{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T22:47:45Z","timestamp":1725662865533},"publisher-location":"New York, NY, USA","reference-count":15,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,6,6]],"date-time":"2019-06-06T00:00:00Z","timestamp":1559779200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,6,6]]},"DOI":"10.1145\/3337801.3337817","type":"proceedings-article","created":{"date-parts":[[2019,7,12]],"date-time":"2019-07-12T19:04:37Z","timestamp":1562958277000},"page":"1-6","update-policy":"http:\/\/dx.doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Effectiveness of performance tuning techniques for general matrix multiplication on the PEZY-SC2"],"prefix":"10.1145","author":[{"given":"Kazuya","family":"Matsumoto","sequence":"first","affiliation":[{"name":"The University of Aizu, Aizu-Wakamatsu, Fukushima Japan"}]},{"given":"Naohito","family":"Nakasato","sequence":"additional","affiliation":[{"name":"The University of Aizu, Aizu-Wakamatsu, Fukushima Japan"}]},{"given":"Toshiaki","family":"Hishinuma","sequence":"additional","affiliation":[{"name":"PEZY Computing, Chiyoda, Tokyo, Japan"}]}],"member":"320","published-online":{"date-parts":[[2019,6,6]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1147\/rd.385.0563"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2011.10.002"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2013.113"},{"key":"e_1_3_2_1_4_1","volume-title":"Proc. ICPP","author":"Jiang L.","year":"2017","unstructured":"L. Jiang , C. Yang , Y. Ao , W. Yin , W. Ma , Q. Sun , F. Liu , R. Lin , and P. Zhang . 2017. Towards highly efficient DGEMM on the emerging SW26010 many-core processor . In Proc. ICPP 2017 . 422--431. L. Jiang, C. Yang, Y. Ao, W. Yin, W. Ma, Q. Sun, F. Liu, R. Lin, and P. Zhang. 2017. Towards highly efficient DGEMM on the emerging SW26010 many-core processor. In Proc. ICPP 2017. 422--431."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2011.311"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-01970-8_89"},{"key":"e_1_3_2_1_7_1","first-page":"2014","article-title":"Implementing level-3 BLAS routines in OpenCL on different processing units","author":"Matsumoto K.","year":"2014","unstructured":"K. Matsumoto , N. Nakasato , and S. Sedukhin . 2014 . Implementing level-3 BLAS routines in OpenCL on different processing units . Technical Report 2014 - 2001 . The University of Aizu. K. Matsumoto, N. Nakasato, and S. Sedukhin. 2014. Implementing level-3 BLAS routines in OpenCL on different processing units. Technical Report 2014-001. The University of Aizu.","journal-title":"Technical Report"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.Companion.2012.59"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2003.1214317"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2063384.2063431"},{"key":"e_1_3_2_1_11_1","volume-title":"Proc. ESPM2","author":"Tanaka H.","year":"2018","unstructured":"H. Tanaka , Y. Ishihara , R. Sakamoto , T. Nakamura , Y. Kimura , and K. Nitadori . 2018. Automatic generation of high-order finite-difference code with temporal blocking for extreme-scale many-core systems . In Proc. ESPM2 2018 . H. Tanaka, Y. Ishihara, R. Sakamoto, T. Nakamura, Y. Kimura, and K. Nitadori. 2018. Automatic generation of high-order finite-difference code with temporal blocking for extreme-scale many-core systems. In Proc. ESPM2 2018."},{"key":"e_1_3_2_1_12_1","unstructured":"S. Torii H. Ishikawa Y. Kimura and M. Saitoh. 2015 (In Japanese). Technologies and future prospects of green supercomputer ZettaScaler. IEICE Trans. Electron. J100-C 11 (2015 (In Japanese)) 537--544. S. Torii H. Ishikawa Y. Kimura and M. Saitoh. 2015 (In Japanese). Technologies and future prospects of green supercomputer ZettaScaler. IEICE Trans. Electron. J100-C 11 (2015 (In Japanese)) 537--544."},{"volume-title":"Proc. SC'08","author":"Volkov V.","key":"e_1_3_2_1_13_1","unstructured":"V. Volkov and J. W. Demmel . 2008. Benchmarking GPUs to tune dense linear algebra . In Proc. SC'08 . IEEE Press, 31:1--31:11. V. Volkov and J. W. Demmel. 2008. Benchmarking GPUs to tune dense linear algebra. In Proc. SC'08. IEEE Press, 31:1--31:11."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8191(00)00086-7"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1177\/1094342017710705"}],"event":{"name":"HEART 2019: The 10th International Symposium on Highly-Efficient Accelerators and Reconfigurable Technologies","acronym":"HEART 2019","location":"Nagasaki Japan"},"container-title":["Proceedings of the 10th International Symposium on Highly-Efficient Accelerators and Reconfigurable Technologies"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3337801.3337817","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,19]],"date-time":"2023-07-19T22:41:14Z","timestamp":1689806474000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3337801.3337817"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6,6]]},"references-count":15,"alternative-id":["10.1145\/3337801.3337817","10.1145\/3337801"],"URL":"https:\/\/doi.org\/10.1145\/3337801.3337817","relation":{},"subject":[],"published":{"date-parts":[[2019,6,6]]},"assertion":[{"value":"2019-06-06","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}