GPGPU-4最新文献

筛选
英文 中文
Automatically generating and tuning GPU code for sparse matrix-vector multiplication from a high-level representation 自动生成和调整GPU代码稀疏矩阵向量乘法从一个高级表示
GPGPU-4 Pub Date : 2011-03-05 DOI: 10.1145/1964179.1964196
Dominik Grewe, Anton Lokhmotov
{"title":"Automatically generating and tuning GPU code for sparse matrix-vector multiplication from a high-level representation","authors":"Dominik Grewe, Anton Lokhmotov","doi":"10.1145/1964179.1964196","DOIUrl":"https://doi.org/10.1145/1964179.1964196","url":null,"abstract":"We propose a system-independent representation of sparse matrix formats that allows a compiler to generate efficient, system-specific code for sparse matrix operations. To show the viability of such a representation we have developed a compiler that generates and tunes code for sparse matrix-vector multiplication (SpMV) on GPUs. We evaluate our framework on six state-of-the-art matrix formats and show that the generated code performs similar to or better than hand-optimized code.","PeriodicalId":317571,"journal":{"name":"GPGPU-4","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116824066","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 57
Floating-point data compression at 75 Gb/s on a GPU 在GPU上以75 Gb/s的速度压缩浮点数据
GPGPU-4 Pub Date : 2011-03-05 DOI: 10.1145/1964179.1964189
M. A. O'Neil, Martin Burtscher
{"title":"Floating-point data compression at 75 Gb/s on a GPU","authors":"M. A. O'Neil, Martin Burtscher","doi":"10.1145/1964179.1964189","DOIUrl":"https://doi.org/10.1145/1964179.1964189","url":null,"abstract":"Numeric simulations often generate large amounts of data that need to be stored or sent to other compute nodes. This paper investigates whether GPUs are powerful enough to make real-time data compression and decompression possible in such environments, that is, whether they can operate at the 32- or 40-Gb/s throughput of emerging network cards. The fastest parallel CPU-based floating-point data compression algorithm operates below 20 Gb/s on eight Xeon cores, which is significantly slower than the network speed and thus insufficient for compression to be practical in high-end networks. As a remedy, we have created the highly parallel GFC compression algorithm for double-precision floating-point data. This algorithm is specifically designed for GPUs. It compresses at a minimum of 75 Gb/s, decompresses at 90 Gb/s and above, and can therefore improve internode communication throughput on current and upcoming networks by fully saturating the interconnection links with compressed data.","PeriodicalId":317571,"journal":{"name":"GPGPU-4","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121298571","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 65
A framework for dynamically instrumenting GPU compute applications within GPU Ocelot 在GPU Ocelot中动态检测GPU计算应用程序的框架
GPGPU-4 Pub Date : 2011-03-05 DOI: 10.1145/1964179.1964192
N. Farooqui, Andrew Kerr, G. Diamos, S. Yalamanchili, K. Schwan
{"title":"A framework for dynamically instrumenting GPU compute applications within GPU Ocelot","authors":"N. Farooqui, Andrew Kerr, G. Diamos, S. Yalamanchili, K. Schwan","doi":"10.1145/1964179.1964192","DOIUrl":"https://doi.org/10.1145/1964179.1964192","url":null,"abstract":"In this paper we present the design and implementation of a dynamic instrumentation infrastructure for PTX programs that procedurally transforms kernels and manages related data structures. We show how performing instrumentation within the GPU Ocelot dynamic compiler infrastructure provides unique capabilities not available to other profiling and instrumentation toolchains for GPU computing. We demonstrate the utility of this instrumentation capability with three example scenarios - (1) performing workload characterization accelerated by a GPU, (2) providing load imbalance information for use by a resource allocator, and (3) providing compute utilization feedback to be used online by a simulated process scheduler that might be found in a hypervisor. Additionally, we measure both (1) the compilation overheads of performing dynamic compilation and (2) the increases in runtimes when executing instrumented kernels. On average, compilation overheads due to instrumentation consisted of 69% of the time needed to parse a kernel module, in the case of the Parboil benchmark suite. Slowdowns for instrumenting each basic block ranged from 1.5x to 5.5x, with the largest slowdowns attributed to kernels with large numbers of short, compute-bound blocks.","PeriodicalId":317571,"journal":{"name":"GPGPU-4","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132339468","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 62
Analyzing program flow within a many-kernel OpenCL application 分析多内核OpenCL应用程序中的程序流
GPGPU-4 Pub Date : 2011-03-05 DOI: 10.1145/1964179.1964193
Perhaad Mistry, Chris Gregg, Norman Rubin, D. Kaeli, K. Hazelwood
