{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T11:44:09Z","timestamp":1766231049901,"version":"3.48.0"},"publisher-location":"New York, NY, USA","reference-count":13,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,9,8]]},"DOI":"10.1145\/3750720.3757287","type":"proceedings-article","created":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T11:42:38Z","timestamp":1766230958000},"page":"64-70","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Superword-Level Parallelism on RISC-V through Custom Instruction Extensions"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-3517-2689","authenticated-orcid":false,"given":"Min-Hsiu","family":"Hsu","sequence":"first","affiliation":[{"name":"National Taiwan University, Taipei, Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5294-5274","authenticated-orcid":false,"given":"Shih-wei","family":"Liao","sequence":"additional","affiliation":[{"name":"National Taiwan University, Taipei, Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1517-9086","authenticated-orcid":false,"given":"Chi-Hung","family":"Wei","sequence":"additional","affiliation":[{"name":"National Taiwan University, Taipei, Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3550-9009","authenticated-orcid":false,"given":"Chi-Bang","family":"Kuan","sequence":"additional","affiliation":[{"name":"Mediatek, Hsinchu, Taiwan"}]}],"member":"320","published-online":{"date-parts":[[2025,12,20]]},"reference":[{"key":"e_1_3_3_1_2_2","volume-title":"Instruction Sets Should Be Free: The Case For RISC-V","author":"Asanovi\u0107 Krste","year":"2014","unstructured":"Krste Asanovi\u0107 and David\u00a0A. Patterson. 2014. Instruction Sets Should Be Free: The Case For RISC-V. Technical Report UCB\/EECS-2014-146. EECS Department, University of California, Berkeley. https:\/\/www2.eecs.berkeley.edu\/Pubs\/TechRpts\/2014\/EECS-2014-146.html"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","unstructured":"Christopher Celio Palmer Dabbelt David\u00a0A. Patterson and Krste Asanovi\u0107. 2016. The Renewed Case for the Reduced Instruction Set Computer: Avoiding ISA Bloat with Macro-Op Fusion for RISC-V. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1607.02318 (2016). 10.48550\/arXiv.1607.02318arXiv:https:\/\/arXiv.org\/abs\/1607.02318.","DOI":"10.48550\/arXiv.1607.02318"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/349299.349320"},{"key":"e_1_3_3_1_5_2","unstructured":"LLVM Project. [n. d.]. TableGen: A Domain-Specific Language for Describing Compiler Backends. https:\/\/llvm.org\/docs\/TableGen\/."},{"key":"e_1_3_3_1_6_2","unstructured":"LLVM Project. n. d.. Low Level Virtual Machine (LLVM). https:\/\/github.com\/llvm\/llvm-project."},{"key":"e_1_3_3_1_7_2","first-page":"105","volume-title":"Proceedings of the 2004 GCC developers summit","author":"Naishlos Dorit","year":"2004","unstructured":"Dorit Naishlos. 2004. Autovectorization in GCC. In Proceedings of the 2004 GCC developers summit. Citeseer, 105\u2013118."},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2006.25"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"crossref","unstructured":"Dorit Nuzman Ira Rosen and Ayal Zaks. 2006. Auto-vectorization of interleaved data for SIMD. ACM SIGPLAN Notices 41 6 (2006) 132\u2013143.","DOI":"10.1145\/1133255.1133997"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP54787.2022.00017"},{"key":"e_1_3_3_1_11_2","unstructured":"QEMU Project. n. d.. Quick Emulator (QEMU). https:\/\/github.com\/qemu\/qemu\/tree\/stable-8.0."},{"key":"e_1_3_3_1_12_2","first-page":"131","volume-title":"GCC Developers Summit","author":"Rosen Ira","year":"2007","unstructured":"Ira Rosen, Dorit Nuzman, and Ayal Zaks. 2007. Loop-aware SLP in GCC. In GCC Developers Summit. 131\u2013142."},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"crossref","unstructured":"Nigel Stephens Stuart Biles Matthias Boettcher Jacob Eapen Mbou Eyole Giacomo Gabrielli Matt Horsnell Grigorios Magklis Alejandro Martinez Nathanael Premillieu et\u00a0al. 2017. The ARM scalable vector extension. IEEE micro 37 2 (2017) 26\u201339.","DOI":"10.1109\/MM.2017.35"},{"key":"e_1_3_3_1_14_2","volume-title":"The RISC-V Instruction Set Manual, Volume I: User-Level ISA, Version 2.1","author":"Waterman Andrew","year":"2016","unstructured":"Andrew Waterman, Yunsup Lee, David\u00a0A. Patterson, and Krste Asanovi\u0107. 2016. The RISC-V Instruction Set Manual, Volume I: User-Level ISA, Version 2.1. Technical Report UCB\/EECS-2016-118. University of California, Berkeley. http:\/\/www.eecs.berkeley.edu\/Pubs\/TechRpts\/2016\/EECS-2016-118.html"}],"event":{"name":"ICPP Workshops '25: The 54th International Conference on Parallel Processing Workshops","location":"San Diego CA USA","acronym":"ICPP Workshops '25"},"container-title":["Workshop Proceedings of the 54th International Conference on Parallel Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3750720.3757287","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T11:42:54Z","timestamp":1766230974000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3750720.3757287"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,8]]},"references-count":13,"alternative-id":["10.1145\/3750720.3757287","10.1145\/3750720"],"URL":"https:\/\/doi.org\/10.1145\/3750720.3757287","relation":{},"subject":[],"published":{"date-parts":[[2025,9,8]]},"assertion":[{"value":"2025-12-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}