-scale matrix multiplication on GPU and an algorithm which could solve block tri-diagonal linear system efficiently in parallel. Benchmark test is conducted. Static test proves the accuracy of the P-EFIT and simulation-test proves the feasibility of using P-EFIT for real-time reconstruction on 65x65 computation grids. (author)
Qin, Cheng-Zhi; Zhan, Lijun
2012-06-01
As one of the important tasks in digital terrain analysis, the calculation of flow accumulations from gridded digital elevation models (DEMs) usually involves two steps in a real application: (1) using an iterative DEM preprocessing algorithm to remove the depressions and flat areas commonly contained in real DEMs, and (2) using a recursive flow-direction algorithm to calculate the flow accumulation for every cell in the DEM. Because both algorithms are computationally intensive, quick calculation of the flow accumulations from a DEM (especially for a large area) presents a practical challenge to personal computer (PC) users. In recent years, rapid increases in hardware capacity of the graphics processing units (GPUs) provided in modern PCs have made it possible to meet this challenge in a PC environment. Parallel computing on GPUs using a compute-unified-device-architecture (CUDA) programming model has been explored to speed up the execution of the single-flow-direction algorithm (SFD). However, the parallel implementation on a GPU of the multiple-flow-direction (MFD) algorithm, which generally performs better than the SFD algorithm, has not been reported. Moreover, GPU-based parallelization of the DEM preprocessing step in the flow-accumulation calculations has not been addressed. This paper proposes a parallel approach to calculate flow accumulations (including both iterative DEM preprocessing and a recursive MFD algorithm) on a CUDA-compatible GPU. For the parallelization of an MFD algorithm (MFD-md), two different parallelization strategies using a GPU are explored. The first parallelization strategy, which has been used in the existing parallel SFD algorithm on GPU, has the problem of computing redundancy. Therefore, we designed a parallelization strategy based on graph theory. The application results show that the proposed parallel approach to calculate flow accumulations on a GPU performs much faster than either sequential algorithms or other parallel GPU
Implementing a Commercial-Strength Parallel Hybrid Movie Recommendation Engine
DEFF Research Database (Denmark)
Amolochitis, Emmanouil; Christou, Ioannis T.; Tan, Zheng-Hua
2014-01-01
AMORE is a hybrid recommendation system that provides movie recommendations for a major triple-play services provider in Greece. Combined with our own implementations of several user-, item-, and content-based recommendation algorithms, AMORE significantly outperforms other state......-of-the-art implementations both in solution quality and response time. AMORE currently serves daily recommendation requests for all active subscribers of the provider's video-on-demand services and has contributed to an increase of rental profits and customer retention....
Parallel implementation of many-body mean-field equations
International Nuclear Information System (INIS)
Chinn, C.R.; Umar, A.S.; Vallieres, M.; Strayer, M.R.
1994-01-01
We describe the numerical methods used to solve the system of stiff, nonlinear partial differential equations resulting from the Hartree-Fock description of many-particle quantum systems, as applied to the structure of the nucleus. The solutions are performed on a three-dimensional Cartesian lattice. Discretization is achieved through the lattice basis-spline collocation method, in which quantum-state vectors and coordinate-space operators are expressed in terms of basis-spline functions on a spatial lattice. All numerical procedures reduce to a series of matrix-vector multiplications and other elementary operations, which we perform on a number of different computing architectures, including the Intel Paragon and the Intel iPSC/860 hypercube. Parallelization is achieved through a combination of mechanisms employing the Gram-Schmidt procedure, broadcasts, global operations, and domain decomposition of state vectors. We discuss the approach to the problems of limited node memory and node-to-node communication overhead inherent in using distributed-memory, multiple-instruction, multiple-data stream parallel computers. An algorithm was developed to reduce the communication overhead by pipelining some of the message passing procedures
Directory of Open Access Journals (Sweden)
Dyon van Vreumingen
2018-05-01
Full Text Available Molecular electronics saw its birth with the idea to build electronic circuitry with single molecules as individual components. Even though commercial applications are still modest, it has served an important part in the study of fundamental physics at the scale of single atoms and molecules. It is now a routine procedure in many research groups around the world to connect a single molecule between two metallic leads. What is unknown is the nature of this coupling between the molecule and the leads. We have demonstrated recently (Tewari, 2018, Ph.D. Thesis our new setup based on a scanning tunneling microscope, which can be used to controllably manipulate single molecules and atomic chains. In this article, we will present the extension of our molecular dynamic simulator attached to this system for the manipulation of single molecules in real time using a graphics processing unit (GPU. This will not only aid in controlled lift-off of single molecules, but will also provide details about changes in the molecular conformations during the manipulation. This information could serve as important input for theoretical models and for bridging the gap between the theory and experiments.
GPU-accelerated 3D neutron diffusion code based on finite difference method
Energy Technology Data Exchange (ETDEWEB)
Xu, Q.; Yu, G.; Wang, K. [Dept. of Engineering Physics, Tsinghua Univ. (China)
2012-07-01
Finite difference method, as a traditional numerical solution to neutron diffusion equation, although considered simpler and more precise than the coarse mesh nodal methods, has a bottle neck to be widely applied caused by the huge memory and unendurable computation time it requires. In recent years, the concept of General-Purpose computation on GPUs has provided us with a powerful computational engine for scientific research. In this study, a GPU-Accelerated multi-group 3D neutron diffusion code based on finite difference method was developed. First, a clean-sheet neutron diffusion code (3DFD-CPU) was written in C++ on the CPU architecture, and later ported to GPUs under NVIDIA's CUDA platform (3DFD-GPU). The IAEA 3D PWR benchmark problem was calculated in the numerical test, where three different codes, including the original CPU-based sequential code, the HYPRE (High Performance Pre-conditioners)-based diffusion code and CITATION, were used as counterpoints to test the efficiency and accuracy of the GPU-based program. The results demonstrate both high efficiency and adequate accuracy of the GPU implementation for neutron diffusion equation. A speedup factor of about 46 times was obtained, using NVIDIA's Geforce GTX470 GPU card against a 2.50 GHz Intel Quad Q9300 CPU processor. Compared with the HYPRE-based code performing in parallel on an 8-core tower server, the speedup of about 2 still could be observed. More encouragingly, without any mathematical acceleration technology, the GPU implementation ran about 5 times faster than CITATION which was speeded up by using the SOR method and Chebyshev extrapolation technique. (authors)
GPU-accelerated 3D neutron diffusion code based on finite difference method
International Nuclear Information System (INIS)
Xu, Q.; Yu, G.; Wang, K.
2012-01-01
Finite difference method, as a traditional numerical solution to neutron diffusion equation, although considered simpler and more precise than the coarse mesh nodal methods, has a bottle neck to be widely applied caused by the huge memory and unendurable computation time it requires. In recent years, the concept of General-Purpose computation on GPUs has provided us with a powerful computational engine for scientific research. In this study, a GPU-Accelerated multi-group 3D neutron diffusion code based on finite difference method was developed. First, a clean-sheet neutron diffusion code (3DFD-CPU) was written in C++ on the CPU architecture, and later ported to GPUs under NVIDIA's CUDA platform (3DFD-GPU). The IAEA 3D PWR benchmark problem was calculated in the numerical test, where three different codes, including the original CPU-based sequential code, the HYPRE (High Performance Pre-conditioners)-based diffusion code and CITATION, were used as counterpoints to test the efficiency and accuracy of the GPU-based program. The results demonstrate both high efficiency and adequate accuracy of the GPU implementation for neutron diffusion equation. A speedup factor of about 46 times was obtained, using NVIDIA's Geforce GTX470 GPU card against a 2.50 GHz Intel Quad Q9300 CPU processor. Compared with the HYPRE-based code performing in parallel on an 8-core tower server, the speedup of about 2 still could be observed. More encouragingly, without any mathematical acceleration technology, the GPU implementation ran about 5 times faster than CITATION which was speeded up by using the SOR method and Chebyshev extrapolation technique. (authors)
International Nuclear Information System (INIS)
Taraglio, S.; Massaioli, F.
1995-08-01
A parallel implementation of a library to build and train Multi Layer Perceptrons via the Back Propagation algorithm is presented. The target machine is the SIMD massively parallel supercomputer Quadrics. Performance measures are provided on three different machines with different number of processors, for two network examples. A sample source code is given
Lashkin, S. V.; Kozelkov, A. S.; Yalozo, A. V.; Gerasimov, V. Yu.; Zelensky, D. K.
2017-12-01
This paper describes the details of the parallel implementation of the SIMPLE algorithm for numerical solution of the Navier-Stokes system of equations on arbitrary unstructured grids. The iteration schemes for the serial and parallel versions of the SIMPLE algorithm are implemented. In the description of the parallel implementation, special attention is paid to computational data exchange among processors under the condition of the grid model decomposition using fictitious cells. We discuss the specific features for the storage of distributed matrices and implementation of vector-matrix operations in parallel mode. It is shown that the proposed way of matrix storage reduces the number of interprocessor exchanges. A series of numerical experiments illustrates the effect of the multigrid SLAE solver tuning on the general efficiency of the algorithm; the tuning involves the types of the cycles used (V, W, and F), the number of iterations of a smoothing operator, and the number of cells for coarsening. Two ways (direct and indirect) of efficiency evaluation for parallelization of the numerical algorithm are demonstrated. The paper presents the results of solving some internal and external flow problems with the evaluation of parallelization efficiency by two algorithms. It is shown that the proposed parallel implementation enables efficient computations for the problems on a thousand processors. Based on the results obtained, some general recommendations are made for the optimal tuning of the multigrid solver, as well as for selecting the optimal number of cells per processor.
International Nuclear Information System (INIS)
Huang Bormin; Mielikainen, Jarno; Oh, Hyunjong; Allen Huang, Hung-Lung
2011-01-01
Satellite-observed radiance is a nonlinear functional of surface properties and atmospheric temperature and absorbing gas profiles as described by the radiative transfer equation (RTE). In the era of hyperspectral sounders with thousands of high-resolution channels, the computation of the radiative transfer model becomes more time-consuming. The radiative transfer model performance in operational numerical weather prediction systems still limits the number of channels we can use in hyperspectral sounders to only a few hundreds. To take the full advantage of such high-resolution infrared observations, a computationally efficient radiative transfer model is needed to facilitate satellite data assimilation. In recent years the programmable commodity graphics processing unit (GPU) has evolved into a highly parallel, multi-threaded, many-core processor with tremendous computational speed and very high memory bandwidth. The radiative transfer model is very suitable for the GPU implementation to take advantage of the hardware's efficiency and parallelism where radiances of many channels can be calculated in parallel in GPUs. In this paper, we develop a GPU-based high-performance radiative transfer model for the Infrared Atmospheric Sounding Interferometer (IASI) launched in 2006 onboard the first European meteorological polar-orbiting satellites, METOP-A. Each IASI spectrum has 8461 spectral channels. The IASI radiative transfer model consists of three modules. The first module for computing the regression predictors takes less than 0.004% of CPU time, while the second module for transmittance computation and the third module for radiance computation take approximately 92.5% and 7.5%, respectively. Our GPU-based IASI radiative transfer model is developed to run on a low-cost personal supercomputer with four GPUs with total 960 compute cores, delivering near 4 TFlops theoretical peak performance. By massively parallelizing the second and third modules, we reached 364x
Accelerating Computation of DCM for ERP in MATLAB by External Function Calls to the GPU
Wang, Wei-Jen; Hsieh, I-Fan; Chen, Chun-Chuan
2013-01-01
This study aims to improve the performance of Dynamic Causal Modelling for Event Related Potentials (DCM for ERP) in MATLAB by using external function calls to a graphics processing unit (GPU). DCM for ERP is an advanced method for studying neuronal effective connectivity. DCM utilizes an iterative procedure, the expectation maximization (EM) algorithm, to find the optimal parameters given a set of observations and the underlying probability model. As the EM algorithm is computationally demanding and the analysis faces possible combinatorial explosion of models to be tested, we propose a parallel computing scheme using the GPU to achieve a fast estimation of DCM for ERP. The computation of DCM for ERP is dynamically partitioned and distributed to threads for parallel processing, according to the DCM model complexity and the hardware constraints. The performance efficiency of this hardware-dependent thread arrangement strategy was evaluated using the synthetic data. The experimental data were used to validate the accuracy of the proposed computing scheme and quantify the time saving in practice. The simulation results show that the proposed scheme can accelerate the computation by a factor of 155 for the parallel part. For experimental data, the speedup factor is about 7 per model on average, depending on the model complexity and the data. This GPU-based implementation of DCM for ERP gives qualitatively the same results as the original MATLAB implementation does at the group level analysis. In conclusion, we believe that the proposed GPU-based implementation is very useful for users as a fast screen tool to select the most likely model and may provide implementation guidance for possible future clinical applications such as online diagnosis. PMID:23840507
Parallel processes: using motivational interviewing as an implementation coaching strategy.
Hettema, Jennifer E; Ernst, Denise; Williams, Jessica Roberts; Miller, Kristin J
2014-07-01
In addition to its clinical efficacy as a communication style for strengthening motivation and commitment to change, motivational interviewing (MI) has been hypothesized to be a potential tool for facilitating evidence-based practice adoption decisions. This paper reports on the rationale and content of MI-based implementation coaching Webinars that, as part of a larger active dissemination strategy, were found to be more effective than passive dissemination strategies at promoting adoption decisions among behavioral health and health providers and administrators. The Motivational Interviewing Treatment Integrity scale (MITI 3.1.1) was used to rate coaching Webinars from 17 community behavioral health organizations and 17 community health centers. The MITI coding system was found to be applicable to the coaching Webinars, and raters achieved high levels of agreement on global and behavior count measurements of fidelity to MI. Results revealed that implementation coaches maintained fidelity to the MI model, exceeding competency benchmarks for almost all measures. Findings suggest that it is feasible to implement MI as a coaching tool.
Design and Implementation of Papyrus: Parallel Aggregate Persistent Storage
Energy Technology Data Exchange (ETDEWEB)
Kim, Jungwon [ORNL; Sajjapongse, Kittisak [ORNL; Lee, Seyong [ORNL; Vetter, Jeffrey S [ORNL
2017-01-01
A surprising development in recently announced HPC platforms is the addition of, sometimes massive amounts of, persistent (nonvolatile) memory (NVM) in order to increase memory capacity and compensate for plateauing I/O capabilities. However, there are no portable and scalable programming interfaces using aggregate NVM effectively. This paper introduces Papyrus: a new software system built to exploit emerging capability of NVM in HPC architectures. Papyrus (or Parallel Aggregate Persistent -YRU- Storage) is a novel programming system that provides features for scalable, aggregate, persistent memory in an extreme-scale system for typical HPC usage scenarios. Papyrus mainly consists of Papyrus Virtual File System (VFS) and Papyrus Template Container Library (TCL). Papyrus VFS provides a uniform aggregate NVM storage image across diverse NVM architectures. It enables Papyrus TCL to provide a portable and scalable high-level container programming interface whose data elements are distributed across multiple NVM nodes without requiring the user to handle complex communication, synchronization, replication, and consistency model. We evaluate Papyrus on two HPC systems, including UTK Beacon and NERSC Cori, using real NVM storage devices.
Parallel asynchronous hardware implementation of image processing algorithms
Coon, Darryl D.; Perera, A. G. U.
1990-01-01
Research is being carried out on hardware for a new approach to focal plane processing. The hardware involves silicon injection mode devices. These devices provide a natural basis for parallel asynchronous focal plane image preprocessing. The simplicity and novel properties of the devices would permit an independent analog processing channel to be dedicated to every pixel. A laminar architecture built from arrays of the devices would form a two-dimensional (2-D) array processor with a 2-D array of inputs located directly behind a focal plane detector array. A 2-D image data stream would propagate in neuron-like asynchronous pulse-coded form through the laminar processor. No multiplexing, digitization, or serial processing would occur in the preprocessing state. High performance is expected, based on pulse coding of input currents down to one picoampere with noise referred to input of about 10 femtoamperes. Linear pulse coding has been observed for input currents ranging up to seven orders of magnitude. Low power requirements suggest utility in space and in conjunction with very large arrays. Very low dark current and multispectral capability are possible because of hardware compatibility with the cryogenic environment of high performance detector arrays. The aforementioned hardware development effort is aimed at systems which would integrate image acquisition and image processing.
High-speed detection of emergent market clustering via an unsupervised parallel genetic algorithm
Directory of Open Access Journals (Sweden)
Dieter Hendricks
2016-02-01
Full Text Available We implement a master-slave parallel genetic algorithm with a bespoke log-likelihood fitness function to identify emergent clusters within price evolutions. We use graphics processing units (GPUs to implement a parallel genetic algorithm and visualise the results using disjoint minimal spanning trees. We demonstrate that our GPU parallel genetic algorithm, implemented on a commercially available general purpose GPU, is able to recover stock clusters in sub-second speed, based on a subset of stocks in the South African market. This approach represents a pragmatic choice for low-cost, scalable parallel computing and is significantly faster than a prototype serial implementation in an optimised C-based fourth-generation programming language, although the results are not directly comparable because of compiler differences. Combined with fast online intraday correlation matrix estimation from high frequency data for cluster identification, the proposed implementation offers cost-effective, near-real-time risk assessment for financial practitioners.
Massive Parallelism of Monte-Carlo Simulation on Low-End Hardware using Graphic Processing Units
Energy Technology Data Exchange (ETDEWEB)
Mburu, Joe Mwangi; Hah, Chang Joo Hah [KEPCO International Nuclear Graduate School, Ulsan (Korea, Republic of)
2014-05-15
Within the past decade, research has been done on utilizing GPU massive parallelization in core simulation with impressive results but unfortunately, not much commercial application has been done in the nuclear field especially in reactor core simulation. The purpose of this paper is to give an introductory concept on the topic and illustrate the potential of exploiting the massive parallel nature of GPU computing on a simple monte-carlo simulation with very minimal hardware specifications. To do a comparative analysis, a simple two dimension monte-carlo simulation is implemented for both the CPU and GPU in order to evaluate performance gain based on the computing devices. The heterogeneous platform utilized in this analysis is done on a slow notebook with only 1GHz processor. The end results are quite surprising whereby high speedups obtained are almost a factor of 10. In this work, we have utilized heterogeneous computing in a GPU-based approach in applying potential high arithmetic intensive calculation. By applying a complex monte-carlo simulation on GPU platform, we have speed up the computational process by almost a factor of 10 based on one million neutrons. This shows how easy, cheap and efficient it is in using GPU in accelerating scientific computing and the results should encourage in exploring further this avenue especially in nuclear reactor physics simulation where deterministic and stochastic calculations are quite favourable in parallelization.
Massive Parallelism of Monte-Carlo Simulation on Low-End Hardware using Graphic Processing Units
International Nuclear Information System (INIS)
Mburu, Joe Mwangi; Hah, Chang Joo Hah
2014-01-01
Within the past decade, research has been done on utilizing GPU massive parallelization in core simulation with impressive results but unfortunately, not much commercial application has been done in the nuclear field especially in reactor core simulation. The purpose of this paper is to give an introductory concept on the topic and illustrate the potential of exploiting the massive parallel nature of GPU computing on a simple monte-carlo simulation with very minimal hardware specifications. To do a comparative analysis, a simple two dimension monte-carlo simulation is implemented for both the CPU and GPU in order to evaluate performance gain based on the computing devices. The heterogeneous platform utilized in this analysis is done on a slow notebook with only 1GHz processor. The end results are quite surprising whereby high speedups obtained are almost a factor of 10. In this work, we have utilized heterogeneous computing in a GPU-based approach in applying potential high arithmetic intensive calculation. By applying a complex monte-carlo simulation on GPU platform, we have speed up the computational process by almost a factor of 10 based on one million neutrons. This shows how easy, cheap and efficient it is in using GPU in accelerating scientific computing and the results should encourage in exploring further this avenue especially in nuclear reactor physics simulation where deterministic and stochastic calculations are quite favourable in parallelization
Haptic Feedback for the GPU-based Surgical Simulator
DEFF Research Database (Denmark)
Sørensen, Thomas Sangild; Mosegaard, Jesper
2006-01-01
The GPU has proven to be a powerful processor to compute spring-mass based surgical simulations. It has not previously been shown however, how to effectively implement haptic interaction with a simulation running entirely on the GPU. This paper describes a method to calculate haptic feedback...... with limited performance cost. It allows easy balancing of the GPU workload between calculations of simulation, visualisation, and the haptic feedback....
GPU computing and applications
See, Simon
2015-01-01
This book presents a collection of state of the art research on GPU Computing and Application. The major part of this book is selected from the work presented at the 2013 Symposium on GPU Computing and Applications held in Nanyang Technological University, Singapore (Oct 9, 2013). Three major domains of GPU application are covered in the book including (1) Engineering design and simulation; (2) Biomedical Sciences; and (3) Interactive & Digital Media. The book also addresses the fundamental issues in GPU computing with a focus on big data processing. Researchers and developers in GPU Computing and Applications will benefit from this book. Training professionals and educators can also benefit from this book to learn the possible application of GPU technology in various areas.
Application of GPU to computational multiphase fluid dynamics
International Nuclear Information System (INIS)
Nagatake, T; Kunugi, T
2010-01-01
The MARS (Multi-interfaces Advection and Reconstruction Solver) [1] is one of the surface volume tracking methods for multi-phase flows. Nowadays, the performance of GPU (Graphics Processing Unit) is much higher than the CPU (Central Processing Unit). In this study, the GPU was applied to the MARS in order to accelerate the computation of multi-phase flows (GPU-MARS), and the performance of the GPU-MARS was discussed. From the performance of the interface tracking method for the analyses of one-directional advection problem, it is found that the computing time of GPU(single GTX280) was around 4 times faster than that of the CPU (Xeon 5040, 4 threads parallelized). From the performance of Poisson Solver by using the algorithm developed in this study, it is found that the performance of the GPU showed around 30 times faster than that of the CPU. Finally, it is confirmed that the GPU showed the large acceleration of the fluid flow computation (GPU-MARS) compared to the CPU. However, it is also found that the double-precision computation of the GPU must perform with very high precision.
Graph coarsening and clustering on the GPU
Fagginger Auer, B.O.; Bisseling, R.H.
2013-01-01
Agglomerative clustering is an effective greedy way to quickly generate graph clusterings of high modularity in a small amount of time. In an effort to use the power offered by multi-core CPU and GPU hardware to solve the clustering problem, we introduce a fine-grained sharedmemory parallel graph
Implementation of QR up- and downdating on a massively parallel |computer
DEFF Research Database (Denmark)
Bendtsen, Claus; Hansen, Per Christian; Madsen, Kaj
1995-01-01
We describe an implementation of QR up- and downdating on a massively parallel computer (the Connection Machine CM-200) and show that the algorithm maps well onto the computer. In particular, we show how the use of corrected semi-normal equations for downdating can be efficiently implemented. We...... also illustrate the use of our algorithms in a new LP algorithm....
GPU-based simulation of optical propagation through turbulence for active and passive imaging
Monnier, Goulven; Duval, François-Régis; Amram, Solène
2014-10-01
IMOTEP is a GPU-based (Graphical Processing Units) software relying on a fast parallel implementation of Fresnel diffraction through successive phase screens. Its applications include active imaging, laser telemetry and passive imaging through turbulence with anisoplanatic spatial and temporal fluctuations. Thanks to parallel implementation on GPU, speedups ranging from 40X to 70X are achieved. The present paper gives a brief overview of IMOTEP models, algorithms, implementation and user interface. It then focuses on major improvements recently brought to the anisoplanatic imaging simulation method. Previously, we took advantage of the computational power offered by the GPU to develop a simulation method based on large series of deterministic realisations of the PSF distorted by turbulence. The phase screen propagation algorithm, by reproducing higher moments of the incident wavefront distortion, provides realistic PSFs. However, we first used a coarse gaussian model to fit the numerical PSFs and characterise there spatial statistics through only 3 parameters (two-dimensional displacements of centroid and width). Meanwhile, this approach was unable to reproduce the effects related to the details of the PSF structure, especially the "speckles" leading to prominent high-frequency content in short-exposure images. To overcome this limitation, we recently implemented a new empirical model of the PSF, based on Principal Components Analysis (PCA), ought to catch most of the PSF complexity. The GPU implementation allows estimating and handling efficiently the numerous (up to several hundreds) principal components typically required under the strong turbulence regime. A first demanding computational step involves PCA, phase screen propagation and covariance estimates. In a second step, realistic instantaneous images, fully accounting for anisoplanatic effects, are quickly generated. Preliminary results are presented.
A two-level parallel direct search implementation for arbitrarily sized objective functions
Energy Technology Data Exchange (ETDEWEB)
Hutchinson, S.A.; Shadid, N.; Moffat, H.K. [Sandia National Labs., Albuquerque, NM (United States)] [and others
1994-12-31
In the past, many optimization schemes for massively parallel computers have attempted to achieve parallel efficiency using one of two methods. In the case of large and expensive objective function calculations, the optimization itself may be run in serial and the objective function calculations parallelized. In contrast, if the objective function calculations are relatively inexpensive and can be performed on a single processor, then the actual optimization routine itself may be parallelized. In this paper, a scheme based upon the Parallel Direct Search (PDS) technique is presented which allows the objective function calculations to be done on an arbitrarily large number (p{sub 2}) of processors. If, p, the number of processors available, is greater than or equal to 2p{sub 2} then the optimization may be parallelized as well. This allows for efficient use of computational resources since the objective function calculations can be performed on the number of processors that allow for peak parallel efficiency and then further speedup may be achieved by parallelizing the optimization. Results are presented for an optimization problem which involves the solution of a PDE using a finite-element algorithm as part of the objective function calculation. The optimum number of processors for the finite-element calculations is less than p/2. Thus, the PDS method is also parallelized. Performance comparisons are given for a nCUBE 2 implementation.
Convolution of large 3D images on GPU and its decomposition
Karas, Pavel; Svoboda, David
2011-12-01
In this article, we propose a method for computing convolution of large 3D images. The convolution is performed in a frequency domain using a convolution theorem. The algorithm is accelerated on a graphic card by means of the CUDA parallel computing model. Convolution is decomposed in a frequency domain using the decimation in frequency algorithm. We pay attention to keeping our approach efficient in terms of both time and memory consumption and also in terms of memory transfers between CPU and GPU which have a significant inuence on overall computational time. We also study the implementation on multiple GPUs and compare the results between the multi-GPU and multi-CPU implementations.
Fast and maliciously secure two-party computation using the GPU
DEFF Research Database (Denmark)
Frederiksen, Tore Kasper; Nielsen, Jesper Buus
2013-01-01
We describe, and implement, a maliciously secure protocol for two-party computation in a parallel computational model. Our protocol is based on Yao’s garbled circuit and an efficient OT extension. The implementation is done using CUDA and yields fast results for maliciously secure two-party compu......-party computation in a financially feasible and practical setting by using a consumer grade CPU and GPU. Our protocol further uses some novel constructions in order to combine garbled circuits and an OT extension in a parallel and maliciously secure setting.......We describe, and implement, a maliciously secure protocol for two-party computation in a parallel computational model. Our protocol is based on Yao’s garbled circuit and an efficient OT extension. The implementation is done using CUDA and yields fast results for maliciously secure two...
GPU Acceleration of DSP for Communication Receivers.
Gunther, Jake; Gunther, Hyrum; Moon, Todd
2017-09-01
Graphics processing unit (GPU) implementations of signal processing algorithms can outperform CPU-based implementations. This paper describes the GPU implementation of several algorithms encountered in a wide range of high-data rate communication receivers including filters, multirate filters, numerically controlled oscillators, and multi-stage digital down converters. These structures are tested by processing the 20 MHz wide FM radio band (88-108 MHz). Two receiver structures are explored: a single channel receiver and a filter bank channelizer. Both run in real time on NVIDIA GeForce GTX 1080 graphics card.
Russkova, Tatiana V.
2017-11-01
One tool to improve the performance of Monte Carlo methods for numerical simulation of light transport in the Earth's atmosphere is the parallel technology. A new algorithm oriented to parallel execution on the CUDA-enabled NVIDIA graphics processor is discussed. The efficiency of parallelization is analyzed on the basis of calculating the upward and downward fluxes of solar radiation in both a vertically homogeneous and inhomogeneous models of the atmosphere. The results of testing the new code under various atmospheric conditions including continuous singlelayered and multilayered clouds, and selective molecular absorption are presented. The results of testing the code using video cards with different compute capability are analyzed. It is shown that the changeover of computing from conventional PCs to the architecture of graphics processors gives more than a hundredfold increase in performance and fully reveals the capabilities of the technology used.
CMFD and GPU acceleration on method of characteristics for hexagonal cores
International Nuclear Information System (INIS)
Han, Yu; Jiang, Xiaofeng; Wang, Dezhong
2014-01-01
Highlights: • A merged hex-mesh CMFD method solved via tri-diagonal matrix inversion. • Alternative hardware acceleration of using inexpensive GPU. • A hex-core benchmark with solution to confirm two acceleration methods. - Abstract: Coarse Mesh Finite Difference (CMFD) has been widely adopted as an effective way to accelerate the source iteration of transport calculation. However in a core with hexagonal assemblies there are non-hexagonal meshes around the edges of assemblies, causing a problem for CMFD if the CMFD equations are still to be solved via tri-diagonal matrix inversion by simply scanning the whole core meshes in different directions. To solve this problem, we propose an unequal mesh CMFD formulation that combines the non-hexagonal cells on the boundary of neighboring assemblies into non-regular hexagonal cells. We also investigated the alternative hardware acceleration of using graphics processing units (GPU) with graphics card in a personal computer. The tool CUDA is employed, which is a parallel computing platform and programming model invented by the company NVIDIA for harnessing the power of GPU. To investigate and implement these two acceleration methods, a 2-D hexagonal core transport code using the method of characteristics (MOC) is developed. A hexagonal mini-core benchmark problem is established to confirm the accuracy of the MOC code and to assess the effectiveness of CMFD and GPU parallel acceleration. For this benchmark problem, the CMFD acceleration increases the speed 16 times while the GPU acceleration speeds it up 25 times. When used simultaneously, they provide a speed gain of 292 times
CMFD and GPU acceleration on method of characteristics for hexagonal cores
Energy Technology Data Exchange (ETDEWEB)
Han, Yu, E-mail: hanyu1203@gmail.com [School of Nuclear Science and Engineering, Shanghai Jiaotong University, Shanghai 200240 (China); Jiang, Xiaofeng [Shanghai NuStar Nuclear Power Technology Co., Ltd., No. 81 South Qinzhou Road, XuJiaHui District, Shanghai 200000 (China); Wang, Dezhong [School of Nuclear Science and Engineering, Shanghai Jiaotong University, Shanghai 200240 (China)
2014-12-15
Highlights: • A merged hex-mesh CMFD method solved via tri-diagonal matrix inversion. • Alternative hardware acceleration of using inexpensive GPU. • A hex-core benchmark with solution to confirm two acceleration methods. - Abstract: Coarse Mesh Finite Difference (CMFD) has been widely adopted as an effective way to accelerate the source iteration of transport calculation. However in a core with hexagonal assemblies there are non-hexagonal meshes around the edges of assemblies, causing a problem for CMFD if the CMFD equations are still to be solved via tri-diagonal matrix inversion by simply scanning the whole core meshes in different directions. To solve this problem, we propose an unequal mesh CMFD formulation that combines the non-hexagonal cells on the boundary of neighboring assemblies into non-regular hexagonal cells. We also investigated the alternative hardware acceleration of using graphics processing units (GPU) with graphics card in a personal computer. The tool CUDA is employed, which is a parallel computing platform and programming model invented by the company NVIDIA for harnessing the power of GPU. To investigate and implement these two acceleration methods, a 2-D hexagonal core transport code using the method of characteristics (MOC) is developed. A hexagonal mini-core benchmark problem is established to confirm the accuracy of the MOC code and to assess the effectiveness of CMFD and GPU parallel acceleration. For this benchmark problem, the CMFD acceleration increases the speed 16 times while the GPU acceleration speeds it up 25 times. When used simultaneously, they provide a speed gain of 292 times.
Design of high-performance parallelized gene predictors in MATLAB.
Rivard, Sylvain Robert; Mailloux, Jean-Gabriel; Beguenane, Rachid; Bui, Hung Tien
2012-04-10
This paper proposes a method of implementing parallel gene prediction algorithms in MATLAB. The proposed designs are based on either Goertzel's algorithm or on FFTs and have been implemented using varying amounts of parallelism on a central processing unit (CPU) and on a graphics processing unit (GPU). Results show that an implementation using a straightforward approach can require over 4.5 h to process 15 million base pairs (bps) whereas a properly designed one could perform the same task in less than five minutes. In the best case, a GPU implementation can yield these results in 57 s. The present work shows how parallelism can be used in MATLAB for gene prediction in very large DNA sequences to produce results that are over 270 times faster than a conventional approach. This is significant as MATLAB is typically overlooked due to its apparent slow processing time even though it offers a convenient environment for bioinformatics. From a practical standpoint, this work proposes two strategies for accelerating genome data processing which rely on different parallelization mechanisms. Using a CPU, the work shows that direct access to the MEX function increases execution speed and that the PARFOR construct should be used in order to take full advantage of the parallelizable Goertzel implementation. When the target is a GPU, the work shows that data needs to be segmented into manageable sizes within the GFOR construct before processing in order to minimize execution time.
Srinivasa, K. G.; Shree Devi, B. N.
2017-10-01
String searching in documents has become a tedious task with the evolution of Big Data. Generation of large data sets demand for a high performance search algorithm in areas such as text mining, information retrieval and many others. The popularity of GPU's for general purpose computing has been increasing for various applications. Therefore it is of great interest to exploit the thread feature of a GPU to provide a high performance search algorithm. This paper proposes an optimized new approach to N-gram model for string search in a number of lengthy documents and its GPU implementation. The algorithm exploits GPGPUs for searching strings in many documents employing character level N-gram matching with parallel Score Table approach and search using CUDA API. The new approach of Score table used for frequency storage of N-grams in a document, makes the search independent of the document's length and allows faster access to the frequency values, thus decreasing the search complexity. The extensive thread feature in a GPU has been exploited to enable parallel pre-processing of trigrams in a document for Score Table creation and parallel search in huge number of documents, thus speeding up the whole search process even for a large pattern size. Experiments were carried out for many documents of varied length and search strings from the standard Lorem Ipsum text on NVIDIA's GeForce GT 540M GPU with 96 cores. Results prove that the parallel approach for Score Table creation and searching gives a good speed up than the same approach executed serially.
A multithreaded parallel implementation of a dynamic programming algorithm for sequence comparison.
Martins, W S; Del Cuvillo, J B; Useche, F J; Theobald, K B; Gao, G R
2001-01-01
This paper discusses the issues involved in implementing a dynamic programming algorithm for biological sequence comparison on a general-purpose parallel computing platform based on a fine-grain event-driven multithreaded program execution model. Fine-grain multithreading permits efficient parallelism exploitation in this application both by taking advantage of asynchronous point-to-point synchronizations and communication with low overheads and by effectively tolerating latency through the overlapping of computation and communication. We have implemented our scheme on EARTH, a fine-grain event-driven multithreaded execution and architecture model which has been ported to a number of parallel machines with off-the-shelf processors. Our experimental results show that the dynamic programming algorithm can be efficiently implemented on EARTH systems with high performance (e.g., speedup of 90 on 120 nodes), good programmability and reasonable cost.
