{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:30:00Z","timestamp":1750221000736,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":16,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,8,5]],"date-time":"2019-08-05T00:00:00Z","timestamp":1564963200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1642441"],"award-info":[{"award-number":["1642441"]}],"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":[[2019,8,5]]},"DOI":"10.1145\/3337821.3337908","type":"proceedings-article","created":{"date-parts":[[2019,7,25]],"date-time":"2019-07-25T12:34:36Z","timestamp":1564058076000},"page":"1-10","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Massively Parallel Automated Software Tuning"],"prefix":"10.1145","author":[{"given":"Jakub","family":"Kurzak","sequence":"first","affiliation":[{"name":"University of Tennessee, Knoxville, Tennessee"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaohung M.","family":"Tsai","sequence":"additional","affiliation":[{"name":"University of Tennessee, Knoxville, Tennessee"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mark","family":"Gates","sequence":"additional","affiliation":[{"name":"University of Tennessee, Knoxville, Tennessee"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ahmad","family":"Abdelfattah","sequence":"additional","affiliation":[{"name":"University of Tennessee, Knoxville, Tennessee"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jack","family":"Dongarra","sequence":"additional","affiliation":[{"name":"University of Tennessee, Knoxville, Tennessee"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2019,8,5]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/2628071.2628092"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.3516"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/263580.263662"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2011.70"},{"key":"e_1_3_2_1_5_1","volume-title":"The LINPACK benchmark: past, present and future. Concurrency and Computation: practice and experience 15, 9","author":"Dongarra Jack J","year":"2003","unstructured":"Jack J Dongarra , Piotr Luszczek , and Antoine Petitet . 2003. The LINPACK benchmark: past, present and future. Concurrency and Computation: practice and experience 15, 9 ( 2003 ), 803--820. Jack J Dongarra, Piotr Luszczek, and Antoine Petitet. 2003. The LINPACK benchmark: past, present and future. Concurrency and Computation: practice and experience 15, 9 (2003), 803--820."},{"key":"e_1_3_2_1_6_1","volume-title":"Speech and Signal Processing, 1998. Proceedings of the 1998 IEEE International Conference on","volume":"3","author":"Frigo Matteo","year":"1998","unstructured":"Matteo Frigo and Steven G Johnson . 1998 . FFTW: An adaptive software architecture for the FFT. In Acoustics , Speech and Signal Processing, 1998. Proceedings of the 1998 IEEE International Conference on , Vol. 3 . IEEE, 1381--1384. Matteo Frigo and Steven G Johnson. 1998. FFTW: An adaptive software architecture for the FFT. In Acoustics, Speech and Signal Processing, 1998. Proceedings of the 1998 IEEE International Conference on, Vol. 3. IEEE, 1381--1384."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-39707-6_11"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2011.311"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2016.197"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Kengo Nakajima Masaki Satoh Takashi Furumura Hiroshi Okuda Takeshi Iwashita Hide Sakaguchi Takahiro Katagiri Masaharu Matsumoto Satoshi Ohshima Hideyuki Jitsumoto etal 2016. ppOpen-HPC: open source infrastructure for development and execution of large-scale scientific applications on post-peta-scale supercomputers with automatic tuning (AT). In Optimization in the Real World. Springer 15--35.   Kengo Nakajima Masaki Satoh Takashi Furumura Hiroshi Okuda Takeshi Iwashita Hide Sakaguchi Takahiro Katagiri Masaharu Matsumoto Satoshi Ohshima Hideyuki Jitsumoto et al. 2016. ppOpen-HPC: open source infrastructure for development and execution of large-scale scientific applications on post-peta-scale supercomputers with automatic tuning (AT). In Optimization in the Real World. Springer 15--35.","DOI":"10.1007\/978-4-431-55420-2_2"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1177\/1094342010385729"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1177\/1094342004041291"},{"key":"e_1_3_2_1_14_1","volume-title":"Tensile: Auto-Tuning GEMM GPU Assembly for All Problem Sizes. In 2018 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW). IEEE, 1066--1075","author":"Tanner David E","year":"2018","unstructured":"David E Tanner . 2018 . Tensile: Auto-Tuning GEMM GPU Assembly for All Problem Sizes. In 2018 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW). IEEE, 1066--1075 . David E Tanner. 2018. Tensile: Auto-Tuning GEMM GPU Assembly for All Problem Sizes. In 2018 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW). IEEE, 1066--1075."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.5555\/762761.762771"},{"key":"e_1_3_2_1_16_1","series-title":"In Journal of Physics: Conference Series","volume-title":"OSKI: A library of automatically tuned sparse matrix kernels","author":"Vuduc Richard","year":"2005","unstructured":"Richard Vuduc , James W Demmel , and Katherine A Yelick . 2005 . OSKI: A library of automatically tuned sparse matrix kernels . In Journal of Physics: Conference Series , Vol. 16 . IOP Publishing , 521. Richard Vuduc, James W Demmel, and Katherine A Yelick. 2005. OSKI: A library of automatically tuned sparse matrix kernels. In Journal of Physics: Conference Series, Vol. 16. IOP Publishing, 521."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8191(00)00086-7"}],"event":{"name":"ICPP 2019: 48th International Conference on Parallel Processing","sponsor":["University of Tsukuba University of Tsukuba"],"location":"Kyoto Japan","acronym":"ICPP 2019"},"container-title":["Proceedings of the 48th International Conference on Parallel Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3337821.3337908","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3337821.3337908","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3337821.3337908","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T00:25:42Z","timestamp":1750206342000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3337821.3337908"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8,5]]},"references-count":16,"alternative-id":["10.1145\/3337821.3337908","10.1145\/3337821"],"URL":"https:\/\/doi.org\/10.1145\/3337821.3337908","relation":{},"subject":[],"published":{"date-parts":[[2019,8,5]]},"assertion":[{"value":"2019-08-05","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}