{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T15:01:28Z","timestamp":1785510088393,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":14,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,3,22]],"date-time":"2026-03-22T00:00:00Z","timestamp":1774137600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["SHF-2217395"],"award-info":[{"award-number":["SHF-2217395"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["CCF-2114319"],"award-info":[{"award-number":["CCF-2114319"]}],"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":[[2026,3,22]]},"DOI":"10.1145\/3818671.3818672","type":"proceedings-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T14:11:26Z","timestamp":1785507086000},"page":"1-7","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Sawtooth Wavefront Reordering: Enhanced CuTile FlashAttention on NVIDIA GB10"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-6718-7787","authenticated-orcid":false,"given":"Yifan","family":"Zhu","sequence":"first","affiliation":[{"name":"University of Rochester, Rochester, New York, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7639-1488","authenticated-orcid":false,"given":"Yekai","family":"Pan","sequence":"additional","affiliation":[{"name":"University of Rochester, Rochester, New York, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4968-6659","authenticated-orcid":false,"given":"Chen","family":"Ding","sequence":"additional","affiliation":[{"name":"University of Rochester, Rochester, New York, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,31]]},"reference":[{"key":"e_1_3_3_1_2_2","volume-title":"NVIDIA CUDA Tile","year":"2025","unstructured":"2025. NVIDIA CUDA Tile. https:\/\/developer.nvidia.com\/cuda\/tile"},{"key":"e_1_3_3_1_3_2","first-page":"1877","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared\u00a0D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et\u00a0al. 2020. Language Models are Few-Shot Learners. In Advances in Neural Information Processing Systems (NeurIPS) , Vol.\u00a033. 1877\u20131901. https:\/\/arxiv.org\/abs\/2005.14165"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1189"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/800213.806539"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/SCW63240.2024.00142"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2014.6835937"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037709"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"crossref","unstructured":"R.\u00a0L. Mattson J. Gecsei D. Slutz and I.\u00a0L. Traiger. 1970. Evaluation techniques for storage hierarchies. IBM System Journal 9 2 (1970) 78\u2013117.","DOI":"10.1147\/sj.92.0078"},{"key":"e_1_3_3_1_10_2","volume-title":"Nsight Compute CLI User Guide","author":"Corporation NVIDIA","year":"2025","unstructured":"NVIDIA Corporation. 2025. Nsight Compute CLI User Guide. NVIDIA Corporation. https:\/\/docs.nvidia.com\/nsight-compute\/NsightComputeCli\/index.html Version 2025.4.1."},{"key":"e_1_3_3_1_11_2","volume-title":"Parallel Thread Execution ISA Version 9.1","author":"Corporation NVIDIA","year":"2026","unstructured":"NVIDIA Corporation. 2026. Parallel Thread Execution ISA Version 9.1. https:\/\/docs.nvidia.com\/cuda\/parallel-thread-execution\/index.html"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2012.16"},{"key":"e_1_3_3_1_13_2","volume-title":"2025 IEEE Hot Chips 37 Symposium (HCS)","author":"Skende Andi","year":"2025","unstructured":"Andi Skende. 2025. NVIDIA GB10 SoC: AI Supercomputer On Your Desk. In 2025 IEEE Hot Chips 37 Symposium (HCS). https:\/\/hc2025.hotchips.org\/assets\/program\/conference\/day2\/21_nvidia_skende_final.pdf"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3695794.3695806"},{"key":"e_1_3_3_1_15_2","volume-title":"Advances in Neural Information Processing Systems (NIPS)","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan\u00a0N. Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is All You Need. In Advances in Neural Information Processing Systems (NIPS) , Vol.\u00a030. https:\/\/arxiv.org\/abs\/1706.03762"}],"event":{"name":"GPGPU '26: Proceedings of the 18th Workshop on General Purpose Processing Using GPU","location":"Pittsburgh PA USA","acronym":"GPGPU '26"},"container-title":["Proceedings of the 18th Workshop on General Purpose Processing Using GPU"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3818671.3818672","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3818671.3818672","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T14:11:36Z","timestamp":1785507096000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3818671.3818672"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,22]]},"references-count":14,"alternative-id":["10.1145\/3818671.3818672","10.1145\/3818671"],"URL":"https:\/\/doi.org\/10.1145\/3818671.3818672","relation":{},"subject":[],"published":{"date-parts":[[2026,3,22]]},"assertion":[{"value":"2026-07-31","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}