{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:17:47Z","timestamp":1750306667660,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":32,"publisher":"ACM","license":[{"start":{"date-parts":[[2015,2,7]],"date-time":"2015-02-07T00:00:00Z","timestamp":1423267200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2015,2,7]]},"DOI":"10.1145\/2716282.2716293","type":"proceedings-article","created":{"date-parts":[[2015,2,3]],"date-time":"2015-02-03T13:43:17Z","timestamp":1422970997000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A comparative investigation of device-specific mechanisms for exploiting HPC accelerators"],"prefix":"10.1145","author":[{"given":"Ayman","family":"Tarakji","sequence":"first","affiliation":[{"name":"RWTH Aachen University, Germany"}]},{"given":"Lukas","family":"B\u00f6rger","sequence":"additional","affiliation":[{"name":"RWTH Aachen University, Germany"}]},{"given":"Rainer","family":"Leupers","sequence":"additional","affiliation":[{"name":"RWTH Aachen University, Germany"}]}],"member":"320","published-online":{"date-parts":[[2015,2,7]]},"reference":[{"volume-title":"LISTS JUNE 2014","year":"2014","key":"e_1_3_2_1_1_1","unstructured":"TOP500 LISTS JUNE 2014 . http:\/\/www.top500.org\/lists\/ 2014 \/06\/. TOP500 LISTS JUNE 2014. http:\/\/www.top500.org\/lists\/2014\/06\/."},{"key":"e_1_3_2_1_2_1","volume-title":"September","author":"Phi Coprocessor Instruction Set Intel Xeon","year":"2012","unstructured":"Intel Xeon Phi Coprocessor Instruction Set Architecture Reference Manual . Technical report , September 2012 . Intel Xeon Phi Coprocessor Instruction Set Architecture Reference Manual. Technical report, September 2012."},{"key":"e_1_3_2_1_3_1","unstructured":"https:\/\/software.intel.com\/sites\/default\/ files\/forum\/278102\/327364001en.pdf.  https:\/\/software.intel.com\/sites\/default\/ files\/forum\/278102\/327364001en.pdf."},{"key":"e_1_3_2_1_4_1","volume-title":"December","author":"Instruction Set Architecture Southern Islands","year":"2012","unstructured":"Southern Islands Instruction Set Architecture . Technical report , December 2012 . http:\/\/developer. amd.com\/resources\/documentation-articles\/ developer-guides-manuals\/. Southern Islands Instruction Set Architecture. Technical report, December 2012. http:\/\/developer. amd.com\/resources\/documentation-articles\/ developer-guides-manuals\/."},{"key":"e_1_3_2_1_5_1","volume-title":"June","author":"White Paper","year":"2012","unstructured":"White Paper | AMD GRAPHICS CORES NEXT (GCN) ARCHITECTURE. Technical report , June 2012 . http:\/\/www.amd.com\/Documents\/GCN_ Architecture _whitepaper.pdf. White Paper | AMD GRAPHICS CORES NEXT (GCN) ARCHITECTURE. Technical report, June 2012. http:\/\/www.amd.com\/Documents\/GCN_ Architecture_whitepaper.pdf."},{"key":"e_1_3_2_1_6_1","volume-title":"Technical report","author":"Phi Coprocessor Vector Microarchitecture Intel Xeon","year":"2013","unstructured":"Intel Xeon Phi Coprocessor Vector Microarchitecture . Technical report , 2013 . Intel Xeon Phi Coprocessor Vector Microarchitecture. Technical report, 2013."},{"key":"e_1_3_2_1_7_1","unstructured":"software.intel.com\/articles\/ intel-xeon-phi-coprocessor-vector-microarchitecture.  software.intel.com\/articles\/ intel-xeon-phi-coprocessor-vector-microarchitecture."},{"key":"e_1_3_2_1_8_1","volume-title":"August","author":"Binary CUDA","year":"2014","unstructured":"CUDA Binary Utilites - Application Note . Technical report , August 2014 . http:\/\/docs.nvidia.com\/cuda\/ pdf\/CUDA\\_Binary\\_Utilities.pdf. CUDA Binary Utilites - Application Note. Technical report, August 2014. http:\/\/docs.nvidia.com\/cuda\/ pdf\/CUDA\\_Binary\\_Utilities.pdf."},{"key":"e_1_3_2_1_9_1","unstructured":"Intel xeon phi coprocessor datasheet April 2014. http:\/\/www.intel.com\/content\/dam\/www\/public\/ us\/en\/documents\/datasheets\/ xeon-phi-coprocessor-datasheet.pdf.  Intel xeon phi coprocessor datasheet April 2014. http:\/\/www.intel.com\/content\/dam\/www\/public\/ us\/en\/documents\/datasheets\/ xeon-phi-coprocessor-datasheet.pdf."},{"key":"e_1_3_2_1_10_1","volume-title":"August","author":"Execution Isa Parallel Thread","year":"2014","unstructured":"Parallel Thread Execution Isa . Technical report , August 2014 . http:\/\/docs.nvidia.com\/pdf\/ptx_isa_4.1.pdf. Parallel Thread Execution Isa. Technical report, August 2014. http:\/\/docs.nvidia.com\/pdf\/ptx_isa_4.1.pdf."},{"key":"e_1_3_2_1_11_1","volume-title":"August","author":"Kepler Tuning CUDA","year":"2014","unstructured":"Tuning CUDA Applications for Kepler . Technical report , August 2014 . http:\/\/docs.nvidia.com\/cuda\/ pdf\/Kepler_Tuning_Guide.pdf. Tuning CUDA Applications for Kepler. Technical report, August 2014. http:\/\/docs.nvidia.com\/cuda\/ pdf\/Kepler_Tuning_Guide.pdf."