Length-Bounded Hybrid CPU/GPU Pattern Matching Algorithm for Deep Packet Inspection
Directory of Open Access Journals (Sweden)
Yi-Shan Lin
2017-01-01
Full Text Available Since frequent communication between applications takes place in high speed networks, deep packet inspection (DPI plays an important role in the network application awareness. The signature-based network intrusion detection system (NIDS contains a DPI technique that examines the incoming packet payloads by employing a pattern matching algorithm that dominates the overall inspection performance. Existing studies focused on implementing efficient pattern matching algorithms by parallel programming on software platforms because of the advantages of lower cost and higher scalability. Either the central processing unit (CPU or the graphic processing unit (GPU were involved. Our studies focused on designing a pattern matching algorithm based on the cooperation between both CPU and GPU. In this paper, we present an enhanced design for our previous work, a length-bounded hybrid CPU/GPU pattern matching algorithm (LHPMA. In the preliminary experiment, the performance and comparison with the previous work are displayed, and the experimental results show that the LHPMA can achieve not only effective CPU/GPU cooperation but also higher throughput than the previous method.
permGPU: Using graphics processing units in RNA microarray association studies
Directory of Open Access Journals (Sweden)
George Stephen L
2010-06-01
Full Text Available Abstract Background Many analyses of microarray association studies involve permutation, bootstrap resampling and cross-validation, that are ideally formulated as embarrassingly parallel computing problems. Given that these analyses are computationally intensive, scalable approaches that can take advantage of multi-core processor systems need to be developed. Results We have developed a CUDA based implementation, permGPU, that employs graphics processing units in microarray association studies. We illustrate the performance and applicability of permGPU within the context of permutation resampling for a number of test statistics. An extensive simulation study demonstrates a dramatic increase in performance when using permGPU on an NVIDIA GTX 280 card compared to an optimized C/C++ solution running on a conventional Linux server. Conclusions permGPU is available as an open-source stand-alone application and as an extension package for the R statistical environment. It provides a dramatic increase in performance for permutation resampling analysis in the context of microarray association studies. The current version offers six test statistics for carrying out permutation resampling analyses for binary, quantitative and censored time-to-event traits.
GPU Accelerated Vector Median Filter
Aras, Rifat; Shen, Yuzhong
2011-01-01
Noise reduction is an important step for most image processing tasks. For three channel color images, a widely used technique is vector median filter in which color values of pixels are treated as 3-component vectors. Vector median filters are computationally expensive; for a window size of n x n, each of the n(sup 2) vectors has to be compared with other n(sup 2) - 1 vectors in distances. General purpose computation on graphics processing units (GPUs) is the paradigm of utilizing high-performance many-core GPU architectures for computation tasks that are normally handled by CPUs. In this work. NVIDIA's Compute Unified Device Architecture (CUDA) paradigm is used to accelerate vector median filtering. which has to the best of our knowledge never been done before. The performance of GPU accelerated vector median filter is compared to that of the CPU and MPI-based versions for different image and window sizes, Initial findings of the study showed 100x improvement of performance of vector median filter implementation on GPUs over CPU implementations and further speed-up is expected after more extensive optimizations of the GPU algorithm .
Semi-automatic tool to ease the creation and optimization of GPU programs
DEFF Research Database (Denmark)
Jepsen, Jacob
2014-01-01
We present a tool that reduces the development time of GPU-executable code. We implement a catalogue of common optimizations specific to the GPU architecture. Through the tool, the programmer can semi-automatically transform a computationally-intensive code section into GPU-executable form...... of the transformations can be performed automatically, which makes the tool usable for both novices and experts in GPU programming....
A GPU-accelerated implicit meshless method for compressible flows
Zhang, Jia-Le; Ma, Zhi-Hua; Chen, Hong-Quan; Cao, Cheng
2018-05-01
This paper develops a recently proposed GPU based two-dimensional explicit meshless method (Ma et al., 2014) by devising and implementing an efficient parallel LU-SGS implicit algorithm to further improve the computational efficiency. The capability of the original 2D meshless code is extended to deal with 3D complex compressible flow problems. To resolve the inherent data dependency of the standard LU-SGS method, which causes thread-racing conditions destabilizing numerical computation, a generic rainbow coloring method is presented and applied to organize the computational points into different groups by painting neighboring points with different colors. The original LU-SGS method is modified and parallelized accordingly to perform calculations in a color-by-color manner. The CUDA Fortran programming model is employed to develop the key kernel functions to apply boundary conditions, calculate time steps, evaluate residuals as well as advance and update the solution in the temporal space. A series of two- and three-dimensional test cases including compressible flows over single- and multi-element airfoils and a M6 wing are carried out to verify the developed code. The obtained solutions agree well with experimental data and other computational results reported in the literature. Detailed analysis on the performance of the developed code reveals that the developed CPU based implicit meshless method is at least four to eight times faster than its explicit counterpart. The computational efficiency of the implicit method could be further improved by ten to fifteen times on the GPU.
Synthetic Aperture Beamformation using the GPU
DEFF Research Database (Denmark)
Hansen, Jens Munk; Schaa, Dana; Jensen, Jørgen Arendt
2011-01-01
A synthetic aperture ultrasound beamformer is implemented for a GPU using the OpenCL framework. The implementation supports beamformation of either RF signals or complex baseband signals. Transmit and receive apodization can be either parametric or dynamic using a fixed F-number, a reference...
Implementing the lattice Boltzmann model on commodity graphics hardware
International Nuclear Information System (INIS)
Kaufman, Arie; Fan, Zhe; Petkov, Kaloian
2009-01-01
Modern graphics processing units (GPUs) can perform general-purpose computations in addition to the native specialized graphics operations. Due to the highly parallel nature of graphics processing, the GPU has evolved into a many-core coprocessor that supports high data parallelism. Its performance has been growing at a rate of squared Moore's law, and its peak floating point performance exceeds that of the CPU by an order of magnitude. Therefore, it is a viable platform for time-sensitive and computationally intensive applications. The lattice Boltzmann model (LBM) computations are carried out via linear operations at discrete lattice sites, which can be implemented efficiently using a GPU-based architecture. Our simulations produce results comparable to the CPU version while improving performance by an order of magnitude. We have demonstrated that the GPU is well suited for interactive simulations in many applications, including simulating fire, smoke, lightweight objects in wind, jellyfish swimming in water, and heat shimmering and mirage (using the hybrid thermal LBM). We further advocate the use of a GPU cluster for large scale LBM simulations and for high performance computing. The Stony Brook Visual Computing Cluster has been the platform for several applications, including simulations of real-time plume dispersion in complex urban environments and thermal fluid dynamics in a pressurized water reactor. Major GPU vendors have been targeting the high performance computing market with GPU hardware implementations. Software toolkits such as NVIDIA CUDA provide a convenient development platform that abstracts the GPU and allows access to its underlying stream computing architecture. However, software programming for a GPU cluster remains a challenging task. We have therefore developed the Zippy framework to simplify GPU cluster programming. Zippy is based on global arrays combined with the stream programming model and it hides the low-level details of the
International Nuclear Information System (INIS)
De Ladurantaye, Vincent; Lavoie, Jean; Bergeron, Jocelyn; Parenteau, Maxime; Lu Huizhong; Pichevar, Ramin; Rouat, Jean
2012-01-01
A parallel implementation of a large spiking neural network is proposed and evaluated. The neural network implements the binding by synchrony process using the Oscillatory Dynamic Link Matcher (ODLM). Scalability, speed and performance are compared for 2 implementations: Message Passing Interface (MPI) and Compute Unified Device Architecture (CUDA) running on clusters of multicore supercomputers and NVIDIA graphical processing units respectively. A global spiking list that represents at each instant the state of the neural network is described. This list indexes each neuron that fires during the current simulation time so that the influence of their spikes are simultaneously processed on all computing units. Our implementation shows a good scalability for very large networks. A complex and large spiking neural network has been implemented in parallel with success, thus paving the road towards real-life applications based on networks of spiking neurons. MPI offers a better scalability than CUDA, while the CUDA implementation on a GeForce GTX 285 gives the best cost to performance ratio. When running the neural network on the GTX 285, the processing speed is comparable to the MPI implementation on RQCHP's Mammouth parallel with 64 notes (128 cores).
Choi, Sunghoon; Lee, Haenghwa; Lee, Donghoon; Choi, Seungyeon; Lee, Chang-Lae; Kwon, Woocheol; Shin, Jungwook; Seo, Chang-Woo; Kim, Hee-Joung
2018-05-01
This work describes the hardware and software developments of a prototype chest digital tomosynthesis (CDT) R/F system. The purpose of this study was to validate the developed system for its possible clinical application on low-dose chest tomosynthesis imaging. The prototype CDT R/F system was operated by carefully controlling the electromechanical subsystems through a synchronized interface. Once a command signal was delivered by the user, a tomosynthesis sweep started to acquire 81 projection views (PVs) in a limited angular range of ±20°. Among the full projection dataset of 81 images, several sets of 21 (quarter view) and 41 (half view) images with equally spaced angle steps were selected to represent a sparse view condition. GPU-accelerated and total-variation (TV) regularization strategy-based compressed sensing (CS) image reconstruction was implemented. The imaged objects were a flat-field using a copper filter to measure the noise power spectrum (NPS), a Catphan ® CTP682 quality assurance (QA) phantom to measure a task-based modulation transfer function (MTF T ask ) of three different cylinders' edge, and an anthropomorphic chest phantom with inserted lung nodules. The authors also verified the accelerated computing power over CPU programming by checking the elapsed time required for the CS method. The resultant absorbed and effective doses that were delivered to the chest phantom from two-view digital radiographic projections, helical computed tomography (CT), and the prototype CDT system were compared. The prototype CDT system was successfully operated, showing little geometric error with fast rise and fall times of R/F x-ray pulse less than 2 and 10 ms, respectively. The in-plane NPS presented essential symmetric patterns as predicted by the central slice theorem. The NPS images from 21 PVs were provided quite different pattern against 41 and 81 PVs due to aliased noise. The voxel variance values which summed all NPS intensities were inversely
First massively parallel algorithm to be implemented in Apollo-II code
International Nuclear Information System (INIS)
Stankovski, Z.
1994-01-01
The collision probability (CP) method in neutron transport, as applied to arbitrary 2D XY geometries, like the TDT module in APOLLO-II, is very time consuming. Consequently RZ or 3D extensions became prohibitive. Fortunately, this method is very suitable for parallelization. Massively parallel computer architectures, especially MIMD machines, bring a new breath to this method. In this paper we present a CM5 implementation of the CP method. Parallelization is applied to the energy groups, using the CMMD message passing library. In our case we use 32 processors for the standard 99-group APOLLIB-II library. The real advantage of this algorithm will appear in the calculation of the future fine multigroup library (about 8000 groups) of the SAPHYR project with a massively parallel computer (to the order of hundreds of processors). (author). 3 tabs., 4 figs., 4 refs
First massively parallel algorithm to be implemented in APOLLO-II code
International Nuclear Information System (INIS)
Stankovski, Z.
1994-01-01
The collision probability method in neutron transport, as applied to arbitrary 2-dimensional geometries, like the two dimensional transport module in APOLLO-II is very time consuming. Consequently 3-dimensional extension became prohibitive. Fortunately, this method is very suitable for parallelization. Massively parallel computer architectures, especially MIMD machines, bring a new breath to this method. In this paper we present a CM5 implementation of the collision probability method. Parallelization is applied to the energy groups, using the CMMD massage passing library. In our case we used 32 processors for the standard 99-group APOLLIB-II library. The real advantage of this algorithm will appear in the calculation of the future multigroup library (about 8000 groups) of the SAPHYR project with a massively parallel computer (to the order of hundreds of processors). (author). 4 refs., 4 figs., 3 tabs
Same-source parallel implementation of the PSU/NCAR MM5
Energy Technology Data Exchange (ETDEWEB)
Michalakes, J.
1997-12-31
The Pennsylvania State/National Center for Atmospheric Research Mesoscale Model is a limited-area model of atmospheric systems, now in its fifth generation, MM5. Designed and maintained for vector and shared-memory parallel architectures, the official version of MM5 does not run on message-passing distributed memory (DM) parallel computers. The authors describe a same-source parallel implementation of the PSU/NCAR MM5 using FLIC, the Fortran Loop and Index Converter. The resulting source is nearly line-for-line identical with the original source code. The result is an efficient distributed memory parallel option to MM5 that can be seamlessly integrated into the official version.
Implementation of Parallel Dynamic Simulation on Shared-Memory vs. Distributed-Memory Environments
Energy Technology Data Exchange (ETDEWEB)
Jin, Shuangshuang; Chen, Yousu; Wu, Di; Diao, Ruisheng; Huang, Zhenyu
2015-12-09
Power system dynamic simulation computes the system response to a sequence of large disturbance, such as sudden changes in generation or load, or a network short circuit followed by protective branch switching operation. It consists of a large set of differential and algebraic equations, which is computational intensive and challenging to solve using single-processor based dynamic simulation solution. High-performance computing (HPC) based parallel computing is a very promising technology to speed up the computation and facilitate the simulation process. This paper presents two different parallel implementations of power grid dynamic simulation using Open Multi-processing (OpenMP) on shared-memory platform, and Message Passing Interface (MPI) on distributed-memory clusters, respectively. The difference of the parallel simulation algorithms and architectures of the two HPC technologies are illustrated, and their performances for running parallel dynamic simulation are compared and demonstrated.
Lee, Tai-Sung; Hu, Yuan; Sherborne, Brad; Guo, Zhuyan; York, Darrin M
2017-07-11
We report the implementation of the thermodynamic integration method on the pmemd module of the AMBER 16 package on GPUs (pmemdGTI). The pmemdGTI code typically delivers over 2 orders of magnitude of speed-up relative to a single CPU core for the calculation of ligand-protein binding affinities with no statistically significant numerical differences and thus provides a powerful new tool for drug discovery applications.
GPU-Accelerated Stony-Brook University 5-class Microphysics Scheme in WRF
Mielikainen, J.; Huang, B.; Huang, A.
2011-12-01
The Weather Research and Forecasting (WRF) model is a next-generation mesoscale numerical weather prediction system. Microphysics plays an important role in weather and climate prediction. Several bulk water microphysics schemes are available within the WRF, with different numbers of simulated hydrometeor classes and methods for estimating their size fall speeds, distributions and densities. Stony-Brook University scheme (SBU-YLIN) is a 5-class scheme with riming intensity predicted to account for mixed-phase processes. In the past few years, co-processing on Graphics Processing Units (GPUs) has been a disruptive technology in High Performance Computing (HPC). GPUs use the ever increasing transistor count for adding more processor cores. Therefore, GPUs are well suited for massively data parallel processing with high floating point arithmetic intensity. Thus, it is imperative to update legacy scientific applications to take advantage of this unprecedented increase in computing power. CUDA is an extension to the C programming language offering programming GPU's directly. It is designed so that its constructs allow for natural expression of data-level parallelism. A CUDA program is organized into two parts: a serial program running on the CPU and a CUDA kernel running on the GPU. The CUDA code consists of three computational phases: transmission of data into the global memory of the GPU, execution of the CUDA kernel, and transmission of results from the GPU into the memory of CPU. CUDA takes a bottom-up point of view of parallelism is which thread is an atomic unit of parallelism. Individual threads are part of groups called warps, within which every thread executes exactly the same sequence of instructions. To test SBU-YLIN, we used a CONtinental United States (CONUS) benchmark data set for 12 km resolution domain for October 24, 2001. A WRF domain is a geographic region of interest discretized into a 2-dimensional grid parallel to the ground. Each grid point has
Directory of Open Access Journals (Sweden)
Nikolay Petrovich Vasilyev
2015-03-01
Full Text Available The paper describes the scope of information security protocols based on PRN G in industrial systems. A method for implementing three-dimensional pseudorandom number generator D O Z E N in hybrid systems is provided. The description and results of studies parallel CUDA-version of the algorithm for use in hybrid data centers and high-performance FPGA-version for use in hardware solutions in controlled facilities of SCADA-systems are given.
Design and implementation of parallel video encoding strategies using divisible load analysis
Li, Ping; Veeravalli, Bharadwaj; Kassim, A.A.
2005-01-01
The processing time needed for motion estimation usually accounts for a significant part of the overall processing time of the video encoder. To improve the video encoding speed, reducing the execution time for motion estimation process is essential. Parallel implementation of video encoding systems
Implementing a low-latency parallel graphic equalizer with heterogeneous computing
Norilo, Vesa; Verstraelen, Martinus Johannes Wilhelmina; Valimaki, Vesa; Svensson, Peter; Kristiansen, Ulf
2015-01-01
This paper describes the implementation of a recently introduced parallel graphic equalizer (PGE) in a heterogeneous way. The control and audio signal processing parts of the PGE are distributed to a PC and to a signal processor, of WaveCore architecture, respectively. This arrangement is
A Simple GPU-Accelerated Two-Dimensional MUSCL-Hancock Solver for Ideal Magnetohydrodynamics
Bard, Christopher; Dorelli, John C.
2013-01-01
We describe our experience using NVIDIA's CUDA (Compute Unified Device Architecture) C programming environment to implement a two-dimensional second-order MUSCL-Hancock ideal magnetohydrodynamics (MHD) solver on a GTX 480 Graphics Processing Unit (GPU). Taking a simple approach in which the MHD variables are stored exclusively in the global memory of the GTX 480 and accessed in a cache-friendly manner (without further optimizing memory access by, for example, staging data in the GPU's faster shared memory), we achieved a maximum speed-up of approx. = 126 for a sq 1024 grid relative to the sequential C code running on a single Intel Nehalem (2.8 GHz) core. This speedup is consistent with simple estimates based on the known floating point performance, memory throughput and parallel processing capacity of the GTX 480.
High-Efficient Parallel CAVLC Encoders on Heterogeneous Multicore Architectures
Directory of Open Access Journals (Sweden)
H. Y. Su
2012-04-01
Full Text Available This article presents two high-efficient parallel realizations of the context-based adaptive variable length coding (CAVLC based on heterogeneous multicore processors. By optimizing the architecture of the CAVLC encoder, three kinds of dependences are eliminated or weaken, including the context-based data dependence, the memory accessing dependence and the control dependence. The CAVLC pipeline is divided into three stages: two scans, coding, and lag packing, and be implemented on two typical heterogeneous multicore architectures. One is a block-based SIMD parallel CAVLC encoder on multicore stream processor STORM. The other is a component-oriented SIMT parallel encoder on massively parallel architecture GPU. Both of them exploited rich data-level parallelism. Experiments results show that compared with the CPU version, more than 70 times of speedup can be obtained for STORM and over 50 times for GPU. The implementation of encoder on STORM can make a real-time processing for 1080p @30fps and GPU-based version can satisfy the requirements for 720p real-time encoding. The throughput of the presented CAVLC encoders is more than 10 times higher than that of published software encoders on DSP and multicore platforms.
Energy Technology Data Exchange (ETDEWEB)
Kerr, John Patrick [Iowa State Univ., Ames, IA (United States)
1992-01-01
The objective of this study was to determine the feasibility of using an Artificial Neural Network (ANN), in particular a backpropagation ANN, to improve the speed and quality of the reconstruction of three-dimensional SPECT (single photon emission computed tomography) images. In addition, since the processing elements (PE)s in each layer of an ANN are independent of each other, the speed and efficiency of the neural network architecture could be better optimized by implementing the ANN on a massively parallel computer. The specific goals of this research were: to implement a fully interconnected backpropagation neural network on a serial computer and a SIMD parallel computer, to identify any reduction in the time required to train these networks on the parallel machine versus the serial machine, to determine if these neural networks can learn to recognize SPECT data by training them on a section of an actual SPECT image, and to determine from the knowledge obtained in this research if full SPECT image reconstruction by an ANN implemented on a parallel computer is feasible both in time required to train the network, and in quality of the images reconstructed.
GPU-FS-kNN: a software tool for fast and scalable kNN computation using GPUs.
Directory of Open Access Journals (Sweden)
Ahmed Shamsul Arefin
Full Text Available BACKGROUND: The analysis of biological networks has become a major challenge due to the recent development of high-throughput techniques that are rapidly producing very large data sets. The exploding volumes of biological data are craving for extreme computational power and special computing facilities (i.e. super-computers. An inexpensive solution, such as General Purpose computation based on Graphics Processing Units (GPGPU, can be adapted to tackle this challenge, but the limitation of the device internal memory can pose a new problem of scalability. An efficient data and computational parallelism with partitioning is required to provide a fast and scalable solution to this problem. RESULTS: We propose an efficient parallel formulation of the k-Nearest Neighbour (kNN search problem, which is a popular method for classifying objects in several fields of research, such as pattern recognition, machine learning and bioinformatics. Being very simple and straightforward, the performance of the kNN search degrades dramatically for large data sets, since the task is computationally intensive. The proposed approach is not only fast but also scalable to large-scale instances. Based on our approach, we implemented a software tool GPU-FS-kNN (GPU-based Fast and Scalable k-Nearest Neighbour for CUDA enabled GPUs. The basic approach is simple and adaptable to other available GPU architectures. We observed speed-ups of 50-60 times compared with CPU implementation on a well-known breast microarray study and its associated data sets. CONCLUSION: Our GPU-based Fast and Scalable k-Nearest Neighbour search technique (GPU-FS-kNN provides a significant performance improvement for nearest neighbour computation in large-scale networks. Source code and the software tool is available under GNU Public License (GPL at https://sourceforge.net/p/gpufsknn/.
International Nuclear Information System (INIS)
Yan Sen-Lin
2014-01-01
The parallel synchronization of three chaotic lasers is used to emulate optoelectronic logic NOR and XNOR gates via modulating the light and the current. We deduce a logical computational equation that governs the chaotic synchronization, logical input, and logical output. We construct fundamental gates based on the three chaotic lasers and define the computational principle depending on the parallel synchronization. The logic gate can be implemented by appropriately synchronizing two chaotic lasers. The system shows practicability and flexibility because it can emulate synchronously an XNOR gate, two NOR gates, and so on. The synchronization can still be deteceted when mismatches exist with a certain range. (general)
Implementation of parallel processing in the basf2 framework for Belle II
International Nuclear Information System (INIS)
Itoh, Ryosuke; Lee, Soohyung; Katayama, N; Mineo, S; Moll, A; Kuhr, T; Heck, M
2012-01-01
Recent PC servers are equipped with multi-core CPUs and it is desired to utilize the full processing power of them for the data analysis in large scale HEP experiments. A software framework basf2 is being developed for the use in the Belle II experiment, a new generation B-factory experiment at KEK, and the parallel event processing to utilize the multi-core CPUs is in its design for the use in the massive data production. The details of the implementation of event parallel processing in the basf2 framework are discussed with the report of preliminary performance study in the realistic use on a 32 core PC server.
Tyagi, Neelam; Bose, Abhijit; Chetty, Indrin J
2004-09-01
We have parallelized the Dose Planning Method (DPM), a Monte Carlo code optimized for radiotherapy class problems, on distributed-memory processor architectures using the Message Passing Interface (MPI). Parallelization has been investigated on a variety of parallel computing architectures at the University of Michigan-Center for Advanced Computing, with respect to efficiency and speedup as a function of the number of processors. We have integrated the parallel pseudo random number generator from the Scalable Parallel Pseudo-Random Number Generator (SPRNG) library to run with the parallel DPM. The Intel cluster consisting of 800 MHz Intel Pentium III processor shows an almost linear speedup up to 32 processors for simulating 1 x 10(8) or more particles. The speedup results are nearly linear on an Athlon cluster (up to 24 processors based on availability) which consists of 1.8 GHz+ Advanced Micro Devices (AMD) Athlon processors on increasing the problem size up to 8 x 10(8) histories. For a smaller number of histories (1 x 10(8)) the reduction of efficiency with the Athlon cluster (down to 83.9% with 24 processors) occurs because the processing time required to simulate 1 x 10(8) histories is less than the time associated with interprocessor communication. A similar trend was seen with the Opteron Cluster (consisting of 1400 MHz, 64-bit AMD Opteron processors) on increasing the problem size. Because of the 64-bit architecture Opteron processors are capable of storing and processing instructions at a faster rate and hence are faster as compared to the 32-bit Athlon processors. We have validated our implementation with an in-phantom dose calculation study using a parallel pencil monoenergetic electron beam of 20 MeV energy. The phantom consists of layers of water, lung, bone, aluminum, and titanium. The agreement in the central axis depth dose curves and profiles at different depths shows that the serial and parallel codes are equivalent in accuracy.
International Nuclear Information System (INIS)
Tyagi, Neelam; Bose, Abhijit; Chetty, Indrin J.
2004-01-01
We have parallelized the Dose Planning Method (DPM), a Monte Carlo code optimized for radiotherapy class problems, on distributed-memory processor architectures using the Message Passing Interface (MPI). Parallelization has been investigated on a variety of parallel computing architectures at the University of Michigan-Center for Advanced Computing, with respect to efficiency and speedup as a function of the number of processors. We have integrated the parallel pseudo random number generator from the Scalable Parallel Pseudo-Random Number Generator (SPRNG) library to run with the parallel DPM. The Intel cluster consisting of 800 MHz Intel Pentium III processor shows an almost linear speedup up to 32 processors for simulating 1x10 8 or more particles. The speedup results are nearly linear on an Athlon cluster (up to 24 processors based on availability) which consists of 1.8 GHz+ Advanced Micro Devices (AMD) Athlon processors on increasing the problem size up to 8x10 8 histories. For a smaller number of histories (1x10 8 ) the reduction of efficiency with the Athlon cluster (down to 83.9% with 24 processors) occurs because the processing time required to simulate 1x10 8 histories is less than the time associated with interprocessor communication. A similar trend was seen with the Opteron Cluster (consisting of 1400 MHz, 64-bit AMD Opteron processors) on increasing the problem size. Because of the 64-bit architecture Opteron processors are capable of storing and processing instructions at a faster rate and hence are faster as compared to the 32-bit Athlon processors. We have validated our implementation with an in-phantom dose calculation study using a parallel pencil monoenergetic electron beam of 20 MeV energy. The phantom consists of layers of water, lung, bone, aluminum, and titanium. The agreement in the central axis depth dose curves and profiles at different depths shows that the serial and parallel codes are equivalent in accuracy
A New GPU-Enabled MODTRAN Thermal Model for the PLUME TRACKER Volcanic Emission Analysis Toolkit
Acharya, P. K.; Berk, A.; Guiang, C.; Kennett, R.; Perkins, T.; Realmuto, V. J.
2013-12-01
Real-time quantification of volcanic gaseous and particulate releases is important for (1) recognizing rapid increases in SO2 gaseous emissions which may signal an impending eruption; (2) characterizing ash clouds to enable safe and efficient commercial aviation; and (3) quantifying the impact of volcanic aerosols on climate forcing. The Jet Propulsion Laboratory (JPL) has developed state-of-the-art algorithms, embedded in their analyst-driven Plume Tracker toolkit, for performing SO2, NH3, and CH4 retrievals from remotely sensed multi-spectral Thermal InfraRed spectral imagery. While Plume Tracker provides accurate results, it typically requires extensive analyst time. A major bottleneck in this processing is the relatively slow but accurate FORTRAN-based MODTRAN atmospheric and plume radiance model, developed by Spectral Sciences, Inc. (SSI). To overcome this bottleneck, SSI in collaboration with JPL, is porting these slow thermal radiance algorithms onto massively parallel, relatively inexpensive and commercially-available GPUs. This paper discusses SSI's efforts to accelerate the MODTRAN thermal emission algorithms used by Plume Tracker. Specifically, we are developing a GPU implementation of the Curtis-Godson averaging and the Voigt in-band transmittances from near line center molecular absorption, which comprise the major computational bottleneck. The transmittance calculations were decomposed into separate functions, individually implemented as GPU kernels, and tested for accuracy and performance relative to the original CPU code. Speedup factors of 14 to 30× were realized for individual processing components on an NVIDIA GeForce GTX 295 graphics card with no loss of accuracy. Due to the separate host (CPU) and device (GPU) memory spaces, a redesign of the MODTRAN architecture was required to ensure efficient data transfer between host and device, and to facilitate high parallel throughput. Currently, we are incorporating the separate GPU kernels into a
International Nuclear Information System (INIS)
Mark Dennis Usang; Mohd Hairie Rabir; Mohd Amin Sharifuldin Salleh; Mohamad Puad Abu
2012-01-01
MPI parallelism are implemented on a SUN Workstation for running MCNPX and on the High Performance Computing Facility (HPC) for running MCNP5. 23 input less obtained from MCNP Criticality Validation Suite are utilized for the purpose of evaluating the amount of speed up achievable by using the parallel capabilities of MPI. More importantly, we will study the economics of using more processors and the type of problem where the performance gain are obvious. This is important to enable better practices of resource sharing especially for the HPC facilities processing time. Future endeavours in this direction might even reveal clues for best MCNP5/ MCNPX coding practices for optimum performance of MPI parallelisms. (author)
GPU in Physics Computation: Case Geant4 Navigation
Seiskari, Otto; Niemi, Tapio
2012-01-01
General purpose computing on graphic processing units (GPU) is a potential method of speeding up scientific computation with low cost and high energy efficiency. We experimented with the particle physics simulation toolkit Geant4 used at CERN to benchmark its geometry navigation functionality on a GPU. The goal was to find out whether Geant4 physics simulations could benefit from GPU acceleration and how difficult it is to modify Geant4 code to run in a GPU. We ported selected parts of Geant4 code to C99 & CUDA and implemented a simple gamma physics simulation utilizing this code to measure efficiency. The performance of the program was tested by running it on two different platforms: NVIDIA GeForce 470 GTX GPU and a 12-core AMD CPU system. Our conclusion was that GPUs can be a competitive alternate for multi-core computers but porting existing software in an efficient way is challenging.
GPU Accelerated Surgical Simulators for Complex Morhpology
DEFF Research Database (Denmark)
Mosegaard, Jesper; Sørensen, Thomas Sangild
2005-01-01
a springmass system in order to simulate a complex organ such as the heart. Computations are accelerated by taking advantage of modern graphics processing units (GPUs). Two GPU implementations are presented. They vary in their generality of spring connections and in the speedup factor they achieve...
Parallelization and implementation of approximate root isolation for nonlinear system by Monte Carlo
Khosravi, Ebrahim
1998-12-01
This dissertation solves a fundamental problem of isolating the real roots of nonlinear systems of equations by Monte-Carlo that were published by Bush Jones. This algorithm requires only function values and can be applied readily to complicated systems of transcendental functions. The implementation of this sequential algorithm provides scientists with the means to utilize function analysis in mathematics or other fields of science. The algorithm, however, is so computationally intensive that the system is limited to a very small set of variables, and this will make it unfeasible for large systems of equations. Also a computational technique was needed for investigating a metrology of preventing the algorithm structure from converging to the same root along different paths of computation. The research provides techniques for improving the efficiency and correctness of the algorithm. The sequential algorithm for this technique was corrected and a parallel algorithm is presented. This parallel method has been formally analyzed and is compared with other known methods of root isolation. The effectiveness, efficiency, enhanced overall performance of the parallel processing of the program in comparison to sequential processing is discussed. The message passing model was used for this parallel processing, and it is presented and implemented on Intel/860 MIMD architecture. The parallel processing proposed in this research has been implemented in an ongoing high energy physics experiment: this algorithm has been used to track neutrinoes in a super K detector. This experiment is located in Japan, and data can be processed on-line or off-line locally or remotely.
GPU-accelerated computation of electron transfer.
Höfinger, Siegfried; Acocella, Angela; Pop, Sergiu C; Narumi, Tetsu; Yasuoka, Kenji; Beu, Titus; Zerbetto, Francesco
2012-11-05
Electron transfer is a fundamental process that can be studied with the help of computer simulation. The underlying quantum mechanical description renders the problem a computationally intensive application. In this study, we probe the graphics processing unit (GPU) for suitability to this type of problem. Time-critical components are identified via profiling of an existing implementation and several different variants are tested involving the GPU at increasing levels of abstraction. A publicly available library supporting basic linear algebra operations on the GPU turns out to accelerate the computation approximately 50-fold with minor dependence on actual problem size. The performance gain does not compromise numerical accuracy and is of significant value for practical purposes. Copyright © 2012 Wiley Periodicals, Inc.
Leamy, Michael J.; Springer, Adam C.
In this research we report parallel implementation of a Cellular Automata-based simulation tool for computing elastodynamic response on complex, two-dimensional domains. Elastodynamic simulation using Cellular Automata (CA) has recently been presented as an alternative, inherently object-oriented technique for accurately and efficiently computing linear and nonlinear wave propagation in arbitrarily-shaped geometries. The local, autonomous nature of the method should lead to straight-forward and efficient parallelization. We address this notion on symmetric multiprocessor (SMP) hardware using a Java-based object-oriented CA code implementing triangular state machines (i.e., automata) and the MPI bindings written in Java (MPJ Express). We use MPJ Express to reconfigure our existing CA code to distribute a domain's automata to cores present on a dual quad-core shared-memory system (eight total processors). We note that this message passing parallelization strategy is directly applicable to computer clustered computing, which will be the focus of follow-on research. Results on the shared memory platform indicate nearly-ideal, linear speed-up. We conclude that the CA-based elastodynamic simulator is easily configured to run in parallel, and yields excellent speed-up on SMP hardware.
GPU-based Branchless Distance-Driven Projection and Backprojection.
Liu, Rui; Fu, Lin; De Man, Bruno; Yu, Hengyong
2017-12-01
Projection and backprojection operations are essential in a variety of image reconstruction and physical correction algorithms in CT. The distance-driven (DD) projection and backprojection are widely used for their highly sequential memory access pattern and low arithmetic cost. However, a typical DD implementation has an inner loop that adjusts the calculation depending on the relative position between voxel and detector cell boundaries. The irregularity of the branch behavior makes it inefficient to be implemented on massively parallel computing devices such as graphics processing units (GPUs). Such irregular branch behaviors can be eliminated by factorizing the DD operation as three branchless steps: integration, linear interpolation, and differentiation, all of which are highly amenable to massive vectorization. In this paper, we implement and evaluate a highly parallel branchless DD algorithm for 3D cone beam CT. The algorithm utilizes the texture memory and hardware interpolation on GPUs to achieve fast computational speed. The developed branchless DD algorithm achieved 137-fold speedup for forward projection and 188-fold speedup for backprojection relative to a single-thread CPU implementation. Compared with a state-of-the-art 32-thread CPU implementation, the proposed branchless DD achieved 8-fold acceleration for forward projection and 10-fold acceleration for backprojection. GPU based branchless DD method was evaluated by iterative reconstruction algorithms with both simulation and real datasets. It obtained visually identical images as the CPU reference algorithm.
Directory of Open Access Journals (Sweden)
Vanaja Gokul
2012-01-01
Full Text Available In distributed systems real time optimizations need to be performed dynamically for better utilization of the network resources. Real time optimizations can be performed effectively by using Cross Layer Optimization (CLO within the network operating system. This paper presents the performance evaluation of Cross Layer Optimization (CLO in comparison with the traditional approach of Single-Layer Optimization (SLO. In the parallel implementation of the approaches the experimental study carried out indicates that the CLO results in a significant improvement in network utilization when compared to SLO. A variant of the Particle Swarm Optimization technique that utilizes Digital Pheromones (PSODP for better performance has been used here. A significantly higher speed up in performance was observed from the parallel implementation of CLO that used PSODP on a cluster of nodes.
Tilton, James C.; Plaza, Antonio J. (Editor); Chang, Chein-I. (Editor)
2008-01-01
The hierarchical image segmentation algorithm (referred to as HSEG) is a hybrid of hierarchical step-wise optimization (HSWO) and constrained spectral clustering that produces a hierarchical set of image segmentations. HSWO is an iterative approach to region grooving segmentation in which the optimal image segmentation is found at N(sub R) regions, given a segmentation at N(sub R+1) regions. HSEG's addition of constrained spectral clustering makes it a computationally intensive algorithm, for all but, the smallest of images. To counteract this, a computationally efficient recursive approximation of HSEG (called RHSEG) has been devised. Further improvements in processing speed are obtained through a parallel implementation of RHSEG. This chapter describes this parallel implementation and demonstrates its computational efficiency on a Landsat Thematic Mapper test scene.
On a model of three-dimensional bursting and its parallel implementation
Tabik, S.; Romero, L. F.; Garzón, E. M.; Ramos, J. I.
