{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T16:49:57Z","timestamp":1771951797670,"version":"3.50.1"},"reference-count":57,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2013,1,1]],"date-time":"2013-01-01T00:00:00Z","timestamp":1356998400000},"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":["ACM Trans. Archit. Code Optim."],"published-print":{"date-parts":[[2013,1]]},"abstract":"<jats:p>\n            This article presents a novel compiler framework for CUDA code generation. The compiler structure is designed to support\n            <jats:italic>autotuning<\/jats:italic>\n            , which employs empirical techniques to evaluate a set of alternative mappings of computation kernels and select the mapping that obtains the best performance. This article introduces a\n            <jats:italic>Transformation Strategy Generator<\/jats:italic>\n            , a meta-optimizer that generates a set of\n            <jats:italic>transformation recipes<\/jats:italic>\n            , which are descriptions of the mapping of the sequential code to parallel CUDA code. These recipes comprise a search space of possible implementations. This system achieves performance comparable and sometimes better than manually tuned libraries and exceeds the performance of a state-of-the-art GPU compiler.\n          <\/jats:p>","DOI":"10.1145\/2400682.2400690","type":"journal-article","created":{"date-parts":[[2013,1,22]],"date-time":"2013-01-22T15:28:56Z","timestamp":1358868536000},"page":"1-25","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":44,"title":["A script-based autotuning compiler system to generate high-performance CUDA code"],"prefix":"10.1145","volume":"9","author":[{"given":"Malik","family":"Khan","sequence":"first","affiliation":[{"name":"University of Southern California\/ISI, NUST, ISB, Pakistan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Protonu","family":"Basu","sequence":"additional","affiliation":[{"name":"University of Utah, UT"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gabe","family":"Rudy","sequence":"additional","affiliation":[{"name":"University of Utah, UT"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mary","family":"Hall","sequence":"additional","affiliation":[{"name":"University of Utah, UT"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chun","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Utah, UT"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jacqueline","family":"Chame","sequence":"additional","affiliation":[{"name":"USC\/Information Sciences Institute, CA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2013,1,20]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2006.37"},{"key":"e_1_2_1_2_1","volume-title":"Proceedings of the 24th International Workshop on Languages and Compilers for Parallel Computing (LCPC). Also Tech. Rep. MINES ParisTech A\/476\/CRI.","author":"Amini M."},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1542476.1542481"},{"key":"e_1_2_1_4_1","first-page":"1","article-title":"PERI auto-tuning","volume":"125","author":"Bailey D. H.","year":"2008","journal-title":"J. Phys."},{"key":"e_1_2_1_5_1","volume-title":"Proceedings of the 5th International Conference on Parallel Processing (Euro-Par'99)","author":"Barreteau M."},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1345206.1345210"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1375527.1375562"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-11970-5_14"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/1654059.1654078"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/263580.263662"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/1941553.1941562"},{"key":"e_1_2_1_12_1","unstructured":"Chame J. Chen C. Hall M. Hollingsworth J. Mahinthakumar K. Marin G. Ramalingam S. Sripathi S. Sripathi V. and Tiwari A. 2011. Peri autotuning of pflotran. J. Phys.  Chame J. Chen C. Hall M. Hollingsworth J. Mahinthakumar K. Marin G. Ramalingam S. Sripathi S. Sripathi V. and Tiwari A. 2011. Peri autotuning of pflotran. J. Phys."},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2005.10"},{"key":"e_1_2_1_15_1","unstructured":"Chen C. Chame J. and Hall M. 2008. CHiLL: A framework for composing high-level loop transformations. Tech. rep. 08-897 University of Southern California.  Chen C. Chame J. and Hall M. 2008. CHiLL: A framework for composing high-level loop transformations. Tech. rep. 08-897 University of Southern California."},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-69330-7_30"},{"key":"e_1_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Chen C. Chame J. Nelson Y. Diniz P. Hall M. and Lucas R. 2007a. Compiler-Assisted performance tuning. J. Phys. 78.  Chen C. Chame J. Nelson Y. Diniz P. Hall M. and Lucas R. 2007a. Compiler-Assisted performance tuning. J. Phys. 78.","DOI":"10.1088\/1742-6596\/78\/1\/012024"},{"key":"e_1_2_1_18_1","volume-title":"Proceedings of the Workshop on Performance Optimization for High-Level Languages and Libraries (POHLL'07)","author":"Chen C."