{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T17:14:22Z","timestamp":1774631662796,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":20,"publisher":"ACM","license":[{"start":{"date-parts":[[2014,5,20]],"date-time":"2014-05-20T00:00:00Z","timestamp":1400544000000},"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":["I\/UCRC IIP-1266245"],"award-info":[{"award-number":["I\/UCRC IIP-1266245"]}],"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":[[2014,5,20]]},"DOI":"10.1145\/2597917.2597943","type":"proceedings-article","created":{"date-parts":[[2014,6,20]],"date-time":"2014-06-20T13:06:05Z","timestamp":1403269565000},"page":"1-10","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Towards a performance-portable FFT library for heterogeneous computing"],"prefix":"10.1145","author":[{"given":"Carlo","family":"del Mundo","sequence":"first","affiliation":[{"name":"NSF Center for High-Performance Reconfigurable Computing, Virginia Tech"}]},{"given":"Wu-chun","family":"Feng","sequence":"additional","affiliation":[{"name":"NSF Center for High-Performance Reconfigurable Computing, Virginia Tech"}]}],"member":"320","published-online":{"date-parts":[[2014,5,20]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"AMD Accelerated Parallel Processing OpenCL Programming Guide July 2012.  AMD Accelerated Parallel Processing OpenCL Programming Guide July 2012."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/1562764.1562783"},{"key":"e_1_3_2_1_3_1","volume-title":"Multimedia and Expo, 2008 IEEE International Conference on, 23 2008-april 26","author":"Brandon L.","year":"2008","unstructured":"L. Brandon , C. Boyd , and N. Govindaraju . Fast Computation of General Fourier Transforms on GPUs . In Multimedia and Expo, 2008 IEEE International Conference on, 23 2008-april 26 2008 . L. Brandon, C. Boyd, and N. Govindaraju. Fast Computation of General Fourier Transforms on GPUs. In Multimedia and Expo, 2008 IEEE International Conference on, 23 2008-april 26 2008."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/1810085.1810128"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2304576.2304604"},{"key":"e_1_3_2_1_6_1","volume-title":"Supercomputing, 2013. Proceedings of the 2013 ACM\/IEEE International Conference on","author":"del Mundo C.","year":"2013","unstructured":"C. del Mundo and W.-c. Feng . Enabling Efficient Intra-Warp Communication for Fourier Transforms in a Many-Core Architecture . In Supercomputing, 2013. Proceedings of the 2013 ACM\/IEEE International Conference on , 2013 . (Poster Publication). C. del Mundo and W.-c. Feng. Enabling Efficient Intra-Warp Communication for Fourier Transforms in a Many-Core Architecture. In Supercomputing, 2013. Proceedings of the 2013 ACM\/IEEE International Conference on, 2013. (Poster Publication)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1941553.1941589"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/IV.2006.53"},{"key":"e_1_3_2_1_9_1","volume-title":"Speech and Signal Processing, 1998. Proceedings of the 1998 IEEE International Conference on","author":"Frigo M.","year":"1998","unstructured":"M. Frigo and S. Johnson . FFTW: An Adaptive Software Architecture for the FFT. In Acoustics , Speech and Signal Processing, 1998. Proceedings of the 1998 IEEE International Conference on , 1998 . M. Frigo and S. Johnson. FFTW: An Adaptive Software Architecture for the FFT. In Acoustics, Speech and Signal Processing, 1998. Proceedings of the 1998 IEEE International Conference on, 1998."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.5555\/1413370.1413373"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/1810085.1810127"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/1815961.1816021"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-71039-4_4"},{"key":"e_1_3_2_1_14_1","volume-title":"Fast Fourier Transform on AMD GPUs","author":"Nukada A.","year":"2011","unstructured":"A. Nukada . Fast Fourier Transform on AMD GPUs , 2011 . A. Nukada. Fast Fourier Transform on AMD GPUs, 2011."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/1654059.1654090"},{"key":"e_1_3_2_1_16_1","volume-title":"Storage and Analysis, 2008. SC 2008. International Conference for, nov.","author":"Nukada A.","year":"2008","unstructured":"A. Nukada , Y. Ogata , T. Endo , and S. Matsuoka . Bandwidth Intensive 3-D FFT Kernel for GPUs using CUDA. In High Performance Computing, Networking , Storage and Analysis, 2008. SC 2008. International Conference for, nov. 2008 . A. Nukada, Y. Ogata, T. Endo, and S. Matsuoka. Bandwidth Intensive 3-D FFT Kernel for GPUs using CUDA. In High Performance Computing, Networking, Storage and Analysis, 2008. SC 2008. International Conference for, nov. 2008."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2366231.2337210"},{"key":"e_1_3_2_1_18_1","volume-title":"IEE Proceedings -, june","author":"Uzun I.","year":"2005","unstructured":"I. Uzun , A. Amira , and A. Bouridane . FPGA Implementations of Fast Fourier Transforms for Real-time Signal and Image Processing. Vision, Image and Signal Processing , IEE Proceedings -, june 2005 . I. Uzun, A. Amira, and A. Bouridane. FPGA Implementations of Fast Fourier Transforms for Real-time Signal and Image Processing. Vision, Image and Signal Processing, IEE Proceedings -, june 2005."},{"key":"e_1_3_2_1_19_1","volume-title":"Fitting FFT Onto the G80 Architecture","author":"Volkov V.","year":"2008","unstructured":"V. Volkov and B. Kazian . Fitting FFT Onto the G80 Architecture . May 2008 . V. Volkov and B. Kazian. Fitting FFT Onto the G80 Architecture. May 2008."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2007.1079"}],"event":{"name":"CF'14: Computing Frontiers Conference","location":"Cagliari Italy","acronym":"CF'14","sponsor":["SIGMICRO ACM Special Interest Group on Microarchitectural Research and Processing"]},"container-title":["Proceedings of the 11th ACM Conference on Computing Frontiers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2597917.2597943","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2597917.2597943","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T07:00:51Z","timestamp":1750230051000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2597917.2597943"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,5,20]]},"references-count":20,"alternative-id":["10.1145\/2597917.2597943","10.1145\/2597917"],"URL":"https:\/\/doi.org\/10.1145\/2597917.2597943","relation":{},"subject":[],"published":{"date-parts":[[2014,5,20]]},"assertion":[{"value":"2014-05-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}