2008-04-01
A mathematical model for the simulation of three-dimensional bursting phenomena and its parallel implementation are presented. The model consists of four nonlinearly coupled partial differential equations that include fast and slow variables, and exhibits bursting in the absence of diffusion. The differential equations have been discretized by means of a second-order accurate in both space and time, linearly-implicit finite difference method in equally-spaced grids. The resulting system of linear algebraic equations at each time level has been solved by means of the Preconditioned Conjugate Gradient (PCG) method. Three different parallel implementations of the proposed mathematical model have been developed; two of these implementations, i.e., the MPI and the PETSc codes, are based on a message passing paradigm, while the third one, i.e., the OpenMP code, is based on a shared space address paradigm. These three implementations are evaluated on two current high performance parallel architectures, i.e., a dual-processor cluster and a Shared Distributed Memory (SDM) system. A novel representation of the results that emphasizes the most relevant factors that affect the performance of the paralled implementations, is proposed. The comparative analysis of the computational results shows that the MPI and the OpenMP implementations are about twice more efficient than the PETSc code on the SDM system. It is also shown that, for the conditions reported here, the nonlinear dynamics of the three-dimensional bursting phenomena exhibits three stages characterized by asynchronous, synchronous and then asynchronous oscillations, before a quiescent state is reached. It is also shown that the fast system reaches steady state in much less time than the slow variables.
cudaBayesreg: Parallel Implementation of a Bayesian Multilevel Model for fMRI Data Analysis
Directory of Open Access Journals (Sweden)
Adelino R. Ferreira da Silva
2011-10-01
Full Text Available Graphic processing units (GPUs are rapidly gaining maturity as powerful general parallel computing devices. A key feature in the development of modern GPUs has been the advancement of the programming model and programming tools. Compute Unified Device Architecture (CUDA is a software platform for massively parallel high-performance computing on Nvidia many-core GPUs. In functional magnetic resonance imaging (fMRI, the volume of the data to be processed, and the type of statistical analysis to perform call for high-performance computing strategies. In this work, we present the main features of the R-CUDA package cudaBayesreg which implements in CUDA the core of a Bayesian multilevel model for the analysis of brain fMRI data. The statistical model implements a Gibbs sampler for multilevel/hierarchical linear models with a normal prior. The main contribution for the increased performance comes from the use of separate threads for fitting the linear regression model at each voxel in parallel. The R-CUDA implementation of the Bayesian model proposed here has been able to reduce significantly the run-time processing of Markov chain Monte Carlo (MCMC simulations used in Bayesian fMRI data analyses. Presently, cudaBayesreg is only configured for Linux systems with Nvidia CUDA support.
Parallel implementation of geometrical shock dynamics for two dimensional converging shock waves
Qiu, Shi; Liu, Kuang; Eliasson, Veronica
2016-10-01
Geometrical shock dynamics (GSD) theory is an appealing method to predict the shock motion in the sense that it is more computationally efficient than solving the traditional Euler equations, especially for converging shock waves. However, to solve and optimize large scale configurations, the main bottleneck is the computational cost. Among the existing numerical GSD schemes, there is only one that has been implemented on parallel computers, with the purpose to analyze detonation waves. To extend the computational advantage of the GSD theory to more general applications such as converging shock waves, a numerical implementation using a spatial decomposition method has been coupled with a front tracking approach on parallel computers. In addition, an efficient tridiagonal system solver for massively parallel computers has been applied to resolve the most expensive function in this implementation, resulting in an efficiency of 0.93 while using 32 HPCC cores. Moreover, symmetric boundary conditions have been developed to further reduce the computational cost, achieving a speedup of 19.26 for a 12-sided polygonal converging shock.
2009-01-01
At the 19th Annual Conference on Parallel Computational Fluid Dynamics held in Antalya, Turkey, in May 2007, the most recent developments and implementations of large-scale and grid computing were presented. This book, comprised of the invited and selected papers of this conference, details those advances, which are of particular interest to CFD and CFD-related communities. It also offers the results related to applications of various scientific and engineering problems involving flows and flow-related topics. Intended for CFD researchers and graduate students, this book is a state-of-the-art presentation of the relevant methodology and implementation techniques of large-scale computing.
Parallel Fixed Point Implementation of a Radial Basis Function Network in an FPGA
Directory of Open Access Journals (Sweden)
Alisson C. D. de Souza
2014-09-01
Full Text Available This paper proposes a parallel fixed point radial basis function (RBF artificial neural network (ANN, implemented in a field programmable gate array (FPGA trained online with a least mean square (LMS algorithm. The processing time and occupied area were analyzed for various fixed point formats. The problems of precision of the ANN response for nonlinear classification using the XOR gate and interpolation using the sine function were also analyzed in a hardware implementation. The entire project was developed using the System Generator platform (Xilinx, with a Virtex-6 xc6vcx240t-1ff1156 as the target FPGA.
Schultz, A.
2010-12-01
3D forward solvers lie at the core of inverse formulations used to image the variation of electrical conductivity within the Earth's interior. This property is associated with variations in temperature, composition, phase, presence of volatiles, and in specific settings, the presence of groundwater, geothermal resources, oil/gas or minerals. The high cost of 3D solutions has been a stumbling block to wider adoption of 3D methods. Parallel algorithms for modeling frequency domain 3D EM problems have not achieved wide scale adoption, with emphasis on fairly coarse grained parallelism using MPI and similar approaches. The communications bandwidth as well as the latency required to send and receive network communication packets is a limiting factor in implementing fine grained parallel strategies, inhibiting wide adoption of these algorithms. Leading Graphics Processor Unit (GPU) companies now produce GPUs with hundreds of GPU processor cores per die. The footprint, in silicon, of the GPU's restricted instruction set is much smaller than the general purpose instruction set required of a CPU. Consequently, the density of processor cores on a GPU can be much greater than on a CPU. GPUs also have local memory, registers and high speed communication with host CPUs, usually through PCIe type interconnects. The extremely low cost and high computational power of GPUs provides the EM geophysics community with an opportunity to achieve fine grained (i.e. massive) parallelization of codes on low cost hardware. The current generation of GPUs (e.g. NVidia Fermi) provides 3 billion transistors per chip die, with nearly 500 processor cores and up to 6 GB of fast (DDR5) GPU memory. This latest generation of GPU supports fast hardware double precision (64 bit) floating point operations of the type required for frequency domain EM forward solutions. Each Fermi GPU board can sustain nearly 1 TFLOP in double precision, and multiple boards can be installed in the host computer system. We
Qualitative and quantitative improvements of PET reconstruction on GPU architecture
International Nuclear Information System (INIS)
Autret, Awen
2016-01-01
In positron emission tomography, reconstructed images suffer from a high noise level and a low resolution. Iterative reconstruction processes require an estimation of the system response (scanner and patient) and the quality of the images depends on the accuracy of this estimate. Accurate and fast to compute models already exists for the attenuation, scattering, random coincidences and dead times. Thus, this thesis focuses on modeling the system components associated with the detector response and the positron range. A new multi-GPU parallelization of the reconstruction based on a cutting of the volume is also proposed to speed up the reconstruction exploiting the computing power of such architectures. The proposed detector response model is based on a multi-ray approach that includes all the detector effects as the geometry and the scattering in the crystals. An evaluation study based on data obtained through Mote Carlo simulation (MCS) showed this model provides reconstructed images with a better contrast to noise ratio and resolution compared with those of the methods from the state of the art. The proposed positron range model is based on a simplified MCS, integrated into the forward projector during the reconstruction. A GPU implementation of this method allows running MCS three order of magnitude faster than the same simulation on GATE, while providing similar results. An evaluation study shows this model integrated in the reconstruction gives images with better contrast recovery and resolution while avoiding artifacts. (author)
Sub-second pencil beam dose calculation on GPU for adaptive proton therapy.
da Silva, Joakim; Ansorge, Richard; Jena, Rajesh
2015-06-21
Although proton therapy delivered using scanned pencil beams has the potential to produce better dose conformity than conventional radiotherapy, the created dose distributions are more sensitive to anatomical changes and patient motion. Therefore, the introduction of adaptive treatment techniques where the dose can be monitored as it is being delivered is highly desirable. We present a GPU-based dose calculation engine relying on the widely used pencil beam algorithm, developed for on-line dose calculation. The calculation engine was implemented from scratch, with each step of the algorithm parallelized and adapted to run efficiently on the GPU architecture. To ensure fast calculation, it employs several application-specific modifications and simplifications, and a fast scatter-based implementation of the computationally expensive kernel superposition step. The calculation time for a skull base treatment plan using two beam directions was 0.22 s on an Nvidia Tesla K40 GPU, whereas a test case of a cubic target in water from the literature took 0.14 s to calculate. The accuracy of the patient dose distributions was assessed by calculating the γ-index with respect to a gold standard Monte Carlo simulation. The passing rates were 99.2% and 96.7%, respectively, for the 3%/3 mm and 2%/2 mm criteria, matching those produced by a clinical treatment planning system.
Fast GPU-based spot extraction for energy-dispersive X-ray Laue diffraction
International Nuclear Information System (INIS)
Alghabi, F.; Schipper, U.; Kolb, A.; Send, S.; Abboud, A.; Pashniak, N.; Pietsch, U.
2014-01-01
This paper describes a novel method for fast online analysis of X-ray Laue spots taken by means of an energy-dispersive X-ray 2D detector. Current pnCCD detectors typically operate at some 100 Hz (up to a maximum of 400 Hz) and have a resolution of 384 × 384 pixels, future devices head for even higher pixel counts and frame rates. The proposed online data analysis is based on a computer utilizing multiple Graphics Processing Units (GPUs), which allow for fast and parallel data processing. Our multi-GPU based algorithm is compliant with the rules of stream-based data processing, for which GPUs are optimized. The paper's main contribution is therefore an alternative algorithm for the determination of spot positions and energies over the full sequence of pnCCD data frames. Furthermore, an improved background suppression algorithm is presented.The resulting system is able to process data at the maximum acquisition rate of 400 Hz. We present a detailed analysis of the spot positions and energies deduced from a prior (single-core) CPU-based and the novel GPU-based data processing, showing that the parallel computed results using the GPU implementation are at least of the same quality as prior CPU-based results. Furthermore, the GPU-based algorithm is able to speed up the data processing by a factor of 7 (in comparison to single-core CPU-based algorithm) which effectively makes the detector system more suitable for online data processing
Explicit integration with GPU acceleration for large kinetic networks
International Nuclear Information System (INIS)
Brock, Benjamin; Belt, Andrew; Billings, Jay Jay; Guidry, Mike
2015-01-01
We demonstrate the first implementation of recently-developed fast explicit kinetic integration algorithms on modern graphics processing unit (GPU) accelerators. Taking as a generic test case a Type Ia supernova explosion with an extremely stiff thermonuclear network having 150 isotopic species and 1604 reactions coupled to hydrodynamics using operator splitting, we demonstrate the capability to solve of order 100 realistic kinetic networks in parallel in the same time that standard implicit methods can solve a single such network on a CPU. This orders-of-magnitude decrease in computation time for solving systems of realistic kinetic networks implies that important coupled, multiphysics problems in various scientific and technical fields that were intractable, or could be simulated only with highly schematic kinetic networks, are now computationally feasible.
International Nuclear Information System (INIS)
Roche-Lima, Abiel; Thulasiram, Ruppa K
2012-01-01
Finite automata, in which each transition is augmented with an output label in addition to the familiar input label, are considered finite-state transducers. Transducers have been used to analyze some fundamental issues in bioinformatics. Weighted finite-state transducers have been proposed to pairwise alignments of DNA and protein sequences; as well as to develop kernels for computational biology. Machine learning algorithms for conditional transducers have been implemented and used for DNA sequence analysis. Transducer learning algorithms are based on conditional probability computation. It is calculated by using techniques, such as pair-database creation, normalization (with Maximum-Likelihood normalization) and parameters optimization (with Expectation-Maximization - EM). These techniques are intrinsically costly for computation, even worse when are applied to bioinformatics, because the databases sizes are large. In this work, we describe a parallel implementation of an algorithm to learn conditional transducers using these techniques. The algorithm is oriented to bioinformatics applications, such as alignments, phylogenetic trees, and other genome evolution studies. Indeed, several experiences were developed using the parallel and sequential algorithm on Westgrid (specifically, on the Breeze cluster). As results, we obtain that our parallel algorithm is scalable, because execution times are reduced considerably when the data size parameter is increased. Another experience is developed by changing precision parameter. In this case, we obtain smaller execution times using the parallel algorithm. Finally, number of threads used to execute the parallel algorithm on the Breezy cluster is changed. In this last experience, we obtain as result that speedup is considerably increased when more threads are used; however there is a convergence for number of threads equal to or greater than 16.
International Nuclear Information System (INIS)
Sharp, G C; Kandasamy, N; Singh, H; Folkert, M
2007-01-01
This paper shows how to significantly accelerate cone-beam CT reconstruction and 3D deformable image registration using the stream-processing model. We describe data-parallel designs for the Feldkamp, Davis and Kress (FDK) reconstruction algorithm, and the demons deformable registration algorithm, suitable for use on a commodity graphics processing unit. The streaming versions of these algorithms are implemented using the Brook programming environment and executed on an NVidia 8800 GPU. Performance results using CT data of a preserved swine lung indicate that the GPU-based implementations of the FDK and demons algorithms achieve a substantial speedup-up to 80 times for FDK and 70 times for demons when compared to an optimized reference implementation on a 2.8 GHz Intel processor. In addition, the accuracy of the GPU-based implementations was found to be excellent. Compared with CPU-based implementations, the RMS differences were less than 0.1 Hounsfield unit for reconstruction and less than 0.1 mm for deformable registration
Research on GPU acceleration for Monte Carlo criticality calculation
International Nuclear Information System (INIS)
Xu, Q.; Yu, G.; Wang, K.
2013-01-01
The Monte Carlo (MC) neutron transport method can be naturally parallelized by multi-core architectures due to the dependency between particles during the simulation. The GPU+CPU heterogeneous parallel mode has become an increasingly popular way of parallelism in the field of scientific supercomputing. Thus, this work focuses on the GPU acceleration method for the Monte Carlo criticality simulation, as well as the computational efficiency that GPUs can bring. The 'neutron transport step' is introduced to increase the GPU thread occupancy. In order to test the sensitivity of the MC code's complexity, a 1D one-group code and a 3D multi-group general purpose code are respectively transplanted to GPUs, and the acceleration effects are compared. The result of numerical experiments shows considerable acceleration effect of the 'neutron transport step' strategy. However, the performance comparison between the 1D code and the 3D code indicates the poor scalability of MC codes on GPUs. (authors)
BFROST: binary features from robust orientation segment tests accelerated on the GPU
CSIR Research Space (South Africa)
Cronje, J
2011-11-01
Full Text Available purpose parallel algo- rithms. The CUDA (Compute Unified Device Architecture) [1] framework from NVidia provides a programmable interface for GPUs. FAST (Features from Accelerated Segment Tests) [2], [3] is one of the fastest and most reliable corner... runs. Our detector detects slightly more keypoints because the decision tree of FAST does not perform a complete segment test. Timing comparisons were performed on a NVidia GeForce GTX 460 for our GPU implementation and on a Intel Core i7 2.67 GHz...
Implementations and interpretations of the talbot-ogden infiltration model
Seo, Mookwon
2014-11-01
The interaction between surface and subsurface hydrology flow systems is important for water supplies. Accurate, efficient numerical models are needed to estimate the movement of water through unsaturated soil. We investigate a water infiltration model and develop very fast serial and parallel implementations that are suitable for a computer with a graphical processing unit (GPU).
Parallel efficient rate control methods for JPEG 2000
Martínez-del-Amor, Miguel Á.; Bruns, Volker; Sparenberg, Heiko
2017-09-01
Since the introduction of JPEG 2000, several rate control methods have been proposed. Among them, post-compression rate-distortion optimization (PCRD-Opt) is the most widely used, and the one recommended by the standard. The approach followed by this method is to first compress the entire image split in code blocks, and subsequently, optimally truncate the set of generated bit streams according to the maximum target bit rate constraint. The literature proposes various strategies on how to estimate ahead of time where a block will get truncated in order to stop the execution prematurely and save time. However, none of them have been defined bearing in mind a parallel implementation. Today, multi-core and many-core architectures are becoming popular for JPEG 2000 codecs implementations. Therefore, in this paper, we analyze how some techniques for efficient rate control can be deployed in GPUs. In order to do that, the design of our GPU-based codec is extended, allowing stopping the process at a given point. This extension also harnesses a higher level of parallelism on the GPU, leading to up to 40% of speedup with 4K test material on a Titan X. In a second step, three selected rate control methods are adapted and implemented in our parallel encoder. A comparison is then carried out, and used to select the best candidate to be deployed in a GPU encoder, which gave an extra 40% of speedup in those situations where it was really employed.
GPU-accelerated FDTD modeling of radio-frequency field-tissue interactions in high-field MRI.
Chi, Jieru; Liu, Feng; Weber, Ewald; Li, Yu; Crozier, Stuart
2011-06-01
The analysis of high-field RF field-tissue interactions requires high-performance finite-difference time-domain (FDTD) computing. Conventional CPU-based FDTD calculations offer limited computing performance in a PC environment. This study presents a graphics processing unit (GPU)-based parallel-computing framework, producing substantially boosted computing efficiency (with a two-order speedup factor) at a PC-level cost. Specific details of implementing the FDTD method on a GPU architecture have been presented and the new computational strategy has been successfully applied to the design of a novel 8-element transceive RF coil system at 9.4 T. Facilitated by the powerful GPU-FDTD computing, the new RF coil array offers optimized fields (averaging 25% improvement in sensitivity, and 20% reduction in loop coupling compared with conventional array structures of the same size) for small animal imaging with a robust RF configuration. The GPU-enabled acceleration paves the way for FDTD to be applied for both detailed forward modeling and inverse design of MRI coils, which were previously impractical.
GPU-accelerated micromagnetic simulations using cloud computing
International Nuclear Information System (INIS)
Jermain, C.L.; Rowlands, G.E.; Buhrman, R.A.; Ralph, D.C.
2016-01-01
Highly parallel graphics processing units (GPUs) can improve the speed of micromagnetic simulations significantly as compared to conventional computing using central processing units (CPUs). We present a strategy for performing GPU-accelerated micromagnetic simulations by utilizing cost-effective GPU access offered by cloud computing services with an open-source Python-based program for running the MuMax3 micromagnetics code remotely. We analyze the scaling and cost benefits of using cloud computing for micromagnetics. - Highlights: • The benefits of cloud computing for GPU-accelerated micromagnetics are examined. • We present the MuCloud software for running simulations on cloud computing. • Simulation run times are measured to benchmark cloud computing performance. • Comparison benchmarks are analyzed between CPU and GPU based solvers.
GPU-accelerated micromagnetic simulations using cloud computing
Energy Technology Data Exchange (ETDEWEB)
Jermain, C.L., E-mail: clj72@cornell.edu [Cornell University, Ithaca, NY 14853 (United States); Rowlands, G.E.; Buhrman, R.A. [Cornell University, Ithaca, NY 14853 (United States); Ralph, D.C. [Cornell University, Ithaca, NY 14853 (United States); Kavli Institute at Cornell, Ithaca, NY 14853 (United States)
2016-03-01
Highly parallel graphics processing units (GPUs) can improve the speed of micromagnetic simulations significantly as compared to conventional computing using central processing units (CPUs). We present a strategy for performing GPU-accelerated micromagnetic simulations by utilizing cost-effective GPU access offered by cloud computing services with an open-source Python-based program for running the MuMax3 micromagnetics code remotely. We analyze the scaling and cost benefits of using cloud computing for micromagnetics. - Highlights: • The benefits of cloud computing for GPU-accelerated micromagnetics are examined. • We present the MuCloud software for running simulations on cloud computing. • Simulation run times are measured to benchmark cloud computing performance. • Comparison benchmarks are analyzed between CPU and GPU based solvers.
GPU Computing in Bayesian Inference of Realized Stochastic Volatility Model
International Nuclear Information System (INIS)
Takaishi, Tetsuya
2015-01-01
The realized stochastic volatility (RSV) model that utilizes the realized volatility as additional information has been proposed to infer volatility of financial time series. We consider the Bayesian inference of the RSV model by the Hybrid Monte Carlo (HMC) algorithm. The HMC algorithm can be parallelized and thus performed on the GPU for speedup. The GPU code is developed with CUDA Fortran. We compare the computational time in performing the HMC algorithm on GPU (GTX 760) and CPU (Intel i7-4770 3.4GHz) and find that the GPU can be up to 17 times faster than the CPU. We also code the program with OpenACC and find that appropriate coding can achieve the similar speedup with CUDA Fortran
An efficient spectral crystal plasticity solver for GPU architectures
Malahe, Michael
2018-03-01
We present a spectral crystal plasticity (CP) solver for graphics processing unit (GPU) architectures that achieves a tenfold increase in efficiency over prior GPU solvers. The approach makes use of a database containing a spectral decomposition of CP simulations performed using a conventional iterative solver over a parameter space of crystal orientations and applied velocity gradients. The key improvements in efficiency come from reducing global memory transactions, exposing more instruction-level parallelism, reducing integer instructions and performing fast range reductions on trigonometric arguments. The scheme also makes more efficient use of memory than prior work, allowing for larger problems to be solved on a single GPU. We illustrate these improvements with a simulation of 390 million crystal grains on a consumer-grade GPU, which executes at a rate of 2.72 s per strain step.
Implementation and analysis of a Navier-Stokes algorithm on parallel computers
Fatoohi, Raad A.; Grosch, Chester E.
1988-01-01
The results of the implementation of a Navier-Stokes algorithm on three parallel/vector computers are presented. The object of this research is to determine how well, or poorly, a single numerical algorithm would map onto three different architectures. The algorithm is a compact difference scheme for the solution of the incompressible, two-dimensional, time-dependent Navier-Stokes equations. The computers were chosen so as to encompass a variety of architectures. They are the following: the MPP, an SIMD machine with 16K bit serial processors; Flex/32, an MIMD machine with 20 processors; and Cray/2. The implementation of the algorithm is discussed in relation to these architectures and measures of the performance on each machine are given. The basic comparison is among SIMD instruction parallelism on the MPP, MIMD process parallelism on the Flex/32, and vectorization of a serial code on the Cray/2. Simple performance models are used to describe the performance. These models highlight the bottlenecks and limiting factors for this algorithm on these architectures. Finally, conclusions are presented.
International Nuclear Information System (INIS)
Laucoin, E.
2008-10-01
Numerical resolution of partial differential equations can be made reliable and efficient through the use of adaptive numerical methods.We present here the work we have done for the design, the implementation and the validation of such a method within an industrial software platform with applications in thermohydraulics. From the geometric point of view, this method can deal both with mesh refinement and mesh coarsening, while ensuring the quality of the mesh cells. Numerically, we use the mortar elements formalism in order to extend the Finite Volumes-Elements method implemented in the Trio-U platform and to deal with the non-conforming meshes arising from the adaptation procedure. Finally, we present an implementation of this method using concepts from domain decomposition methods for ensuring its efficiency while running in a parallel execution context. (author)
GPU Linear algebra extensions for GNU/Octave
International Nuclear Information System (INIS)
Bosi, L B; Mariotti, M; Santocchia, A
2012-01-01
Octave is one of the most widely used open source tools for numerical analysis and liner algebra. Our project aims to improve Octave by introducing support for GPU computing in order to speed up some linear algebra operations. The core of our work is a C library that executes some BLAS operations concerning vector- vector, vector matrix and matrix-matrix functions on the GPU. OpenCL functions are used to program GPU kernels, which are bound within the GNU/octave framework. We report the project implementation design and some preliminary results about performance.
International Nuclear Information System (INIS)
Pandya, Tara M.; Johnson, Seth R.; Evans, Thomas M.; Davidson, Gregory G.; Hamilton, Steven P.; Godfrey, Andrew T.
2015-01-01
This paper discusses the implementation, capabilities, and validation of Shift, a massively parallel Monte Carlo radiation transport package developed and maintained at Oak Ridge National Laboratory. It has been developed to scale well from laptop to small computing clusters to advanced supercomputers. Special features of Shift include hybrid capabilities for variance reduction such as CADIS and FW-CADIS, and advanced parallel decomposition and tally methods optimized for scalability on supercomputing architectures. Shift has been validated and verified against various reactor physics benchmarks and compares well to other state-of-the-art Monte Carlo radiation transport codes such as MCNP5, CE KENO-VI, and OpenMC. Some specific benchmarks used for verification and validation include the CASL VERA criticality test suite and several Westinghouse AP1000 ® problems. These benchmark and scaling studies show promising results
Implementation of a parallel algorithm for spherical SN calculations on the IBM 3090
International Nuclear Information System (INIS)
Haghighat, A.; Lawrence, R.D.
1989-01-01
Parallel S N algorithms based on domain decomposition in angle are straightforward to develop in Cartesian geometry because the computation of the angular fluxes for a specific discrete ordinate can be performed independently of all other angles. This is not the case for curvilinear geometries, where the angular redistribution component of the discretized streaming operator results in coupling between angular fluxes along adjacent discrete ordinates. Previously, the authors developed a parallel algorithm for S N calculations in spherical geometry and examined its iterative convergence for criticality and detector problems with differing scattering/absorption ratios. In this paper, the authors describe the implementation of the algorithm on an IBM 3090 Model 400 (four processors) and present computational results illustrating the efficiency of the algorithm relative to serial execution
Synthetic Aperture Sequential Beamforming implemented on multi-core platforms
DEFF Research Database (Denmark)
Kjeldsen, Thomas; Lassen, Lee; Hemmsen, Martin Christian
2014-01-01
This paper compares several computational ap- proaches to Synthetic Aperture Sequential Beamforming (SASB) targeting consumer level parallel processors such as multi-core CPUs and GPUs. The proposed implementations demonstrate that ultrasound imaging using SASB can be executed in real- time with ...... per second) on an Intel Core i7 2600 CPU with an AMD HD7850 and a NVIDIA GTX680 GPU. The fastest CPU and GPU implementations use 14% and 1.3% of the real-time budget of 62 ms/frame, respectively. The maximum achieved processing rate is 1265 frames/s....
Survey of using GPU CUDA programming model in medical image analysis
Directory of Open Access Journals (Sweden)
T. Kalaiselvi
2017-01-01
Full Text Available With the technology development of medical industry, processing data is expanding rapidly and computation time also increases due to many factors like 3D, 4D treatment planning, the increasing sophistication of MRI pulse sequences and the growing complexity of algorithms. Graphics processing unit (GPU addresses these problems and gives the solutions for using their features such as, high computation throughput, high memory bandwidth, support for floating-point arithmetic and low cost. Compute unified device architecture (CUDA is a popular GPU programming model introduced by NVIDIA for parallel computing. This review paper briefly discusses the need of GPU CUDA computing in the medical image analysis. The GPU performances of existing algorithms are analyzed and the computational gain is discussed. A few open issues, hardware configurations and optimization principles of existing methods are discussed. This survey concludes the few optimization techniques with the medical imaging algorithms on GPU. Finally, limitation and future scope of GPU programming are discussed.
Energy Technology Data Exchange (ETDEWEB)
Madduri, Kamesh; Ediger, David; Jiang, Karl; Bader, David A.; Chavarria-Miranda, Daniel
2009-02-15
We present a new lock-free parallel algorithm for computing betweenness centralityof massive small-world networks. With minor changes to the data structures, ouralgorithm also achieves better spatial cache locality compared to previous approaches. Betweenness centrality is a key algorithm kernel in HPCS SSCA#2, a benchmark extensively used to evaluate the performance of emerging high-performance computing architectures for graph-theoretic computations. We design optimized implementations of betweenness centrality and the SSCA#2 benchmark for two hardware multithreaded systems: a Cray XMT system with the Threadstorm processor, and a single-socket Sun multicore server with the UltraSPARC T2 processor. For a small-world network of 134 million vertices and 1.073 billion edges, the 16-processor XMT system and the 8-core Sun Fire T5120 server achieve TEPS scores (an algorithmic performance count for the SSCA#2 benchmark) of 160 million and 90 million respectively, which corresponds to more than a 2X performance improvement over the previous parallel implementations. To better characterize the performance of these multithreaded systems, we correlate the SSCA#2 performance results with data from the memory-intensive STREAM and RandomAccess benchmarks. Finally, we demonstrate the applicability of our implementation to analyze massive real-world datasets by computing approximate betweenness centrality for a large-scale IMDb movie-actor network.
Parallel computation for blood cell classification in medical hyperspectral imagery
International Nuclear Information System (INIS)
Li, Wei; Wu, Lucheng; Qiu, Xianbo; Ran, Qiong; Xie, Xiaoming
2016-01-01
With the advantage of fine spectral resolution, hyperspectral imagery provides great potential for cell classification. This paper provides a promising classification system including the following three stages: (1) band selection for a subset of spectral bands with distinctive and informative features, (2) spectral-spatial feature extraction, such as local binary patterns (LBP), and (3) followed by an effective classifier. Moreover, these three steps are further implemented on graphics processing units (GPU) respectively, which makes the system real-time and more practical. The GPU parallel implementation is compared with the serial implementation on central processing units (CPU). Experimental results based on real medical hyperspectral data demonstrate that the proposed system is able to offer high accuracy and fast speed, which are appealing for cell classification in medical hyperspectral imagery. (paper)
Bailey, Stephanie L; Bono, Rose S; Nash, Denis; Kimmel, April D
2018-01-01
Spreadsheet software is increasingly used to implement systems science models informing health policy decisions, both in academia and in practice where technical capacity may be limited. However, spreadsheet models are prone to unintentional errors that may not always be identified using standard error-checking techniques. Our objective was to illustrate, through a methodologic case study analysis, the impact of unintentional errors on model projections by implementing parallel model versions. We leveraged a real-world need to revise an existing spreadsheet model designed to inform HIV policy. We developed three parallel versions of a previously validated spreadsheet-based model; versions differed by the spreadsheet cell-referencing approach (named single cells; column/row references; named matrices). For each version, we implemented three model revisions (re-entry into care; guideline-concordant treatment initiation; immediate treatment initiation). After standard error-checking, we identified unintentional errors by comparing model output across the three versions. Concordant model output across all versions was considered error-free. We calculated the impact of unintentional errors as the percentage difference in model projections between model versions with and without unintentional errors, using +/-5% difference to define a material error. We identified 58 original and 4,331 propagated unintentional errors across all model versions and revisions. Over 40% (24/58) of original unintentional errors occurred in the column/row reference model version; most (23/24) were due to incorrect cell references. Overall, >20% of model spreadsheet cells had material unintentional errors. When examining error impact along the HIV care continuum, the percentage difference between versions with and without unintentional errors ranged from +3% to +16% (named single cells), +26% to +76% (column/row reference), and 0% (named matrices). Standard error-checking techniques may not
Directory of Open Access Journals (Sweden)
Naumenko Mikhail
2018-01-01
Full Text Available Modern parallel computing algorithm has been applied to the solution of the few-body problem. The approach is based on Feynman’s continual integrals method implemented in C++ programming language using NVIDIA CUDA technology. A wide range of 3-body and 4-body bound systems has been considered including nuclei described as consisting of protons and neutrons (e.g., 3,4He and nuclei described as consisting of clusters and nucleons (e.g., 6He. The correctness of the results was checked by the comparison with the exactly solvable 4-body oscillatory system and experimental data.
Naumenko, Mikhail; Samarin, Viacheslav
2018-02-01
Modern parallel computing algorithm has been applied to the solution of the few-body problem. The approach is based on Feynman's continual integrals method implemented in C++ programming language using NVIDIA CUDA technology. A wide range of 3-body and 4-body bound systems has been considered including nuclei described as consisting of protons and neutrons (e.g., 3,4He) and nuclei described as consisting of clusters and nucleons (e.g., 6He). The correctness of the results was checked by the comparison with the exactly solvable 4-body oscillatory system and experimental data.
Fast implementations of 3D PET reconstruction using vector and parallel programming techniques
International Nuclear Information System (INIS)
Guerrero, T.M.; Cherry, S.R.; Dahlbom, M.; Ricci, A.R.; Hoffman, E.J.
1993-01-01
Computationally intensive techniques that offer potential clinical use have arisen in nuclear medicine. Examples include iterative reconstruction, 3D PET data acquisition and reconstruction, and 3D image volume manipulation including image registration. One obstacle in achieving clinical acceptance of these techniques is the computational time required. This study focuses on methods to reduce the computation time for 3D PET reconstruction through the use of fast computer hardware, vector and parallel programming techniques, and algorithm optimization. The strengths and weaknesses of i860 microprocessor based workstation accelerator boards are investigated in implementations of 3D PET reconstruction
Li, Pengcheng; Liu, Celong; Li, Xianpeng; He, Honghui; Ma, Hui
2016-09-20
In earlier studies, we developed scattering models and the corresponding CPU-based Monte Carlo simulation programs to study the behavior of polarized photons as they propagate through complex biological tissues. Studying the simulation results in high degrees of freedom that created a demand for massive simulation tasks. In this paper, we report a parallel implementation of the simulation program based on the compute unified device architecture running on a graphics processing unit (GPU). Different schemes for sphere-only simulations and sphere-cylinder mixture simulations were developed. Diverse optimizing methods were employed to achieve the best acceleration. The final-version GPU program is hundreds of times faster than the CPU version. Dependence of the performance on input parameters and precision were also studied. It is shown that using single precision in the GPU simulations results in very limited losses in accuracy. Consumer-level graphics cards, even those in laptop computers, are more cost-effective than scientific graphics cards for single-precision computation.
Accelerating Spaceborne SAR Imaging Using Multiple CPU/GPU Deep Collaborative Computing
Directory of Open Access Journals (Sweden)
Fan Zhang
2016-04-01
Full Text Available With the development of synthetic aperture radar (SAR technologies in recent years, the huge amount of remote sensing data brings challenges for real-time imaging processing. Therefore, high performance computing (HPC methods have been presented to accelerate SAR imaging, especially the GPU based methods. In the classical GPU based imaging algorithm, GPU is employed to accelerate image processing by massive parallel computing, and CPU is only used to perform the auxiliary work such as data input/output (IO. However, the computing capability of CPU is ignored and underestimated. In this work, a new deep collaborative SAR imaging method based on multiple CPU/GPU is proposed to achieve real-time SAR imaging. Through the proposed tasks partitioning and scheduling strategy, the whole image can be generated with deep collaborative multiple CPU/GPU computing. In the part of CPU parallel imaging, the advanced vector extension (AVX method is firstly introduced into the multi-core CPU parallel method for higher efficiency. As for the GPU parallel imaging, not only the bottlenecks of memory limitation and frequent data transferring are broken, but also kinds of optimized strategies are applied, such as streaming, parallel pipeline and so on. Experimental results demonstrate that the deep CPU/GPU collaborative imaging method enhances the efficiency of SAR imaging on single-core CPU by 270 times and realizes the real-time imaging in that the imaging rate outperforms the raw data generation rate.
Accelerating Spaceborne SAR Imaging Using Multiple CPU/GPU Deep Collaborative Computing.
Zhang, Fan; Li, Guojun; Li, Wei; Hu, Wei; Hu, Yuxin
2016-04-07
With the development of synthetic aperture radar (SAR) technologies in recent years, the huge amount of remote sensing data brings challenges for real-time imaging processing. Therefore, high performance computing (HPC) methods have been presented to accelerate SAR imaging, especially the GPU based methods. In the classical GPU based imaging algorithm, GPU is employed to accelerate image processing by massive parallel computing, and CPU is only used to perform the auxiliary work such as data input/output (IO). However, the computing capability of CPU is ignored and underestimated. In this work, a new deep collaborative SAR imaging method based on multiple CPU/GPU is proposed to achieve real-time SAR imaging. Through the proposed tasks partitioning and scheduling strategy, the whole image can be generated with deep collaborative multiple CPU/GPU computing. In the part of CPU parallel imaging, the advanced vector extension (AVX) method is firstly introduced into the multi-core CPU parallel method for higher efficiency. As for the GPU parallel imaging, not only the bottlenecks of memory limitation and frequent data transferring are broken, but also kinds of optimized strategies are applied, such as streaming, parallel pipeline and so on. Experimental results demonstrate that the deep CPU/GPU collaborative imaging method enhances the efficiency of SAR imaging on single-core CPU by 270 times and realizes the real-time imaging in that the imaging rate outperforms the raw data generation rate.
QR-decomposition based SENSE reconstruction using parallel architecture.
