{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T03:48:13Z","timestamp":1772164093333,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,6,11]],"date-time":"2018-06-11T00:00:00Z","timestamp":1528675200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100011030","name":"U.S. Department of Energy","doi-asserted-by":"publisher","award":["63823"],"award-info":[{"award-number":["63823"]}],"id":[{"id":"10.13039\/100011030","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1440749,1513120,1629548"],"award-info":[{"award-number":["1440749,1513120,1629548"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2018,6,11]]},"DOI":"10.1145\/3192366.3192397","type":"proceedings-article","created":{"date-parts":[[2018,6,12]],"date-time":"2018-06-12T08:16:01Z","timestamp":1528791361000},"page":"736-751","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["GPU code optimization using abstract kernel emulation and sensitivity analysis"],"prefix":"10.1145","author":[{"given":"Changwan","family":"Hong","sequence":"first","affiliation":[{"name":"Ohio State University, USA"}]},{"given":"Aravind","family":"Sukumaran-Rajam","sequence":"additional","affiliation":[{"name":"Ohio State University, USA"}]},{"given":"Jinsung","family":"Kim","sequence":"additional","affiliation":[{"name":"Ohio State University, USA"}]},{"given":"Prashant Singh","family":"Rawat","sequence":"additional","affiliation":[{"name":"Ohio State University, USA"}]},{"given":"Sriram","family":"Krishnamoorthy","sequence":"additional","affiliation":[{"name":"Pacific Northwest National Laboratory, USA"}]},{"given":"Louis-No\u00ebl","family":"Pouchet","sequence":"additional","affiliation":[{"name":"Colorado State University, USA"}]},{"given":"Fabrice","family":"Rastello","sequence":"additional","affiliation":[{"name":"Grenoble Alpes University, France \/ Inria, France"}]},{"given":"P.","family":"Sadayappan","sequence":"additional","affiliation":[{"name":"Ohio State University, USA"}]}],"member":"320","published-online":{"date-parts":[[2018,6,11]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/2628071.2628092"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/1837853.1693470"},{"key":"e_1_3_2_2_3_1","volume-title":"Compiler Construction","author":"Baskaran Muthu","unstructured":"Muthu Baskaran , Jj Ramanujam , and P Sadayappan . 2010. Automatic C-to-CUDA code generation for affine programs . In Compiler Construction . Springer , 244-263. Muthu Baskaran, Jj Ramanujam, and P Sadayappan. 2010. Automatic C-to-CUDA code generation for affine programs. In Compiler Construction. Springer, 244-263."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/1379022.1375595"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2011.70"},{"key":"e_1_3_2_2_6_1","unstructured":"CUDA occupancy calculator [n. d.]. CUDA occupancy calculator. https:\/\/developer.download.nvidia.com\/compute\/cuda\/CUDA_Occupancy_calculator.xls  CUDA occupancy calculator [n. d.]. CUDA occupancy calculator. https:\/\/developer.download.nvidia.com\/compute\/cuda\/CUDA_Occupancy_calculator.xls"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"crossref","unstructured":"Leonardo Dagum and Ramesh Menon. 1998. OpenMP: an industry standard API for shared-memory programming. IEEE computational science and engineering 5 1 (1998) 46-55.   Leonardo Dagum and Ramesh Menon. 1998. OpenMP: an industry standard API for shared-memory programming. IEEE computational science and engineering 5 1 (1998) 46-55.","DOI":"10.1109\/99.660313"},{"key":"e_1_3_2_2_8_1","volume-title":"Report on the sunway taihulight system. PDF). www.netlib.org. Retrieved June 20","author":"Dongarra Jack","year":"2016","unstructured":"Jack Dongarra . 2016. Report on the sunway taihulight system. PDF). www.netlib.org. Retrieved June 20 ( 2016 ). Jack Dongarra. 2016. Report on the sunway taihulight system. PDF). www.netlib.org. Retrieved June 20 (2016)."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2581122.2544160"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2458523.2458526"},{"key":"e_1_3_2_2_11_1","first-page":"311","volume-title":"Proceedings of the 26th ACM International Conference on Supercomputing (ICS '12)","author":"Holewinski Justin","unstructured":"Justin Holewinski , Louis-No\u00ebl Pouchet , and P. Sadayappan . 2012. High-performance Code Generation for Stencil Computations on GPU Architectures . In Proceedings of the 26th ACM International Conference on Supercomputing (ICS '12) . ACM, 311 - 320 . Justin Holewinski, Louis-No\u00ebl Pouchet, and P. Sadayappan. 