{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T12:17:28Z","timestamp":1763468248607,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2015,1,31]],"date-time":"2015-01-31T00:00:00Z","timestamp":1422662400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"NSF","award":["CSR-1319501"],"award-info":[{"award-number":["CSR-1319501"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2015,1,31]]},"DOI":"10.1145\/2668930.2688046","type":"proceedings-article","created":{"date-parts":[[2015,1,12]],"date-time":"2015-01-12T20:42:45Z","timestamp":1421095365000},"page":"253-264","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":24,"title":["NUPAR"],"prefix":"10.1145","author":[{"given":"Yash","family":"Ukidave","sequence":"first","affiliation":[{"name":"Northeastern University, Boston, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fanny Nina","family":"Paravecino","sequence":"additional","affiliation":[{"name":"Northeastern University, Boston, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leiming","family":"Yu","sequence":"additional","affiliation":[{"name":"Northeastern University, Boston, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Charu","family":"Kalra","sequence":"additional","affiliation":[{"name":"Northeastern University, Boston, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amir","family":"Momeni","sequence":"additional","affiliation":[{"name":"Northeastern University, Boston, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongliang","family":"Chen","sequence":"additional","affiliation":[{"name":"Northeastern University, Boston, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nick","family":"Materise","sequence":"additional","affiliation":[{"name":"Northeastern University, Boston, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brett","family":"Daley","sequence":"additional","affiliation":[{"name":"Northeastern University, Boston, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Perhaad","family":"Mistry","sequence":"additional","affiliation":[{"name":"Advanced Micro Devices Inc., Boxborough, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Kaeli","sequence":"additional","affiliation":[{"name":"Northeastern University, Boston, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2015,1,31]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"CUDA C Programming Guide. NVIDIA Corporation Feb 2014.  CUDA C Programming Guide. NVIDIA Corporation Feb 2014."},{"key":"e_1_3_2_1_2_1","unstructured":"3DMark. http:\/\/www.futuremark.com\/benchmarks.  3DMark. http:\/\/www.futuremark.com\/benchmarks."},{"key":"e_1_3_2_1_3_1","volume-title":"OpenCL programming guide. URL http:\/\/developer. amd. com\/sdks\/AMDAPPSDK\/documentation","author":"Accelerated Parallel Processing AMD.","year":"2011","unstructured":"AMD. Accelerated Parallel Processing : OpenCL programming guide. URL http:\/\/developer. amd. com\/sdks\/AMDAPPSDK\/documentation , 2011 . AMD. Accelerated Parallel Processing: OpenCL programming guide. URL http:\/\/developer. amd. com\/sdks\/AMDAPPSDK\/documentation, 2011."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2012.51"},{"key":"e_1_3_2_1_6_1","first-page":"80","article-title":"Efficient Evaluation of Doubly Periodic Green Functions in 3D Scattering","volume":"1176","author":"Bruno O. P.","year":"2013","unstructured":"O. P. Bruno , S. P. Shipman , C. Turc , and V. Stephanos . Efficient Evaluation of Doubly Periodic Green Functions in 3D Scattering , Including Wood Anomaly Frequencies. Arxiv, 1307 . 1176 : 80 -- 110 , 2013 . O. P. Bruno, S. P. Shipman, C. Turc, and V. Stephanos. Efficient Evaluation of Doubly Periodic Green Functions in 3D Scattering, Including Wood Anomaly Frequencies. Arxiv, 1307.1176:80--110, 2013.","journal-title":"Including Wood Anomaly Frequencies. Arxiv, 1307"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"e_1_3_2_1_8_1","first-page":"1","article-title":"Efficient gpu spatial-temporal multitasking","author":"Chen D.","year":"2014","unstructured":"D. Chen , H. P. Huynh , R. S. M. Goh , and K. Rupnow . Efficient gpu spatial-temporal multitasking . IEEE Transactions on Parallel and Distributed Systems, page 1 , 2014 . D. Chen, H. P. Huynh, R. S. M. Goh, and K. Rupnow. Efficient gpu spatial-temporal multitasking. IEEE Transactions on Parallel and Distributed Systems, page 1, 2014.","journal-title":"IEEE Transactions on Parallel and Distributed Systems, page"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2000.854761"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1735688.1735702"},{"key":"e_1_3_2_1_11_1","volume-title":"http:\/\/www.crysis.com","author":"Frankfurt C.","year":"2007","unstructured":"C. Frankfurt . Crysis. http:\/\/www.crysis.com , 2007 . C. Frankfurt. Crysis. http:\/\/www.crysis.com, 2007."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2006.1598115"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2009.4919639"},{"key":"e_1_3_2_1_14_1","first-page":"330","volume-title":"Proceedings of the 30th annual ACM\/IEEE international symposium on Microarchitecture","author":"Lee C.","year":"1997","unstructured":"C. Lee , M. Potkonjak , and W. H. Mangione-Smith . Mediabench: a tool for evaluating and synthesizing multimedia and communicatons systems . In Proceedings of the 30th annual ACM\/IEEE international symposium on Microarchitecture , pages 330 -- 335 . IEEE Computer Society , 1997 . C. Lee, M. Potkonjak, and W. H. Mangione-Smith. Mediabench: a tool for evaluating and synthesizing multimedia and communicatons systems. In Proceedings of the 30th annual ACM\/IEEE international symposium on Microarchitecture, pages 330--335. IEEE Computer Society, 1997."},{"key":"e_1_3_2_1_15_1","volume-title":"AMD Fusion Developer Summit","author":"Mantor M.","year":"2011","unstructured":"M. Mantor and M. Houston . AMD Graphics Core Next . In AMD Fusion Developer Summit , 2011 . M. Mantor and M. Houston. AMD Graphics Core Next. In AMD Fusion Developer Summit, 2011."