Ullah, Irfan; Nisar, Habab; Raza, Haseeb; Qasim, Malik; Inam, Omair; Omer, Hammad
2018-04-01
Magnetic Resonance Imaging (MRI) is a powerful medical imaging technique that provides essential clinical information about the human body. One major limitation of MRI is its long scan time. Implementation of advance MRI algorithms on a parallel architecture (to exploit inherent parallelism) has a great potential to reduce the scan time. Sensitivity Encoding (SENSE) is a Parallel Magnetic Resonance Imaging (pMRI) algorithm that utilizes receiver coil sensitivities to reconstruct MR images from the acquired under-sampled k-space data. At the heart of SENSE lies inversion of a rectangular encoding matrix. This work presents a novel implementation of GPU based SENSE algorithm, which employs QR decomposition for the inversion of the rectangular encoding matrix. For a fair comparison, the performance of the proposed GPU based SENSE reconstruction is evaluated against single and multicore CPU using openMP. Several experiments against various acceleration factors (AFs) are performed using multichannel (8, 12 and 30) phantom and in-vivo human head and cardiac datasets. Experimental results show that GPU significantly reduces the computation time of SENSE reconstruction as compared to multi-core CPU (approximately 12x speedup) and single-core CPU (approximately 53x speedup) without any degradation in the quality of the reconstructed images. Copyright © 2018 Elsevier Ltd. All rights reserved.
Implementation of highly parallel and large scale GW calculations within the OpenAtom software
Ismail-Beigi, Sohrab
The need to describe electronic excitations with better accuracy than provided by band structures produced by Density Functional Theory (DFT) has been a long-term enterprise for the computational condensed matter and materials theory communities. In some cases, appropriate theoretical frameworks have existed for some time but have been difficult to apply widely due to computational cost. For example, the GW approximation incorporates a great deal of important non-local and dynamical electronic interaction effects but has been too computationally expensive for routine use in large materials simulations. OpenAtom is an open source massively parallel ab initiodensity functional software package based on plane waves and pseudopotentials (http://charm.cs.uiuc.edu/OpenAtom/) that takes advantage of the Charm + + parallel framework. At present, it is developed via a three-way collaboration, funded by an NSF SI2-SSI grant (ACI-1339804), between Yale (Ismail-Beigi), IBM T. J. Watson (Glenn Martyna) and the University of Illinois at Urbana Champaign (Laxmikant Kale). We will describe the project and our current approach towards implementing large scale GW calculations with OpenAtom. Potential applications of large scale parallel GW software for problems involving electronic excitations in semiconductor and/or metal oxide systems will be also be pointed out.
Parallel Implementation and Scaling of an Adaptive Mesh Discrete Ordinates Algorithm for Transport
International Nuclear Information System (INIS)
Howell, L H
2004-01-01
Block-structured adaptive mesh refinement (AMR) uses a mesh structure built up out of locally-uniform rectangular grids. In the BoxLib parallel framework used by the Raptor code, each processor operates on one or more of these grids at each refinement level. The decomposition of the mesh into grids and the distribution of these grids among processors may change every few timesteps as a calculation proceeds. Finer grids use smaller timesteps than coarser grids, requiring additional work to keep the system synchronized and ensure conservation between different refinement levels. In a paper for NECDC 2002 I presented preliminary results on implementation of parallel transport sweeps on the AMR mesh, conjugate gradient acceleration, accuracy of the AMR solution, and scalar speedup of the AMR algorithm compared to a uniform fully-refined mesh. This paper continues with a more in-depth examination of the parallel scaling properties of the scheme, both in single-level and multi-level calculations. Both sweeping and setup costs are considered. The algorithm scales with acceptable performance to several hundred processors. Trends suggest, however, that this is the limit for efficient calculations with traditional transport sweeps, and that modifications to the sweep algorithm will be increasingly needed as job sizes in the thousands of processors become common
Progress in parallel implementation of the multilevel plane wave time domain algorithm
Liu, Yang
2013-07-01
The computational complexity and memory requirements of classical schemes for evaluating transient electromagnetic fields produced by Ns dipoles active for Nt time steps scale as O(NtN s 2) and O(Ns 2), respectively. The multilevel plane wave time domain (PWTD) algorithm [A.A. Ergin et al., Antennas and Propagation Magazine, IEEE, vol. 41, pp. 39-52, 1999], viz. the extension of the frequency domain fast multipole method (FMM) to the time domain, reduces the above costs to O(NtNslog2Ns) and O(Ns α) with α = 1.5 for surface current distributions and α = 4/3 for volumetric ones. Its favorable computational and memory costs notwithstanding, serial implementations of the PWTD scheme unfortunately remain somewhat limited in scope and ill-suited to tackle complex real-world scattering problems, and parallel implementations are called for. © 2013 IEEE.
Directory of Open Access Journals (Sweden)
Rongwang Yin
2018-01-01
Full Text Available A mathematical model for multistage hydraulically fractured horizontal wells (MFHWs in tight oil and gas reservoirs was derived by considering the variations in the permeability and porosity of tight oil and gas reservoirs that depend on formation pressure and mixed fluid properties and introducing the pseudo-pressure; analytical solutions were presented using the Newman superposition principle. The CPU-GPU asynchronous computing model was designed based on the CUDA platform, and the analytic solution was decomposed into infinite summation and integral forms for parallel computation. Implementation of this algorithm on an Intel i5 4590 CPU and NVIDIA GT 730 GPU demonstrates that computation speed increased by almost 80 times, which meets the requirement for real-time calculation of the formation pressure of MFHWs.
GPU-Vote: A Framework for Accelerating Voting Algorithms on GPU.
Braak, van den G.J.W.; Nugteren, C.; Mesman, B.; Corporaal, H.; Kaklamanis, C.; Papatheodorou, T.; Spirakis, P.G.
2012-01-01
Voting algorithms, such as histogram and Hough transforms, are frequently used algorithms in various domains, such as statistics and image processing. Algorithms in these domains may be accelerated using GPUs. Implementing voting algorithms efficiently on a GPU however is far from trivial due to
SU-E-T-37: A GPU-Based Pencil Beam Algorithm for Dose Calculations in Proton Radiation Therapy
International Nuclear Information System (INIS)
Kalantzis, G; Leventouri, T; Tachibana, H; Shang, C
2015-01-01
Purpose: Recent developments in radiation therapy have been focused on applications of charged particles, especially protons. Over the years several dose calculation methods have been proposed in proton therapy. A common characteristic of all these methods is their extensive computational burden. In the current study we present for the first time, to our best knowledge, a GPU-based PBA for proton dose calculations in Matlab. Methods: In the current study we employed an analytical expression for the protons depth dose distribution. The central-axis term is taken from the broad-beam central-axis depth dose in water modified by an inverse square correction while the distribution of the off-axis term was considered Gaussian. The serial code was implemented in MATLAB and was launched on a desktop with a quad core Intel Xeon X5550 at 2.67GHz with 8 GB of RAM. For the parallelization on the GPU, the parallel computing toolbox was employed and the code was launched on a GTX 770 with Kepler architecture. The performance comparison was established on the speedup factors. Results: The performance of the GPU code was evaluated for three different energies: low (50 MeV), medium (100 MeV) and high (150 MeV). Four square fields were selected for each energy, and the dose calculations were performed with both the serial and parallel codes for a homogeneous water phantom with size 300×300×300 mm3. The resolution of the PBs was set to 1.0 mm. The maximum speedup of ∼127 was achieved for the highest energy and the largest field size. Conclusion: A GPU-based PB algorithm for proton dose calculations in Matlab was presented. A maximum speedup of ∼127 was achieved. Future directions of the current work include extension of our method for dose calculation in heterogeneous phantoms
International Nuclear Information System (INIS)
Ding, Aiping; Liu, Tianyu; Liang, Chao; Ji, Wei; Shephard, Mark S.; Xu, X George; Brown, Forrest B.
2011-01-01
Monte Carlo simulation is ideally suited for solving Boltzmann neutron transport equation in inhomogeneous media. However, routine applications require the computation time to be reduced to hours and even minutes in a desktop system. The interest in adopting GPUs for Monte Carlo acceleration is rapidly mounting, fueled partially by the parallelism afforded by the latest GPU technologies and the challenge to perform full-size reactor core analysis on a routine basis. In this study, Monte Carlo codes for a fixed-source neutron transport problem and an eigenvalue/criticality problem were developed for CPU and GPU environments, respectively, to evaluate issues associated with computational speedup afforded by the use of GPUs. The results suggest that a speedup factor of 30 in Monte Carlo radiation transport of neutrons is within reach using the state-of-the-art GPU technologies. However, for the eigenvalue/criticality problem, the speedup was 8.5. In comparison, for a task of voxelizing unstructured mesh geometry that is more parallel in nature, the speedup of 45 was obtained. It was observed that, to date, most attempts to adopt GPUs for Monte Carlo acceleration were based on naïve implementations and have not yielded the level of anticipated gains. Successful implementation of Monte Carlo schemes for GPUs will likely require the development of an entirely new code. Given the prediction that future-generation GPU products will likely bring exponentially improved computing power and performances, innovative hardware and software solutions may make it possible to achieve full-core Monte Carlo calculation within one hour using a desktop computer system in a few years. (author)
International Nuclear Information System (INIS)
Liu Yuan; Du Zhihui; Chung, Shin Kee; Hooper, Shaun; Blair, David; Wen Linqing
2012-01-01
We present a graphics processing unit (GPU)-accelerated time-domain low-latency algorithm to search for gravitational waves (GWs) from coalescing binaries of compact objects based on the summed parallel infinite impulse response (SPIIR) filtering technique. The aim is to facilitate fast detection of GWs with a minimum delay to allow prompt electromagnetic follow-up observations. To maximize the GPU acceleration, we apply an efficient batched parallel computing model that significantly reduces the number of synchronizations in SPIIR and optimizes the usage of the memory and hardware resource. Our code is tested on the CUDA ‘Fermi’ architecture in a GTX 480 graphics card and its performance is compared with a single core of Intel Core i7 920 (2.67 GHz). A 58-fold speedup is achieved while giving results in close agreement with the CPU implementation. Our result indicates that it is possible to conduct a full search for GWs from compact binary coalescence in real time with only one desktop computer equipped with a Fermi GPU card for the initial LIGO detectors which in the past required more than 100 CPUs. (paper)
Frog: Asynchronous Graph Processing on GPU with Hybrid Coloring Model
Energy Technology Data Exchange (ETDEWEB)
Shi, Xuanhua; Luo, Xuan; Liang, Junling; Zhao, Peng; Di, Sheng; He, Bingsheng; Jin, Hai
2018-01-01
GPUs have been increasingly used to accelerate graph processing for complicated computational problems regarding graph theory. Many parallel graph algorithms adopt the asynchronous computing model to accelerate the iterative convergence. Unfortunately, the consistent asynchronous computing requires locking or atomic operations, leading to significant penalties/overheads when implemented on GPUs. As such, coloring algorithm is adopted to separate the vertices with potential updating conflicts, guaranteeing the consistency/correctness of the parallel processing. Common coloring algorithms, however, may suffer from low parallelism because of a large number of colors generally required for processing a large-scale graph with billions of vertices. We propose a light-weight asynchronous processing framework called Frog with a preprocessing/hybrid coloring model. The fundamental idea is based on Pareto principle (or 80-20 rule) about coloring algorithms as we observed through masses of realworld graph coloring cases. We find that a majority of vertices (about 80%) are colored with only a few colors, such that they can be read and updated in a very high degree of parallelism without violating the sequential consistency. Accordingly, our solution separates the processing of the vertices based on the distribution of colors. In this work, we mainly answer three questions: (1) how to partition the vertices in a sparse graph with maximized parallelism, (2) how to process large-scale graphs that cannot fit into GPU memory, and (3) how to reduce the overhead of data transfers on PCIe while processing each partition. We conduct experiments on real-world data (Amazon, DBLP, YouTube, RoadNet-CA, WikiTalk and Twitter) to evaluate our approach and make comparisons with well-known non-preprocessed (such as Totem, Medusa, MapGraph and Gunrock) and preprocessed (Cusha) approaches, by testing four classical algorithms (BFS, PageRank, SSSP and CC). On all the tested applications and
International Nuclear Information System (INIS)
Cui, X.; Mueller, F.; Zhang, Y.; Potok, Thomas E.
2009-01-01
Accelerating hardware devices represent a novel promise for improving the performance for many problem domains but it is not clear for which domains what accelerators are suitable. While there is no room in general-purpose processor design to significantly increase the processor frequency, developers are instead resorting to multi-core chips duplicating conventional computing capabilities on a single die. Yet, accelerators offer more radical designs with a much higher level of parallelism and novel programming environments. This present work assesses the viability of text mining on CUDA. Text mining is one of the key concepts that has become prominent as an effective means to index the Internet, but its applications range beyond this scope and extend to providing document similarity metrics, the subject of this work. We have developed and optimized text search algorithms for GPUs to exploit their potential for massive data processing. We discuss the algorithmic challenges of parallelization for text search problems on GPUs and demonstrate the potential of these devices in experiments by reporting significant speedups. Our study may be one of the first to assess more complex text search problems for suitability for GPU devices, and it may also be one of the first to exploit and report on atomic instruction usage that have recently become available in NVIDIA devices
D'Angelo, Gianni; Rampone, Salvatore
2014-01-01
The huge quantity of data produced in Biomedical research needs sophisticated algorithmic methodologies for its storage, analysis, and processing. High Performance Computing (HPC) appears as a magic bullet in this challenge. However, several hard to solve parallelization and load balancing problems arise in this context. Here we discuss the HPC-oriented implementation of a general purpose learning algorithm, originally conceived for DNA analysis and recently extended to treat uncertainty on data (U-BRAIN). The U-BRAIN algorithm is a learning algorithm that finds a Boolean formula in disjunctive normal form (DNF), of approximately minimum complexity, that is consistent with a set of data (instances) which may have missing bits. The conjunctive terms of the formula are computed in an iterative way by identifying, from the given data, a family of sets of conditions that must be satisfied by all the positive instances and violated by all the negative ones; such conditions allow the computation of a set of coefficients (relevances) for each attribute (literal), that form a probability distribution, allowing the selection of the term literals. The great versatility that characterizes it, makes U-BRAIN applicable in many of the fields in which there are data to be analyzed. However the memory and the execution time required by the running are of O(n(3)) and of O(n(5)) order, respectively, and so, the algorithm is unaffordable for huge data sets. We find mathematical and programming solutions able to lead us towards the implementation of the algorithm U-BRAIN on parallel computers. First we give a Dynamic Programming model of the U-BRAIN algorithm, then we minimize the representation of the relevances. When the data are of great size we are forced to use the mass memory, and depending on where the data are actually stored, the access times can be quite different. According to the evaluation of algorithmic efficiency based on the Disk Model, in order to reduce the costs of
Large Scale Simulations of the Euler Equations on GPU Clusters
Liebmann, Manfred; Douglas, Craig C.; Haase, Gundolf; Horvá th, Zoltá n
2010-01-01
The paper investigates the scalability of a parallel Euler solver, using the Vijayasundaram method, on a GPU cluster with 32 Nvidia Geforce GTX 295 boards. The aim of this research is to enable large scale fluid dynamics simulations with up to one
GPU-Boosted Camera-Only Indoor Localization
DEFF Research Database (Denmark)
Özkil, Ali Gürcan; Fan, Zhun; Kristensen, Jens Klæstrup
relies on local image features detection, description and matching; by parallelizing these computationally intensive tasks on the graphical processing unit (GPU), it is possible to do online localization using a Topometric Appearance Map. The method is developed as an integral part of a mobile service...
Parallel Implementation of Gamma-Point Pseudopotential Plane-Wave DFT with Exact Exchange
International Nuclear Information System (INIS)
Bylaska, Eric J.; Tsemekhman, Kiril L.; Baden, Scott B.; Weare, John H.; Jonsson, Hannes
2011-01-01
One of the more persistent failures of conventional density functional theory (DFT) methods has been their failure to yield localized charge states such as polarons, excitons and solitons in solid-state and extended systems. It has been suggested that conventional DFT functionals, which are not self-interaction free, tend to favor delocalized electronic states since self-interaction creates a Coulomb barrier to charge localization. Pragmatic approaches in which the exchange correlation functionals are augmented with small amount of exact exchange (hybrid-DFT, e.g. B3LYP and PBE0) have shown promise in localizing charge states and predicting accurate band gaps and reaction barriers. We have developed a parallel algorithm for implementing exact exchange into pseudopotential plane-wave density functional theory and we have implemented it in the NWChem program package. The technique developed can readily be employed in plane-wave DFT programs. Furthermore, atomic forces and stresses are straightforward to implement, making it applicable to both confined and extended systems, as well as to Car-Parrinello ab initio molecular dynamic simulations. This method has been applied to several systems for which conventional DFT methods do not work well, including calculations for band gaps in oxides and the electronic structure of a charge trapped state in the Fe(II) containing mica, annite.
A GPU-based solution for fast calculation of the betweenness centrality in large weighted networks
Directory of Open Access Journals (Sweden)
Rui Fan
2017-12-01
Full Text Available Betweenness, a widely employed centrality measure in network science, is a decent proxy for investigating network loads and rankings. However, its extremely high computational cost greatly hinders its applicability in large networks. Although several parallel algorithms have been presented to reduce its calculation cost for unweighted networks, a fast solution for weighted networks, which are commonly encountered in many realistic applications, is still lacking. In this study, we develop an efficient parallel GPU-based approach to boost the calculation of the betweenness centrality (BC for large weighted networks. We parallelize the traditional Dijkstra algorithm by selecting more than one frontier vertex each time and then inspecting the frontier vertices simultaneously. By combining the parallel SSSP algorithm with the parallel BC framework, our GPU-based betweenness algorithm achieves much better performance than its CPU counterparts. Moreover, to further improve performance, we integrate the work-efficient strategy, and to address the load-imbalance problem, we introduce a warp-centric technique, which assigns many threads rather than one to a single frontier vertex. Experiments on both realistic and synthetic networks demonstrate the efficiency of our solution, which achieves 2.9× to 8.44× speedups over the parallel CPU implementation. Our algorithm is open-source and free to the community; it is publicly available through https://dx.doi.org/10.6084/m9.figshare.4542405. Considering the pervasive deployment and declining price of GPUs in personal computers and servers, our solution will offer unprecedented opportunities for exploring betweenness-related problems and will motivate follow-up efforts in network science.
Implementation of an Agent-Based Parallel Tissue Modelling Framework for the Intel MIC Architecture
Directory of Open Access Journals (Sweden)
Maciej Cytowski
2017-01-01
Full Text Available Timothy is a novel large scale modelling framework that allows simulating of biological processes involving different cellular colonies growing and interacting with variable environment. Timothy was designed for execution on massively parallel High Performance Computing (HPC systems. The high parallel scalability of the implementation allows for simulations of up to 109 individual cells (i.e., simulations at tissue spatial scales of up to 1 cm3 in size. With the recent advancements of the Timothy model, it has become critical to ensure appropriate performance level on emerging HPC architectures. For instance, the introduction of blood vessels supplying nutrients to the tissue is a very important step towards realistic simulations of complex biological processes, but it greatly increased the computational complexity of the model. In this paper, we describe the process of modernization of the application in order to achieve high computational performance on HPC hybrid systems based on modern Intel® MIC architecture. Experimental results on the Intel Xeon Phi™ coprocessor x100 and the Intel Xeon Phi processor x200 are presented.
Implementing O(N N-Body Algorithms Efficiently in Data-Parallel Languages
Directory of Open Access Journals (Sweden)
Yu Hu
1996-01-01
Full Text Available The optimization techniques for hierarchical O(N N-body algorithms described here focus on managing the data distribution and the data references, both between the memories of different nodes and within the memory hierarchy of each node. We show how the techniques can be expressed in data-parallel languages, such as High Performance Fortran (HPF and Connection Machine Fortran (CMF. The effectiveness of our techniques is demonstrated on an implementation of Anderson's hierarchical O(N N-body method for the Connection Machine system CM-5/5E. Of the total execution time, communication accounts for about 10–20% of the total time, with the average efficiency for arithmetic operations being about 40% and the total efficiency (including communication being about 35%. For the CM-5E, a performance in excess of 60 Mflop/s per node (peak 160 Mflop/s per node has been measured.
Implementation of a 3D plasma particle-in-cell code on a MIMD parallel computer
International Nuclear Information System (INIS)
Liewer, P.C.; Lyster, P.; Wang, J.
1993-01-01
A three-dimensional plasma particle-in-cell (PIC) code has been implemented on the Intel Delta MIMD parallel supercomputer using the General Concurrent PIC algorithm. The GCPIC algorithm uses a domain decomposition to divide the computation among the processors: A processor is assigned a subdomain and all the particles in it. Particles must be exchanged between processors as they move. Results are presented comparing the efficiency for 1-, 2- and 3-dimensional partitions of the three dimensional domain. This algorithm has been found to be very efficient even when a large fraction (e.g. 30%) of the particles must be exchanged at every time step. On the 512-node Intel Delta, up to 125 million particles have been pushed with an electrostatic push time of under 500 nsec/particle/time step
Directory of Open Access Journals (Sweden)
Socrates A. Mylonas
2003-06-01
Full Text Available This paper describes the application of a new texture characterization algorithm for the segmentation of medical ultrasound images. The morphology of these images poses significant problems for the application of traditional image processing techniques and their analysis has been the subject of research for several years. The basis of the algorithm is an optimum signal modelling algorithm (Least Mean Squares-based, which estimates a set of parameters from small image regions. The algorithm has been converted to a structure suitable for implementation on a Parallel Virtual Machine (PVM consisting of a Network of Workstations (NoW, to improve processing speed. Tests were initially carried out on standard textured images. This paper describes preliminary results of the application of the algorithm in texture discrimination and segmentation of medical ultrasound images. The images examined are primarily used in the diagnosis of carotid plaques, which are linked to the risk of stroke.
Design and Implementation of a New DELTA Parallel Robot in Robotics Competitions
Directory of Open Access Journals (Sweden)
Jonqlan Lin
2015-10-01
Full Text Available This investigation concerns the design and implementation of the DELTA parallel robot, covering the entire mechatronic process, involving kinematics, control design and optimizing methods. To accelerate the construction of the robot, 3D printing is used to fabricate end-effector parts. The parts are modular, low-cost, reconfigurable and can be assembled in less time than is required for conventionally fabricated parts. The controller, including the control algorithm and human-machine interface (HMI, is coded using the Borland C++ Builder 6 Personal software environment. The integration of the motion controller with image recognition into an opto-mechatronics system is presented. The robot system has been entered into robotic competitions in Taiwan. The experimental results reveal that the proposed DELTA robot completed the tasks in those competitions successfully.
SU-D-BRD-03: A Gateway for GPU Computing in Cancer Radiotherapy Research
Energy Technology Data Exchange (ETDEWEB)
Jia, X; Folkerts, M [The University of Texas Southwestern Medical Ctr, Dallas, TX (United States); Shi, F; Yan, H; Yan, Y; Jiang, S [UT Southwestern Medical Center, Dallas, TX (United States); Sivagnanam, S; Majumdar, A [University of California San Diego, La Jolla, CA (United States)
2014-06-01
Purpose: Graphics Processing Unit (GPU) has become increasingly important in radiotherapy. However, it is still difficult for general clinical researchers to access GPU codes developed by other researchers, and for developers to objectively benchmark their codes. Moreover, it is quite often to see repeated efforts spent on developing low-quality GPU codes. The goal of this project is to establish an infrastructure for testing GPU codes, cross comparing them, and facilitating code distributions in radiotherapy community. Methods: We developed a system called Gateway for GPU Computing in Cancer Radiotherapy Research (GCR2). A number of GPU codes developed by our group and other developers can be accessed via a web interface. To use the services, researchers first upload their test data or use the standard data provided by our system. Then they can select the GPU device on which the code will be executed. Our system offers all mainstream GPU hardware for code benchmarking purpose. After the code running is complete, the system automatically summarizes and displays the computing results. We also released a SDK to allow the developers to build their own algorithm implementation and submit their binary codes to the system. The submitted code is then systematically benchmarked using a variety of GPU hardware and representative data provided by our system. The developers can also compare their codes with others and generate benchmarking reports. Results: It is found that the developed system is fully functioning. Through a user-friendly web interface, researchers are able to test various GPU codes. Developers also benefit from this platform by comprehensively benchmarking their codes on various GPU platforms and representative clinical data sets. Conclusion: We have developed an open platform allowing the clinical researchers and developers to access the GPUs and GPU codes. This development will facilitate the utilization of GPU in radiation therapy field.
Rodrigues, Manuel J.; Fernandes, David E.; Silveirinha, Mário G.; Falcão, Gabriel
2018-01-01
This work introduces a parallel computing framework to characterize the propagation of electron waves in graphene-based nanostructures. The electron wave dynamics is modeled using both "microscopic" and effective medium formalisms and the numerical solution of the two-dimensional massless Dirac equation is determined using a Finite-Difference Time-Domain scheme. The propagation of electron waves in graphene superlattices with localized scattering centers is studied, and the role of the symmetry of the microscopic potential in the electron velocity is discussed. The computational methodologies target the parallel capabilities of heterogeneous multi-core CPU and multi-GPU environments and are built with the OpenCL parallel programming framework which provides a portable, vendor agnostic and high throughput-performance solution. The proposed heterogeneous multi-GPU implementation achieves speedup ratios up to 75x when compared to multi-thread and multi-core CPU execution, reducing simulation times from several hours to a couple of minutes.
International Nuclear Information System (INIS)
Sotiropoulou, C L; Gkaitatzis, S; Kordas, K; Nikolaidis, S; Petridou, C; Annovi, A; Beretta, M; Volpi, G
2014-01-01
The parallel 2D pixel clustering FPGA implementation used for the input system of the ATLAS Fast TracKer (FTK) processor is presented. The input system for the FTK processor will receive data from the Pixel and micro-strip detectors from inner ATLAS read out drivers (RODs) at full rate, for total of 760Gbs, as sent by the RODs after level-1 triggers. Clustering serves two purposes, the first is to reduce the high rate of the received data before further processing, the second is to determine the cluster centroid to obtain the best spatial measurement. For the pixel detectors the clustering is implemented by using a 2D-clustering algorithm that takes advantage of a moving window technique to minimize the logic required for cluster identification. The cluster detection window size can be adjusted for optimizing the cluster identification process. Additionally, the implementation can be parallelized by instantiating multiple cores to identify different clusters independently thus exploiting more FPGA resources. This flexibility makes the implementation suitable for a variety of demanding image processing applications. The implementation is robust against bit errors in the input data stream and drops all data that cannot be identified. In the unlikely event of missing control words, the implementation will ensure stable data processing by inserting the missing control words in the data stream. The 2D pixel clustering implementation is developed and tested in both single flow and parallel versions. The first parallel version with 16 parallel cluster identification engines is presented. The input data from the RODs are received through S-Links and the processing units that follow the clustering implementation also require a single data stream, therefore data parallelizing (demultiplexing) and serializing (multiplexing) modules are introduced in order to accommodate the parallelized version and restore the data stream afterwards. The results of the first hardware tests of
Blaze-DEMGPU: Modular high performance DEM framework for the GPU architecture
Directory of Open Access Journals (Sweden)
Nicolin Govender
2016-01-01
Full Text Available Blaze-DEMGPU is a modular GPU based discrete element method (DEM framework that supports polyhedral shaped particles. The high level performance is attributed to the light weight and Single Instruction Multiple Data (SIMD that the GPU architecture offers. Blaze-DEMGPU offers suitable algorithms to conduct DEM simulations on the GPU and these algorithms can be extended and modified. Since a large number of scientific simulations are particle based, many of the algorithms and strategies for GPU implementation present in Blaze-DEMGPU can be applied to other fields. Blaze-DEMGPU will make it easier for new researchers to use high performance GPU computing as well as stimulate wider GPU research efforts by the DEM community.
High-speed parallel implementation of a modified PBR algorithm on DSP-based EH topology
Rajan, K.; Patnaik, L. M.; Ramakrishna, J.
1997-08-01
Algebraic Reconstruction Technique (ART) is an age-old method used for solving the problem of three-dimensional (3-D) reconstruction from projections in electron microscopy and radiology. In medical applications, direct 3-D reconstruction is at the forefront of investigation. The simultaneous iterative reconstruction technique (SIRT) is an ART-type algorithm with the potential of generating in a few iterations tomographic images of a quality comparable to that of convolution backprojection (CBP) methods. Pixel-based reconstruction (PBR) is similar to SIRT reconstruction, and it has been shown that PBR algorithms give better quality pictures compared to those produced by SIRT algorithms. In this work, we propose a few modifications to the PBR algorithms. The modified algorithms are shown to give better quality pictures compared to PBR algorithms. The PBR algorithm and the modified PBR algorithms are highly compute intensive, Not many attempts have been made to reconstruct objects in the true 3-D sense because of the high computational overhead. In this study, we have developed parallel two-dimensional (2-D) and 3-D reconstruction algorithms based on modified PBR. We attempt to solve the two problems encountered by the PBR and modified PBR algorithms, i.e., the long computational time and the large memory requirements, by parallelizing the algorithm on a multiprocessor system. We investigate the possible task and data partitioning schemes by exploiting the potential parallelism in the PBR algorithm subject to minimizing the memory requirement. We have implemented an extended hypercube (EH) architecture for the high-speed execution of the 3-D reconstruction algorithm using the commercially available fast floating point digital signal processor (DSP) chips as the processing elements (PEs) and dual-port random access memories (DPR) as channels between the PEs. We discuss and compare the performances of the PBR algorithm on an IBM 6000 RISC workstation, on a Silicon
Known-plaintext attack on the double phase encoding and its implementation with parallel hardware
Wei, Hengzheng; Peng, Xiang; Liu, Haitao; Feng, Songlin; Gao, Bruce Z.
2008-03-01
A known-plaintext attack on the double phase encryption scheme implemented with parallel hardware is presented. The double random phase encoding (DRPE) is one of the most representative optical cryptosystems developed in mid of 90's and derives quite a few variants since then. Although the DRPE encryption system has a strong power resisting to a brute-force attack, the inherent architecture of DRPE leaves a hidden trouble due to its linearity nature. Recently the real security strength of this opto-cryptosystem has been doubted and analyzed from the cryptanalysis point of view. In this presentation, we demonstrate that the optical cryptosystems based on DRPE architecture are vulnerable to known-plain text attack. With this attack the two encryption keys in the DRPE can be accessed with the help of the phase retrieval technique. In our approach, we adopt hybrid input-output algorithm (HIO) to recover the random phase key in the object domain and then infer the key in frequency domain. Only a plaintext-ciphertext pair is sufficient to create vulnerability. Moreover this attack does not need to select particular plaintext. The phase retrieval technique based on HIO is an iterative process performing Fourier transforms, so it fits very much into the hardware implementation of the digital signal processor (DSP). We make use of the high performance DSP to accomplish the known-plaintext attack. Compared with the software implementation, the speed of the hardware implementation is much fast. The performance of this DSP-based cryptanalysis system is also evaluated.
GPU based numerical simulation of core shooting process
Directory of Open Access Journals (Sweden)
Yi-zhong Zhang
2017-11-01
Full Text Available Core shooting process is the most widely used technique to make sand cores and it plays an important role in the quality of sand cores. Although numerical simulation can hopefully optimize the core shooting process, research on numerical simulation of the core shooting process is very limited. Based on a two-fluid model (TFM and a kinetic-friction constitutive correlation, a program for 3D numerical simulation of the core shooting process has been developed and achieved good agreements with in-situ experiments. To match the needs of engineering applications, a graphics processing unit (GPU has also been used to improve the calculation efficiency. The parallel algorithm based on the Compute Unified Device Architecture (CUDA platform can significantly decrease computing time by multi-threaded GPU. In this work, the program accelerated by CUDA parallelization method was developed and the accuracy of the calculations was ensured by comparing with in-situ experimental results photographed by a high-speed camera. The design and optimization of the parallel algorithm were discussed. The simulation result of a sand core test-piece indicated the improvement of the calculation efficiency by GPU. The developed program has also been validated by in-situ experiments with a transparent core-box, a high-speed camera, and a pressure measuring system. The computing time of the parallel program was reduced by nearly 95% while the simulation result was still quite consistent with experimental data. The GPU parallelization method can successfully solve the problem of low computational efficiency of the 3D sand shooting simulation program, and thus the developed GPU program is appropriate for engineering applications.
Strategies for regular segmented reductions on GPU
DEFF Research Database (Denmark)
Larsen, Rasmus Wriedt; Henriksen, Troels
2017-01-01
We present and evaluate an implementation technique for regular segmented reductions on GPUs. Existing techniques tend to be either consistent in performance but relatively inefficient in absolute terms, or optimised for specific workloads and thereby exhibiting bad performance for certain input...... is in the context of the Futhark compiler, the implementation technique is applicable to any library or language that has a need for segmented reductions. We evaluate the technique on four microbenchmarks, two of which we also compare to implementations in the CUB library for GPU programming, as well as on two...
Fast phase processing in off-axis holography by CUDA including parallel phase unwrapping.
Backoach, Ohad; Kariv, Saar; Girshovitz, Pinhas; Shaked, Natan T
2016-02-22
We present parallel processing implementation for rapid extraction of the quantitative phase maps from off-axis holograms on the Graphics Processing Unit (GPU) of the computer using computer unified device architecture (CUDA) programming. To obtain efficient implementation, we parallelized both the wrapped phase map extraction algorithm and the two-dimensional phase unwrapping algorithm. In contrast to previous implementations, we utilized unweighted least squares phase unwrapping algorithm that better suits parallelism. We compared the proposed algorithm run times on the CPU and the GPU of the computer for various sizes of off-axis holograms. Using the GPU implementation, we extracted the unwrapped phase maps from the recorded off-axis holograms at 35 frames per second (fps) for 4 mega pixel holograms, and at 129 fps for 1 mega pixel holograms, which presents the fastest processing framerates obtained so far, to the best of our knowledge. We then used common-path off-axis interferometric imaging to quantitatively capture the phase maps of a micro-organism with rapid flagellum movements.
A nonvoxel-based dose convolution/superposition algorithm optimized for scalable GPU architectures
Energy Technology Data Exchange (ETDEWEB)
Neylon, J., E-mail: jneylon@mednet.ucla.edu; Sheng, K.; Yu, V.; Low, D. A.; Kupelian, P.; Santhanam, A. [Department of Radiation Oncology, University of California Los Angeles, 200 Medical Plaza, #B265, Los Angeles, California 90095 (United States); Chen, Q. [Department of Radiation Oncology, University of Virginia, 1300 Jefferson Park Avenue, Charlottesville, California 22908 (United States)
2014-10-15
, respectively. Accuracy was investigated using three distinct phantoms with varied geometries and heterogeneities and on a series of 14 segmented lung CT data sets. Performance gains were calculated using three 256 mm cube homogenous water phantoms, with isotropic voxel dimensions of 1, 2, and 4 mm. Results: The nonvoxel-based GPU algorithm was independent of the data size and provided significant computational gains over the CPU algorithm for large CT data sizes. The parameter search analysis also showed that the ray combination of 8 zenithal and 8 azimuthal angles along with 1 mm radial sampling and 2 mm parallel ray spacing maintained dose accuracy with greater than 99% of voxels passing the γ test. Combining the acceleration obtained from GPU parallelization with the sampling optimization, the authors achieved a total performance improvement factor of >175 000 when compared to our voxel-based ground truth CPU benchmark and a factor of 20 compared with a voxel-based GPU dose convolution method. Conclusions: The nonvoxel-based convolution method yielded substantial performance improvements over a generic GPU implementation, while maintaining accuracy as compared to a CPU computed ground truth dose distribution. Such an algorithm can be a key contribution toward developing tools for adaptive radiation therapy systems.
A nonvoxel-based dose convolution/superposition algorithm optimized for scalable GPU architectures
International Nuclear Information System (INIS)
Neylon, J.; Sheng, K.; Yu, V.; Low, D. A.; Kupelian, P.; Santhanam, A.; Chen, Q.