},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2004.65"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/314403.314414"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2011.33"},{"key":"e_1_2_1_22_1","volume-title":"Proceeding of the 2008 ACM\/IEEE Conference on Supercomputing. 4.","author":"Datta K."},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-69330-7_10"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/301618.301661"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10766-006-0012-3"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-13374-9_4"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/1513895.1513902"},{"key":"e_1_2_1_28_1","volume-title":"The parboil benchmark suite","year":"2007"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/73560.73588"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/143369.143427"},{"key":"e_1_2_1_31_1","unstructured":"Kirk D. and Hwu W. 2010. Programming Massively Parallel Processors: A Hands-On Approach. Morgan Kaufmann Publishers.   Kirk D. and Hwu W. 2010. Programming Massively Parallel Processors: A Hands-On Approach. Morgan Kaufmann Publishers."},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/1504176.1504194"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/1735688.1735698"},{"key":"e_1_2_1_34_1","unstructured":"Nath R. Tomov S. and Dongarra J. 2010. An improved magma gemm for fermi gpus. Tech. rep. UT-CS-10-655 (also LAPACK working note 227) University of Tennessee Computer Science technical report. July.  Nath R. Tomov S. and Dongarra J. 2010. An improved magma gemm for fermi gpus. Tech. rep. UT-CS-10-655 (also LAPACK working note 227) University of Tennessee Computer Science technical report. July."},{"key":"e_1_2_1_35_1","volume-title":"Workshop on Profile and Feedback-Directed Compilation.","author":"Nisbet A. P.","year":"1998"},{"key":"e_1_2_1_36_1","volume-title":"Proceedings of the 9th IEEE\/ACM International Symposium on Code Generation and Optimization (CGO'11)","author":"Park E."},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2007.21"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/1375581.1375594"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2004.840306"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/1183401.1183437"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/1454115.1454155"},{"key":"e_1_2_1_42_1","volume-title":"Proceedings of the 23rd International Conference on Languages and Compilers for Parallel Computing (LCPC'10)","author":"Rudy G."},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/1810085.1810120"},{"key":"e_1_2_1_44_1","volume-title":"Proceedings of the 4th International Workshop on Automatic Performance Tuning.","author":"Shin J."},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/781131.781141"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2009.5161054"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1177\/1094342011414744"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-89740-8_1"},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-28652-0_2"},{"key":"e_1_2_1_50_1","volume-title":"In Proceedings of the Conference on Supercomputing.","author":"Volkov V."},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/16\/1\/071"},{"key":"e_1_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/16\/1\/071"},{"key":"e_1_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1002\/spe.v35:2"},{"key":"e_1_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8191(00)00086-7"},{"key":"e_1_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/76263.76337"},{"key":"e_1_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/1806596.1806606"},{"key":"e_1_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1002\/spe.1089"},{"key":"e_1_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/1088149.1088168"}],"container-title":["ACM Transactions on Architecture and Code Optimization"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2400682.2400690","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2400682.2400690","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T09:35:01Z","timestamp":1750239301000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2400682.2400690"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,1]]},"references-count":57,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2013,1]]}},"alternative-id":["10.1145\/2400682.2400690"],"URL":"https:\/\/doi.org\/10.1145\/2400682.2400690","relation":{},"ISSN":["1544-3566","1544-3973"],"issn-type":[{"value":"1544-3566","type":"print"},{"value":"1544-3973","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,1]]},"assertion":[{"value":"2012-02-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2012-10-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2013-01-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}