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2458523.2458529"},{"key":"e_1_3_2_1_17_1","volume-title":"The OpenCL Specification 2.0","author":"Munshi A.","year":"2014","unstructured":"A. Munshi . The OpenCL Specification 2.0 . Khronos OpenCL Working Group , 2014 . A. Munshi. The OpenCL Specification 2.0. Khronos OpenCL Working Group, 2014."},{"issue":"10","key":"e_1_3_2_1_18_1","first-page":"2003","article-title":"A new fdtd algorithm based on alternating-direction implicit method. Microwave Theory and Techniques","volume":"47","author":"Namiki T.","year":"1999","unstructured":"T. Namiki . A new fdtd algorithm based on alternating-direction implicit method. Microwave Theory and Techniques , IEEE Transactions on , 47 ( 10 ): 2003 -- 2007 , 1999 . T. Namiki. A new fdtd algorithm based on alternating-direction implicit method. Microwave Theory and Techniques, IEEE Transactions on, 47(10):2003--2007, 1999.","journal-title":"IEEE Transactions on"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2006.302743"},{"key":"e_1_3_2_1_20_1","volume-title":"On spectral clustering: Analysis and an algorithm. Advances in neural information processing systems, 2:849--856","author":"Ng A. Y.","year":"2002","unstructured":"A. Y. Ng , M. I. Jordan , Y. Weiss , On spectral clustering: Analysis and an algorithm. Advances in neural information processing systems, 2:849--856 , 2002 . A. Y. Ng, M. I. Jordan, Y. Weiss, et al. On spectral clustering: Analysis and an algorithm. Advances in neural information processing systems, 2:849--856, 2002."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2010.41"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11331-9_60"},{"key":"e_1_3_2_1_23_1","unstructured":"NVIDIA. Visual Profiler 2011.  NVIDIA. Visual Profiler 2011."},{"key":"e_1_3_2_1_24_1","volume-title":"NVIDIA's Next Generation CUDA Computer Architecture Kepler GK110","author":"NVIDIA.","year":"2012","unstructured":"NVIDIA. NVIDIA's Next Generation CUDA Computer Architecture Kepler GK110 . 2012 . NVIDIA. NVIDIA's Next Generation CUDA Computer Architecture Kepler GK110. 2012."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/0021-9991(88)90002-2"},{"key":"e_1_3_2_1_26_1","volume-title":"A course in digital signal processing","author":"Porat B.","year":"1997","unstructured":"B. Porat . A course in digital signal processing , volume 1 . Wiley New York , 1997 . B. Porat. A course in digital signal processing, volume 1. Wiley New York, 1997."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/HOTCHIPS.2013.7478286"},{"key":"e_1_3_2_1_28_1","volume-title":"GTC","author":"Schmidt J.","year":"2014","unstructured":"J. Schmidt . A Flexible IIR Filtering Implementation for Audio Processing. Technicolor Research & Innovation , GTC , 2014 . J. Schmidt. A Flexible IIR Filtering Implementation for Audio Processing. Technicolor Research & Innovation, GTC, 2014."},{"key":"e_1_3_2_1_29_1","volume-title":"A fast implementation of the level set method without solving partial differential equations","author":"Shi Y.","year":"2005","unstructured":"Y. Shi and W. C. Karl . A fast implementation of the level set method without solving partial differential equations . Boston University , Department of Electrical and Computer Engineering, 2005 . Y. Shi and W. C. Karl. A fast implementation of the level set method without solving partial differential equations. Boston University, Department of Electrical and Computer Engineering, 2005."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/8.60985"},{"key":"e_1_3_2_1_31_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_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-89740-8_2"},{"key":"e_1_3_2_1_33_1","volume-title":"Augmenting Operating Systems With the GPU","author":"Sun W.","year":"2011","unstructured":"W. Sun and R. Ricci . Augmenting Operating Systems With the GPU . 2011 . W. Sun and R. Ricci. Augmenting Operating Systems With the GPU. 2011."},{"key":"e_1_3_2_1_34_1","first-page":"31","volume-title":"Proceedings of the 2008 ACM\/IEEE conference on Supercomputing","author":"Volkov V.","unstructured":"V. Volkov and J. W. Demmel . Benchmarking gpus to tune dense linear algebra . In Proceedings of the 2008 ACM\/IEEE conference on Supercomputing , page 31 . IEEE Press, 2008. V. Volkov and J. W. Demmel. Benchmarking gpus to tune dense linear algebra. In Proceedings of the 2008 ACM\/IEEE conference on Supercomputing, page 31. IEEE Press, 2008."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2555243.2555254"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1049\/el.2010.2016"}],"event":{"name":"ICPE'15: ACM\/SPEC International Conference on Performance Engineering","sponsor":["SIGMETRICS ACM Special Interest Group on Measurement and Evaluation","SIGSOFT ACM Special Interest Group on Software Engineering","SPEC SPEC Research Group"],"location":"Austin Texas USA","acronym":"ICPE'15"},"container-title":["Proceedings of the 6th ACM\/SPEC International Conference on Performance Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2668930.2688046","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2668930.2688046","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T07:19:37Z","timestamp":1750231177000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2668930.2688046"}},"subtitle":["A Benchmark Suite for Modern GPU Architectures"],"short-title":[],"issued":{"date-parts":[[2015,1,31]]},"references-count":35,"alternative-id":["10.1145\/2668930.2688046","10.1145\/2668930"],"URL":"https:\/\/doi.org\/10.1145\/2668930.2688046","relation":{},"subject":[],"published":{"date-parts":[[2015,1,31]]},"assertion":[{"value":"2015-01-31","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}