2014-01-01
, respectively. Accuracy was investigated using three distinct phantoms with varied geometries and heterogeneities and on a series of 14 segmented lung CT data sets. Performance gains were calculated using three 256 mm cube homogenous water phantoms, with isotropic voxel dimensions of 1, 2, and 4 mm. Results: The nonvoxel-based GPU algorithm was independent of the data size and provided significant computational gains over the CPU algorithm for large CT data sizes. The parameter search analysis also showed that the ray combination of 8 zenithal and 8 azimuthal angles along with 1 mm radial sampling and 2 mm parallel ray spacing maintained dose accuracy with greater than 99% of voxels passing the γ test. Combining the acceleration obtained from GPU parallelization with the sampling optimization, the authors achieved a total performance improvement factor of >175 000 when compared to our voxel-based ground truth CPU benchmark and a factor of 20 compared with a voxel-based GPU dose convolution method. Conclusions: The nonvoxel-based convolution method yielded substantial performance improvements over a generic GPU implementation, while maintaining accuracy as compared to a CPU computed ground truth dose distribution. Such an algorithm can be a key contribution toward developing tools for adaptive radiation therapy systems
Algorithm and Implementation of Distributed ESN Using Spark Framework and Parallel PSO
Directory of Open Access Journals (Sweden)
Kehe Wu
2017-04-01
Full Text Available The echo state network (ESN employs a huge reservoir with sparsely and randomly connected internal nodes and only trains the output weights, which avoids the suboptimal problem, exploding and vanishing gradients, high complexity and other disadvantages faced by traditional recurrent neural network (RNN training. In light of the outstanding adaption to nonlinear dynamical systems, ESN has been applied into a wide range of applications. However, in the era of Big Data, with an enormous amount of data being generated continuously every day, the data are often distributed and stored in real applications, and thus the centralized ESN training process is prone to being technologically unsuitable. In order to achieve the requirement of Big Data applications in the real world, in this study we propose an algorithm and its implementation for distributed ESN training. The mentioned algorithm is based on the parallel particle swarm optimization (P-PSO technique and the implementation uses Spark, a famous large-scale data processing framework. Four extremely large-scale datasets, including artificial benchmarks, real-world data and image data, are adopted to verify our framework on a stretchable platform. Experimental results indicate that the proposed work is accurate in the era of Big Data, regarding speed, accuracy and generalization capabilities.
GPU-based relative fuzzy connectedness image segmentation
International Nuclear Information System (INIS)
Zhuge Ying; Ciesielski, Krzysztof C.; Udupa, Jayaram K.; Miller, Robert W.
2013-01-01
Purpose:Recently, clinical radiological research and practice are becoming increasingly quantitative. Further, images continue to increase in size and volume. For quantitative radiology to become practical, it is crucial that image segmentation algorithms and their implementations are rapid and yield practical run time on very large data sets. The purpose of this paper is to present a parallel version of an algorithm that belongs to the family of fuzzy connectedness (FC) algorithms, to achieve an interactive speed for segmenting large medical image data sets. Methods: The most common FC segmentations, optimizing an ℓ ∞ -based energy, are known as relative fuzzy connectedness (RFC) and iterative relative fuzzy connectedness (IRFC). Both RFC and IRFC objects (of which IRFC contains RFC) can be found via linear time algorithms, linear with respect to the image size. The new algorithm, P-ORFC (for parallel optimal RFC), which is implemented by using NVIDIA’s Compute Unified Device Architecture (CUDA) platform, considerably improves the computational speed of the above mentioned CPU based IRFC algorithm. Results: Experiments based on four data sets of small, medium, large, and super data size, achieved speedup factors of 32.8×, 22.9×, 20.9×, and 17.5×, correspondingly, on the NVIDIA Tesla C1060 platform. Although the output of P-ORFC need not precisely match that of IRFC output, it is very close to it and, as the authors prove, always lies between the RFC and IRFC objects. Conclusions: A parallel version of a top-of-the-line algorithm in the family of FC has been developed on the NVIDIA GPUs. An interactive speed of segmentation has been achieved, even for the largest medical image data set. Such GPU implementations may play a crucial role in automatic anatomy recognition in clinical radiology.
GPU-based relative fuzzy connectedness image segmentation
Energy Technology Data Exchange (ETDEWEB)
Zhuge Ying; Ciesielski, Krzysztof C.; Udupa, Jayaram K.; Miller, Robert W. [Radiation Oncology Branch, National Cancer Institute, National Institutes of Health, Bethesda, Maryland 20892 (United States); Department of Mathematics, West Virginia University, Morgantown, West Virginia 26506 (United States) and Medical Image Processing Group, Department of Radiology, University of Pennsylvania, Philadelphia, Pennsylvania 19104 (United States); Medical Image Processing Group, Department of Radiology, University of Pennsylvania, Philadelphia, Pennsylvania 19104 (United States); Radiation Oncology Branch, National Cancer Institute, National Institutes of Health, Bethesda, Maryland 20892 (United States)
2013-01-15
Purpose:Recently, clinical radiological research and practice are becoming increasingly quantitative. Further, images continue to increase in size and volume. For quantitative radiology to become practical, it is crucial that image segmentation algorithms and their implementations are rapid and yield practical run time on very large data sets. The purpose of this paper is to present a parallel version of an algorithm that belongs to the family of fuzzy connectedness (FC) algorithms, to achieve an interactive speed for segmenting large medical image data sets. Methods: The most common FC segmentations, optimizing an Script-Small-L {sub {infinity}}-based energy, are known as relative fuzzy connectedness (RFC) and iterative relative fuzzy connectedness (IRFC). Both RFC and IRFC objects (of which IRFC contains RFC) can be found via linear time algorithms, linear with respect to the image size. The new algorithm, P-ORFC (for parallel optimal RFC), which is implemented by using NVIDIA's Compute Unified Device Architecture (CUDA) platform, considerably improves the computational speed of the above mentioned CPU based IRFC algorithm. Results: Experiments based on four data sets of small, medium, large, and super data size, achieved speedup factors of 32.8 Multiplication-Sign , 22.9 Multiplication-Sign , 20.9 Multiplication-Sign , and 17.5 Multiplication-Sign , correspondingly, on the NVIDIA Tesla C1060 platform. Although the output of P-ORFC need not precisely match that of IRFC output, it is very close to it and, as the authors prove, always lies between the RFC and IRFC objects. Conclusions: A parallel version of a top-of-the-line algorithm in the family of FC has been developed on the NVIDIA GPUs. An interactive speed of segmentation has been achieved, even for the largest medical image data set. Such GPU implementations may play a crucial role in automatic anatomy recognition in clinical radiology.
GPU-based relative fuzzy connectedness image segmentation.
Zhuge, Ying; Ciesielski, Krzysztof C; Udupa, Jayaram K; Miller, Robert W
2013-01-01
Recently, clinical radiological research and practice are becoming increasingly quantitative. Further, images continue to increase in size and volume. For quantitative radiology to become practical, it is crucial that image segmentation algorithms and their implementations are rapid and yield practical run time on very large data sets. The purpose of this paper is to present a parallel version of an algorithm that belongs to the family of fuzzy connectedness (FC) algorithms, to achieve an interactive speed for segmenting large medical image data sets. The most common FC segmentations, optimizing an [script-l](∞)-based energy, are known as relative fuzzy connectedness (RFC) and iterative relative fuzzy connectedness (IRFC). Both RFC and IRFC objects (of which IRFC contains RFC) can be found via linear time algorithms, linear with respect to the image size. The new algorithm, P-ORFC (for parallel optimal RFC), which is implemented by using NVIDIA's Compute Unified Device Architecture (CUDA) platform, considerably improves the computational speed of the above mentioned CPU based IRFC algorithm. Experiments based on four data sets of small, medium, large, and super data size, achieved speedup factors of 32.8×, 22.9×, 20.9×, and 17.5×, correspondingly, on the NVIDIA Tesla C1060 platform. Although the output of P-ORFC need not precisely match that of IRFC output, it is very close to it and, as the authors prove, always lies between the RFC and IRFC objects. A parallel version of a top-of-the-line algorithm in the family of FC has been developed on the NVIDIA GPUs. An interactive speed of segmentation has been achieved, even for the largest medical image data set. Such GPU implementations may play a crucial role in automatic anatomy recognition in clinical radiology.
GPU-based relative fuzzy connectedness image segmentation
Zhuge, Ying; Ciesielski, Krzysztof C.; Udupa, Jayaram K.; Miller, Robert W.
2013-01-01
Purpose: Recently, clinical radiological research and practice are becoming increasingly quantitative. Further, images continue to increase in size and volume. For quantitative radiology to become practical, it is crucial that image segmentation algorithms and their implementations are rapid and yield practical run time on very large data sets. The purpose of this paper is to present a parallel version of an algorithm that belongs to the family of fuzzy connectedness (FC) algorithms, to achieve an interactive speed for segmenting large medical image data sets. Methods: The most common FC segmentations, optimizing an ℓ∞-based energy, are known as relative fuzzy connectedness (RFC) and iterative relative fuzzy connectedness (IRFC). Both RFC and IRFC objects (of which IRFC contains RFC) can be found via linear time algorithms, linear with respect to the image size. The new algorithm, P-ORFC (for parallel optimal RFC), which is implemented by using NVIDIA’s Compute Unified Device Architecture (CUDA) platform, considerably improves the computational speed of the above mentioned CPU based IRFC algorithm. Results: Experiments based on four data sets of small, medium, large, and super data size, achieved speedup factors of 32.8×, 22.9×, 20.9×, and 17.5×, correspondingly, on the NVIDIA Tesla C1060 platform. Although the output of P-ORFC need not precisely match that of IRFC output, it is very close to it and, as the authors prove, always lies between the RFC and IRFC objects. Conclusions: A parallel version of a top-of-the-line algorithm in the family of FC has been developed on the NVIDIA GPUs. An interactive speed of segmentation has been achieved, even for the largest medical image data set. Such GPU implementations may play a crucial role in automatic anatomy recognition in clinical radiology. PMID:23298094
A High-Performance Parallel FDTD Method Enhanced by Using SSE Instruction Set
Directory of Open Access Journals (Sweden)
Dau-Chyrh Chang
2012-01-01
Full Text Available We introduce a hardware acceleration technique for the parallel finite difference time domain (FDTD method using the SSE (streaming (single instruction multiple data SIMD extensions instruction set. The implementation of SSE instruction set to parallel FDTD method has achieved the significant improvement on the simulation performance. The benchmarks of the SSE acceleration on both the multi-CPU workstation and computer cluster have demonstrated the advantages of (vector arithmetic logic unit VALU acceleration over GPU acceleration. Several engineering applications are employed to demonstrate the performance of parallel FDTD method enhanced by SSE instruction set.
Opticks : GPU Optical Photon Simulation for Particle Physics using NVIDIA® OptiX™
C, Blyth Simon
2017-10-01
Opticks is an open source project that integrates the NVIDIA OptiX GPU ray tracing engine with Geant4 toolkit based simulations. Massive parallelism brings drastic performance improvements with optical photon simulation speedup expected to exceed 1000 times Geant4 when using workstation GPUs. Optical photon simulation time becomes effectively zero compared to the rest of the simulation. Optical photons from scintillation and Cherenkov processes are allocated, generated and propagated entirely on the GPU, minimizing transfer overheads and allowing CPU memory usage to be restricted to optical photons that hit photomultiplier tubes or other photon detectors. Collecting hits into standard Geant4 hit collections then allows the rest of the simulation chain to proceed unmodified. Optical physics processes of scattering, absorption, scintillator reemission and boundary processes are implemented in CUDA OptiX programs based on the Geant4 implementations. Wavelength dependent material and surface properties as well as inverse cumulative distribution functions for reemission are interleaved into GPU textures providing fast interpolated property lookup or wavelength generation. Geometry is provided to OptiX in the form of CUDA programs that return bounding boxes for each primitive and ray geometry intersection positions. Some critical parts of the geometry such as photomultiplier tubes have been implemented analytically with the remainder being tessellated. OptiX handles the creation and application of a choice of acceleration structures such as boundary volume hierarchies and the transparent use of multiple GPUs. OptiX supports interoperation with OpenGL and CUDA Thrust that has enabled unprecedented visualisations of photon propagations to be developed using OpenGL geometry shaders to provide interactive time scrubbing and CUDA Thrust photon indexing to enable interactive history selection.
Using the CPU and GPU for real-time video enhancement on a mobile computer
CSIR Research Space (South Africa)
Bachoo, AK
2010-09-01
Full Text Available . In this paper, the current advances in mobile CPU and GPU hardware are used to implement video enhancement algorithms in a new way on a mobile computer. Both the CPU and GPU are used effectively to achieve realtime performance for complex image enhancement...
International Nuclear Information System (INIS)
Bao Bo-Cheng; Feng Fei; Dong Wei; Pan Sai-Hu
2013-01-01
A flux-controlled memristor characterized by smooth cubic nonlinearity is taken as an example, upon which the voltage—current relationships (VCRs) between two parallel memristive circuits — a parallel memristor and capacitor circuit (the parallel MC circuit), and a parallel memristor and inductor circuit (the parallel ML circuit) — are investigated. The results indicate that the VCR between these two parallel memristive circuits is closely related to the circuit parameters, and the frequency and amplitude of the sinusoidal voltage stimulus. An equivalent circuit model of the memristor is built, upon which the circuit simulations and experimental measurements of both the parallel MC circuit and the parallel ML circuit are performed, and the results verify the theoretical analysis results
Hoekstra, A.G.; Sloot, P.M.A.; Haan, M.J.; Hertzberger, L.O.; van Leeuwen, J.
1991-01-01
New developments in Computer Science, both hardware and software, offer researchers, such as physicists, unprecedented possibilities to solve their computational intensive problems.However, full exploitation of e.g. new massively parallel computers, parallel languages or runtime environments
GPU-based high performance Monte Carlo simulation in neutron transport
Energy Technology Data Exchange (ETDEWEB)
Heimlich, Adino; Mol, Antonio C.A.; Pereira, Claudio M.N.A. [Instituto de Engenharia Nuclear (IEN/CNEN-RJ), Rio de Janeiro, RJ (Brazil). Lab. de Inteligencia Artificial Aplicada], e-mail: cmnap@ien.gov.br
2009-07-01
Graphics Processing Units (GPU) are high performance co-processors intended, originally, to improve the use and quality of computer graphics applications. Since researchers and practitioners realized the potential of using GPU for general purpose, their application has been extended to other fields out of computer graphics scope. The main objective of this work is to evaluate the impact of using GPU in neutron transport simulation by Monte Carlo method. To accomplish that, GPU- and CPU-based (single and multicore) approaches were developed and applied to a simple, but time-consuming problem. Comparisons demonstrated that the GPU-based approach is about 15 times faster than a parallel 8-core CPU-based approach also developed in this work. (author)
GPU-based high performance Monte Carlo simulation in neutron transport
International Nuclear Information System (INIS)
Heimlich, Adino; Mol, Antonio C.A.; Pereira, Claudio M.N.A.
2009-01-01
Graphics Processing Units (GPU) are high performance co-processors intended, originally, to improve the use and quality of computer graphics applications. Since researchers and practitioners realized the potential of using GPU for general purpose, their application has been extended to other fields out of computer graphics scope. The main objective of this work is to evaluate the impact of using GPU in neutron transport simulation by Monte Carlo method. To accomplish that, GPU- and CPU-based (single and multicore) approaches were developed and applied to a simple, but time-consuming problem. Comparisons demonstrated that the GPU-based approach is about 15 times faster than a parallel 8-core CPU-based approach also developed in this work. (author)
Papaya Tree Detection with UAV Images Using a GPU-Accelerated Scale-Space Filtering Method
Directory of Open Access Journals (Sweden)
Hao Jiang
2017-07-01
Full Text Available The use of unmanned aerial vehicles (UAV can allow individual tree detection for forest inventories in a cost-effective way. The scale-space filtering (SSF algorithm is commonly used and has the capability of detecting trees of different crown sizes. In this study, we made two improvements with regard to the existing method and implementations. First, we incorporated SSF with a Lab color transformation to reduce over-detection problems associated with the original luminance image. Second, we ported four of the most time-consuming processes to the graphics processing unit (GPU to improve computational efficiency. The proposed method was implemented using PyCUDA, which enabled access to NVIDIA’s compute unified device architecture (CUDA through high-level scripting of the Python language. Our experiments were conducted using two images captured by the DJI Phantom 3 Professional and a most recent NVIDIA GPU GTX1080. The resulting accuracy was high, with an F-measure larger than 0.94. The speedup achieved by our parallel implementation was 44.77 and 28.54 for the first and second test image, respectively. For each 4000 × 3000 image, the total runtime was less than 1 s, which was sufficient for real-time performance and interactive application.
FARGO3D: A NEW GPU-ORIENTED MHD CODE
Energy Technology Data Exchange (ETDEWEB)
Benitez-Llambay, Pablo [Instituto de Astronomía Teórica y Experimental, Observatorio Astronónomico, Universidad Nacional de Córdoba. Laprida 854, X5000BGR, Córdoba (Argentina); Masset, Frédéric S., E-mail: pbllambay@oac.unc.edu.ar, E-mail: masset@icf.unam.mx [Instituto de Ciencias Físicas, Universidad Nacional Autónoma de México (UNAM), Apdo. Postal 48-3,62251-Cuernavaca, Morelos (Mexico)
2016-03-15
We present the FARGO3D code, recently publicly released. It is a magnetohydrodynamics code developed with special emphasis on the physics of protoplanetary disks and planet–disk interactions, and parallelized with MPI. The hydrodynamics algorithms are based on finite-difference upwind, dimensionally split methods. The magnetohydrodynamics algorithms consist of the constrained transport method to preserve the divergence-free property of the magnetic field to machine accuracy, coupled to a method of characteristics for the evaluation of electromotive forces and Lorentz forces. Orbital advection is implemented, and an N-body solver is included to simulate planets or stars interacting with the gas. We present our implementation in detail and present a number of widely known tests for comparison purposes. One strength of FARGO3D is that it can run on either graphical processing units (GPUs) or central processing units (CPUs), achieving large speed-up with respect to CPU cores. We describe our implementation choices, which allow a user with no prior knowledge of GPU programming to develop new routines for CPUs, and have them translated automatically for GPUs.
GPU-Accelerated Foreground Segmentation and Labeling for Real-Time Video Surveillance
Directory of Open Access Journals (Sweden)
Wei Song
2016-09-01
Full Text Available Real-time and accurate background modeling is an important researching topic in the fields of remote monitoring and video surveillance. Meanwhile, effective foreground detection is a preliminary requirement and decision-making basis for sustainable energy management, especially in smart meters. The environment monitoring results provide a decision-making basis for energy-saving strategies. For real-time moving object detection in video, this paper applies a parallel computing technology to develop a feedback foreground–background segmentation method and a parallel connected component labeling (PCCL algorithm. In the background modeling method, pixel-wise color histograms in graphics processing unit (GPU memory is generated from sequential images. If a pixel color in the current image does not locate around the peaks of its histogram, it is segmented as a foreground pixel. From the foreground segmentation results, a PCCL algorithm is proposed to cluster the foreground pixels into several groups in order to distinguish separate blobs. Because the noisy spot and sparkle in the foreground segmentation results always contain a small quantity of pixels, the small blobs are removed as noise in order to refine the segmentation results. The proposed GPU-based image processing algorithms are implemented using the compute unified device architecture (CUDA toolkit. The testing results show a significant enhancement in both speed and accuracy.
GPU accelerated likelihoods for stereo-based articulated tracking
DEFF Research Database (Denmark)
Friborg, Rune Møllegaard; Hauberg, Søren; Erleben, Kenny
2010-01-01
than a traditional CPU implementation. We explain the non-intuitive steps required to attain an optimized GPU implementation, where the dominant part is to hide the memory latency effectively. Benchmarks show that computations which previously required several minutes, are now performed in few seconds....
SU-D-207-04: GPU-Based 4D Cone-Beam CT Reconstruction Using Adaptive Meshing Method
International Nuclear Information System (INIS)
Zhong, Z; Gu, X; Iyengar, P; Mao, W; Wang, J; Guo, X
2015-01-01
Purpose: Due to the limited number of projections at each phase, the image quality of a four-dimensional cone-beam CT (4D-CBCT) is often degraded, which decreases the accuracy of subsequent motion modeling. One of the promising methods is the simultaneous motion estimation and image reconstruction (SMEIR) approach. The objective of this work is to enhance the computational speed of the SMEIR algorithm using adaptive feature-based tetrahedral meshing and GPU-based parallelization. Methods: The first step is to generate the tetrahedral mesh based on the features of a reference phase 4D-CBCT, so that the deformation can be well captured and accurately diffused from the mesh vertices to voxels of the image volume. After the mesh generation, the updated motion model and other phases of 4D-CBCT can be obtained by matching the 4D-CBCT projection images at each phase with the corresponding forward projections of the deformed reference phase of 4D-CBCT. The entire process of this 4D-CBCT reconstruction method is implemented on GPU, resulting in significantly increasing the computational efficiency due to its tremendous parallel computing ability. Results: A 4D XCAT digital phantom was used to test the proposed mesh-based image reconstruction algorithm. The image Result shows both bone structures and inside of the lung are well-preserved and the tumor position can be well captured. Compared to the previous voxel-based CPU implementation of SMEIR, the proposed method is about 157 times faster for reconstructing a 10 -phase 4D-CBCT with dimension 256×256×150. Conclusion: The GPU-based parallel 4D CBCT reconstruction method uses the feature-based mesh for estimating motion model and demonstrates equivalent image Result with previous voxel-based SMEIR approach, with significantly improved computational speed
Multi-GPU hybrid programming accelerated three-dimensional phase-field model in binary alloy
Directory of Open Access Journals (Sweden)
Changsheng Zhu
2018-03-01
Full Text Available In the process of dendritic growth simulation, the computational efficiency and the problem scales have extremely important influence on simulation efficiency of three-dimensional phase-field model. Thus, seeking for high performance calculation method to improve the computational efficiency and to expand the problem scales has a great significance to the research of microstructure of the material. A high performance calculation method based on MPI+CUDA hybrid programming model is introduced. Multi-GPU is used to implement quantitative numerical simulations of three-dimensional phase-field model in binary alloy under the condition of multi-physical processes coupling. The acceleration effect of different GPU nodes on different calculation scales is explored. On the foundation of multi-GPU calculation model that has been introduced, two optimization schemes, Non-blocking communication optimization and overlap of MPI and GPU computing optimization, are proposed. The results of two optimization schemes and basic multi-GPU model are compared. The calculation results show that the use of multi-GPU calculation model can improve the computational efficiency of three-dimensional phase-field obviously, which is 13 times to single GPU, and the problem scales have been expanded to 8193. The feasibility of two optimization schemes is shown, and the overlap of MPI and GPU computing optimization has better performance, which is 1.7 times to basic multi-GPU model, when 21 GPUs are used.
Masset, Frédéric
2015-09-01
GFARGO is a GPU version of FARGO. It is written in C and C for CUDA and runs only on NVIDIA’s graphics cards. Though it corresponds to the standard, isothermal version of FARGO, not all functionnalities of the CPU version have been translated to CUDA. The code is available in single and double precision versions, the latter compatible with FERMI architectures. GFARGO can run on a graphics card connected to the display, allowing the user to see in real time how the fields evolve.
A parallel implementation of particle tracking with space charge effects on an INTEL iPSC/860
International Nuclear Information System (INIS)
Chang, L.; Bourianoff, G.; Cole, B.; Machida, S.
1993-05-01
Particle-tracking simulation is one of the scientific applications that is well-suited to parallel computations. At the Superconducting Super Collider, it has been theoretically and empirically demonstrated that particle tracking on a designed lattice can achieve very high parallel efficiency on a MIMD Intel iPSC/860 machine. The key to such success is the realization that the particles can be tracked independently without considering their interaction. The perfectly parallel nature of particle tracking is broken if the interaction effects between particles are included. The space charge introduces an electromagnetic force that will affect the motion of tracked particles in 3-D space. For accurate modeling of the beam dynamics with space charge effects, one needs to solve three-dimensional Maxwell field equations, usually by a particle-in-cell (PIC) algorithm. This will require each particle to communicate with its neighbor grids to compute the momentum changes at each time step. It is expected that the 3-D PIC method will degrade parallel efficiency of particle-tracking implementation on any parallel computer. In this paper, we describe an efficient scheme for implementing particle tracking with space charge effects on an INTEL iPSC/860 machine. Experimental results show that a parallel efficiency of 75% can be obtained
Graf, Daniel; Beuerle, Matthias; Schurkus, Henry F; Luenser, Arne; Savasci, Gökcen; Ochsenfeld, Christian
2018-05-08
An efficient algorithm for calculating the random phase approximation (RPA) correlation energy is presented that is as accurate as the canonical molecular orbital resolution-of-the-identity RPA (RI-RPA) with the important advantage of an effective linear-scaling behavior (instead of quartic) for large systems due to a formulation in the local atomic orbital space. The high accuracy is achieved by utilizing optimized minimax integration schemes and the local Coulomb metric attenuated by the complementary error function for the RI approximation. The memory bottleneck of former atomic orbital (AO)-RI-RPA implementations ( Schurkus, H. F.; Ochsenfeld, C. J. Chem. Phys. 2016 , 144 , 031101 and Luenser, A.; Schurkus, H. F.; Ochsenfeld, C. J. Chem. Theory Comput. 2017 , 13 , 1647 - 1655 ) is addressed by precontraction of the large 3-center integral matrix with the Cholesky factors of the ground state density reducing the memory requirements of that matrix by a factor of [Formula: see text]. Furthermore, we present a parallel implementation of our method, which not only leads to faster RPA correlation energy calculations but also to a scalable decrease in memory requirements, opening the door for investigations of large molecules even on small- to medium-sized computing clusters. Although it is known that AO methods are highly efficient for extended systems, where sparsity allows for reaching the linear-scaling regime, we show that our work also extends the applicability when considering highly delocalized systems for which no linear scaling can be achieved. As an example, the interlayer distance of two covalent organic framework pore fragments (comprising 384 atoms in total) is analyzed.
Massively parallel simulator of optical coherence tomography of inhomogeneous turbid media.
Malektaji, Siavash; Lima, Ivan T; Escobar I, Mauricio R; Sherif, Sherif S
2017-10-01
An accurate and practical simulator for Optical Coherence Tomography (OCT) could be an important tool to study the underlying physical phenomena in OCT such as multiple light scattering. Recently, many researchers have investigated simulation of OCT of turbid media, e.g., tissue, using Monte Carlo methods. The main drawback of these earlier simulators is the long computational time required to produce accurate results. We developed a massively parallel simulator of OCT of inhomogeneous turbid media that obtains both Class I diffusive reflectivity, due to ballistic and quasi-ballistic scattered photons, and Class II diffusive reflectivity due to multiply scattered photons. This Monte Carlo-based simulator is implemented on graphic processing units (GPUs), using the Compute Unified Device Architecture (CUDA) platform and programming model, to exploit the parallel nature of propagation of photons in tissue. It models an arbitrary shaped sample medium as a tetrahedron-based mesh and uses an advanced importance sampling scheme. This new simulator speeds up simulations of OCT of inhomogeneous turbid media by about two orders of magnitude. To demonstrate this result, we have compared the computation times of our new parallel simulator and its serial counterpart using two samples of inhomogeneous turbid media. We have shown that our parallel implementation reduced simulation time of OCT of the first sample medium from 407 min to 92 min by using a single GPU card, to 12 min by using 8 GPU cards and to 7 min by using 16 GPU cards. For the second sample medium, the OCT simulation time was reduced from 209 h to 35.6 h by using a single GPU card, and to 4.65 h by using 8 GPU cards, and to only 2 h by using 16 GPU cards. Therefore our new parallel simulator is considerably more practical to use than its central processing unit (CPU)-based counterpart. Our new parallel OCT simulator could be a practical tool to study the different physical phenomena underlying OCT
Directory of Open Access Journals (Sweden)
Kim De Leeneer
Full Text Available Despite improvements in terms of sequence quality and price per basepair, Sanger sequencing remains restricted to screening of individual disease genes. The development of massively parallel sequencing (MPS technologies heralded an era in which molecular diagnostics for multigenic disorders becomes reality. Here, we outline different PCR amplification based strategies for the screening of a multitude of genes in a patient cohort. We performed a thorough evaluation in terms of set-up, coverage and sequencing variants on the data of 10 GS-FLX experiments (over 200 patients. Crucially, we determined the actual coverage that is required for reliable diagnostic results using MPS, and provide a tool to calculate the number of patients that can be screened in a single run. Finally, we provide an overview of factors contributing to false negative or false positive mutation calls and suggest ways to maximize sensitivity and specificity, both important in a routine setting. By describing practical strategies for screening of multigenic disorders in a multitude of samples and providing answers to questions about minimum required coverage, the number of patients that can be screened in a single run and the factors that may affect sensitivity and specificity we hope to facilitate the implementation of MPS technology in molecular diagnostics.
Zaidi, H; Morel, Christian
1998-01-01
This paper describes the implementation of the Eidolon Monte Carlo program designed to simulate fully three-dimensional (3D) cylindrical positron tomographs on a MIMD parallel architecture. The original code was written in Objective-C and developed under the NeXTSTEP development environment. Different steps involved in porting the software on a parallel architecture based on PowerPC 604 processors running under AIX 4.1 are presented. Basic aspects and strategies of running Monte Carlo calculations on parallel computers are described. A linear decrease of the computing time was achieved with the number of computing nodes. The improved time performances resulting from parallelisation of the Monte Carlo calculations makes it an attractive tool for modelling photon transport in 3D positron tomography. The parallelisation paradigm used in this work is independent from the chosen parallel architecture
DEFF Research Database (Denmark)
The following topics are dealt with: parallel scientific computing; numerical algorithms; parallel nonnumerical algorithms; cloud computing; evolutionary computing; metaheuristics; applied mathematics; GPU computing; multicore systems; hybrid architectures; hierarchical parallelism; HPC systems......; power monitoring; energy monitoring; and distributed computing....
ALICE HLT high speed tracking on GPU
Gorbunov, Sergey; Aamodt, Kenneth; Alt, Torsten; Appelshauser, Harald; Arend, Andreas; Bach, Matthias; Becker, Bruce; Bottger, Stefan; Breitner, Timo; Busching, Henner; Chattopadhyay, Sukalyan; Cleymans, Jean; Cicalo, Corrado; Das, Indranil; Djuvsland, Oystein; Engel, Heiko; Erdal, Hege Austrheim; Fearick, Roger; Haaland, Oystein Senneset; Hille, Per Thomas; Kalcher, Sebastian; Kanaki, Kalliopi; Kebschull, Udo Wolfgang; Kisel, Ivan; Kretz, Matthias; Lara, Camillo; Lindal, Sven; Lindenstruth, Volker; Masoodi, Arshad Ahmad; Ovrebekk, Gaute; Panse, Ralf; Peschek, Jorg; Ploskon, Mateusz; Pocheptsov, Timur; Ram, Dinesh; Rascanu, Theodor; Richter, Matthias; Rohrich, Dieter; Ronchetti, Federico; Skaali, Bernhard; Smorholm, Olav; Stokkevag, Camilla; Steinbeck, Timm Morten; Szostak, Artur; Thader, Jochen; Tveter, Trine; Ullaland, Kjetil; Vilakazi, Zeblon; Weis, Robert; Yin, Zhong-Bao; Zelnicek, Pierre
2011-01-01
The on-line event reconstruction in ALICE is performed by the High Level Trigger, which should process up to 2000 events per second in proton-proton collisions and up to 300 central events per second in heavy-ion collisions, corresponding to an inp ut data stream of 30 GB/s. In order to fulfill the time requirements, a fast on-line tracker has been developed. The algorithm combines a Cellular Automaton method being used for a fast pattern recognition and the Kalman Filter method for fitting of found trajectories and for the final track selection. The tracker was adapted to run on Graphics Processing Units (GPU) using the NVIDIA Compute Unified Device Architecture (CUDA) framework. The implementation of the algorithm had to be adjusted at many points to allow for an efficient usage of the graphics cards. In particular, achieving a good overall workload for many processor cores, efficient transfer to and from the GPU, as well as optimized utilization of the different memories the GPU offers turned out to be cri...
A GPU-based calculation using the three-dimensional FDTD method for electromagnetic field analysis.
Nagaoka, Tomoaki; Watanabe, Soichi
2010-01-01
Numerical simulations with the numerical human model using the finite-difference time domain (FDTD) method have recently been performed frequently in a number of fields in biomedical engineering. However, the FDTD calculation runs too slowly. We focus, therefore, on general purpose programming on the graphics processing unit (GPGPU). The three-dimensional FDTD method was implemented on the GPU using Compute Unified Device Architecture (CUDA). In this study, we used the NVIDIA Tesla C1060 as a GPGPU board. The performance of the GPU is evaluated in comparison with the performance of a conventional CPU and a vector supercomputer. The results indicate that three-dimensional FDTD calculations using a GPU can significantly reduce run time in comparison with that using a conventional CPU, even a native GPU implementation of the three-dimensional FDTD method, while the GPU/CPU speed ratio varies with the calculation domain and thread block size.
Simulation of isothermal multi-phase fuel-coolant interaction using MPS method with GPU acceleration
Energy Technology Data Exchange (ETDEWEB)
Gou, W.; Zhang, S.; Zheng, Y. [Zhejiang Univ., Hangzhou (China). Center for Engineering and Scientific Computation
2016-07-15
The energetic fuel-coolant interaction (FCI) has been one of the primary safety concerns in nuclear power plants. Graphical processing unit (GPU) implementation of the moving particle semi-implicit (MPS) method is presented and used to simulate the fuel coolant interaction problem. The governing equations are discretized with the particle interaction model of MPS. Detailed implementation on single-GPU is introduced. The three-dimensional broken dam is simulated to verify the developed GPU acceleration MPS method. The proposed GPU acceleration algorithm and developed code are then used to simulate the FCI problem. As a summary of results, the developed GPU-MPS method showed a good agreement with the experimental observation and theoretical prediction.
Numerical simulation of lava flow using a GPU SPH model
Directory of Open Access Journals (Sweden)
Eugenio Rustico
2011-12-01
Full Text Available A smoothed particle hydrodynamics (SPH method for lava-flow modeling was implemented on a graphical processing unit (GPU using the compute unified device architecture (CUDA developed by NVIDIA. This resulted in speed-ups of up to two orders of magnitude. The three-dimensional model can simulate lava flow on a real topography with free-surface, non-Newtonian fluids, and with phase change. The entire SPH code has three main components, neighbor list construction, force computation, and integration of the equation of motion, and it is computed on the GPU, fully exploiting the computational power. The simulation speed achieved is one to two orders of magnitude faster than the equivalent central processing unit (CPU code. This GPU implementation of SPH allows high resolution SPH modeling in hours and days, rather than in weeks and months, on inexpensive and readily available hardware.
STEM image simulation with hybrid CPU/GPU programming
International Nuclear Information System (INIS)
Yao, Y.; Ge, B.H.; Shen, X.; Wang, Y.G.; Yu, R.C.
2016-01-01
STEM image simulation is achieved via hybrid CPU/GPU programming under parallel algorithm architecture to speed up calculation on a personal computer (PC). To utilize the calculation power of a PC fully, the simulation is performed using the GPU core and multi-CPU cores at the same time to significantly improve efficiency. GaSb and an artificial GaSb/InAs interface with atom diffusion have been used to verify the computation. - Highlights: • STEM image simulation is achieved by hybrid CPU/GPU programming under parallel algorithm architecture to speed up the calculation in the personal computer (PC). • In order to fully utilize the calculation power of the PC, the simulation is performed by GPU core and multi-CPU cores at the same time so efficiency is improved significantly. • GaSb and artificial GaSb/InAs interface with atom diffusion have been used to verify the computation. The results reveal some unintuitive phenomena about the contrast variation with the atom numbers.
STEM image simulation with hybrid CPU/GPU programming
Energy Technology Data Exchange (ETDEWEB)
Yao, Y., E-mail: yaoyuan@iphy.ac.cn; Ge, B.H.; Shen, X.; Wang, Y.G.; Yu, R.C.
