{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T11:48:07Z","timestamp":1762084087710,"version":"build-2065373602"},"publisher-location":"New York, NY, USA","reference-count":28,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,2,27]],"date-time":"2023-02-27T00:00:00Z","timestamp":1677456000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"European Union?s Horizon 2020\/EuroHPC","award":["955606"],"award-info":[{"award-number":["955606"]}]},{"DOI":"10.13039\/501100004359","name":"Vetenskapsr\u00e5det","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004359","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,2,27]]},"DOI":"10.1145\/3578178.3578239","type":"proceedings-article","created":{"date-parts":[[2023,2,10]],"date-time":"2023-02-10T17:19:05Z","timestamp":1676049545000},"page":"55-63","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["A Case Study on DaCe Portability & Performance for Batched Discrete Fourier Transforms"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6384-2630","authenticated-orcid":false,"given":"M\u00e5ns Ivar","family":"Andersson","sequence":"first","affiliation":[{"name":"KTH Royal Institute of Technology, Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0639-0639","authenticated-orcid":false,"given":"Stefano","family":"Markidis","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology, Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,2,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/FPL.2014.6927450"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"M\u00e5ns\u00a0I Andersson N\u00a0Arul Murugan Artur Podobas and Stefano Markidis. 2022. Breaking Down the Parallel Performance of GROMACS a High-Performance Molecular Dynamics Software. arXiv preprint arXiv:2208.13658(2022).","DOI":"10.1007\/978-3-031-30442-2_25"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356173"},{"key":"e_1_3_2_1_4_1","unstructured":"Gabriel Bengtsson. 2020. Development of Stockham Fast Fourier Transform using Data-Centric Parallel Programming."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/P3HPC49587.2019.00006"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2017.05.138"},{"key":"e_1_3_2_1_7_1","volume-title":"Mamba: Portable Array-based Abstractions for Heterogeneous High-Performance Systems. In 2021 International Workshop on Performance, Portability and Productivity in HPC (P3HPC). IEEE, 10\u201321","author":"Dykes Tim","year":"2021","unstructured":"Tim Dykes, Cl\u00e9ment Foyer, Harvey Richardson, Martin Svedin, Artur Podobas, Niclas Jansson, Stefano Markidis, Adrian Tate, and Simon McIntosh-Smith. 2021. Mamba: Portable Array-based Abstractions for Heterogeneous High-Performance Systems. In 2021 International Workshop on Performance, Portability and Productivity in HPC (P3HPC). IEEE, 10\u201321."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/XSW.2013.7"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"Franz Franchetti and al.2018. SPIRAL: Extreme Performance Portability. From High Level Specification to High Performance Code 106 11(2018).","DOI":"10.1109\/JPROC.2018.2875253"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/301618.301661"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2004.840301"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Tobias Gysi Christoph M\u00fcller Oleksandr Zinenko Stephan Herhut Eddie Davis Tobias Wicky Oliver Fuhrer Torsten Hoefler and Tobias Grosser. 2020. Domain-specific multi-level IR rewriting for GPU. arXiv preprint arXiv:2005.13014(2020).","DOI":"10.1145\/3469030"},{"key":"e_1_3_2_1_13_1","unstructured":"Yifei He Artur Podobas M\u00e5ns\u00a0I Andersson and Stefano Markidis. 2022. FFTc: An MLIR Dialect for Developing HPC Fast Fourier Transform Libraries. arXiv preprint arXiv:2207.06803(2022)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3282307"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Richard\u00a0D Hornung and Jeffrey\u00a0A Keasler. 2014. The RAJA portability layer: overview and status. (2014).","DOI":"10.2172\/1169830"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"e_1_3_2_1_17_1","volume-title":"CGO","author":"Lattner C.","year":"2004","unstructured":"C. Lattner and V. Adve. 2004. LLVM: a compilation framework for lifelong program analysis amp; transformation. In CGO 2004.75\u201386."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO51591.2021.9370308"},{"volume-title":"Nvidia tensor core programmability, performance & precision. In 2018 IEEE international parallel and distributed processing symposium workshops (IPDPSW)","author":"Markidis Stefano","key":"e_1_3_2_1_19_1","unstructured":"Stefano Markidis, Steven\u00a0Wei Der\u00a0Chien, Erwin Laure, Ivy\u00a0Bo Peng, and Jeffrey\u00a0S Vetter. 2018. Nvidia tensor core programmability, performance & precision. In 2018 IEEE international parallel and distributed processing symposium workshops (IPDPSW). IEEE, 522\u2013531."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45545-0_17"},{"key":"e_1_3_2_1_21_1","unstructured":"Simon\u00a0J Pennycook Jason\u00a0D Sewall and Victor\u00a0W Lee. 2016. A metric for performance portability. arXiv preprint arXiv:1611.07409(2016)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2017.8091024"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2017.2703149"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Charles Van\u00a0Loan. 1992. Computational frameworks for the fast Fourier transform. SIAM.","DOI":"10.1137\/1.9781611970999"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1137\/19M1282040"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3086466"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3357156"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476176"}],"event":{"name":"HPC ASIA 2023: International Conference on High Performance Computing in Asia-Pacific Region","acronym":"HPC ASIA 2023","location":"Singapore Singapore"},"container-title":["Proceedings of the International Conference on High Performance Computing in Asia-Pacific Region"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3578178.3578239","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3578178.3578239","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:49:20Z","timestamp":1750182560000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3578178.3578239"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,27]]},"references-count":28,"alternative-id":["10.1145\/3578178.3578239","10.1145\/3578178"],"URL":"https:\/\/doi.org\/10.1145\/3578178.3578239","relation":{},"subject":[],"published":{"date-parts":[[2023,2,27]]},"assertion":[{"value":"2023-02-27","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}