{"title":"Analyzing program flow within a many-kernel OpenCL application","authors":"Perhaad Mistry, Chris Gregg, Norman Rubin, D. Kaeli, K. Hazelwood","doi":"10.1145/1964179.1964193","DOIUrl":"https://doi.org/10.1145/1964179.1964193","url":null,"abstract":"Many developers have begun to realize that heterogeneous multi-core and many-core computer systems can provide significant performance opportunities to a range of applications. Typical applications possess multiple components that can be parallelized; developers need to be equipped with proper performance tools to analyze program flow and identify application bottlenecks. In this paper, we analyze and profile the components of the Speeded Up Robust Features (SURF) Computer Vision algorithm written in OpenCL. Our profiling framework is developed using built-in OpenCL API function calls, without the need for an external profiler. We show we can begin to identify performance bottlenecks and performance issues present in individual components on different hardware platforms. We demonstrate that by using run-time profiling using the OpenCL specification, we can provide an application developer with a fine-grained look at performance, and that this information can be used to tailor performance improvements for specific platforms.","PeriodicalId":317571,"journal":{"name":"GPGPU-4","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115458541","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 32
Unstructured grid applications on GPU: performance analysis and improvement GPU上的非结构化网格应用:性能分析和改进
GPGPU-4 Pub Date : 2011-03-05 DOI: 10.1145/1964179.1964197
L. Solano-Quinde, Z. Wang, Brett M. Bode, Arun Kumar Somani
{"title":"Unstructured grid applications on GPU: performance analysis and improvement","authors":"L. Solano-Quinde, Z. Wang, Brett M. Bode, Arun Kumar Somani","doi":"10.1145/1964179.1964197","DOIUrl":"https://doi.org/10.1145/1964179.1964197","url":null,"abstract":"Performance of applications running on GPUs is mainly affected by hardware occupancy and global memory latency. Scientific applications that rely on analysis using unstructured grids could benefit from the high performance capabilities provided by GPUs, however, its memory access pattern and algorithm limit the potential benefits.\u0000 In this paper we analyze the algorithm for unstructured grid analysis on the basis of hardware occupancy and memory access efficiency. In general, the algorithm can be divided into three stages: cell-oriented analysis, edge-oriented analysis and information update, which present different memory access patterns. Based on the analysis we modify the algorithm to make it suitable for GPUs. The proposed algorithm aims for high hardware occupancy and efficient global memory access. Finally, through implementation we show that our design achieves up to 88 times speedup compared to the sequential CPU version.","PeriodicalId":317571,"journal":{"name":"GPGPU-4","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125072433","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 20
A new method for GPU based irregular reductions and its application to k-means clustering 基于GPU的不规则约简新方法及其在k-means聚类中的应用
GPGPU-4 Pub Date : 2011-03-05 DOI: 10.1145/1964179.1964182
Balaji Dhanasekaran, Norman Rubin
{"title":"A new method for GPU based irregular reductions and its application to k-means clustering","authors":"Balaji Dhanasekaran, Norman Rubin","doi":"10.1145/1964179.1964182","DOIUrl":"https://doi.org/10.1145/1964179.1964182","url":null,"abstract":"A frequently used method of clustering is a technique called k-means clustering. The k-means algorithm consists of two steps: A map step, which is simple to execute on a GPU, and a reduce step, which is more problematic. Previous researchers have used a hybrid approach in which the map step is computed on the GPU and the reduce step is performed on the CPU. In this work, we present a new algorithm for irregular reductions and apply it to k-means such that the GPU executes both the map and reduce steps. We provide experimental comparisons using OpenCL. Our results show that our scheme is 3.2 times faster than the hybrid scheme for k = 10, an average 1.5 times faster when the number of clusters, k = 100 and on average equal for k = 400, on an ATI Radeon® HD 5870 (best speedup was 3.5 times) compared to the hybrid approach. In addition, we compare the GPU code with the standard OpenMP benchmark, MineBench. In that implementation, both the map and reduce steps are computed on the CPU. For large data sizes, the new GPU scheme shows great promise, with performance up to 35 times faster than MineBench on a four core Intel i7 CPU.","PeriodicalId":317571,"journal":{"name":"GPGPU-4","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128416728","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 24
Fast Mersenne prime testing on the GPU 在GPU上进行快速梅森质数测试
GPGPU-4 Pub Date : 2011-03-05 DOI: 10.1145/1964179.1964188
Andrew Thall