2016-07-15
STEM image simulation is achieved via hybrid CPU/GPU programming under parallel algorithm architecture to speed up calculation on a personal computer (PC). To utilize the calculation power of a PC fully, the simulation is performed using the GPU core and multi-CPU cores at the same time to significantly improve efficiency. GaSb and an artificial GaSb/InAs interface with atom diffusion have been used to verify the computation. - Highlights: • STEM image simulation is achieved by hybrid CPU/GPU programming under parallel algorithm architecture to speed up the calculation in the personal computer (PC). • In order to fully utilize the calculation power of the PC, the simulation is performed by GPU core and multi-CPU cores at the same time so efficiency is improved significantly. • GaSb and artificial GaSb/InAs interface with atom diffusion have been used to verify the computation. The results reveal some unintuitive phenomena about the contrast variation with the atom numbers.
Vulnerable GPU Memory Management: Towards Recovering Raw Data from GPU
Directory of Open Access Journals (Sweden)
Zhou Zhe
2017-04-01
Full Text Available According to previous reports, information could be leaked from GPU memory; however, the security implications of such a threat were mostly over-looked, because only limited information could be indirectly extracted through side-channel attacks. In this paper, we propose a novel algorithm for recovering raw data directly from the GPU memory residues of many popular applications such as Google Chrome and Adobe PDF reader. Our algorithm enables harvesting highly sensitive information including credit card numbers and email contents from GPU memory residues. Evaluation results also indicate that nearly all GPU-accelerated applications are vulnerable to such attacks, and adversaries can launch attacks without requiring any special privileges both on traditional multi-user operating systems, and emerging cloud computing scenarios.
An efficient implementation of parallel molecular dynamics method on SMP cluster architecture
International Nuclear Information System (INIS)
Suzuki, Masaaki; Okuda, Hiroshi; Yagawa, Genki
2003-01-01
The authors have applied MPI/OpenMP hybrid parallel programming model to parallelize a molecular dynamics (MD) method on a symmetric multiprocessor (SMP) cluster architecture. In that architecture, it can be expected that the hybrid parallel programming model, which uses the message passing library such as MPI for inter-SMP node communication and the loop directive such as OpenMP for intra-SNP node parallelization, is the most effective one. In this study, the parallel performance of the hybrid style has been compared with that of conventional flat parallel programming style, which uses only MPI, both in cases the fast multipole method (FMM) is employed for computing long-distance interactions and that is not employed. The computer environments used here are Hitachi SR8000/MPP placed at the University of Tokyo. The results of calculation are as follows. Without FMM, the parallel efficiency using 16 SMP nodes (128 PEs) is: 90% with the hybrid style, 75% with the flat-MPI style for MD simulation with 33,402 atoms. With FMM, the parallel efficiency using 16 SMP nodes (128 PEs) is: 60% with the hybrid style, 48% with the flat-MPI style for MD simulation with 117,649 atoms. (author)
GPU-BSM: a GPU-based tool to map bisulfite-treated reads.
Directory of Open Access Journals (Sweden)
Andrea Manconi
Full Text Available Cytosine DNA methylation is an epigenetic mark implicated in several biological processes. Bisulfite treatment of DNA is acknowledged as the gold standard technique to study methylation. This technique introduces changes in the genomic DNA by converting cytosines to uracils while 5-methylcytosines remain nonreactive. During PCR amplification 5-methylcytosines are amplified as cytosine, whereas uracils and thymines as thymine. To detect the methylation levels, reads treated with the bisulfite must be aligned against a reference genome. Mapping these reads to a reference genome represents a significant computational challenge mainly due to the increased search space and the loss of information introduced by the treatment. To deal with this computational challenge we devised GPU-BSM, a tool based on modern Graphics Processing Units. Graphics Processing Units are hardware accelerators that are increasingly being used successfully to accelerate general-purpose scientific applications. GPU-BSM is a tool able to map bisulfite-treated reads from whole genome bisulfite sequencing and reduced representation bisulfite sequencing, and to estimate methylation levels, with the goal of detecting methylation. Due to the massive parallelization obtained by exploiting graphics cards, GPU-BSM aligns bisulfite-treated reads faster than other cutting-edge solutions, while outperforming most of them in terms of unique mapped reads.
Cao, Jianfang; Chen, Lichao; Wang, Min; Tian, Yun
2018-01-01
The Canny operator is widely used to detect edges in images. However, as the size of the image dataset increases, the edge detection performance of the Canny operator decreases and its runtime becomes excessive. To improve the runtime and edge detection performance of the Canny operator, in this paper, we propose a parallel design and implementation for an Otsu-optimized Canny operator using a MapReduce parallel programming model that runs on the Hadoop platform. The Otsu algorithm is used to optimize the Canny operator's dual threshold and improve the edge detection performance, while the MapReduce parallel programming model facilitates parallel processing for the Canny operator to solve the processing speed and communication cost problems that occur when the Canny edge detection algorithm is applied to big data. For the experiments, we constructed datasets of different scales from the Pascal VOC2012 image database. The proposed parallel Otsu-Canny edge detection algorithm performs better than other traditional edge detection algorithms. The parallel approach reduced the running time by approximately 67.2% on a Hadoop cluster architecture consisting of 5 nodes with a dataset of 60,000 images. Overall, our approach system speeds up the system by approximately 3.4 times when processing large-scale datasets, which demonstrates the obvious superiority of our method. The proposed algorithm in this study demonstrates both better edge detection performance and improved time performance.
Li, Chuan; Petukh, Marharyta; Li, Lin; Alexov, Emil
2013-08-15
Due to the enormous importance of electrostatics in molecular biology, calculating the electrostatic potential and corresponding energies has become a standard computational approach for the study of biomolecules and nano-objects immersed in water and salt phase or other media. However, the electrostatics of large macromolecules and macromolecular complexes, including nano-objects, may not be obtainable via explicit methods and even the standard continuum electrostatics methods may not be applicable due to high computational time and memory requirements. Here, we report further development of the parallelization scheme reported in our previous work (Li, et al., J. Comput. Chem. 2012, 33, 1960) to include parallelization of the molecular surface and energy calculations components of the algorithm. The parallelization scheme utilizes different approaches such as space domain parallelization, algorithmic parallelization, multithreading, and task scheduling, depending on the quantity being calculated. This allows for efficient use of the computing resources of the corresponding computer cluster. The parallelization scheme is implemented in the popular software DelPhi and results in speedup of several folds. As a demonstration of the efficiency and capability of this methodology, the electrostatic potential, and electric field distributions are calculated for the bovine mitochondrial supercomplex illustrating their complex topology, which cannot be obtained by modeling the supercomplex components alone. Copyright © 2013 Wiley Periodicals, Inc.
Dewaraja, Yuni K; Ljungberg, Michael; Majumdar, Amitava; Bose, Abhijit; Koral, Kenneth F
2002-02-01
This paper reports the implementation of the SIMIND Monte Carlo code on an IBM SP2 distributed memory parallel computer. Basic aspects of running Monte Carlo particle transport calculations on parallel architectures are described. Our parallelization is based on equally partitioning photons among the processors and uses the Message Passing Interface (MPI) library for interprocessor communication and the Scalable Parallel Random Number Generator (SPRNG) to generate uncorrelated random number streams. These parallelization techniques are also applicable to other distributed memory architectures. A linear increase in computing speed with the number of processors is demonstrated for up to 32 processors. This speed-up is especially significant in Single Photon Emission Computed Tomography (SPECT) simulations involving higher energy photon emitters, where explicit modeling of the phantom and collimator is required. For (131)I, the accuracy of the parallel code is demonstrated by comparing simulated and experimental SPECT images from a heart/thorax phantom. Clinically realistic SPECT simulations using the voxel-man phantom are carried out to assess scatter and attenuation correction.
Directory of Open Access Journals (Sweden)
Wang Kai
2011-05-01
Full Text Available Abstract Background Gene-gene interaction in genetic association studies is computationally intensive when a large number of SNPs are involved. Most of the latest Central Processing Units (CPUs have multiple cores, whereas Graphics Processing Units (GPUs also have hundreds of cores and have been recently used to implement faster scientific software. However, currently there are no genetic analysis software packages that allow users to fully utilize the computing power of these multi-core devices for genetic interaction analysis for binary traits. Findings Here we present a novel software package GENIE, which utilizes the power of multiple GPU or CPU processor cores to parallelize the interaction analysis. GENIE reads an entire genetic association study dataset into memory and partitions the dataset into fragments with non-overlapping sets of SNPs. For each fragment, GENIE analyzes: 1 the interaction of SNPs within it in parallel, and 2 the interaction between the SNPs of the current fragment and other fragments in parallel. We tested GENIE on a large-scale candidate gene study on high-density lipoprotein cholesterol. Using an NVIDIA Tesla C1060 graphics card, the GPU mode of GENIE achieves a speedup of 27 times over its single-core CPU mode run. Conclusions GENIE is open-source, economical, user-friendly, and scalable. Since the computing power and memory capacity of graphics cards are increasing rapidly while their cost is going down, we anticipate that GENIE will achieve greater speedups with faster GPU cards. Documentation, source code, and precompiled binaries can be downloaded from http://www.cceb.upenn.edu/~mli/software/GENIE/.
Samaké, Abdoulaye; Rampal, Pierre; Bouillon, Sylvain; Ólason, Einar
2017-12-01
We present a parallel implementation framework for a new dynamic/thermodynamic sea-ice model, called neXtSIM, based on the Elasto-Brittle rheology and using an adaptive mesh. The spatial discretisation of the model is done using the finite-element method. The temporal discretisation is semi-implicit and the advection is achieved using either a pure Lagrangian scheme or an Arbitrary Lagrangian Eulerian scheme (ALE). The parallel implementation presented here focuses on the distributed-memory approach using the message-passing library MPI. The efficiency and the scalability of the parallel algorithms are illustrated by the numerical experiments performed using up to 500 processor cores of a cluster computing system. The performance obtained by the proposed parallel implementation of the neXtSIM code is shown being sufficient to perform simulations for state-of-the-art sea ice forecasting and geophysical process studies over geographical domain of several millions squared kilometers like the Arctic region.
International Nuclear Information System (INIS)
Nieto, J.; Sanz, D.; Guillén, P.; Esquembri, S.; Arcas, G. de; Ruiz, M.; Vega, J.; Castro, R.
2016-01-01
Highlights: • To test an image acquisition and processing system for Camera Link devices based in a FPGA, compliant with ITER fast controllers. • To move data acquired from the set NI1483-NIPXIe7966R directly to a NVIDIA GPU using NVIDIA GPUDirect RDMA technology. • To obtain a methodology to include GPUs processing in ITER Fast Plant Controllers, using EPICS integration through Nominal Device Support (NDS). - Abstract: The two dominant technologies that are being used in real time image processing are Field Programmable Gate Array (FPGA) and Graphical Processor Unit (GPU) due to their algorithm parallelization capabilities. But not much work has been done to standardize how these technologies can be integrated in data acquisition systems, where control and supervisory requirements are in place, such as ITER (International Thermonuclear Experimental Reactor). This work proposes an architecture, and a development methodology, to develop image acquisition and processing systems based on FPGAs and GPUs compliant with ITER fast controller solutions. A use case based on a Camera Link device connected to an FPGA DAQ device (National Instruments FlexRIO technology), and a NVIDIA Tesla GPU series card has been developed and tested. The architecture proposed has been designed to optimize system performance by minimizing data transfer operations and CPU intervention thanks to the use of NVIDIA GPUDirect RDMA and DMA technologies. This allows moving the data directly between the different hardware elements (FPGA DAQ-GPU-CPU) avoiding CPU intervention and therefore the use of intermediate CPU memory buffers. A special effort has been put to provide a development methodology that, maintaining the highest possible abstraction from the low level implementation details, allows obtaining solutions that conform to CODAC Core System standards by providing EPICS and Nominal Device Support.
Energy Technology Data Exchange (ETDEWEB)
Nieto, J., E-mail: jnieto@sec.upm.es [Grupo de Investigación en Instrumentación y Acústica Aplicada, Universidad Politécnica de Madrid, Crta. Valencia Km-7, Madrid 28031 (Spain); Sanz, D.; Guillén, P.; Esquembri, S.; Arcas, G. de; Ruiz, M. [Grupo de Investigación en Instrumentación y Acústica Aplicada, Universidad Politécnica de Madrid, Crta. Valencia Km-7, Madrid 28031 (Spain); Vega, J.; Castro, R. [Asociación EURATOM/CIEMAT para Fusión, Madrid (Spain)
2016-11-15
Highlights: • To test an image acquisition and processing system for Camera Link devices based in a FPGA, compliant with ITER fast controllers. • To move data acquired from the set NI1483-NIPXIe7966R directly to a NVIDIA GPU using NVIDIA GPUDirect RDMA technology. • To obtain a methodology to include GPUs processing in ITER Fast Plant Controllers, using EPICS integration through Nominal Device Support (NDS). - Abstract: The two dominant technologies that are being used in real time image processing are Field Programmable Gate Array (FPGA) and Graphical Processor Unit (GPU) due to their algorithm parallelization capabilities. But not much work has been done to standardize how these technologies can be integrated in data acquisition systems, where control and supervisory requirements are in place, such as ITER (International Thermonuclear Experimental Reactor). This work proposes an architecture, and a development methodology, to develop image acquisition and processing systems based on FPGAs and GPUs compliant with ITER fast controller solutions. A use case based on a Camera Link device connected to an FPGA DAQ device (National Instruments FlexRIO technology), and a NVIDIA Tesla GPU series card has been developed and tested. The architecture proposed has been designed to optimize system performance by minimizing data transfer operations and CPU intervention thanks to the use of NVIDIA GPUDirect RDMA and DMA technologies. This allows moving the data directly between the different hardware elements (FPGA DAQ-GPU-CPU) avoiding CPU intervention and therefore the use of intermediate CPU memory buffers. A special effort has been put to provide a development methodology that, maintaining the highest possible abstraction from the low level implementation details, allows obtaining solutions that conform to CODAC Core System standards by providing EPICS and Nominal Device Support.
GPU applications for data processing
Energy Technology Data Exchange (ETDEWEB)
Vladymyrov, Mykhailo, E-mail: mykhailo.vladymyrov@cern.ch [LPI - Lebedev Physical Institute of the Russian Academy of Sciences, RUS-119991 Moscow (Russian Federation); Aleksandrov, Andrey [LPI - Lebedev Physical Institute of the Russian Academy of Sciences, RUS-119991 Moscow (Russian Federation); INFN sezione di Napoli, I-80125 Napoli (Italy); Tioukov, Valeri [INFN sezione di Napoli, I-80125 Napoli (Italy)
2015-12-31
Modern experiments that use nuclear photoemulsion imply fast and efficient data acquisition from the emulsion can be performed. The new approaches in developing scanning systems require real-time processing of large amount of data. Methods that use Graphical Processing Unit (GPU) computing power for emulsion data processing are presented here. It is shown how the GPU-accelerated emulsion processing helped us to rise the scanning speed by factor of nine.
Ultrafast convolution/superposition using tabulated and exponential kernels on GPU
Energy Technology Data Exchange (ETDEWEB)
Chen Quan; Chen Mingli; Lu Weiguo [TomoTherapy Inc., 1240 Deming Way, Madison, Wisconsin 53717 (United States)
2011-03-15
Purpose: Collapsed-cone convolution/superposition (CCCS) dose calculation is the workhorse for IMRT dose calculation. The authors present a novel algorithm for computing CCCS dose on the modern graphic processing unit (GPU). Methods: The GPU algorithm includes a novel TERMA calculation that has no write-conflicts and has linear computation complexity. The CCCS algorithm uses either tabulated or exponential cumulative-cumulative kernels (CCKs) as reported in literature. The authors have demonstrated that the use of exponential kernels can reduce the computation complexity by order of a dimension and achieve excellent accuracy. Special attentions are paid to the unique architecture of GPU, especially the memory accessing pattern, which increases performance by more than tenfold. Results: As a result, the tabulated kernel implementation in GPU is two to three times faster than other GPU implementations reported in literature. The implementation of CCCS showed significant speedup on GPU over single core CPU. On tabulated CCK, speedups as high as 70 are observed; on exponential CCK, speedups as high as 90 are observed. Conclusions: Overall, the GPU algorithm using exponential CCK is 1000-3000 times faster over a highly optimized single-threaded CPU implementation using tabulated CCK, while the dose differences are within 0.5% and 0.5 mm. This ultrafast CCCS algorithm will allow many time-sensitive applications to use accurate dose calculation.
GPU-based cone beam computed tomography.
Noël, Peter B; Walczak, Alan M; Xu, Jinhui; Corso, Jason J; Hoffmann, Kenneth R; Schafer, Sebastian
2010-06-01
The use of cone beam computed tomography (CBCT) is growing in the clinical arena due to its ability to provide 3D information during interventions, its high diagnostic quality (sub-millimeter resolution), and its short scanning times (60 s). In many situations, the short scanning time of CBCT is followed by a time-consuming 3D reconstruction. The standard reconstruction algorithm for CBCT data is the filtered backprojection, which for a volume of size 256(3) takes up to 25 min on a standard system. Recent developments in the area of Graphic Processing Units (GPUs) make it possible to have access to high-performance computing solutions at a low cost, allowing their use in many scientific problems. We have implemented an algorithm for 3D reconstruction of CBCT data using the Compute Unified Device Architecture (CUDA) provided by NVIDIA (NVIDIA Corporation, Santa Clara, California), which was executed on a NVIDIA GeForce GTX 280. Our implementation results in improved reconstruction times from minutes, and perhaps hours, to a matter of seconds, while also giving the clinician the ability to view 3D volumetric data at higher resolutions. We evaluated our implementation on ten clinical data sets and one phantom data set to observe if differences occur between CPU and GPU-based reconstructions. By using our approach, the computation time for 256(3) is reduced from 25 min on the CPU to 3.2 s on the GPU. The GPU reconstruction time for 512(3) volumes is 8.5 s. Copyright 2009 Elsevier Ireland Ltd. All rights reserved.
A Real-Time Capable Software-Defined Receiver Using GPU for Adaptive Anti-Jam GPS Sensors
Seo, Jiwon; Chen, Yu-Hsuan; De Lorenzo, David S.; Lo, Sherman; Enge, Per; Akos, Dennis; Lee, Jiyun
2011-01-01
Due to their weak received signal power, Global Positioning System (GPS) signals are vulnerable to radio frequency interference. Adaptive beam and null steering of the gain pattern of a GPS antenna array can significantly increase the resistance of GPS sensors to signal interference and jamming. Since adaptive array processing requires intensive computational power, beamsteering GPS receivers were usually implemented using hardware such as field-programmable gate arrays (FPGAs). However, a software implementation using general-purpose processors is much more desirable because of its flexibility and cost effectiveness. This paper presents a GPS software-defined radio (SDR) with adaptive beamsteering capability for anti-jam applications. The GPS SDR design is based on an optimized desktop parallel processing architecture using a quad-core Central Processing Unit (CPU) coupled with a new generation Graphics Processing Unit (GPU) having massively parallel processors. This GPS SDR demonstrates sufficient computational capability to support a four-element antenna array and future GPS L5 signal processing in real time. After providing the details of our design and optimization schemes for future GPU-based GPS SDR developments, the jamming resistance of our GPS SDR under synthetic wideband jamming is presented. Since the GPS SDR uses commercial-off-the-shelf hardware and processors, it can be easily adopted in civil GPS applications requiring anti-jam capabilities. PMID:22164116
A Real-Time Capable Software-Defined Receiver Using GPU for Adaptive Anti-Jam GPS Sensors
Directory of Open Access Journals (Sweden)
Dennis Akos
2011-09-01
Full Text Available Due to their weak received signal power, Global Positioning System (GPS signals are vulnerable to radio frequency interference. Adaptive beam and null steering of the gain pattern of a GPS antenna array can significantly increase the resistance of GPS sensors to signal interference and jamming. Since adaptive array processing requires intensive computational power, beamsteering GPS receivers were usually implemented using hardware such as field-programmable gate arrays (FPGAs. However, a software implementation using general-purpose processors is much more desirable because of its flexibility and cost effectiveness. This paper presents a GPS software-defined radio (SDR with adaptive beamsteering capability for anti-jam applications. The GPS SDR design is based on an optimized desktop parallel processing architecture using a quad-core Central Processing Unit (CPU coupled with a new generation Graphics Processing Unit (GPU having massively parallel processors. This GPS SDR demonstrates sufficient computational capability to support a four-element antenna array and future GPS L5 signal processing in real time. After providing the details of our design and optimization schemes for future GPU-based GPS SDR developments, the jamming resistance of our GPS SDR under synthetic wideband jamming is presented. Since the GPS SDR uses commercial-off-the-shelf hardware and processors, it can be easily adopted in civil GPS applications requiring anti-jam capabilities.
Magee, Daniel J.; Niemeyer, Kyle E.
2018-03-01
The expedient design of precision components in aerospace and other high-tech industries requires simulations of physical phenomena often described by partial differential equations (PDEs) without exact solutions. Modern design problems require simulations with a level of resolution difficult to achieve in reasonable amounts of time-even in effectively parallelized solvers. Though the scale of the problem relative to available computing power is the greatest impediment to accelerating these applications, significant performance gains can be achieved through careful attention to the details of memory communication and access. The swept time-space decomposition rule reduces communication between sub-domains by exhausting the domain of influence before communicating boundary values. Here we present a GPU implementation of the swept rule, which modifies the algorithm for improved performance on this processing architecture by prioritizing use of private (shared) memory, avoiding interblock communication, and overwriting unnecessary values. It shows significant improvement in the execution time of finite-difference solvers for one-dimensional unsteady PDEs, producing speedups of 2 - 9 × for a range of problem sizes, respectively, compared with simple GPU versions and 7 - 300 × compared with parallel CPU versions. However, for a more sophisticated one-dimensional system of equations discretized with a second-order finite-volume scheme, the swept rule performs 1.2 - 1.9 × worse than a standard implementation for all problem sizes.
Limpanuparb, Taweetham; Milthorpe, Josh; Rendell, Alistair P
2014-10-30
Use of the modern parallel programming language X10 for computing long-range Coulomb and exchange interactions is presented. By using X10, a partitioned global address space language with support for task parallelism and the explicit representation of data locality, the resolution of the Ewald operator can be parallelized in a straightforward manner including use of both intranode and internode parallelism. We evaluate four different schemes for dynamic load balancing of integral calculation using X10's work stealing runtime, and report performance results for long-range HF energy calculation of large molecule/high quality basis running on up to 1024 cores of a high performance cluster machine. Copyright © 2014 Wiley Periodicals, Inc.
Parallel implementation of a dynamic unstructured chimera method in the DLR finite volume TAU-code
International Nuclear Information System (INIS)
Madrane, A.; Raichle, A.; Stuermer, A.
2004-01-01
Aerodynamic problems involving moving geometries have many applications, including store separation, high-speed train entering into a tunnel, simulation of full configurations of the helicopter and fast maneuverability. Overset grid method offers the option of calculating these procedures. The solution process uses a grid system that discretizes the problem domain by using separately generated but overlapping unstructured grids that update and exchange boundary information through interpolation. However, such computations are complicated and time consuming. Parallel computing offers a very effective way to improve the productivity in doing computational fluid dynamics (CFD). Therefore the purpose of this study is to develop an efficient parallel computation algorithm for analyzing the flowfield of complex geometries using overset grids method. The strategy adopted in the parallelization of the overset grids method including the use of data structures and communication, is described. Numerical results are presented to demonstrate the efficiency of the resulting parallel overset grids method. (author)
Parallel implementation of a dynamic unstructured chimera method in the DLR finite volume TAU-code
Energy Technology Data Exchange (ETDEWEB)
Madrane, A.; Raichle, A.; Stuermer, A. [German Aerospace Center, DLR, Numerical Methods, Inst. of Aerodynamics and Flow Technology, Braunschweig (Germany)]. E-mail: aziz.madrane@dlr.de
2004-07-01
Aerodynamic problems involving moving geometries have many applications, including store separation, high-speed train entering into a tunnel, simulation of full configurations of the helicopter and fast maneuverability. Overset grid method offers the option of calculating these procedures. The solution process uses a grid system that discretizes the problem domain by using separately generated but overlapping unstructured grids that update and exchange boundary information through interpolation. However, such computations are complicated and time consuming. Parallel computing offers a very effective way to improve the productivity in doing computational fluid dynamics (CFD). Therefore the purpose of this study is to develop an efficient parallel computation algorithm for analyzing the flowfield of complex geometries using overset grids method. The strategy adopted in the parallelization of the overset grids method including the use of data structures and communication, is described. Numerical results are presented to demonstrate the efficiency of the resulting parallel overset grids method. (author)
Accelerating Pseudo-Random Number Generator for MCNP on GPU
Gong, Chunye; Liu, Jie; Chi, Lihua; Hu, Qingfeng; Deng, Li; Gong, Zhenghu
2010-09-01
Pseudo-random number generators (PRNG) are intensively used in many stochastic algorithms in particle simulations, artificial neural networks and other scientific computation. The PRNG in Monte Carlo N-Particle Transport Code (MCNP) requires long period, high quality, flexible jump and fast enough. In this paper, we implement such a PRNG for MCNP on NVIDIA's GTX200 Graphics Processor Units (GPU) using CUDA programming model. Results shows that 3.80 to 8.10 times speedup are achieved compared with 4 to 6 cores CPUs and more than 679.18 million double precision random numbers can be generated per second on GPU.
Hagan, Aaron; Sawant, Amit; Folkerts, Michael; Modiri, Arezoo
2018-01-01
We report on the design, implementation and characterization of a multi-graphic processing unit (GPU) computational platform for higher-order optimization in radiotherapy treatment planning. In collaboration with a commercial vendor (Varian Medical Systems, Palo Alto, CA), a research prototype GPU-enabled Eclipse (V13.6) workstation was configured. The hardware consisted of dual 8-core Xeon processors, 256 GB RAM and four NVIDIA Tesla K80 general purpose GPUs. We demonstrate the utility of this platform for large radiotherapy optimization problems through the development and characterization of a parallelized particle swarm optimization (PSO) four dimensional (4D) intensity modulated radiation therapy (IMRT) technique. The PSO engine was coupled to the Eclipse treatment planning system via a vendor-provided scripting interface. Specific challenges addressed in this implementation were (i) data management and (ii) non-uniform memory access (NUMA). For the former, we alternated between parameters over which the computation process was parallelized. For the latter, we reduced the amount of data required to be transferred over the NUMA bridge. The datasets examined in this study were approximately 300 GB in size, including 4D computed tomography images, anatomical structure contours and dose deposition matrices. For evaluation, we created a 4D-IMRT treatment plan for one lung cancer patient and analyzed computation speed while varying several parameters (number of respiratory phases, GPUs, PSO particles, and data matrix sizes). The optimized 4D-IMRT plan enhanced sparing of organs at risk by an average reduction of 26% in maximum dose, compared to the clinical optimized IMRT plan, where the internal target volume was used. We validated our computation time analyses in two additional cases. The computation speed in our implementation did not monotonically increase with the number of GPUs. The optimal number of GPUs (five, in our study) is directly related to the
GPU accelerated CT reconstruction for clinical use: quality driven performance
Vaz, Michael S.; Sneyders, Yuri; McLin, Matthew; Ricker, Alan; Kimpe, Tom
2007-03-01
We present performance and quality analysis of GPU accelerated FDK filtered backprojection for cone beam computed tomography (CBCT) reconstruction. Our implementation of the FDK CT reconstruction algorithm does not compromise fidelity at any stage and yields a result that is within 1 HU of a reference C++ implementation. Our streaming implementation is able to perform reconstruction as the images are acquired; it addresses low latency as well as fast throughput, which are key considerations for a "real-time" design. Further, it is scaleable to multiple GPUs for increased performance. The implementation does not place any constraints on image acquisition; it works effectively for arbitrary angular coverage with arbitrary angular spacing. As such, this GPU accelerated CT reconstruction solution may easily be used with scanners that are already deployed. We are able to reconstruct a 512 x 512 x 340 volume from 625 projections, each sized 1024 x 768, in less than 50 seconds. The quoted 50 second timing encompasses the entire reconstruction using bilinear interpolation and includes filtering on the CPU, uploading the filtered projections to the GPU, and also downloading the reconstructed volume from GPU memory to system RAM.
A distributed multi-GPU system for high speed electron microscopic tomographic reconstruction
International Nuclear Information System (INIS)
Zheng, Shawn Q.; Branlund, Eric; Kesthelyi, Bettina; Braunfeld, Michael B.; Cheng, Yifan; Sedat, John W.; Agard, David A.
2011-01-01
Full resolution electron microscopic tomographic (EMT) reconstruction of large-scale tilt series requires significant computing power. The desire to perform multiple cycles of iterative reconstruction and realignment dramatically increases the pressing need to improve reconstruction performance. This has motivated us to develop a distributed multi-GPU (graphics processing unit) system to provide the required computing power for rapid constrained, iterative reconstructions of very large three-dimensional (3D) volumes. The participating GPUs reconstruct segments of the volume in parallel, and subsequently, the segments are assembled to form the complete 3D volume. Owing to its power and versatility, the CUDA (NVIDIA, USA) platform was selected for GPU implementation of the EMT reconstruction. For a system containing 10 GPUs provided by 5 GTX295 cards, 10 cycles of SIRT reconstruction for a tomogram of 4096 2 x512 voxels from an input tilt series containing 122 projection images of 4096 2 pixels (single precision float) takes a total of 1845 s of which 1032 s are for computation with the remainder being the system overhead. The same system takes only 39 s total to reconstruct 1024 2 x256 voxels from 122 1024 2 pixel projections. While the system overhead is non-trivial, performance analysis indicates that adding extra GPUs to the system would lead to steadily enhanced overall performance. Therefore, this system can be easily expanded to generate superior computing power for very large tomographic reconstructions and especially to empower iterative cycles of reconstruction and realignment. -- Highlights: → A distributed multi-GPU system has been developed for electron microscopic tomography (EMT). → This system allows for rapid constrained, iterative reconstruction of very large volumes. → This system can be easily expanded to generate superior computing power for large-scale iterative EMT realignment.
A distributed multi-GPU system for high speed electron microscopic tomographic reconstruction
Energy Technology Data Exchange (ETDEWEB)
Zheng, Shawn Q.; Branlund, Eric; Kesthelyi, Bettina; Braunfeld, Michael B.; Cheng, Yifan; Sedat, John W. [The Howard Hughes Medical Institute and the W.M. Keck Advanced Microscopy Laboratory, Department of Biochemistry and Biophysics, University of California, San Francisco, 600, 16th Street, Room S412D, CA 94158-2517 (United States); Agard, David A., E-mail: agard@msg.ucsf.edu [The Howard Hughes Medical Institute and the W.M. Keck Advanced Microscopy Laboratory, Department of Biochemistry and Biophysics, University of California, San Francisco, 600, 16th Street, Room S412D, CA 94158-2517 (United States)
2011-07-15
Full resolution electron microscopic tomographic (EMT) reconstruction of large-scale tilt series requires significant computing power. The desire to perform multiple cycles of iterative reconstruction and realignment dramatically increases the pressing need to improve reconstruction performance. This has motivated us to develop a distributed multi-GPU (graphics processing unit) system to provide the required computing power for rapid constrained, iterative reconstructions of very large three-dimensional (3D) volumes. The participating GPUs reconstruct segments of the volume in parallel, and subsequently, the segments are assembled to form the complete 3D volume. Owing to its power and versatility, the CUDA (NVIDIA, USA) platform was selected for GPU implementation of the EMT reconstruction. For a system containing 10 GPUs provided by 5 GTX295 cards, 10 cycles of SIRT reconstruction for a tomogram of 4096{sup 2}x512 voxels from an input tilt series containing 122 projection images of 4096{sup 2} pixels (single precision float) takes a total of 1845 s of which 1032 s are for computation with the remainder being the system overhead. The same system takes only 39 s total to reconstruct 1024{sup 2}x256 voxels from 122 1024{sup 2} pixel projections. While the system overhead is non-trivial, performance analysis indicates that adding extra GPUs to the system would lead to steadily enhanced overall performance. Therefore, this system can be easily expanded to generate superior computing power for very large tomographic reconstructions and especially to empower iterative cycles of reconstruction and realignment. -- Highlights: {yields} A distributed multi-GPU system has been developed for electron microscopic tomography (EMT). {yields} This system allows for rapid constrained, iterative reconstruction of very large volumes. {yields} This system can be easily expanded to generate superior computing power for large-scale iterative EMT realignment.
gPGA: GPU Accelerated Population Genetics Analyses.
Directory of Open Access Journals (Sweden)
Chunbao Zhou
Full Text Available The isolation with migration (IM model is important for studies in population genetics and phylogeography. IM program applies the IM model to genetic data drawn from a pair of closely related populations or species based on Markov chain Monte Carlo (MCMC simulations of gene genealogies. But computational burden of IM program has placed limits on its application.With strong computational power, Graphics Processing Unit (GPU has been widely used in many fields. In this article, we present an effective implementation of IM program on one GPU based on Compute Unified Device Architecture (CUDA, which we call gPGA.Compared with IM program, gPGA can achieve up to 52.30X speedup on one GPU. The evaluation results demonstrate that it allows datasets to be analyzed effectively and rapidly for research on divergence population genetics. The software is freely available with source code at https://github.com/chunbaozhou/gPGA.
Jeong, Wonki; Pfister, Hanspeter; Beyer, Johanna; Hadwiger, Markus
2011-01-01
for fair comparison. The main focus of this chapter is introducing the GPU algorithms and their implementation details, which are the core components of the interactive segmentation and visualization system. © 2011 Copyright © 2011 NVIDIA Corporation
GPU Based Software Correlators - Perspectives for VLBI2010
Hobiger, Thomas; Kimura, Moritaka; Takefuji, Kazuhiro; Oyama, Tomoaki; Koyama, Yasuhiro; Kondo, Tetsuro; Gotoh, Tadahiro; Amagai, Jun
2010-01-01
Caused by historical separation and driven by the requirements of the PC gaming industry, Graphics Processing Units (GPUs) have evolved to massive parallel processing systems which entered the area of non-graphic related applications. Although a single processing core on the GPU is much slower and provides less functionality than its counterpart on the CPU, the huge number of these small processing entities outperforms the classical processors when the application can be parallelized. Thus, in recent years various radio astronomical projects have started to make use of this technology either to realize the correlator on this platform or to establish the post-processing pipeline with GPUs. Therefore, the feasibility of GPUs as a choice for a VLBI correlator is being investigated, including pros and cons of this technology. Additionally, a GPU based software correlator will be reviewed with respect to energy consumption/GFlop/sec and cost/GFlop/sec.
Implementation science: a role for parallel dual processing models of reasoning?
Directory of Open Access Journals (Sweden)
Phillips Paddy A
2006-05-01
Full Text Available Abstract Background A better theoretical base for understanding professional behaviour change is needed to support evidence-based changes in medical practice. Traditionally strategies to encourage changes in clinical practices have been guided empirically, without explicit consideration of underlying theoretical rationales for such strategies. This paper considers a theoretical framework for reasoning from within psychology for identifying individual differences in cognitive processing between doctors that could moderate the decision to incorporate new evidence into their clinical decision-making. Discussion Parallel dual processing models of reasoning posit two cognitive modes of information processing that are in constant operation as humans reason. One mode has been described as experiential, fast and heuristic; the other as rational, conscious and rule based. Within such models, the uptake of new research evidence can be represented by the latter mode; it is reflective, explicit and intentional. On the other hand, well practiced clinical judgments can be positioned in the experiential mode, being automatic, reflexive and swift. Research suggests that individual differences between people in both cognitive capacity (e.g., intelligence and cognitive processing (e.g., thinking styles influence how both reasoning modes interact. This being so, it is proposed that these same differences between doctors may moderate the uptake of new research evidence. Such dispositional characteristics have largely been ignored in research investigating effective strategies in implementing research evidence. Whilst medical decision-making occurs in a complex social environment with multiple influences and decision makers, it remains true that an individual doctor's judgment still retains a key position in terms of diagnostic and treatment decisions for individual patients. This paper argues therefore, that individual differences between doctors in terms of
Implementation science: a role for parallel dual processing models of reasoning?