2012. High-performance Code Generation for Stencil Computations on GPU Architectures. In Proceedings of the 26th ACM International Conference on Supercomputing (ICS '12). ACM, 311-320."},{"key":"e_1_3_2_2_12_1","volume-title":"Sriram Krishnamoorthy, Louis-Noel Pouchet, Fabrice Rastello, and P. Sadayappan.","author":"Hong Changwan","year":"2018","unstructured":"Changwan Hong , Aravind Sukumaran-Rajam , Jinsung Kim , Prashant Singh Rawat , Sriram Krishnamoorthy, Louis-Noel Pouchet, Fabrice Rastello, and P. Sadayappan. 2018 . GPU Code Optimization using Abstract Kernel Emulation and Sensitivity Analysis. Technical Report. Ohio State University . Changwan Hong, Aravind Sukumaran-Rajam, Jinsung Kim, Prashant Singh Rawat, Sriram Krishnamoorthy, Louis-Noel Pouchet, Fabrice Rastello, and P. Sadayappan. 2018. GPU Code Optimization using Abstract Kernel Emulation and Sensitivity Analysis. Technical Report. Ohio State University."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/1555815.1555775"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32820-6_90"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2013.6494986"},{"key":"e_1_3_2_2_16_1","volume-title":"COMPASS: A Framework for Automated Performance Modeling and Prediction. In ACM International Conference on Supercomputing (ICS15)","author":"Lee Seyong","unstructured":"Seyong Lee , Jeremy S. Meredith , and Jeffrey S. Vetter . 2015 . COMPASS: A Framework for Automated Performance Modeling and Prediction. In ACM International Conference on Supercomputing (ICS15) . Seyong Lee, Jeremy S. Meredith, and Jeffrey S. Vetter. 2015. COMPASS: A Framework for Automated Performance Modeling and Prediction. In ACM International Conference on Supercomputing (ICS15)."},{"key":"e_1_3_2_2_17_1","volume-title":"Efficient Heterogeneous Computing. In HPDC '14: Proceedings of the ACM Symposium on High-Performance Parallel and Distributed Computing, Short Paper.","author":"Lee Seyong","year":"2014","unstructured":"Seyong Lee and Jeffrey S Vetter . 2014 . OpenARC: Open Accelerator Research Compiler for Directive-Based , Efficient Heterogeneous Computing. In HPDC '14: Proceedings of the ACM Symposium on High-Performance Parallel and Distributed Computing, Short Paper. Seyong Lee and Jeffrey S Vetter. 2014. OpenARC: Open Accelerator Research Compiler for Directive-Based, Efficient Heterogeneous Computing. In HPDC '14: Proceedings of the ACM Symposium on High-Performance Parallel and Distributed Computing, Short Paper."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2010.26"},{"key":"e_1_3_2_2_19_1","volume-title":"Optimizing tensor contraction expressions for hybrid CPU-GPU execution. Cluster computing 16, 1","author":"Ma Wenjing","year":"2013","unstructured":"Wenjing Ma , Sriram Krishnamoorthy , Oreste Villa , Karol Kowalski , and Gagan Agrawal . 2013. Optimizing tensor contraction expressions for hybrid CPU-GPU execution. Cluster computing 16, 1 ( 2013 ), 131-155. Wenjing Ma, Sriram Krishnamoorthy, Oreste Villa, Karol Kowalski, and Gagan Agrawal. 2013. Optimizing tensor contraction expressions for hybrid CPU-GPU execution. Cluster computing 16, 1 (2013), 131-155."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2628071.2628087"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2503210.2503268"},{"key":"e_1_3_2_2_22_1","unstructured":"Nervana maxas [n. d.]. Nervana maxas. https:\/\/github.com\/NervanaSystems\/maxas\/  Nervana maxas [n. d.]. Nervana maxas. https:\/\/github.com\/NervanaSystems\/maxas\/"},{"key":"e_1_3_2_2_23_1","volume-title":"SASS","author":"NVIDIA","year":"2018","unstructured":"NVIDIA SASS 2018 . CUDA Binary Utilities. http:\/\/docs.nvidia.com\/cuda\/cuda-binary-utilities\/index.html NVIDIA SASS 2018. CUDA Binary Utilities. http:\/\/docs.nvidia.com\/cuda\/cuda-binary-utilities\/index.html"},{"key":"e_1_3_2_2_24_1","unstructured":"NWChem Download 2017. NWChem Download. http:\/\/www.nwchem-sw.org\/index.php\/Download  NWChem Download 2017. NWChem Download. http:\/\/www.nwchem-sw.org\/index.php\/Download"},{"key":"e_1_3_2_2_25_1","volume-title":"Micro-benchmarking the GT200 GPU","author":"Papadopoulou Misel-Myrto","year":"2009","unstructured":"Misel-Myrto Papadopoulou , Maryam Sadooghi-Alvandi , and Henry Wong . 2009. Micro-benchmarking the GT200 GPU . Computer Group, ECE , University of Toronto , Tech. Rep ( 2009 ). Misel-Myrto Papadopoulou, Maryam Sadooghi-Alvandi, and Henry Wong. 2009. Micro-benchmarking the GT200 GPU. Computer Group, ECE, University of Toronto, Tech. Rep (2009)."