{"title":"Fast Mersenne prime testing on the GPU","authors":"Andrew Thall","doi":"10.1145/1964179.1964188","DOIUrl":"https://doi.org/10.1145/1964179.1964188","url":null,"abstract":"The Lucas-Lehmer test for Mersenne primality can be efficiently parallelized for GPU-based computation. The gpuLucas project implements an irrational-base discrete weighted transform approach (IBDWT) using balanced-integers, non-power-of-two transforms, and carry-save radix representations. gpuLucas uses the CUDA programming language and requires the double-precision floating point capabilities of recent GPUs. Results show up to 7×speedups over benchmark averages for optimized sequential code and factor-of-two speedups over CUDALucas, another GPU-based Lucas-Lehmer tester developed independently and with a different optimization strategy. This work demonstrates techniques for implementing GPU-based number theoretic algorithms on very large numbers, including fast multiplication, prefix-sum-based carry-propagation, and the use of carry-save arithmetic with balanced integers. The work presents timing profiles of convolution-based integer multiplication based on the IBDWT, in particular for non-power-of-two transformations, and establishes the usefulness of the software as a GPU benchmarking application and as a platform for large-integer and polynomial experimentation.","PeriodicalId":317571,"journal":{"name":"GPGPU-4","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131860008","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 4
Reducing branch divergence in GPU programs 减少GPU程序中的分支分歧
GPGPU-4 Pub Date : 2011-03-05 DOI: 10.1145/1964179.1964184
Tianyi David Han, Tarek S. Abdelrahman
{"title":"Reducing branch divergence in GPU programs","authors":"Tianyi David Han, Tarek S. Abdelrahman","doi":"10.1145/1964179.1964184","DOIUrl":"https://doi.org/10.1145/1964179.1964184","url":null,"abstract":"Branch divergence has a significant impact on the performance of GPU programs. We propose two novel software-based optimizations, called iteration delaying and branch distribution that aim to reduce branch divergence. Iteration delaying targets a divergent branch enclosed by a loop within a kernel. It improves performance by executing loop iterations that take the same branch direction and delaying those that take the other direction until later iterations. Branch distribution reduces the length of divergent code by factoring out structurally similar code from the branch paths. We conduct a preliminary evaluation of the two optimizations using both synthetic benchmarks and a highly-optimized real-world application. Our evaluation shows that they improve the performance of the synthetic benchmarks by as much as 30% and 80% respectively, and that of the real-world application by 12% and 16% respectively.","PeriodicalId":317571,"journal":{"name":"GPGPU-4","volume":"122 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128256285","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 194
Register packing for cyclic reduction: a case study 登记包装循环减少:一个案例研究
GPGPU-4 Pub Date : 2011-03-05 DOI: 10.1145/1964179.1964185
A. Davidson, John Douglas Owens
{"title":"Register packing for cyclic reduction: a case study","authors":"A. Davidson, John Douglas Owens","doi":"10.1145/1964179.1964185","DOIUrl":"https://doi.org/10.1145/1964179.1964185","url":null,"abstract":"We generalize a method for avoiding GPU shared communication when dealing with a downsweep pattern. We apply this generalization to Cyclic Reduction, a tridiagonal solver with this pattern. Previously, Cyclic Reduction suffered poor performance when compared to other tridiagonal solvers on the GPU due to performance issues stemming from shared-memory bandwidth bottlenecks and step-efficiency. We address this problem by applying our down-sweep shared-memory communication-reducing methodology. Our re-mapping also allows Cyclic Reduction to solve larger systems directly in a virtual block. By using our generalized mapping, we improve Cyclic Reduction's performance on a GPU by a factor of 3-4.5x over the original CR implementation, making it 1.5-3x faster than other GPU tridiagonal solvers.","PeriodicalId":317571,"journal":{"name":"GPGPU-4","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130261440","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 49
Quantifying NUMA and contention effects in multi-GPU systems 量化多gpu系统中的NUMA和争用效应
GPGPU-4 Pub Date : 2011-03-05 DOI: 10.1145/1964179.1964194
Kyle Spafford, J. Meredith, J. Vetter
{"title":"Quantifying NUMA and contention effects in multi-GPU systems","authors":"Kyle Spafford, J. Meredith, J. Vetter","doi":"10.1145/1964179.1964194","DOIUrl":"https://doi.org/10.1145/1964179.1964194","url":null,"abstract":"As system architects strive for increased density and power efficiency, the traditional compute node is being augmented with an increasing number of graphics processing units (GPUs). The integration of multiple GPUs per node introduces complex performance phenomena including non-uniform memory access (NUMA) and contention for shared system resources. Utilizing the Keeneland system, this paper quantifies these effects and presents some guidance on programming strategies to maximize performance in multi-GPU environments.","PeriodicalId":317571,"journal":{"name":"GPGPU-4","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131602163","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 54
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信
小红书