Sladek, Ruth M; Phillips, Paddy A; Bond, Malcolm J
2006-05-25
A better theoretical base for understanding professional behaviour change is needed to support evidence-based changes in medical practice. Traditionally strategies to encourage changes in clinical practices have been guided empirically, without explicit consideration of underlying theoretical rationales for such strategies. This paper considers a theoretical framework for reasoning from within psychology for identifying individual differences in cognitive processing between doctors that could moderate the decision to incorporate new evidence into their clinical decision-making. Parallel dual processing models of reasoning posit two cognitive modes of information processing that are in constant operation as humans reason. One mode has been described as experiential, fast and heuristic; the other as rational, conscious and rule based. Within such models, the uptake of new research evidence can be represented by the latter mode; it is reflective, explicit and intentional. On the other hand, well practiced clinical judgments can be positioned in the experiential mode, being automatic, reflexive and swift. Research suggests that individual differences between people in both cognitive capacity (e.g., intelligence) and cognitive processing (e.g., thinking styles) influence how both reasoning modes interact. This being so, it is proposed that these same differences between doctors may moderate the uptake of new research evidence. Such dispositional characteristics have largely been ignored in research investigating effective strategies in implementing research evidence. Whilst medical decision-making occurs in a complex social environment with multiple influences and decision makers, it remains true that an individual doctor's judgment still retains a key position in terms of diagnostic and treatment decisions for individual patients. This paper argues therefore, that individual differences between doctors in terms of reasoning are important considerations in any
Parallel Implementation of the Multi-Dimensional Spectral Code SPECT3D on large 3D grids.
Golovkin, Igor E.; Macfarlane, Joseph J.; Woodruff, Pamela R.; Pereyra, Nicolas A.
2006-10-01
The multi-dimensional collisional-radiative, spectral analysis code SPECT3D can be used to study radiation from complex plasmas. SPECT3D can generate instantaneous and time-gated images and spectra, space-resolved and streaked spectra, which makes it a valuable tool for post-processing hydrodynamics calculations and direct comparison between simulations and experimental data. On large three dimensional grids, transporting radiation along lines of sight (LOS) requires substantial memory and CPU resources. Currently, the parallel option in SPECT3D is based on parallelization over photon frequencies and allows for a nearly linear speed-up for a variety of problems. In addition, we are introducing a new parallel mechanism that will greatly reduce memory requirements. In the new implementation, spatial domain decomposition will be utilized allowing transport along a LOS to be performed only on the mesh cells the LOS crosses. The ability to operate on a fraction of the grid is crucial for post-processing the results of large-scale three-dimensional hydrodynamics simulations. We will present a parallel implementation of the code and provide a scalability study performed on a Linux cluster.
GAMUT: GPU accelerated microRNA analysis to uncover target genes through CUDA-miRanda
2014-01-01
Background Non-coding sequences such as microRNAs have important roles in disease processes. Computational microRNA target identification (CMTI) is becoming increasingly important since traditional experimental methods for target identification pose many difficulties. These methods are time-consuming, costly, and often need guidance from computational methods to narrow down candidate genes anyway. However, most CMTI methods are computationally demanding, since they need to handle not only several million query microRNA and reference RNA pairs, but also several million nucleotide comparisons within each given pair. Thus, the need to perform microRNA identification at such large scale has increased the demand for parallel computing. Methods Although most CMTI programs (e.g., the miRanda algorithm) are based on a modified Smith-Waterman (SW) algorithm, the existing parallel SW implementations (e.g., CUDASW++ 2.0/3.0, SWIPE) are unable to meet this demand in CMTI tasks. We present CUDA-miRanda, a fast microRNA target identification algorithm that takes advantage of massively parallel computing on Graphics Processing Units (GPU) using NVIDIA's Compute Unified Device Architecture (CUDA). CUDA-miRanda specifically focuses on the local alignment of short (i.e., ≤ 32 nucleotides) sequences against longer reference sequences (e.g., 20K nucleotides). Moreover, the proposed algorithm is able to report multiple alignments (up to 191 top scores) and the corresponding traceback sequences for any given (query sequence, reference sequence) pair. Results Speeds over 5.36 Giga Cell Updates Per Second (GCUPs) are achieved on a server with 4 NVIDIA Tesla M2090 GPUs. Compared to the original miRanda algorithm, which is evaluated on an Intel Xeon E5620@2.4 GHz CPU, the experimental results show up to 166 times performance gains in terms of execution time. In addition, we have verified that the exact same targets were predicted in both CUDA-miRanda and the original mi
Byun, Hye Suk; El-Naggar, Mohamed Y.; Kalia, Rajiv K.; Nakano, Aiichiro; Vashishta, Priya
2017-10-01
Kinetic Monte Carlo (KMC) simulations are used to study long-time dynamics of a wide variety of systems. Unfortunately, the conventional KMC algorithm is not scalable to larger systems, since its time scale is inversely proportional to the simulated system size. A promising approach to resolving this issue is the synchronous parallel KMC (SPKMC) algorithm, which makes the time scale size-independent. This paper introduces a formal derivation of the SPKMC algorithm based on local transition-state and time-dependent Hartree approximations, as well as its scalable parallel implementation based on a dual linked-list cell method. The resulting algorithm has achieved a weak-scaling parallel efficiency of 0.935 on 1024 Intel Xeon processors for simulating biological electron transfer dynamics in a 4.2 billion-heme system, as well as decent strong-scaling parallel efficiency. The parallel code has been used to simulate a lattice of cytochrome complexes on a bacterial-membrane nanowire, and it is broadly applicable to other problems such as computational synthesis of new materials.
Directory of Open Access Journals (Sweden)
Adel Omar Dahmane
2008-01-01
Full Text Available Multistage parallel interference cancellation- (MPIC- based detectors allow to mitigate multiple-access interference in direct-sequence code-division multiple-access (DS-CDMA systems. They are considered serious candidates for practical implementation showing a good tradeoff between performance and complexity. Better performance is obtained when decision feedback (DF is employed. Although MPIC and DF-MPIC have the same arithmetic complexity, DF-MPIC needs much more FPGA resources when compared to MPIC without decision feedback. In this letter, FPGA implementation of block parallel DF-MPIC (BP-DF-MPIC is proposed allowing better tradeoff between performance and FPGA area occupancy. To reach an uncoded bit-error rate of 10−3, BP-DF-MPIC shows a 1.5 dB improvement over the MPIC without decision feedback with only 8% increase in FPGA resources compared to 69% for DF-MPIC.
International Nuclear Information System (INIS)
Wong Unhong; Wong Honcheng; Tang Zesheng
2010-01-01
The smoothed particle hydrodynamics (SPH), which is a class of meshfree particle methods (MPMs), has a wide range of applications from micro-scale to macro-scale as well as from discrete systems to continuum systems. Graphics hardware, originally designed for computer graphics, now provide unprecedented computational power for scientific computation. Particle system needs a huge amount of computations in physical simulation. In this paper, an efficient parallel implementation of a SPH method on graphics hardware using the Compute Unified Device Architecture is developed for fluid simulation. Comparing to the corresponding CPU implementation, our experimental results show that the new approach allows significant speedups of fluid simulation through handling huge amount of computations in parallel on graphics hardware.
Basket Option Pricing Using GP-GPU Hardware Acceleration
Douglas, Craig C.
2010-08-01
We introduce a basket option pricing problem arisen in financial mathematics. We discretized the problem based on the alternating direction implicit (ADI) method and parallel cyclic reduction is applied to solve the set of tridiagonal matrices generated by the ADI method. To reduce the computational time of the problem, a general purpose graphics processing units (GP-GPU) environment is considered. Numerical results confirm the convergence and efficiency of the proposed method. © 2010 IEEE.
GPU-accelerated back-projection revisited. Squeezing performance by careful tuning
Energy Technology Data Exchange (ETDEWEB)
Papenhausen, Eric; Zheng, Ziyi; Mueller, Klaus [Stony Brook Univ., NY (United States). Computer Science Dept.
2011-07-01
In recent years, GPUs have become an increasingly popular tool in computed tomography (CT) reconstruction. In this paper, we discuss performance optimization techniques for a GPU-based filtered-backprojection reconstruction implementation. We explore the different optimization techniques we used and explain how those techniques affected performance. Our results show a nearly 50% increase in performance when compared to the current top ranked GPU implementation. (orig.)
The GENGA code: gravitational encounters in N-body simulations with GPU acceleration
International Nuclear Information System (INIS)
Grimm, Simon L.; Stadel, Joachim G.
2014-01-01
We describe an open source GPU implementation of a hybrid symplectic N-body integrator, GENGA (Gravitational ENcounters with Gpu Acceleration), designed to integrate planet and planetesimal dynamics in the late stage of planet formation and stability analyses of planetary systems. GENGA uses a hybrid symplectic integrator to handle close encounters with very good energy conservation, which is essential in long-term planetary system integration. We extended the second-order hybrid integration scheme to higher orders. The GENGA code supports three simulation modes: integration of up to 2048 massive bodies, integration with up to a million test particles, or parallel integration of a large number of individual planetary systems. We compare the results of GENGA to Mercury and pkdgrav2 in terms of energy conservation and performance and find that the energy conservation of GENGA is comparable to Mercury and around two orders of magnitude better than pkdgrav2. GENGA runs up to 30 times faster than Mercury and up to 8 times faster than pkdgrav2. GENGA is written in CUDA C and runs on all NVIDIA GPUs with a computing capability of at least 2.0.
The GENGA code: gravitational encounters in N-body simulations with GPU acceleration
Energy Technology Data Exchange (ETDEWEB)
Grimm, Simon L.; Stadel, Joachim G., E-mail: sigrimm@physik.uzh.ch [Institute for Computational Science, University of Zürich, Winterthurerstrasse 190, CH-8057 Zürich (Switzerland)
2014-11-20
We describe an open source GPU implementation of a hybrid symplectic N-body integrator, GENGA (Gravitational ENcounters with Gpu Acceleration), designed to integrate planet and planetesimal dynamics in the late stage of planet formation and stability analyses of planetary systems. GENGA uses a hybrid symplectic integrator to handle close encounters with very good energy conservation, which is essential in long-term planetary system integration. We extended the second-order hybrid integration scheme to higher orders. The GENGA code supports three simulation modes: integration of up to 2048 massive bodies, integration with up to a million test particles, or parallel integration of a large number of individual planetary systems. We compare the results of GENGA to Mercury and pkdgrav2 in terms of energy conservation and performance and find that the energy conservation of GENGA is comparable to Mercury and around two orders of magnitude better than pkdgrav2. GENGA runs up to 30 times faster than Mercury and up to 8 times faster than pkdgrav2. GENGA is written in CUDA C and runs on all NVIDIA GPUs with a computing capability of at least 2.0.
A Parallel Algebraic Multigrid Solver on Graphics Processing Units
Haase, Gundolf; Liebmann, Manfred; Douglas, Craig C.; Plank, Gernot
2010-01-01
-vector multiplication scheme underlying the PCG-AMG algorithm is presented for the many-core GPU architecture. A performance comparison of the parallel solver shows that a singe Nvidia Tesla C1060 GPU board delivers the performance of a sixteen node Infiniband cluster
Implementation of a Monte Carlo algorithm for neutron transport on a massively parallel SIMD machine
International Nuclear Information System (INIS)
Baker, R.S.
1992-01-01
We present some results from the recent adaptation of a vectorized Monte Carlo algorithm to a massively parallel architecture. The performance of the algorithm on a single processor Cray Y-MP and a Thinking Machine Corporations CM-2 and CM-200 is compared for several test problems. The results show that significant speedups are obtainable for vectorized Monte Carlo algorithms on massively parallel machines, even when the algorithms are applied to realistic problems which require extensive variance reduction. However, the architecture of the Connection Machine does place some limitations on the regime in which the Monte Carlo algorithm may be expected to perform well
Implementation of a Monte Carlo algorithm for neutron transport on a massively parallel SIMD machine
International Nuclear Information System (INIS)
Baker, R.S.
1993-01-01
We present some results from the recent adaptation of a vectorized Monte Carlo algorithm to a massively parallel architecture. The performance of the algorithm on a single processor Cray Y-MP and a Thinking Machine Corporations CM-2 and CM-200 is compared for several test problems. The results show that significant speedups are obtainable for vectorized Monte Carlo algorithms on massively parallel machines, even when the algorithms are applied to realistic problems which require extensive variance reduction. However, the architecture of the Connection Machine does place some limitations on the regime in which the Monte Carlo algorithm may be expected to perform well. (orig.)
Abdellah, Marwan; Eldeib, Ayman; Owis, Mohamed I
2015-01-01
This paper features an advanced implementation of the X-ray rendering algorithm that harnesses the giant computing power of the current commodity graphics processors to accelerate the generation of high resolution digitally reconstructed radiographs (DRRs). The presented pipeline exploits the latest features of NVIDIA Graphics Processing Unit (GPU) architectures, mainly bindless texture objects and dynamic parallelism. The rendering throughput is substantially improved by exploiting the interoperability mechanisms between CUDA and OpenGL. The benchmarks of our optimized rendering pipeline reflect its capability of generating DRRs with resolutions of 2048(2) and 4096(2) at interactive and semi interactive frame-rates using an NVIDIA GeForce 970 GTX device.
Robust Cell Detection for Large-Scale 3D Microscopy Using GPU-Accelerated Iterative Voting
Directory of Open Access Journals (Sweden)
Leila Saadatifard
2018-04-01
Full Text Available High-throughput imaging techniques, such as Knife-Edge Scanning Microscopy (KESM,are capable of acquiring three-dimensional whole-organ images at sub-micrometer resolution. These images are challenging to segment since they can exceed several terabytes (TB in size, requiring extremely fast and fully automated algorithms. Staining techniques are limited to contrast agents that can be applied to large samples and imaged in a single pass. This requires maximizing the number of structures labeled in a single channel, resulting in images that are densely packed with spatial features. In this paper, we propose a three-dimensional approach for locating cells based on iterative voting. Due to the computational complexity of this algorithm, a highly efficient GPU implementation is required to make it practical on large data sets. The proposed algorithm has a limited number of input parameters and is highly parallel.
Algorithms for a parallel implementation of Hidden Markov Models with a small state space
DEFF Research Database (Denmark)
Nielsen, Jesper; Sand, Andreas
2011-01-01
Two of the most important algorithms for Hidden Markov Models are the forward and the Viterbi algorithms. We show how formulating these using linear algebra naturally lends itself to parallelization. Although the obtained algorithms are slow for Hidden Markov Models with large state spaces...
Parallelization of ultrasonic field simulations for non destructive testing
International Nuclear Information System (INIS)
Lambert, Jason
2015-01-01
The Non Destructive Testing field increasingly uses simulation. It is used at every step of the whole control process of an industrial part, from speeding up control development to helping experts understand results. During this thesis, a fast ultrasonic field simulation tool dedicated to the computation of an ultrasonic field radiated by a phase array probe in an isotropic specimen has been developed. During this thesis, a simulation tool dedicated to the fast computation of an ultrasonic field radiated by a phased array probe in an isotropic specimen has been developed. Its performance enables an interactive usage. To benefit from the commonly available parallel architectures, a regular model (aimed at removing divergent branching) derived from the generic CIVA model has been developed. First, a reference implementation was developed to validate this model against CIVA results, and to analyze its performance behaviour before optimization. The resulting code has been optimized for three kinds of parallel architectures commonly available in workstations: general purpose processors (GPP), many-core co-processors (Intel MIC) and graphics processing units (nVidia GPU). On the GPP and the MIC, the algorithm was reorganized and implemented to benefit from both parallelism levels, multithreading and vector instructions. On the GPU, the multiple steps of field computing have been divided in multiple successive CUDA kernels. Moreover, libraries dedicated to each architecture were used to speedup Fast Fourier Transforms, Intel MKL on GPP and MIC and nVidia cuFFT on GPU. Performance and hardware adequation of the produced codes were thoroughly studied for each architecture. On multiple realistic control configurations, interactive performance was reached. Perspectives to address more complex configurations were drawn. Finally, the integration and the industrialization of this code in the commercial NDT platform CIVA is discussed. (author) [fr
gWEGA: GPU-accelerated WEGA for molecular superposition and shape comparison.
Yan, Xin; Li, Jiabo; Gu, Qiong; Xu, Jun
2014-06-05
Virtual screening of a large chemical library for drug lead identification requires searching/superimposing a large number of three-dimensional (3D) chemical structures. This article reports a graphic processing unit (GPU)-accelerated weighted Gaussian algorithm (gWEGA) that expedites shape or shape-feature similarity score-based virtual screening. With 86 GPU nodes (each node has one GPU card), gWEGA can screen 110 million conformations derived from an entire ZINC drug-like database with diverse antidiabetic agents as query structures within 2 s (i.e., screening more than 55 million conformations per second). The rapid screening speed was accomplished through the massive parallelization on multiple GPU nodes and rapid prescreening of 3D structures (based on their shape descriptors and pharmacophore feature compositions). Copyright © 2014 Wiley Periodicals, Inc.
An Investigation of the Performance of the Colored Gauss-Seidel Solver on CPU and GPU
International Nuclear Information System (INIS)
Yoon, Jong Seon; Choi, Hyoung Gwon; Jeon, Byoung Jin
2017-01-01
The performance of the colored Gauss–Seidel solver on CPU and GPU was investigated for the two- and three-dimensional heat conduction problems by using different mesh sizes. The heat conduction equation was discretized by the finite difference method and finite element method. The CPU yielded good performance for small problems but deteriorated when the total memory required for computing was larger than the cache memory for large problems. In contrast, the GPU performed better as the mesh size increased because of the latency hiding technique. Further, GPU computation by the colored Gauss–Siedel solver was approximately 7 times that by the single CPU. Furthermore, the colored Gauss–Seidel solver was found to be approximately twice that of the Jacobi solver when parallel computing was conducted on the GPU.
An Investigation of the Performance of the Colored Gauss-Seidel Solver on CPU and GPU
Energy Technology Data Exchange (ETDEWEB)
Yoon, Jong Seon; Choi, Hyoung Gwon [Seoul Nat’l Univ. of Science and Technology, Seoul (Korea, Republic of); Jeon, Byoung Jin [Yonsei Univ., Seoul (Korea, Republic of)
2017-02-15
The performance of the colored Gauss–Seidel solver on CPU and GPU was investigated for the two- and three-dimensional heat conduction problems by using different mesh sizes. The heat conduction equation was discretized by the finite difference method and finite element method. The CPU yielded good performance for small problems but deteriorated when the total memory required for computing was larger than the cache memory for large problems. In contrast, the GPU performed better as the mesh size increased because of the latency hiding technique. Further, GPU computation by the colored Gauss–Siedel solver was approximately 7 times that by the single CPU. Furthermore, the colored Gauss–Seidel solver was found to be approximately twice that of the Jacobi solver when parallel computing was conducted on the GPU.
Directory of Open Access Journals (Sweden)
Marco Scutari
2017-03-01
Full Text Available It is well known in the literature that the problem of learning the structure of Bayesian networks is very hard to tackle: Its computational complexity is super-exponential in the number of nodes in the worst case and polynomial in most real-world scenarios. Efficient implementations of score-based structure learning benefit from past and current research in optimization theory, which can be adapted to the task by using the network score as the objective function to maximize. This is not true for approaches based on conditional independence tests, called constraint-based learning algorithms. The only optimization in widespread use, backtracking, leverages the symmetries implied by the definitions of neighborhood and Markov blanket. In this paper we illustrate how backtracking is implemented in recent versions of the bnlearn R package, and how it degrades the stability of Bayesian network structure learning for little gain in terms of speed. As an alternative, we describe a software architecture and framework that can be used to parallelize constraint-based structure learning algorithms (also implemented in bnlearn and we demonstrate its performance using four reference networks and two real-world data sets from genetics and systems biology. We show that on modern multi-core or multiprocessor hardware parallel implementations are preferable over backtracking, which was developed when single-processor machines were the norm.
Directory of Open Access Journals (Sweden)
T. Stefański
2014-12-01
Full Text Available Parallel implementation of the discrete Green's function formulation of the finite-difference time-domain (DGF-FDTD method was developed on a multicore central processing unit. DGF-FDTD avoids computations of the electromagnetic field in free-space cells and does not require domain termination by absorbing boundary conditions. Computed DGF-FDTD solutions are compatible with the FDTD grid enabling the perfect hybridization of FDTD with the use of time-domain integral equation methods. The developed implementation can be applied to simulations of antenna characteristics. For the sake of example, arrays of Yagi-Uda antennas were simulated with the use of parallel DGF-FDTD. The efficiency of parallel computations was investigated as a function of the number of current elements in the FDTD grid. Although the developed method does not apply the fast Fourier transform for convolution computations, advantages stemming from the application of DGF-FDTD instead of FDTD can be demonstrated for one-dimensional wire antennas when simulation results are post-processed by the near-to-far-field transformation.
Directory of Open Access Journals (Sweden)
Fang Huang
2016-06-01
Full Text Available In some digital Earth engineering applications, spatial interpolation algorithms are required to process and analyze large amounts of data. Due to its powerful computing capacity, heterogeneous computing has been used in many applications for data processing in various fields. In this study, we explore the design and implementation of a parallel universal kriging spatial interpolation algorithm using the OpenCL programming model on heterogeneous computing platforms for massive Geo-spatial data processing. This study focuses primarily on transforming the hotspots in serial algorithms, i.e., the universal kriging interpolation function, into the corresponding kernel function in OpenCL. We also employ parallelization and optimization techniques in our implementation to improve the code performance. Finally, based on the results of experiments performed on two different high performance heterogeneous platforms, i.e., an NVIDIA graphics processing unit system and an Intel Xeon Phi system (MIC, we show that the parallel universal kriging algorithm can achieve the highest speedup of up to 40× with a single computing device and the highest speedup of up to 80× with multiple devices.
International Nuclear Information System (INIS)
Egger, M.L.; Scheurer, A.H.; Joseph, C.
1996-01-01
The issue of long reconstruction times in PET has been addressed from several points of view, resulting in an affordable dedicated system capable of handling routine 3D reconstruction in a few minutes per frame: on the hardware side using fast processors and a parallel architecture, and on the software side, using efficient implementations of computationally less intensive algorithms. Execution times obtained for the PRT-1 data set on a parallel system of five hybrid nodes, each combining an Alpha processor for computation and a transputer for communication, are the following (256 sinograms of 96 views by 128 radial samples): Ramp algorithm 56 s, Favor 81 s and reprojection algorithm of Kinahan and Rogers 187 s. The implementation of fast rebinning algorithms has shown our hardware platform to become communications-limited; they execute faster on a conventional single-processor Alpha workstation: single-slice rebinning 7 s, Fourier rebinning 22 s, 2D filtered backprojection 5 s. The scalability of the system has been demonstrated, and a saturation effect at network sizes above ten nodes has become visible; new T9000-based products lifting most of the constraints on network topology and link throughput are expected to result in improved parallel efficiency and scalability properties
Implementation of a microcomputer based distance relay for parallel transmission lines
International Nuclear Information System (INIS)
Phadke, A.G.; Jihuang, L.
1986-01-01
Distance relaying for parallel transmission lines is a difficult application problem with conventional phase and ground distance relays. It is known that for cross-country faults involving dissimilar phases and ground, three phase tripping may result. This paper summarizes a newly developed microcomputer based relay which is capable of classifying the cross-country fault correctly. The paper describes the principle of operation and results of laboratory tests of this relay
Directory of Open Access Journals (Sweden)
Nam Ling
2013-07-01
Full Text Available Hough Transform has been widely used for straight line detection in low-definition and still images, but it suffers from execution time and resource requirements. Field Programmable Gate Arrays (FPGA provide a competitive alternative for hardware acceleration to reap tremendous computing performance. In this paper, we propose a novel parallel Hough Transform (PHT and FPGA architecture-associated framework for real-time straight line detection in high-definition videos. A resource-optimized Canny edge detection method with enhanced non-maximum suppression conditions is presented to suppress most possible false edges and obtain more accurate candidate edge pixels for subsequent accelerated computation. Then, a novel PHT algorithm exploiting spatial angle-level parallelism is proposed to upgrade computational accuracy by improving the minimum computational step. Moreover, the FPGA based multi-level pipelined PHT architecture optimized by spatial parallelism ensures real-time computation for 1,024 × 768 resolution videos without any off-chip memory consumption. This framework is evaluated on ALTERA DE2-115 FPGA evaluation platform at a maximum frequency of 200 MHz, and it can calculate straight line parameters in 15.59 ms on the average for one frame. Qualitative and quantitative evaluation results have validated the system performance regarding data throughput, memory bandwidth, resource, speed and robustness.
Lu, Xiaofeng; Song, Li; Shen, Sumin; He, Kang; Yu, Songyu; Ling, Nam
2013-07-17
Hough Transform has been widely used for straight line detection in low-definition and still images, but it suffers from execution time and resource requirements. Field Programmable Gate Arrays (FPGA) provide a competitive alternative for hardware acceleration to reap tremendous computing performance. In this paper, we propose a novel parallel Hough Transform (PHT) and FPGA architecture-associated framework for real-time straight line detection in high-definition videos. A resource-optimized Canny edge detection method with enhanced non-maximum suppression conditions is presented to suppress most possible false edges and obtain more accurate candidate edge pixels for subsequent accelerated computation. Then, a novel PHT algorithm exploiting spatial angle-level parallelism is proposed to upgrade computational accuracy by improving the minimum computational step. Moreover, the FPGA based multi-level pipelined PHT architecture optimized by spatial parallelism ensures real-time computation for 1,024 × 768 resolution videos without any off-chip memory consumption. This framework is evaluated on ALTERA DE2-115 FPGA evaluation platform at a maximum frequency of 200 MHz, and it can calculate straight line parameters in 15.59 ms on the average for one frame. Qualitative and quantitative evaluation results have validated the system performance regarding data throughput, memory bandwidth, resource, speed and robustness.
DEFF Research Database (Denmark)
Dollerup, Niels; Jepsen, Michael S.; Damkilde, Lars
2013-01-01
The artide describes a robust and effective implementation of the interior point optimization algorithm. The adopted method includes a precalculation step, which reduces the number of variables by fulfilling the equilibrium equations a priori. This work presents an improved implementation of the ...
A Fully Parallel VLSI-implementation of the Viterbi Decoding Algorithm
DEFF Research Database (Denmark)
Sparsø, Jens; Jørgensen, Henrik Nordtorp; Paaske, Erik
1989-01-01
In this paper we describe the implementation of a K = 7, R = 1/2 single-chip Viterbi decoder intended to operate at 10-20 Mbit/sec. We propose a general, regular and area efficient floor-plan that is also suitable for implementation of decoders for codes with different generator polynomials...
GPU-Based Point Cloud Superpositioning for Structural Comparisons of Protein Binding Sites.
Leinweber, Matthias; Fober, Thomas; Freisleben, Bernd
2018-01-01
In this paper, we present a novel approach to solve the labeled point cloud superpositioning problem for performing structural comparisons of protein binding sites. The solution is based on a parallel evolution strategy that operates on large populations and runs on GPU hardware. The proposed evolution strategy reduces the likelihood of getting stuck in a local optimum of the multimodal real-valued optimization problem represented by labeled point cloud superpositioning. The performance of the GPU-based parallel evolution strategy is compared to a previously proposed CPU-based sequential approach for labeled point cloud superpositioning, indicating that the GPU-based parallel evolution strategy leads to qualitatively better results and significantly shorter runtimes, with speed improvements of up to a factor of 1,500 for large populations. Binary classification tests based on the ATP, NADH, and FAD protein subsets of CavBase, a database containing putative binding sites, show average classification rate improvements from about 92 percent (CPU) to 96 percent (GPU). Further experiments indicate that the proposed GPU-based labeled point cloud superpositioning approach can be superior to traditional protein comparison approaches based on sequence alignments.
Sotiropoulou, C-L; The ATLAS collaboration; Annovi, A; Beretta, M; Kordas, K; Nikolaidis, S; Petridou, C; Volpi, G
2014-01-01
The parallel 2D pixel clustering FPGA implementation used for the input system of the ATLAS Fast TracKer (FTK) processor is presented. The input system for the FTK processor will receive data from the Pixel and micro-strip detectors from inner ATLAS read out drivers (RODs) at full rate, for total of 760Gbs, as sent by the RODs after level-1 triggers. Clustering serves two purposes, the first is to reduce the high rate of the received data before further processing, the second is to determine the cluster centroid to obtain the best spatial measurement. For the pixel detectors the clustering is implemented by using a 2D-clustering algorithm that takes advantage of a moving window technique to minimize the logic required for cluster identification. The cluster detection window size can be adjusted for optimizing the cluster identification process. Additionally, the implementation can be parallelized by instantiating multiple cores to identify different clusters independently thus exploiting more FPGA resources. ...
Sotiropoulou, C-L; The ATLAS collaboration; Annovi, A; Beretta, M; Kordas, K; Nikolaidis, S; Petridou, C; Volpi, G
2014-01-01
The parallel 2D pixel clustering FPGA implementation used for the input system of the ATLAS Fast TracKer (FTK) processor is presented. The input system for the FTK processor will receive data from the Pixel and micro-strip detectors from inner ATLAS read out drivers (RODs) at full rate, for total of 760Gbs, as sent by the RODs after level1 triggers. Clustering serves two purposes, the first is to reduce the high rate of the received data before further processing, the second is to determine the cluster centroid to obtain the best spatial measurement. For the pixel detectors the clustering is implemented by using a 2D-clustering algorithm that takes advantage of a moving window technique to minimize the logic required for cluster identification. The cluster detection window size can be adjusted for optimizing the cluster identification process. Additionally, the implementation can be parallelized by instantiating multiple cores to identify different clusters independently thus exploiting more FPGA resources. T...
International Nuclear Information System (INIS)
Ammendola, R.; Biagioni, A.; Cretaro, P.; Frezza, O.; Cicero, F. Lo; Lonardo, A.; Martinelli, M.; Paolucci, P.S.; Pastorelli, E.; Chiozzi, S.; Ramusino, A. Cotta; Fiorini, M.; Gianoli, A.; Neri, I.; Lorenzo, S. Di; Fantechi, R.; Piandani, R.; Pontisso, L.; Lamanna, G.; Piccini, M.
2017-01-01
This project aims to exploit the parallel computing power of a commercial Graphics Processing Unit (GPU) to implement fast pattern matching in the Ring Imaging Cherenkov (RICH) detector for the level 0 (L0) trigger of the NA62 experiment. In this approach, the ring-fitting algorithm is seedless, being fed with raw RICH data, with no previous information on the ring position from other detectors. Moreover, since the L0 trigger is provided with a more elaborated information than a simple multiplicity number, it results in a higher selection power. Two methods have been studied in order to reduce the data transfer latency from the readout boards of the detector to the GPU, i.e., the use of a dedicated NIC device driver with very low latency and a direct data transfer protocol from a custom FPGA-based NIC to the GPU. The performance of the system, developed through the FPGA approach, for multi-ring Cherenkov online reconstruction obtained during the NA62 physics runs is presented.
Directory of Open Access Journals (Sweden)
J. Adam Wilson
2009-07-01
Full Text Available The clock speeds of modern computer processors have nearly plateaued in the past five years. Consequently, neural prosthetic systems that rely on processing large quantities of data in a short period of time face a bottleneck, in that it may not be possible to process all of the data recorded from an electrode array with high channel counts and bandwidth, such as electrocorticographic grids or other implantable systems. Therefore, in this study a method of using the processing capabilities of a graphics card (GPU was developed for real-time neural signal processing of a brain-computer interface (BCI. The NVIDIA CUDA system was used to offload processing to the GPU, which is capable of running many operations in parallel, potentially greatly increasing the speed of existing algorithms. The BCI system records many channels of data, which are processed and translated into a control signal, such as the movement of a computer cursor. This signal processing chain involves computing a matrix-matrix multiplication (i.e., a spatial filter, followed by calculating the power spectral density on every channel using an auto-regressive method, and finally classifying appropriate features for control. In this study, the first two computationally-intensive steps were implemented on the GPU, and the speed was compared to both the current implementation and a CPU-based implementation that uses multi-threading. Significant performance gains were obtained with GPU processing: the current implementation processed 1000 channels in 933 ms, while the new GPU method took only 27 ms, an improvement of nearly 35 times.
Wilson, J Adam; Williams, Justin C
2009-01-01
The clock speeds of modern computer processors have nearly plateaued in the past 5 years. Consequently, neural prosthetic systems that rely on processing large quantities of data in a short period of time face a bottleneck, in that it may not be possible to process all of the data recorded from an electrode array with high channel counts and bandwidth, such as electrocorticographic grids or other implantable systems. Therefore, in this study a method of using the processing capabilities of a graphics card [graphics processing unit (GPU)] was developed for real-time neural signal processing of a brain-computer interface (BCI). The NVIDIA CUDA system was used to offload processing to the GPU, which is capable of running many operations in parallel, potentially greatly increasing the speed of existing algorithms. The BCI system records many channels of data, which are processed and translated into a control signal, such as the movement of a computer cursor. This signal processing chain involves computing a matrix-matrix multiplication (i.e., a spatial filter), followed by calculating the power spectral density on every channel using an auto-regressive method, and finally classifying appropriate features for control. In this study, the first two computationally intensive steps were implemented on the GPU, and the speed was compared to both the current implementation and a central processing unit-based implementation that uses multi-threading. Significant performance gains were obtained with GPU processing: the current implementation processed 1000 channels of 250 ms in 933 ms, while the new GPU method took only 27 ms, an improvement of nearly 35 times.
Accelerating the XGBoost algorithm using GPU computing
Directory of Open Access Journals (Sweden)
Rory Mitchell
2017-07-01
Full Text Available We present a CUDA-based implementation of a decision tree construction algorithm within the gradient boosting library XGBoost. The tree construction algorithm is executed entirely on the graphics processing unit (GPU and shows high performance with a variety of datasets and settings, including sparse input matrices. Individual boosting iterations are parallelised, combining two approaches. An interleaved approach is used for shallow trees, switching to a more conventional radix sort-based approach for larger depths. We show speedups of between 3× and 6× using a Titan X compared to a 4 core i7 CPU, and 1.2× using a Titan X compared to 2× Xeon CPUs (24 cores. We show that it is possible to process the Higgs dataset (10 million instances, 28 features entirely within GPU memory. The algorithm is made available as a plug-in within the XGBoost library and fully supports all XGBoost features including classification, regression and ranking tasks.
Hybrid parallel computing architecture for multiview phase shifting
Zhong, Kai; Li, Zhongwei; Zhou, Xiaohui; Shi, Yusheng; Wang, Congjun
2014-11-01
The multiview phase-shifting method shows its powerful capability in achieving high resolution three-dimensional (3-D) shape measurement. Unfortunately, this ability results in very high computation costs and 3-D computations have to be processed offline. To realize real-time 3-D shape measurement, a hybrid parallel computing architecture is proposed for multiview phase shifting. In this architecture, the central processing unit can co-operate with the graphic processing unit (GPU) to achieve hybrid parallel computing. The high computation cost procedures, including lens distortion rectification, phase computation, correspondence, and 3-D reconstruction, are implemented in GPU, and a three-layer kernel function model is designed to simultaneously realize coarse-grained and fine-grained paralleling computing. Experimental results verify that the developed system can perform 50 fps (frame per second) real-time 3-D measurement with 260 K 3-D points per frame. A speedup of up to 180 times is obtained for the performance of the proposed technique using a NVIDIA GT560Ti graphics card rather than a sequential C in a 3.4 GHZ Inter Core i7 3770.
Research on GPU-accelerated algorithm in 3D finite difference neutron diffusion calculation method
International Nuclear Information System (INIS)
Xu Qi; Yu Ganglin; Wang Kan; Sun Jialong
2014-01-01
In this paper, the adaptability of the neutron diffusion numerical algorithm on GPUs was studied, and a GPU-accelerated multi-group 3D neutron diffusion code based on finite difference method was developed. The IAEA 3D PWR benchmark problem was calculated in the numerical test. The results demonstrate both high efficiency and adequate accuracy of the GPU implementation for neutron diffusion equation. (authors)
GPU-accelerated simulations of isolated black holes
Lewis, Adam G. M.; Pfeiffer, Harald P.