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2774959.2774965"},{"key":"e_1_3_2_2_27_1","volume-title":"Resource Conscious Reuse-Driven Tiling for GPUs. In International Conference on Parallel Architectures and Compilation Techniques. 99-111","author":"Rawat Prashant","unstructured":"Prashant Rawat , Changwan Hong , Mahesh Ravishankar , Vinod Grover , Louis-Noel Pouchet , Atanas Rountev , and P. Sadayappan . 2016 . Resource Conscious Reuse-Driven Tiling for GPUs. In International Conference on Parallel Architectures and Compilation Techniques. 99-111 . Prashant Rawat, Changwan Hong, Mahesh Ravishankar, Vinod Grover, Louis-Noel Pouchet, Atanas Rountev, and P. Sadayappan. 2016. Resource Conscious Reuse-Driven Tiling for GPUs. In International Conference on Parallel Architectures and Compilation Techniques. 99-111."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2012.16"},{"key":"e_1_3_2_2_29_1","volume-title":"Many-body methods in chemistry and physics: MBPT and coupled-cluster theory","author":"Shavitt Isaiah","unstructured":"Isaiah Shavitt and Rodney J Bartlett . 2009. Many-body methods in chemistry and physics: MBPT and coupled-cluster theory . Cambridge university press . Isaiah Shavitt and Rodney J Bartlett. 2009. Many-body methods in chemistry and physics: MBPT and coupled-cluster theory. Cambridge university press."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/2370036.2145819"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-28652-0_2"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2010.04.018"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2400682.2400713"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/103135.103136"},{"key":"e_1_3_2_2_35_1","unstructured":"Whitepaper 2012. NVIDIA Tesla K100. http:\/\/www.nvidia.com\/content\/PDF\/product-specifications\/GeForce_GTX_680_Whitepaper_FINAL.pdf  Whitepaper 2012. NVIDIA Tesla K100. http:\/\/www.nvidia.com\/content\/PDF\/product-specifications\/GeForce_GTX_680_Whitepaper_FINAL.pdf"},{"key":"e_1_3_2_2_36_1","unstructured":"Whitepaper 2016. NVIDIA Tesla P100. https:\/\/images.nvidia.com\/content\/pdf\/tesla\/whitepaper\/pascal-architecture-whitepaper.pdf  Whitepaper 2016. NVIDIA Tesla P100. https:\/\/images.nvidia.com\/content\/pdf\/tesla\/whitepaper\/pascal-architecture-whitepaper.pdf"},{"key":"e_1_3_2_2_37_1","volume-title":"OpenACC-first experiences with real-world applications. Euro-Par 2012 Parallel Processing","author":"Wienke Sandra","year":"2012","unstructured":"Sandra Wienke , Paul Springer , Christian Terboven , and Dieter an Mey . 2012. OpenACC-first experiences with real-world applications. Euro-Par 2012 Parallel Processing ( 2012 ), 859-870. Sandra Wienke, Paul Springer, Christian Terboven, and Dieter an Mey. 2012. OpenACC-first experiences with real-world applications. Euro-Par 2012 Parallel Processing (2012), 859-870."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/1498765.1498785"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2018.00086"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3018743.3018755"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.5555\/2014698.2014875"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079079.3079083"}],"event":{"name":"PLDI '18: ACM SIGPLAN Conference on Programming Language Design and Implementation","location":"Philadelphia PA USA","acronym":"PLDI '18","sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages"]},"container-title":["Proceedings of the 39th ACM SIGPLAN Conference on Programming Language Design and Implementation"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3192366.3192397","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3192366.3192397","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3192366.3192397","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:07:53Z","timestamp":1750198073000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3192366.3192397"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6,11]]},"references-count":42,"alternative-id":["10.1145\/3192366.3192397","10.1145\/3192366"],"URL":"https:\/\/doi.org\/10.1145\/3192366.3192397","relation":{"is-identical-to":[{"id-type":"doi","id":"10.1145\/3296979.3192397","asserted-by":"object"}]},"subject":[],"published":{"date-parts":[[2018,6,11]]},"assertion":[{"value":"2018-06-11","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}