{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T17:57:55Z","timestamp":1773511075070,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","license":[{"start":{"date-parts":[[2010,6,19]],"date-time":"2010-06-19T00:00:00Z","timestamp":1276905600000},"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":[[2010,6,19]]},"DOI":"10.1145\/1815961.1816021","type":"proceedings-article","created":{"date-parts":[[2010,6,22]],"date-time":"2010-06-22T08:21:27Z","timestamp":1277194887000},"page":"451-460","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":265,"title":["Debunking the 100X GPU vs. CPU myth"],"prefix":"10.1145","author":[{"given":"Victor W.","family":"Lee","sequence":"first","affiliation":[{"name":"Intel Corporation, Santa Clara, CA, USA"}]},{"given":"Changkyu","family":"Kim","sequence":"additional","affiliation":[{"name":"Intel Corporation, Santa Clara, CA, USA"}]},{"given":"Jatin","family":"Chhugani","sequence":"additional","affiliation":[{"name":"Intel Corporation, Santa Clara, CA, USA"}]},{"given":"Michael","family":"Deisher","sequence":"additional","affiliation":[{"name":"Intel Corporation, Hillsboro, OR, USA"}]},{"given":"Daehyun","family":"Kim","sequence":"additional","affiliation":[{"name":"Intel Corporation, Santa Clara, CA, USA"}]},{"given":"Anthony D.","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Intel Corporation, Santa Clara, CA, USA"}]},{"given":"Nadathur","family":"Satish","sequence":"additional","affiliation":[{"name":"Intel Corporation, Santa Clara, CA, USA"}]},{"given":"Mikhail","family":"Smelyanskiy","sequence":"additional","affiliation":[{"name":"Intel Corporation, Santa Clara, CA, USA"}]},{"given":"Srinivas","family":"Chennupaty","sequence":"additional","affiliation":[{"name":"Intel Corporation, Hillsboro, OR, USA"}]},{"given":"Per","family":"Hammarlund","sequence":"additional","affiliation":[{"name":"Intel Corporation, Hillsboro, OR, USA"}]},{"given":"Ronak","family":"Singhal","sequence":"additional","affiliation":[{"name":"Intel Corporation, Hillsboro, OR, USA"}]},{"given":"Pradeep","family":"Dubey","sequence":"additional","affiliation":[{"name":"Intel Corporation, Santa Clara, CA, USA"}]}],"member":"320","published-online":{"date-parts":[[2010,6,19]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"http:\/\/developer.download.nvidia.com\/compute\/cuda\/2_1\/toolkit\/docs\/ CUBLAS_Library_2.1.pdf","author":"Library CUDA BLAS","year":"2008","unstructured":"CUDA BLAS Library . http:\/\/developer.download.nvidia.com\/compute\/cuda\/2_1\/toolkit\/docs\/ CUBLAS_Library_2.1.pdf , 2008 . CUDA BLAS Library. http:\/\/developer.download.nvidia.com\/compute\/cuda\/2_1\/toolkit\/docs\/ CUBLAS_Library_2.1.pdf, 2008."},{"key":"e_1_3_2_1_2_1","volume-title":"http:\/\/developer.download.nvidia.com\/compute\/cuda\/2_1\/toolkit\/docs\/ CUFFT_Library_2.1.pdf","author":"Library CUDA CUFFT","year":"2008","unstructured":"CUDA CUFFT Library . http:\/\/developer.download.nvidia.com\/compute\/cuda\/2_1\/toolkit\/docs\/ CUFFT_Library_2.1.pdf , 2008 . CUDA CUFFT Library. http:\/\/developer.download.nvidia.com\/compute\/cuda\/2_1\/toolkit\/docs\/ CUFFT_Library_2.1.pdf, 2008."},{"key":"e_1_3_2_1_3_1","volume-title":"http:\/\/gpgpu.org\/","year":"2009","unstructured":"General-purpose computation on graphics hardware. http:\/\/gpgpu.org\/ , 2009 . General-purpose computation on graphics hardware. http:\/\/gpgpu.org\/, 2009."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/1555754.1555810"},{"key":"e_1_3_2_1_7_1","first-page":"114","volume-title":"Proceedings of the Third SIAM Conference on Parallel Processing for Scientific Computing","author":"Bailey D. H.","year":"1989","unstructured":"D. H. Bailey . A high-performance fft algorithm for vector supercomputers-abstract . In Proceedings of the Third SIAM Conference on Parallel Processing for Scientific Computing , page 114 , Philadelphia, PA, USA , 1989 . Society for Industrial and Applied Mathematics. D. H. Bailey. A high-performance fft algorithm for vector supercomputers-abstract. In Proceedings of the Third SIAM Conference on Parallel Processing for Scientific Computing, page 114, Philadelphia, PA, USA, 1989. Society for Industrial and Applied Mathematics."