{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T01:44:48Z","timestamp":1773193488147,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":32,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,6,21]],"date-time":"2023-06-21T00:00:00Z","timestamp":1687305600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,6,21]]},"DOI":"10.1145\/3577193.3593708","type":"proceedings-article","created":{"date-parts":[[2023,6,20]],"date-time":"2023-06-20T18:47:05Z","timestamp":1687286825000},"page":"180-191","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Wafer-Scale Fast Fourier Transforms"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4757-4215","authenticated-orcid":false,"given":"Marcelo","family":"Orenes-Vera","sequence":"first","affiliation":[{"name":"Princeton University, Princeton, New Jersey, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8980-6170","authenticated-orcid":false,"given":"Ilya","family":"Sharapov","sequence":"additional","affiliation":[{"name":"Cerebras Systems, Sunnyvale, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3057-5820","authenticated-orcid":false,"given":"Robert","family":"Schreiber","sequence":"additional","affiliation":[{"name":"Cerebras Systems, Sunnyvale, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3137-166X","authenticated-orcid":false,"given":"Mathias","family":"Jacquelin","sequence":"additional","affiliation":[{"name":"Cerebras Systems, Sunnyvale, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0017-2995","authenticated-orcid":false,"given":"Philippe","family":"Vandermersch","sequence":"additional","affiliation":[{"name":"Cerebras Systems, Sunnyvale, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7434-2860","authenticated-orcid":false,"given":"Sharan","family":"Chetlur","sequence":"additional","affiliation":[{"name":"Cerebras Systems, Sunnyvale, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,6,21]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-50371-0_19"},{"key":"e_1_3_2_1_2_1","unstructured":"Alan Ayala Stanimire Tomov Piotr Luszczek S\u00e9bastien Cayrols Gerald Ragghianti and Jack Dongarra. 2020. Interim Report on Benchmarking FFT Libraries on High Performance Systems.  Alan Ayala Stanimire Tomov Piotr Luszczek S\u00e9bastien Cayrols Gerald Ragghianti and Jack Dongarra. 2020. Interim Report on Benchmarking FFT Libraries on High Performance Systems."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1177\/109434209100500306"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2006.1639320"},{"key":"e_1_3_2_1_5_1","volume-title":"An algorithm for the machine calculation of complex Fourier series. Mathematics of computation 19, 90","author":"Cooley James W","year":"1965","unstructured":"James W Cooley and John W Tukey . 1965. An algorithm for the machine calculation of complex Fourier series. Mathematics of computation 19, 90 ( 1965 ), 297--301. James W Cooley and John W Tukey. 1965. An algorithm for the machine calculation of complex Fourier series. Mathematics of computation 19, 90 (1965), 297--301."},{"key":"e_1_3_2_1_6_1","unstructured":"Lisandro Dalcin. 2019. MPI for Python. https:\/\/github.com\/mpi4py\/mpi4py-fft.  Lisandro Dalcin. 2019. MPI for Python. https:\/\/github.com\/mpi4py\/mpi4py-fft."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2019.02.006"},{"key":"e_1_3_2_1_8_1","volume-title":"A Portable 3D FFT Package for Distributed-Memory Parallel Architectures","author":"Ding Hong Q","unstructured":"Hong Q Ding , Robert D Ferraro , and Donald B Gennery . 1995. A Portable 3D FFT Package for Distributed-Memory Parallel Architectures .. In PPSC. SIAM , San Francisco , 70--71. Hong Q Ding, Robert D Ferraro, and Donald B Gennery. 1995. A Portable 3D FFT Package for Distributed-Memory Parallel Architectures.. In PPSC. SIAM, San Francisco, 70--71."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1137\/S1064827594266891"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2004.840301"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/71.238626"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.newast.2015.06.003"},{"key":"e_1_3_2_1_13_1","unstructured":"Intel. 2021. Math Kernel Library (MKL). https:\/\/software.intel.com\/mkl.  Intel. 2021. Math Kernel Library (MKL). https:\/\/software.intel.com\/mkl."},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings of the International Conference on Parallel and Distributed Processing Techniques and Applications, PDPTA. 27--30","author":"Kettimuthu Rajkumar","year":"2005","unstructured":"Rajkumar Kettimuthu and Sankara Muthukrishnan . 2005 . A performance study of parallel FFT in clos and mesh networks . In Proceedings of the International Conference on Parallel and Distributed Processing Techniques and Applications, PDPTA. 27--30 . Rajkumar Kettimuthu and Sankara Muthukrishnan. 