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.5555\/2023025.2023037"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2010.5650274"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/1735688.1735702"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2011.45"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2012.23"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.Companion.2012.66"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.5555\/2523262"},{"key":"e_1_3_2_1_19_1","unstructured":"K. Karimi N. G. Dickson and F. Hamze. A Performance Comparison of CUDA and OpenCL. http:\/\/arxiv.org\/abs\/1005.2581 May 2010.  K. Karimi N. G. Dickson and F. Hamze. A Performance Comparison of CUDA and OpenCL. http:\/\/arxiv.org\/abs\/1005.2581 May 2010."},{"key":"e_1_3_2_1_20_1","volume-title":"The fifth international workshop on automatic performance tuning, page 7","author":"Komatsu K.","year":"2010","unstructured":"K. Komatsu , K. Sato , Y. Arai , K. Koyama , H. Takizawa , and H. Kobayashi . Evaluating performance and portability of OpenCL programs . In The fifth international workshop on automatic performance tuning, page 7 , 2010 . K. Komatsu, K. Sato, Y. Arai, K. Koyama, H. Takizawa, and H. Kobayashi. Evaluating performance and portability of OpenCL programs. In The fifth international workshop on automatic performance tuning, page 7, 2010."},{"key":"e_1_3_2_1_21_1","volume-title":"International Journal of High Performance Computing Applications, page 1094342014528252","author":"Mclntosh-Smith S.","year":"2014","unstructured":"S. Mclntosh-Smith , J. Price , R. B. Sessions , and A. A. Ibarra . High performance in silico virtual drug screening on many-core processors . International Journal of High Performance Computing Applications, page 1094342014528252 , 2014 . S. Mclntosh-Smith, J. Price, R. B. Sessions, and A. A. Ibarra. High performance in silico virtual drug screening on many-core processors. International Journal of High Performance Computing Applications, page 1094342014528252, 2014."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.5555\/2049883"},{"key":"e_1_3_2_1_23_1","volume-title":"NVIDIA\u2019s Next Generation CUDA Compute Architecture: Kepler GK110. Technical report","author":"NVIDIA.","year":"2012","unstructured":"NVIDIA. NVIDIA\u2019s Next Generation CUDA Compute Architecture: Kepler GK110. Technical report , 2012 . NVIDIA. NVIDIA\u2019s Next Generation CUDA Compute Architecture: Kepler GK110. Technical report, 2012."},{"key":"e_1_3_2_1_24_1","unstructured":"www.nvidia.com\/content\/PDF\/kepler\/NVIDIAKepler-GK110-Architecture-Whitepaper.pdf.  www.nvidia.com\/content\/PDF\/kepler\/NVIDIAKepler-GK110-Architecture-Whitepaper.pdf."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2012.07.005"},{"key":"e_1_3_2_1_26_1","volume-title":"Parboil: A revised benchmark suite for scientific and commercial throughput computing","author":"Stratton J. A.","year":"2012","unstructured":"J. A. Stratton , C. Rodrigues , I.-J. Sung , N. Obeid , L.-W. Chang , N. Anssari , G. D. Liu , and W.-m. W. Hwu . Parboil: A revised benchmark suite for scientific and commercial throughput computing . Center for Reliable and High-Performance Computing , 2012 . J. A. Stratton, C. Rodrigues, I.-J. Sung, N. Obeid, L.-W. Chang, N. Anssari, G. D. Liu, and W.-m. W. Hwu. Parboil: A revised benchmark suite for scientific and commercial throughput computing. Center for Reliable and High-Performance Computing, 2012."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2014.16"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/2597917.2597927"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.5555\/2033408.2033459"},{"key":"e_1_3_2_1_30_1","volume":"3","author":"Thouti K.","year":"2012","unstructured":"K. Thouti and S. Sathe . Comparison of OpenMP & OpenCL Parallel Processing Technologies. In International Journal of Advanced Computer Science and Applications Vol. 3 , 2012 . K. Thouti and S. Sathe. Comparison of OpenMP & OpenCL Parallel Processing Technologies. In International Journal of Advanced Computer Science and Applications Vol. 3, 2012.","journal-title":"Comparison of OpenMP & OpenCL Parallel Processing Technologies. In International Journal of Advanced Computer Science and Applications"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/223982.224449"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32820-6_85"}],"event":{"name":"GPGPU-8: General-purpose Processing with Graphics Processing Units 8","sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages"],"location":"San Francisco CA USA","acronym":"GPGPU-8"},"container-title":["Proceedings of the 8th Workshop on General Purpose Processing using GPUs"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2716282.2716293","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2716282.2716293","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T07:00:42Z","timestamp":1750230042000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2716282.2716293"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,2,7]]},"references-count":32,"alternative-id":["10.1145\/2716282.2716293","10.1145\/2716282"],"URL":"https:\/\/doi.org\/10.1145\/2716282.2716293","relation":{},"subject":[],"published":{"date-parts":[[2015,2,7]]},"assertion":[{"value":"2015-02-07","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}