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1654059.1654078"},{"key":"e_1_3_2_1_9_1","unstructured":"C. Bennemann M. Beinker D. Egloff and M. Gauckler. Teraflops for games and derivatives pricing. http:\/\/quantcatalyst.com\/download.php? file=DerivativesPricing.pdf.  C. Bennemann M. Beinker D. Egloff and M. Gauckler. Teraflops for games and derivatives pricing. http:\/\/quantcatalyst.com\/download.php? file=DerivativesPricing.pdf."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1454115.1454128"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/1555815.1555777"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2006.18"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2008.917729"},{"key":"e_1_3_2_1_14_1","first-page":"11","article-title":"High-performance physical simulations on next-generation architecture with many cores","author":"Chen Y.-K.","year":"2007","unstructured":"Y.-K. Chen , J. Chhugani , C. J. Hughes , D. Kim , S. Kumar , V. W. Lee , A. Lin , A. D. Nguyen , E. Sifakis , and M. Smelyanskiy . High-performance physical simulations on next-generation architecture with many cores . Intel Technology Journal , 11 , 2007 . Y.-K. Chen, J. Chhugani, C. J. Hughes, D. Kim, S. Kumar, V. W. Lee, A. Lin, A. D. Nguyen, E. Sifakis, and M. Smelyanskiy. High-performance physical simulations on next-generation architecture with many cores. Intel Technology Journal, 11, 2007.","journal-title":"Intel Technology Journal"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.14778\/1454159.1454171"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.5555\/1413370.1413375"},{"key":"e_1_3_2_1_17_1","volume-title":"Discrete Fourier transform on multicore","author":"Franchetti F.","year":"2009","unstructured":"F. Franchetti , M. P\u00fcschel , Y. Voronenko , S. Chellappa , and J. M. F. Moura . Discrete Fourier transform on multicore . IEEE Signal Processing Magazine, special issue on \"Signal Processing on Platforms with Multiple Cores \", 26(6):90--102, 2009 . F. Franchetti, M. P\u00fcschel, Y. Voronenko, S. Chellappa, and J. M. F. Moura. Discrete Fourier transform on multicore. IEEE Signal Processing Magazine, special issue on \"Signal Processing on Platforms with Multiple Cores\", 26(6):90--102, 2009."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2004.840301"},{"key":"e_1_3_2_1_19_1","volume-title":"4th ABINIT Developer Workshop","author":"Genovese L.","year":"2009","unstructured":"L. Genovese . Graphic processing units: A possible answer to HPC . In 4th ABINIT Developer Workshop , 2009 . L. Genovese. Graphic processing units: A possible answer to HPC. In 4th ABINIT Developer Workshop, 2009."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/1142473.1142511"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.5555\/1413370.1413373"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/1555815.1555775"},{"key":"e_1_3_2_1_23_1","unstructured":"Intel Advanced Vector Extensions Programming Reference.  Intel Advanced Vector Extensions Programming Reference."},{"key":"e_1_3_2_1_24_1","volume-title":"SSE4 Programming Reference","year":"2007","unstructured":"Intel. SSE4 Programming Reference . 2007 . Intel. SSE4 Programming Reference. 2007."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2005.10"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF01189337"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/1807167.1807206"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/1250662.1250683"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2008.38"},{"key":"e_1_3_2_1_30_1","volume-title":"Fermi Architecture White Paper","author":"Leischner N.","year":"2009","unstructured":"N. Leischner , V. Osipov , and P. Sanders . Fermi Architecture White Paper , 2009 . N. Leischner, V. Osipov, and P. Sanders. Fermi Architecture White Paper, 2009."},{"key":"e_1_3_2_1_31_1","unstructured":"P. Lyman and H. R. Varian. How much information. http:\/\/www2.sims.berkeley.edu\/research\/projects\/how-much-info-2003\/ 2003.  P. Lyman and H. R. Varian. How much information. http:\/\/www2.sims.berkeley.edu\/research\/projects\/how-much-info-2003\/ 2003."},{"key":"e_1_3_2_1_32_1","unstructured":"NVIDIA. NVIDIA CUDA Zone. http:\/\/www.nvidia.com\/object\/cuda_home.html 2009.  NVIDIA. NVIDIA CUDA Zone. http:\/\/www.nvidia.com\/object\/cuda_home.html 2009."