2018-05-01
We present a port of the numerical relativity code SpEC which is capable of running on NVIDIA GPUs. Since this code must be maintained in parallel with SpEC itself, a primary design consideration is to perform as few explicit code changes as possible. We therefore rely on a hierarchy of automated porting strategies. At the highest level we use TLoops, a C++ library of our design, to automatically emit CUDA code equivalent to tensorial expressions written into C++ source using a syntax similar to analytic calculation. Next, we trace out and cache explicit matrix representations of the numerous linear transformations in the SpEC code, which allows these to be performed on the GPU using pre-existing matrix-multiplication libraries. We port the few remaining important modules by hand. In this paper we detail the specifics of our port, and present benchmarks of it simulating isolated black hole spacetimes on several generations of NVIDIA GPU.
An SDR-Based Real-Time Testbed for GNSS Adaptive Array Anti-Jamming Algorithms Accelerated by GPU
Directory of Open Access Journals (Sweden)
Hailong Xu
2016-03-01
Full Text Available Nowadays, software-defined radio (SDR has become a common approach to evaluate new algorithms. However, in the field of Global Navigation Satellite System (GNSS adaptive array anti-jamming, previous work has been limited due to the high computational power demanded by adaptive algorithms, and often lack flexibility and configurability. In this paper, the design and implementation of an SDR-based real-time testbed for GNSS adaptive array anti-jamming accelerated by a Graphics Processing Unit (GPU are documented. This testbed highlights itself as a feature-rich and extendible platform with great flexibility and configurability, as well as high computational performance. Both Space-Time Adaptive Processing (STAP and Space-Frequency Adaptive Processing (SFAP are implemented with a wide range of parameters. Raw data from as many as eight antenna elements can be processed in real-time in either an adaptive nulling or beamforming mode. To fully take advantage of the parallelism resource provided by the GPU, a batched method in programming is proposed. Tests and experiments are conducted to evaluate both the computational and anti-jamming performance. This platform can be used for research and prototyping, as well as a real product in certain applications.
Huhn, William Paul; Lange, Björn; Yu, Victor; Blum, Volker; Lee, Seyong; Yoon, Mina
Density-functional theory has been well established as the dominant quantum-mechanical computational method in the materials community. Large accurate simulations become very challenging on small to mid-scale computers and require high-performance compute platforms to succeed. GPU acceleration is one promising approach. In this talk, we present a first implementation of all-electron density-functional theory in the FHI-aims code for massively parallel GPU-based platforms. Special attention is paid to the update of the density and to the integration of the Hamiltonian and overlap matrices, realized in a domain decomposition scheme on non-uniform grids. The initial implementation scales well across nodes on ORNL's Titan Cray XK7 supercomputer (8 to 64 nodes, 16 MPI ranks/node) and shows an overall speed up in runtime due to utilization of the K20X Tesla GPUs on each Titan node of 1.4x, with the charge density update showing a speed up of 2x. Further acceleration opportunities will be discussed. Work supported by the LDRD Program of ORNL managed by UT-Battle, LLC, for the U.S. DOE and by the Oak Ridge Leadership Computing Facility, which is a DOE Office of Science User Facility supported under Contract DE-AC05-00OR22725.
GPU-accelerated algorithms for many-particle continuous-time quantum walks
Piccinini, Enrico; Benedetti, Claudia; Siloi, Ilaria; Paris, Matteo G. A.; Bordone, Paolo
2017-06-01
Many-particle continuous-time quantum walks (CTQWs) represent a resource for several tasks in quantum technology, including quantum search algorithms and universal quantum computation. In order to design and implement CTQWs in a realistic scenario, one needs effective simulation tools for Hamiltonians that take into account static noise and fluctuations in the lattice, i.e. Hamiltonians containing stochastic terms. To this aim, we suggest a parallel algorithm based on the Taylor series expansion of the evolution operator, and compare its performances with those of algorithms based on the exact diagonalization of the Hamiltonian or a 4th order Runge-Kutta integration. We prove that both Taylor-series expansion and Runge-Kutta algorithms are reliable and have a low computational cost, the Taylor-series expansion showing the additional advantage of a memory allocation not depending on the precision of calculation. Both algorithms are also highly parallelizable within the SIMT paradigm, and are thus suitable for GPGPU computing. In turn, we have benchmarked 4 NVIDIA GPUs and 3 quad-core Intel CPUs for a 2-particle system over lattices of increasing dimension, showing that the speedup provided by GPU computing, with respect to the OPENMP parallelization, lies in the range between 8x and (more than) 20x, depending on the frequency of post-processing. GPU-accelerated codes thus allow one to overcome concerns about the execution time, and make it possible simulations with many interacting particles on large lattices, with the only limit of the memory available on the device.
DEFF Research Database (Denmark)
Knecht, Stefan; Jensen, Hans Jørgen Aagaard; Fleig, Timo
2010-01-01
We present a parallel implementation of a large-scale relativistic double-group configuration interaction CIprogram. It is applicable with a large variety of two- and four-component Hamiltonians. The parallel algorithm is based on a distributed data model in combination with a static load balanci...
O'Keeffe, C J; Ren, Ruichao; Orkoulas, G
2007-11-21
Spatial updating grand canonical Monte Carlo algorithms are generalizations of random and sequential updating algorithms for lattice systems to continuum fluid models. The elementary steps, insertions or removals, are constructed by generating points in space either at random (random updating) or in a prescribed order (sequential updating). These algorithms have previously been developed only for systems of impenetrable spheres for which no particle overlap occurs. In this work, spatial updating grand canonical algorithms are generalized to continuous, soft-core potentials to account for overlapping configurations. Results on two- and three-dimensional Lennard-Jones fluids indicate that spatial updating grand canonical algorithms, both random and sequential, converge faster than standard grand canonical algorithms. Spatial algorithms based on sequential updating not only exhibit the fastest convergence but also are ideal for parallel implementation due to the absence of strict detailed balance and the nature of the updating that minimizes interprocessor communication. Parallel simulation results for three-dimensional Lennard-Jones fluids show a substantial reduction of simulation time for systems of moderate and large size. The efficiency improvement by parallel processing through domain decomposition is always in addition to the efficiency improvement by sequential updating.
Implementation of hybrid parallel kanban-CONWIP system: A case study
Directory of Open Access Journals (Sweden)
Joshua Prakash
2014-12-01
Full Text Available The most common form of production control strategy in lean management is the pull system. One emerging form of pull system uses kanban and CONWIP systems to handle products with different demand patterns. Case studies have protractedly depicted the actual implementation of pull systems; however, the use of hybrid systems is rare. This paper examines the procedures involved in implementing a hybrid system in a low variety/low volume shop floor. This paper presents discussions on shop floor constraints in the proposed system and how the simplicity of a pull system is able to reduce work-in-process inventory by 23%. Guidelines for the replication of the system for similar production environments are also provided. The case study proves that pull systems can be successfully implemented in production environments that do not conform to the typical prerequisites of the kanban system.
GPU based contouring method on grid DEM data
Tan, Liheng; Wan, Gang; Li, Feng; Chen, Xiaohui; Du, Wenlong
2017-08-01
This paper presents a novel method to generate contour lines from grid DEM data based on the programmable GPU pipeline. The previous contouring approaches often use CPU to construct a finite element mesh from the raw DEM data, and then extract contour segments from the elements. They also need a tracing or sorting strategy to generate the final continuous contours. These approaches can be heavily CPU-costing and time-consuming. Meanwhile the generated contours would be unsmooth if the raw data is sparsely distributed. Unlike the CPU approaches, we employ the GPU's vertex shader to generate a triangular mesh with arbitrary user-defined density, in which the height of each vertex is calculated through a third-order Cardinal spline function. Then in the same frame, segments are extracted from the triangles by the geometry shader, and translated to the CPU-side with an internal order in the GPU's transform feedback stage. Finally we propose a "Grid Sorting" algorithm to achieve the continuous contour lines by travelling the segments only once. Our method makes use of multiple stages of GPU pipeline for computation, which can generate smooth contour lines, and is significantly faster than the previous CPU approaches. The algorithm can be easily implemented with OpenGL 3.3 API or higher on consumer-level PCs.
Parallel implementation of D-Phylo algorithm for maximum likelihood clusters.
Malik, Shamita; Sharma, Dolly; Khatri, Sunil Kumar
2017-03-01
This study explains a newly developed parallel algorithm for phylogenetic analysis of DNA sequences. The newly designed D-Phylo is a more advanced algorithm for phylogenetic analysis using maximum likelihood approach. The D-Phylo while misusing the seeking capacity of k -means keeps away from its real constraint of getting stuck at privately conserved motifs. The authors have tested the behaviour of D-Phylo on Amazon Linux Amazon Machine Image(Hardware Virtual Machine)i2.4xlarge, six central processing unit, 122 GiB memory, 8 × 800 Solid-state drive Elastic Block Store volume, high network performance up to 15 processors for several real-life datasets. Distributing the clusters evenly on all the processors provides us the capacity to accomplish a near direct speed if there should arise an occurrence of huge number of processors.
Grid-based Parallel Data Streaming Implemented for the Gyrokinetic Toroidal Code
International Nuclear Information System (INIS)
Klasky, S.; Ethier, S.; Lin, Z.; Martins, K.; McCune, D.; Samtaney, R.
2003-01-01
We have developed a threaded parallel data streaming approach using Globus to transfer multi-terabyte simulation data from a remote supercomputer to the scientist's home analysis/visualization cluster, as the simulation executes, with negligible overhead. Data transfer experiments show that this concurrent data transfer approach is more favorable compared with writing to local disk and then transferring this data to be post-processed. The present approach is conducive to using the grid to pipeline the simulation with post-processing and visualization. We have applied this method to the Gyrokinetic Toroidal Code (GTC), a 3-dimensional particle-in-cell code used to study microturbulence in magnetic confinement fusion from first principles plasma theory
Wheatley, Thomas E.; Michaloski, John L.; Lumia, Ronald
1989-01-01
Analysis of a robot control system leads to a broad range of processing requirements. One fundamental requirement of a robot control system is the necessity of a microcomputer system in order to provide sufficient processing capability.The use of multiple processors in a parallel architecture is beneficial for a number of reasons, including better cost performance, modular growth, increased reliability through replication, and flexibility for testing alternate control strategies via different partitioning. A survey of the progression from low level control synchronizing primitives to higher level communication tools is presented. The system communication and control mechanisms of existing robot control systems are compared to the hierarchical control model. The impact of this design methodology on the current robot control systems is explored.
Experimental implementation of parallel riverbed erosion to study vegetation uprooting by flow
Perona, Paolo; Edmaier, Katharina; Crouzy, Benoît
2014-05-01
In nature, flow erosion leading to the uprooting of vegetation is often a delayed process that gradually reduces anchoring by root exposure and correspondingly increases drag on the exposed biomass. The process determining scouring or deposition of the riverbed, and consequently plant root exposure is complex and scale dependent. At the local scale, it is hydrodynamically driven and depends on obstacle porosity, as well as sediment vs obstacle size ratio. At a larger scale it results from morphodynamic conditions, which mostly depend on riverbed topography and stream bedload transport capacity. In the latter case, ablation of sediment gradually reduces local bed elevation around the obstacle at a scale larger than the obstacle size, and uprooting eventually occurs when flow drag exceeds the residual anchoring. Ideally, one would study the timescales of vegetation uprooting by flow by inducing parallel bed erosion. This condition is not trivial to obtain experimentally because bed elevation adjustments occur in relation to longitudinal changes in sediment apportion as described by Exner's equation. In this work, we study the physical conditions leading to parallel bed erosion by reducing Exner equation closed for bedload transport to a nonlinear partial differential equation, and showing that this is a particular "boundary value" problem. Eventually, we use the data of Edmaier (2014) from a small scale mobile-bed flume setup to verify the proposed theoretical framework, and to show how such a simple experiment can provide useful insights into the timescales of the uprooting process (Edmaier et al., 2011). REFERENCES - Edmaier, K., P. Burlando, and P. Perona (2011). Mechanisms of vegetation uprooting by flow in alluvial non-cohesive sediment. Hydrology and Earth System Sciences, vol. 15, p. 1615-1627. - Edmaier, K. Uprooting mechanisms of juvenile vegetation by flow. PhD thesis, EPFL, in preparation.
Massively Parallel Dimension Independent Adaptive Metropolis
Chen, Yuxin
2015-05-14
This work considers black-box Bayesian inference over high-dimensional parameter spaces. The well-known and widely respected adaptive Metropolis (AM) algorithm is extended herein to asymptotically scale uniformly with respect to the underlying parameter dimension, by respecting the variance, for Gaussian targets. The result- ing algorithm, referred to as the dimension-independent adaptive Metropolis (DIAM) algorithm, also shows improved performance with respect to adaptive Metropolis on non-Gaussian targets. This algorithm is further improved, and the possibility of probing high-dimensional targets is enabled, via GPU-accelerated numerical libraries and periodically synchronized concurrent chains (justified a posteriori). Asymptoti- cally in dimension, this massively parallel dimension-independent adaptive Metropolis (MPDIAM) GPU implementation exhibits a factor of four improvement versus the CPU-based Intel MKL version alone, which is itself already a factor of three improve- ment versus the serial version. The scaling to multiple CPUs and GPUs exhibits a form of strong scaling in terms of the time necessary to reach a certain convergence criterion, through a combination of longer time per sample batch (weak scaling) and yet fewer necessary samples to convergence. This is illustrated by e ciently sampling from several Gaussian and non-Gaussian targets for dimension d 1000.
GPU-based Scalable Volumetric Reconstruction for Multi-view Stereo
Energy Technology Data Exchange (ETDEWEB)
Kim, H; Duchaineau, M; Max, N
2011-09-21
We present a new scalable volumetric reconstruction algorithm for multi-view stereo using a graphics processing unit (GPU). It is an effectively parallelized GPU algorithm that simultaneously uses a large number of GPU threads, each of which performs voxel carving, in order to integrate depth maps with images from multiple views. Each depth map, triangulated from pair-wise semi-dense correspondences, represents a view-dependent surface of the scene. This algorithm also provides scalability for large-scale scene reconstruction in a high resolution voxel grid by utilizing streaming and parallel computation. The output is a photo-realistic 3D scene model in a volumetric or point-based representation. We demonstrate the effectiveness and the speed of our algorithm with a synthetic scene and real urban/outdoor scenes. Our method can also be integrated with existing multi-view stereo algorithms such as PMVS2 to fill holes or gaps in textureless regions.
DEFF Research Database (Denmark)
Dollerup, Niels; Jepsen, Michael S.; Frier, Christian
2014-01-01
A robust and effective finite element based implementation of lower bound limit state analysis applying an interior point formulation is presented in this paper. The lower bound formulation results in a convex optimization problem consisting of a number of linear constraints from the equilibrium...
International Nuclear Information System (INIS)
Kudela, Henryk; Kosior, Andrzej
2014-01-01
Understanding the dynamics and the mutual interaction among various types of vortical motions is a key ingredient in clarifying and controlling fluid motion. In the paper several different cases related to vortex tube interactions are presented. Due to problems with very long computation times on the single processor, the vortex-in-cell (VIC) method is implemented on the multicore architecture of a graphics processing unit (GPU). Numerical results of leapfrogging of two vortex rings for inviscid and viscous fluid are presented as test cases for the new multi-GPU implementation of the VIC method. Influence of the Reynolds number on the reconnection process is shown for two examples: antiparallel vortex tubes and orthogonally offset vortex tubes. Our aim is to show the great potential of the VIC method for solutions of three-dimensional flow problems and that the VIC method is very well suited for parallel computation. (paper)
Directory of Open Access Journals (Sweden)
Narayanan Manikandan
2016-01-01
Full Text Available Software development life cycle has been characterized by destructive disconnects between activities like planning, analysis, design, and programming. Particularly software developed with prediction based results is always a big challenge for designers. Time series data forecasting like currency exchange, stock prices, and weather report are some of the areas where an extensive research is going on for the last three decades. In the initial days, the problems with financial analysis and prediction were solved by statistical models and methods. For the last two decades, a large number of Artificial Neural Networks based learning models have been proposed to solve the problems of financial data and get accurate results in prediction of the future trends and prices. This paper addressed some architectural design related issues for performance improvement through vectorising the strengths of multivariate econometric time series models and Artificial Neural Networks. It provides an adaptive approach for predicting exchange rates and it can be called hybrid methodology for predicting exchange rates. This framework is tested for finding the accuracy and performance of parallel algorithms used.
International Nuclear Information System (INIS)
Solchenbach, K.; Thole, C.A.; Trottenberg, U.
1987-01-01
For a wide class of problems in scientific computing, in particular for partial differential equations, the multigrid principle has proved to yield highly efficient numerical methods. However, the principle has to be applied carefully: if the multigrid components are not chosen adequately with respect to the given problem, the efficiency may be much smaller than possible. This has been demonstrated for many practical problems. Unfortunately, the general theories on multigrid convergence do not give much help in constructing really efficient multigrid algorithms. Although some progress has been made in bridging the gap between theory and practice during the last few years, there are still several theoretical approaches which are misleading rather than helpful with respect to the objective of real efficiency. The research in finding highly efficient algorithms for non-model applications therefore is still a sophisticated mixture of theoretical considerations, a transfer of experiences from model to real life problems and systematical experimental work. The emphasis of the practical research activity today lies - among others - in the following fields: - finding efficient multigrid components for really complex problems, - combining the multigrid approach with advanced discretizative techniques: - constructing highly parallel multigrid algorithms. In this paper, we want to deal mainly with the last topic
Zeng, Qiao; Liang, WanZhen
2015-10-07
The time-dependent density functional theory (TDDFT) has become the most popular method to calculate the electronic excitation energies, describe the excited-state properties, and perform the excited-state geometric optimization of medium and large-size molecules due to the implementation of analytic excited-state energy gradient and Hessian in many electronic structure software packages. To describe the molecules in condensed phase, one usually adopts the computationally efficient hybrid Quantum Mechanics/Molecular Mechanics (QM/MM) models. Here, we extend our previous work on the energy gradient of TDDFT/MM excited state to account for the mutual polarization effects between QM and MM regions, which is believed to hold a crucial position in the potential energy surface of molecular systems when the photoexcitation-induced charge rearrangement in the QM region is drastic. The implementation of a simple polarizable TDDFT/MM (TDDFT/MMpol) model in Q-Chem/CHARMM interface with both the linear response and the state-specific features has been realized. Several benchmark tests and preliminary applications are exhibited to confirm our implementation and assess the effects of different treatment of environmental polarization on the excited-state properties, and the efficiency of parallel implementation is demonstrated as well.
Massively parallel Monte Carlo for many-particle simulations on GPUs
Energy Technology Data Exchange (ETDEWEB)
Anderson, Joshua A.; Jankowski, Eric [Department of Chemical Engineering, University of Michigan, Ann Arbor, MI 48109 (United States); Grubb, Thomas L. [Department of Materials Science and Engineering, University of Michigan, Ann Arbor, MI 48109 (United States); Engel, Michael [Department of Chemical Engineering, University of Michigan, Ann Arbor, MI 48109 (United States); Glotzer, Sharon C., E-mail: sglotzer@umich.edu [Department of Chemical Engineering, University of Michigan, Ann Arbor, MI 48109 (United States); Department of Materials Science and Engineering, University of Michigan, Ann Arbor, MI 48109 (United States)
2013-12-01
Current trends in parallel processors call for the design of efficient massively parallel algorithms for scientific computing. Parallel algorithms for Monte Carlo simulations of thermodynamic ensembles of particles have received little attention because of the inherent serial nature of the statistical sampling. In this paper, we present a massively parallel method that obeys detailed balance and implement it for a system of hard disks on the GPU. We reproduce results of serial high-precision Monte Carlo runs to verify the method. This is a good test case because the hard disk equation of state over the range where the liquid transforms into the solid is particularly sensitive to small deviations away from the balance conditions. On a Tesla K20, our GPU implementation executes over one billion trial moves per second, which is 148 times faster than on a single Intel Xeon E5540 CPU core, enables 27 times better performance per dollar, and cuts energy usage by a factor of 13. With this improved performance we are able to calculate the equation of state for systems of up to one million hard disks. These large system sizes are required in order to probe the nature of the melting transition, which has been debated for the last forty years. In this paper we present the details of our computational method, and discuss the thermodynamics of hard disks separately in a companion paper.
A fast implementation of the incremental backprojection algorithms for parallel beam geometries
International Nuclear Information System (INIS)
Chen, C.M.; Wang, C.Y.; Cho, Z.H.
1996-01-01
Filtered-backprojection algorithms are the most widely used approaches for reconstruction of computed tomographic (CT) images, such as X-ray CT and positron emission tomographic (PET) images. The Incremental backprojection algorithm is a fast backprojection approach based on restructuring the Shepp and Logan algorithm. By exploiting interdependency (position and values) of adjacent pixels, the Incremental algorithm requires only O(N) and O(N 2 ) multiplications in contrast to O(N 2 ) and O(N 3 ) multiplications for the Shepp and Logan algorithm in two-dimensional (2-D) and three-dimensional (3-D) backprojections, respectively, for each view, where N is the size of the image in each dimension. In addition, it may reduce the number of additions for each pixel computation. The improvement achieved by the Incremental algorithm in practice was not, however, as significant as expected. One of the main reasons is due to inevitably visiting pixels outside the beam in the searching flow scheme originally developed for the Incremental algorithm. To optimize implementation of the Incremental algorithm, an efficient scheme, namely, coded searching flow scheme, is proposed in this paper to minimize the overhead caused by searching for all pixels in a beam. The key idea of this scheme is to encode the searching flow for all pixels inside each beam. While backprojecting, all pixels may be visited without any overhead due to using the coded searching flow as the a priori information. The proposed coded searching flow scheme has been implemented on a Sun Sparc 10 and a Sun Sparc 20 workstations. The implementation results show that the proposed scheme is 1.45--2.0 times faster than the original searching flow scheme for most cases tested
Programming massively parallel processors a hands-on approach
Kirk, David B
2010-01-01
Programming Massively Parallel Processors discusses basic concepts about parallel programming and GPU architecture. ""Massively parallel"" refers to the use of a large number of processors to perform a set of computations in a coordinated parallel way. The book details various techniques for constructing parallel programs. It also discusses the development process, performance level, floating-point format, parallel patterns, and dynamic parallelism. The book serves as a teaching guide where parallel programming is the main topic of the course. It builds on the basics of C programming for CUDA, a parallel programming environment that is supported on NVI- DIA GPUs. Composed of 12 chapters, the book begins with basic information about the GPU as a parallel computer source. It also explains the main concepts of CUDA, data parallelism, and the importance of memory access efficiency using CUDA. The target audience of the book is graduate and undergraduate students from all science and engineering disciplines who ...
König, Katharina; Peifer, Martin; Fassunke, Jana; Ihle, Michaela A; Künstlinger, Helen; Heydt, Carina; Stamm, Katrin; Ueckeroth, Frank; Vollbrecht, Claudia; Bos, Marc; Gardizi, Masyar; Scheffler, Matthias; Nogova, Lucia; Leenders, Frauke; Albus, Kerstin; Meder, Lydia; Becker, Kerstin; Florin, Alexandra; Rommerscheidt-Fuss, Ursula; Altmüller, Janine; Kloth, Michael; Nürnberg, Peter; Henkel, Thomas; Bikár, Sven-Ernö; Sos, Martin L; Geese, William J; Strauss, Lewis; Ko, Yon-Dschun; Gerigk, Ulrich; Odenthal, Margarete; Zander, Thomas; Wolf, Jürgen; Merkelbach-Bruse, Sabine; Buettner, Reinhard; Heukamp, Lukas C
2015-07-01
The Network Genomic Medicine Lung Cancer was set up to rapidly translate scientific advances into early clinical trials of targeted therapies in lung cancer performing molecular analyses of more than 3500 patients annually. Because sequential analysis of the relevant driver mutations on fixated samples is challenging in terms of workload, tissue availability, and cost, we established multiplex parallel sequencing in routine diagnostics. The aim was to analyze all therapeutically relevant mutations in lung cancer samples in a high-throughput fashion while significantly reducing turnaround time and amount of input DNA compared with conventional dideoxy sequencing of single polymerase chain reaction amplicons. In this study, we demonstrate the feasibility of a 102 amplicon multiplex polymerase chain reaction followed by sequencing on an Illumina sequencer on formalin-fixed paraffin-embedded tissue in routine diagnostics. Analysis of a validation cohort of 180 samples showed this approach to require significantly less input material and to be more reliable, robust, and cost-effective than conventional dideoxy sequencing. Subsequently, 2657 lung cancer patients were analyzed. We observed that comprehensive biomarker testing provided novel information in addition to histological diagnosis and clinical staging. In 2657 consecutively analyzed lung cancer samples, we identified driver mutations at the expected prevalence. Furthermore we found potentially targetable DDR2 mutations at a frequency of 3% in both adenocarcinomas and squamous cell carcinomas. Overall, our data demonstrate the utility of systematic sequencing analysis in a clinical routine setting and highlight the dramatic impact of such an approach on the availability of therapeutic strategies for the targeted treatment of individual cancer patients.
Directory of Open Access Journals (Sweden)
Bachmann M.
2011-12-01
Full Text Available The concept of fully adaptive multiresolution finite volume schemes has been developed and investigated during the past decade. Here grid adaptation is realized by performing a multiscale decomposition of the discrete data at hand. By means of hard thresholding the resulting multiscale data are compressed. From the remaining data a locally refined grid is constructed. The aim of the present work is to give a self-contained overview on the construction of an appropriate multiresolution analysis using biorthogonal wavelets, its efficient realization by means of hash maps using global cell identifiers and the parallelization of the multiresolution-based grid adaptation via MPI using space-filling curves. Le concept des schémas de volumes finis multi-échelles et adaptatifs a été développé et etudié pendant les dix dernières années. Ici le maillage adaptatif est réalisé en effectuant une décomposition multi-échelle des données discrètes proches. En les tronquant à l’aide d’une valeur seuil fixée, les données multi-échelles obtenues sont compressées. A partir de celles-ci, le maillage est raffiné localement. Le but de ce travail est de donner un aperçu concis de la construction d’une analyse appropriée de multiresolution utilisant les fonctions ondelettes biorthogonales, de son efficacité d’application en terme de tables de hachage en utilisant des identification globales de cellule et de la parallélisation du maillage adaptatif multirésolution via MPI à l’aide des courbes remplissantes.
Cost-effective GPU-grid for genome-wide epistasis calculations.
Pütz, B; Kam-Thong, T; Karbalai, N; Altmann, A; Müller-Myhsok, B
2013-01-01
Until recently, genotype studies were limited to the investigation of single SNP effects due to the computational burden incurred when studying pairwise interactions of SNPs. However, some genetic effects as simple as coloring (in plants and animals) cannot be ascribed to a single locus but only understood when epistasis is taken into account [1]. It is expected that such effects are also found in complex diseases where many genes contribute to the clinical outcome of affected individuals. Only recently have such problems become feasible computationally. The inherently parallel structure of the problem makes it a perfect candidate for massive parallelization on either grid or cloud architectures. Since we are also dealing with confidential patient data, we were not able to consider a cloud-based solution but had to find a way to process the data in-house and aimed to build a local GPU-based grid structure. Sequential epistatsis calculations were ported to GPU using CUDA at various levels. Parallelization on the CPU was compared to corresponding GPU counterparts with regards to performance and cost. A cost-effective solution was created by combining custom-built nodes equipped with relatively inexpensive consumer-level graphics cards with highly parallel GPUs in a local grid. The GPU method outperforms current cluster-based systems on a price/performance criterion, as a single GPU shows speed performance comparable up to 200 CPU cores. The outlined approach will work for problems that easily lend themselves to massive parallelization. Code for various tasks has been made available and ongoing development of tools will further ease the transition from sequential to parallel algorithms.
International Nuclear Information System (INIS)
Phillips, Carolyn L.; Anderson, Joshua A.; Glotzer, Sharon C.
2011-01-01
Highlights: → Molecular Dynamics codes implemented on GPUs have achieved two-order of magnitude computational accelerations. → Brownian Dynamics and Dissipative Particle Dynamics simulations require a large number of random numbers per time step. → We introduce a method for generating small batches of pseudorandom numbers distributed over many threads of calculations. → With this method, Dissipative Particle Dynamics is implemented on a GPU device without requiring thread-to-thread communication. - Abstract: Brownian Dynamics (BD), also known as Langevin Dynamics, and Dissipative Particle Dynamics (DPD) are implicit solvent methods commonly used in models of soft matter and biomolecular systems. The interaction of the numerous solvent particles with larger particles is coarse-grained as a Langevin thermostat is applied to individual particles or to particle pairs. The Langevin thermostat requires a pseudo-random number generator (PRNG) to generate the stochastic force applied to each particle or pair of neighboring particles during each time step in the integration of Newton's equations of motion. In a Single-Instruction-Multiple-Thread (SIMT) GPU parallel computing environment, small batches of random numbers must be generated over thousands of threads and millions of kernel calls. In this communication we introduce a one-PRNG-per-kernel-call-per-thread scheme, in which a micro-stream of pseudorandom numbers is generated in each thread and kernel call. These high quality, statistically robust micro-streams require no global memory for state storage, are more computationally efficient than other PRNG schemes in memory-bound kernels, and uniquely enable the DPD simulation method without requiring communication between threads.
Parallel Implementation of the CCSDS 1.2.3 Standard for Hyperspectral Lossless Compression
Directory of Open Access Journals (Sweden)
Daniel Báscones
2017-09-01
Full Text Available Hyperspectral imaging is a technology which, by sensing hundreds of wavelengths per pixel, enables fine studies of the captured objects. This produces great amounts of data that require equally big storage, and compression with algorithms such as the Consultative Committee for Space Data Systems (CCSDS 1.2.3 standard is a must. However, the speed of this lossless compression algorithm is not enough in some real-time scenarios if we use a single-core processor. This is where architectures such as Field Programmable Gate Arrays (FPGAs and Graphics Processing Units (GPUs can shine best. In this paper, we present both FPGA and OpenCL implementations of the CCSDS 1.2.3 algorithm. The proposed paralellization method has been implemented on the Virtex-7 XC7VX690T, Virtex-5 XQR5VFX130 and Virtex-4 XC2VFX60 FPGAs, and on the GT440 and GT610 GPUs, and tested using hyperspectral data from NASA’s Airborne Visible Infra-Red Imaging Spectrometer (AVIRIS. Both approaches fulfill our real-time requirements. This paper attempts to shed some light on the comparison between both approaches, including other works from existing literature, explaining the trade-offs of each one.
GPU-Accelerated Real-Time Surveillance De-Weathering
Pettersson, Niklas
2013-01-01
A fully automatic de-weathering system to increase the visibility/stability in surveillance applications during bad weather has been developed. Rain, snow and haze during daylight are handled in real-time performance with acceleration from CUDA implemented algorithms. Video from fixed cameras is processed on a PC with no need of special hardware except an NVidia GPU. The system does not use any background model and does not require any precalibration. Increase in contrast is obtained in all h...
International Nuclear Information System (INIS)
Park, Sook Hee
2001-02-01
This thesis implements and analyzes the parallel and networked computing libraries based on the multiprocessor computer architecture as well as networked computers, aiming at improving the computation speed of ET(Electrical Tomography) system which requires enormous CPU time in reconstructing the unknown internal state of the target object. As an instance of the typical tomography technology, ET partitions the cross-section of the target object into the tiny elements and calculates the resistivity of them with signal values measured at the boundary electrodes surrounding the surface of the object after injecting the predetermined current pattern through the object. The number of elements is determined considering the trade-off between the accuracy of the reconstructed image and the computation time. As the elements become more finer, the number of element increases, and the system can get the better image. However, the reconstruction time increases polynomially with the number of partitioned elements since the procedure consists of a number of time consuming matrix operations such as multiplication, inverse, pseudo inverse, Jacobian and so on. Consequently, the demand for improving computation speed via multiple processor grows indispensably. Moreover, currently released PCs can be stuffed with up to 4 CPUs interconnected to the shared memory while some operating systems enable the application process to benefit from such computer by allocating the threaded job to each CPU, resulting in concurrent processing. In addition, a networked computing or cluster computing environment is commonly available to almost every computer which contains communication protocol and is connected to local or global network. After partitioning the given job(numerical operation), each CPU or computer calculates the partial result independently, and the results are merged via common memory to produce the final result. It is desirable to adopt the commonly used library such as Matlab to
Energy Technology Data Exchange (ETDEWEB)
2017-04-04
A parallelization of the k-means++ seed selection algorithm on three distinct hardware platforms: GPU, multicore CPU, and multithreaded architecture. K-means++ was developed by David Arthur and Sergei Vassilvitskii in 2007 as an extension of the k-means data clustering technique. These algorithms allow people to cluster multidimensional data, by attempting to minimize the mean distance of data points within a cluster. K-means++ improved upon traditional k-means by using a more intelligent approach to selecting the initial seeds for the clustering process. While k-means++ has become a popular alternative to traditional k-means clustering, little work has been done to parallelize this technique. We have developed original C++ code for parallelizing the algorithm on three unique hardware architectures: GPU using NVidia's CUDA/Thrust framework, multicore CPU using OpenMP, and the Cray XMT multithreaded architecture. By parallelizing the process for these platforms, we are able to perform k-means++ clustering much more quickly than it could be done before.
Energy Technology Data Exchange (ETDEWEB)
Ha, Woo Seok; Kim, Soo Mee; Park, Min Jae; Lee, Dong Soo; Lee, Jae Sung [Seoul National University, Seoul (Korea, Republic of)
2009-10-15
The maximum likelihood-expectation maximization (ML-EM) is the statistical reconstruction algorithm derived from probabilistic model of the emission and detection processes. Although the ML-EM has many advantages in accuracy and utility, the use of the ML-EM is limited due to the computational burden of iterating processing on a CPU (central processing unit). In this study, we developed a parallel computing technique on GPU (graphic processing unit) for ML-EM algorithm. Using Geforce 9800 GTX+ graphic card and CUDA (compute unified device architecture) the projection and backprojection in ML-EM algorithm were parallelized by NVIDIA's technology. The time delay on computations for projection, errors between measured and estimated data and backprojection in an iteration were measured. Total time included the latency in data transmission between RAM and GPU memory. The total computation time of the CPU- and GPU-based ML-EM with 32 iterations were 3.83 and 0.26 sec, respectively. In this case, the computing speed was improved about 15 times on GPU. When the number of iterations increased into 1024, the CPU- and GPU-based computing took totally 18 min and 8 sec, respectively. The improvement was about 135 times and was caused by delay on CPU-based computing after certain iterations. On the other hand, the GPU-based computation provided very small variation on time delay per iteration due to use of shared memory. The GPU-based parallel computation for ML-EM improved significantly the computing speed and stability. The developed GPU-based ML-EM algorithm could be easily modified for some other imaging geometries
International Nuclear Information System (INIS)
Ha, Woo Seok; Kim, Soo Mee; Park, Min Jae; Lee, Dong Soo; Lee, Jae Sung
2009-01-01
The maximum likelihood-expectation maximization (ML-EM) is the statistical reconstruction algorithm derived from probabilistic model of the emission and detection processes. Although the ML-EM has many advantages in accuracy and utility, the use of the ML-EM is limited due to the computational burden of iterating processing on a CPU (central processing unit). In this study, we developed a parallel computing technique on GPU (graphic processing unit) for ML-EM algorithm. Using Geforce 9800 GTX+ graphic card and CUDA (compute unified device architecture) the projection and backprojection in ML-EM algorithm were parallelized by NVIDIA's technology. The time delay on computations for projection, errors between measured and estimated data and backprojection in an iteration were measured. Total time included the latency in data transmission between RAM and GPU memory. The total computation time of the CPU- and GPU-based ML-EM with 32 iterations were 3.83 and 0.26 sec, respectively. In this case, the computing speed was improved about 15 times on GPU. When the number of iterations increased into 1024, the CPU- and GPU-based computing took totally 18 min and 8 sec, respectively. The improvement was about 135 times and was caused by delay on CPU-based computing after certain iterations. On the other hand, the GPU-based computation provided very small variation on time delay per iteration due to use of shared memory. The GPU-based parallel computation for ML-EM improved significantly the computing speed and stability. The developed GPU-based ML-EM algorithm could be easily modified for some other imaging geometries