2005. A performance study of parallel FFT in clos and mesh networks. In Proceedings of the International Conference on Parallel and Distributed Processing Techniques and Applications, PDPTA. 27--30."},{"key":"e_1_3_2_1_15_1","unstructured":"LAMMPS. 2021. Molecular Dynamics Simulator. https:\/\/www.lammps.org.  LAMMPS. 2021. Molecular Dynamics Simulator. https:\/\/www.lammps.org."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2503210.2503298"},{"key":"e_1_3_2_1_17_1","volume-title":"Multi-Wafer AI Cluster. In 2021 IEEE Hot Chips 33 Symposium (HCS). IEEE Computer Society, 1--41","author":"Lie Sean","year":"2021","unstructured":"Sean Lie . 2021 . Multi-Million Core , Multi-Wafer AI Cluster. In 2021 IEEE Hot Chips 33 Symposium (HCS). IEEE Computer Society, 1--41 . Sean Lie. 2021. Multi-Million Core, Multi-Wafer AI Cluster. In 2021 IEEE Hot Chips 33 Symposium (HCS). IEEE Computer Society, 1--41."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3092312"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1155\/1995\/637864"},{"key":"e_1_3_2_1_20_1","unstructured":"Timothy Pickett Morgan. 2018. Peeling the Covers Off the Summit Supercomputer. https:\/\/www.nextplatform.com\/2018\/06\/26\/peeling-the-covers-off-the-summit-supercomputer\/.  Timothy Pickett Morgan. 2018. Peeling the Covers Off the Summit Supercomputer. https:\/\/www.nextplatform.com\/2018\/06\/26\/peeling-the-covers-off-the-summit-supercomputer\/."},{"key":"e_1_3_2_1_21_1","unstructured":"NumPy. 2022. Discrete Fourier Transform. https:\/\/numpy.org\/doc\/stable\/reference\/routines.fft.html.  NumPy. 2022. Discrete Fourier Transform. https:\/\/numpy.org\/doc\/stable\/reference\/routines.fft.html."},{"key":"e_1_3_2_1_22_1","unstructured":"Nvidia. 2021. CuFFT. https:\/\/developer.nvidia.com\/cufft.  Nvidia. 2021. CuFFT. https:\/\/developer.nvidia.com\/cufft."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071089"},{"key":"e_1_3_2_1_24_1","unstructured":"ORNL. 2018. Summit Supercomputer. https:\/\/www.ornl.gov\/news\/ornl-launches-summit-supercomputer.  ORNL. 2018. Summit Supercomputer. https:\/\/www.ornl.gov\/news\/ornl-launches-summit-supercomputer."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1137\/11082748X"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1137\/120885887"},{"key":"e_1_3_2_1_27_1","unstructured":"Steve Plimpton. 2018. fftMPI a distributed-memory parallel FFT library. https:\/\/lammps.github.io\/fftmpi\/.  Steve Plimpton. 2018. fftMPI a distributed-memory parallel FFT library. https:\/\/lammps.github.io\/fftmpi\/."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.5555\/3433701.3433778"},{"key":"e_1_3_2_1_29_1","volume-title":"Parallel computations","author":"Swarztrauber Paul N","unstructured":"Paul N Swarztrauber . 1982. Vectorizing the FFTs . In Parallel computations . Elsevier , 51--83. Paul N Swarztrauber. 1982. Vectorizing the FFTs. In Parallel computations. Elsevier, 51--83."},{"key":"e_1_3_2_1_30_1","volume-title":"International Conference on Parallel Processing and Applied Mathematics. Springer, 606--614","author":"Takahashi Daisuke","year":"2009","unstructured":"Daisuke Takahashi . 2009 . An implementation of parallel 3-D FFT with 2-D decomposition on a massively parallel cluster of multi-core processors . In International Conference on Parallel Processing and Applied Mathematics. Springer, 606--614 . Daisuke Takahashi. 2009. An implementation of parallel 3-D FFT with 2-D decomposition on a massively parallel cluster of multi-core processors. In International Conference on Parallel Processing and Applied Mathematics. Springer, 606--614."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45009-2_8"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","unstructured":"Charles Van Loan. 1992. Computational frameworks for the fast Fourier transform. SIAM.  Charles Van Loan. 1992. Computational frameworks for the fast Fourier transform. SIAM.","DOI":"10.1137\/1.9781611970999"}],"event":{"name":"ICS '23: 37th International Conference on Supercomputing","location":"Orlando FL USA","acronym":"ICS '23","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 37th International Conference on Supercomputing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3577193.3593708","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:47:31Z","timestamp":1750178851000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3577193.3593708"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,21]]},"references-count":32,"alternative-id":["10.1145\/3577193.3593708","10.1145\/3577193"],"URL":"https:\/\/doi.org\/10.1145\/3577193.3593708","relation":{},"subject":[],"published":{"date-parts":[[2023,6,21]]},"assertion":[{"value":"2023-06-21","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}