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2007.01012.x"},{"key":"e_1_3_2_1_34_1","unstructured":"V. Podlozhnyuk and M. Harris. Monte Carlo Option Pricing. http:\/\/developer.download.nvidia.com\/compute\/cuda\/sdk\/website\/projects\/MonteCarlo\/doc\/MonteCarlo.pdf.  V. Podlozhnyuk and M. Harris. Monte Carlo Option Pricing. http:\/\/developer.download.nvidia.com\/compute\/cuda\/sdk\/website\/projects\/MonteCarlo\/doc\/MonteCarlo.pdf."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2004.840306"},{"key":"e_1_3_2_1_36_1","unstructured":"R. Ramanathan. Extending the world.s most popular processor architecture. Intel Whitepaper.  R. Ramanathan. Extending the world.s most popular processor architecture. Intel Whitepaper."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/1555815.1555793"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/1179622.1179679"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2009.5161005"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/1807167.1807207"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/1360612.1360617"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/1375527.1375572"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2009.164"},{"key":"e_1_3_2_1_44_1","unstructured":"The IMPACT Research Group UIUC. Parboil benchmark suite. http:\/\/impact.crhc.illinois.edu\/parboil.php.  The IMPACT Research Group UIUC. Parboil benchmark suite. http:\/\/impact.crhc.illinois.edu\/parboil.php."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1080\/10618560802238275"},{"key":"e_1_3_2_1_46_1","volume-title":"Technical reference: Base operating system and extensions","author":"Univ N.","year":"2009","unstructured":"N. Univ . of Illinois. Technical reference: Base operating system and extensions , volume 2 , 2009 . N. Univ. of Illinois. Technical reference: Base operating system and extensions, volume 2, 2009."},{"key":"e_1_3_2_1_47_1","volume-title":"The sparse matrix vector product on GPUs. Technical report","author":"Vazquez F.","year":"2009","unstructured":"F. Vazquez , E. M. Garzon , J.A. Martinez , and J.J. Fernandez . The sparse matrix vector product on GPUs. Technical report , University of Almeria , June 2009 . F. Vazquez, E. M. Garzon, J.A.Martinez, and J.J.Fernandez. The sparse matrix vector product on GPUs. Technical report, University of Almeria, June 2009."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.5555\/1413370.1413402"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/1362622.1362674"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/1498765.1498785"},{"key":"e_1_3_2_1_52_1","volume-title":"Workshop on High Performance Image Reconstruction (HPIR)","author":"Xu W.","year":"2009","unstructured":"W. Xu and K. Mueller . A performance-driven study of regularization methods for gpu-accelerated iterative ct . In Workshop on High Performance Image Reconstruction (HPIR) , 2009 . W. Xu and K. Mueller. A performance-driven study of regularization methods for gpu-accelerated iterative ct. In Workshop on High Performance Image Reconstruction (HPIR), 2009."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CSSE.2008.1448"}],"event":{"name":"ISCA '10: The 37th Annual International Symposium on Computer Architecture","location":"Saint-Malo France","acronym":"ISCA '10","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture","IEEE CS"]},"container-title":["Proceedings of the 37th annual international symposium on Computer architecture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1815961.1816021","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1815961.1816021","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T07:39:44Z","timestamp":1750232384000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1815961.1816021"}},"subtitle":["an evaluation of throughput computing on CPU and GPU"],"short-title":[],"issued":{"date-parts":[[2010,6,19]]},"references-count":50,"alternative-id":["10.1145\/1815961.1816021","10.1145\/1815961"],"URL":"https:\/\/doi.org\/10.1145\/1815961.1816021","relation":{"is-identical-to":[{"id-type":"doi","id":"10.1145\/1816038.1816021","asserted-by":"object"}]},"subject":[],"published":{"date-parts":[[2010,6,19]]},"assertion":[{"value":"2010-06-19","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}