{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T13:39:09Z","timestamp":1770817149288,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":17,"publisher":"ACM","license":[{"start":{"date-parts":[[2010,6,2]],"date-time":"2010-06-02T00:00:00Z","timestamp":1275436800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100002855","name":"Ministry of Science and Technology of the People's Republic of China","doi-asserted-by":"publisher","award":["45210130-0442"],"award-info":[{"award-number":["45210130-0442"]}],"id":[{"id":"10.13039\/501100002855","id-type":"DOI","asserted-by":"publisher"}]},{"name":"China HGJ Significant Project","award":["2009ZX01036-001-002-4"],"award-info":[{"award-number":["2009ZX01036-001-002-4"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2010,6,2]]},"DOI":"10.1145\/1810085.1810128","type":"proceedings-article","created":{"date-parts":[[2010,6,8]],"date-time":"2010-06-08T12:37:34Z","timestamp":1276000654000},"page":"315-324","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":62,"title":["Large-scale FFT on GPU clusters"],"prefix":"10.1145","author":[{"given":"Yifeng","family":"Chen","sequence":"first","affiliation":[{"name":"Peking University, Beijing, China"}]},{"given":"Xiang","family":"Cui","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}]},{"given":"Hong","family":"Mei","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2010,6,2]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"CUDA CUFFT Library Version 2.3. NVIDIA Corp. 2009. CUDA CUFFT Library Version 2.3 . NVIDIA Corp. 2009."},{"key":"e_1_3_2_1_2_1","unstructured":"CUDA Programming Guide Version 2.3. NVIDIA Corp. 2009. CUDA Programming Guide Version 2.3 . NVIDIA Corp. 2009."},{"key":"e_1_3_2_1_3_1","volume-title":"http:\/\/www.nvidia.com\/object\/io1258539409179.html","author":"IDIA","year":"2009","unstructured":"NV IDIA Tesla GPUs to communicate faster over Mellanox infiniband networks. http:\/\/www.nvidia.com\/object\/io1258539409179.html , 2009 . NVIDIA Tesla GPUs to communicate faster over Mellanox infiniband networks. http:\/\/www.nvidia.com\/object\/io1258539409179.html, 2009."},{"key":"e_1_3_2_1_4_1","first-page":"34","volume-title":"ICS'94","year":"1994","unstructured":"Agarwal, Gustavson, and Zubair. A high performance parallel algorithm for 1-D FFT . In ICS'94 , pages 34 -- 40 . IEEE Computer Society , 1994 . Agarwal, Gustavson, and Zubair. A high performance parallel algorithm for 1-D FFT. In ICS'94, pages 34--40. IEEE Computer Society, 1994."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/973097.973098"},{"key":"e_1_3_2_1_6_1","unstructured":"I. Corp. http:\/\/software.intel.com\/en-us\/intel-mkl\/.  I. Corp. http:\/\/software.intel.com\/en-us\/intel-mkl\/."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPADS.2009.8"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1513895.1513901"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.5555\/1413370.1413373"},{"key":"e_1_3_2_1_10_1","volume-title":"Fourier transforms for the Bluegene\/L communication network. Master's thesis","author":"Jagode H.","year":"2005","unstructured":"H. Jagode . Fourier transforms for the Bluegene\/L communication network. Master's thesis , The University of Edinburgh , 2005 . H. Jagode. Fourier transforms for the Bluegene\/L communication network. Master's thesis, The University of Edinburgh, 2005."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/1513895.1513905"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/1654059.1654090"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.5555\/1413370.1413376"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/1345206.1345220"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.5555\/1413370.1413402"},{"key":"e_1_3_2_1_16_1","unstructured":"V. Volkov and B. Kazian. FFT prototype. http:\/\/www.cs.berkeley.edu\/volkov\/.  V. Volkov and B. Kazian. FFT prototype. http:\/\/www.cs.berkeley.edu\/volkov\/."},{"key":"e_1_3_2_1_17_1","unstructured":"V. Volkov and B. Kazian. Fitting FFT onto the G80 architecture. http:\/\/www.cs.berkeley.edu\/ May 2008.  V. Volkov and B. Kazian. Fitting FFT onto the G80 architecture. http:\/\/www.cs.berkeley.edu\/ May 2008."}],"event":{"name":"ICS'10: International Conference on Supercomputing","location":"Tsukuba Ibaraki Japan","acronym":"ICS'10","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 24th ACM International Conference on Supercomputing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1810085.1810128","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1810085.1810128","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T11:23:24Z","timestamp":1750245804000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1810085.1810128"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,6,2]]},"references-count":17,"alternative-id":["10.1145\/1810085.1810128","10.1145\/1810085"],"URL":"https:\/\/doi.org\/10.1145\/1810085.1810128","relation":{},"subject":[],"published":{"date-parts":[[2010,6,2]]},"assertion":[{"value":"2010-06-02","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}