{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T06:45:12Z","timestamp":1785912312560,"version":"3.56.0"},"reference-count":64,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NSF","award":["CCF-2452081,CAREER-2341039,CAREER-2047521"],"award-info":[{"award-number":["CCF-2452081,CAREER-2341039,CAREER-2047521"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/isca66397.2026.00094","type":"proceedings-article","created":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T19:16:32Z","timestamp":1785870992000},"page":"1226-1240","source":"Crossref","is-referenced-by-count":0,"title":["RoCC: Harnessing Raster Operations Pipeline for Efficient Tensor Collective Communication"],"prefix":"10.1109","author":[{"given":"Yuan","family":"Feng","sequence":"first","affiliation":[{"name":"University of California, Merced"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Wong","sequence":"additional","affiliation":[{"name":"University of California, Riverside"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hyeran","family":"Jeon","sequence":"additional","affiliation":[{"name":"University of California, Merced"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Blackwell GPU Architecture"},{"key":"ref2","volume-title":"Arm multimedia ip: Accelerating ai","year":"2025"},{"key":"ref3","article-title":"Qwen technical report","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/RTAS58335.2023.00012"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00079"},{"key":"ref6","volume-title":"Flux: Fast software-based communication overlap on gpus through kernel fusion","author":"Chang","year":"2024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2020373.2020375"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071117"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2021.3113475"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1189"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3695053.3731011"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00065"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2540708.2540743"},{"key":"ref14","volume-title":"Tokenweave: Efficient computecommunication overlap for distributed 1lm inference","author":"Gond","year":"2025"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00080"},{"key":"ref16","article-title":"Flashoverlap: A lightweight design for efficiently overlapping communication and computation","author":"Hong","year":"2025","journal-title":"arXiv preprint"},{"key":"ref17","volume-title":"NVDIA Hopper GPU architecture revealed. 4nm die & 18432 shaders","author":"Olsan"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00106"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00070"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783717"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/2499368.2451118"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00047"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2018.00038"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00073"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2016.7446062"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/isca45697.2020.00085"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-04888-3_12"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00027"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2928289"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071054"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2008.31"},{"key":"ref32","article-title":"Deepseek-v3 technical report","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","volume-title":"Symbolic Tensor Graph (STG) Generator","author":"Man","year":"2025"},{"key":"ref34","volume-title":"NVIDIA Hopper Architecture In-Depth","author":"Andersch"},{"key":"ref35","first-page":"28","article-title":"Cacti 6.0: A tool to model large caches","volume":"27","author":"Muralimanohar","year":"2009","journal-title":"HP laboratories"},{"key":"ref36","article-title":"NVIDIA Turing Architecture Whitepaper","year":"2018","journal-title":"NVIDIA Corporation, White Paper"},{"key":"ref37","year":"2020","journal-title":"NVIDIA A100 Tensor Core GPU"},{"key":"ref38","article-title":"Nvidia ampere ga102 gpu architecture: Second-generation rtx","year":"2021","journal-title":"NVIDIA Corporation, Whitepaper"},{"key":"ref39","article-title":"NVIDIA A100 Tensor Core GPU Architecture","volume-title":"Tech. Rep.","year":"2022"},{"key":"ref40","year":"2025","journal-title":"NCCL: Optimized primitives for collective multi-GPU communication"},{"key":"ref41","year":"2025","journal-title":"Nsight Compute Documentation, NVIDIA Corporation"},{"key":"ref42","volume-title":"Atomic memory operators in a parallel processor","author":"Nyland","year":"2006"},{"key":"ref43","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1145\/3307650.3322222","article-title":"Linebacker: Preserving victim cache lines in idle register files of gpus","volume-title":"Proceedings of the 46th International Symposium on Computer Architecture","author":"Oh","year":"2019"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640410"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00094"},{"key":"ref46","volume-title":"Tensor Parallelism"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3695053.3731025"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00049"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS48437.2020.00018"},{"key":"ref50","volume-title":"Cache-based control of atomic operations in conjunction with an external alu block","author":"Roberts","year":"2008"},{"key":"ref51","article-title":"Chakra: Advancing performance benchmarking and co-design using standardized execution traces","author":"Sridharan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref52","first-page":"197","article-title":"Mgpusim: Enabling multi-gpu performance modeling and optimization","volume-title":"2019 ACM\/IEEE 46th Annual International Symposium on Computer Architecture (ISCA)","author":"Sun","year":"2019"},{"key":"ref53","year":"2025","journal-title":"GPU Specs Database"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/HCS61935.2024.10665247"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD56317.2022.00062"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3519941.3535064"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3332466.3374520"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001201"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589078"},{"key":"ref60","volume-title":"Comet: Fine-grained computation-communication overlapping for mixture-of-experts","author":"Zhang","year":"2025"},{"key":"ref61","article-title":"Comet: Fine-grained computationcommunication overlapping for mixture-of-experts","author":"Zhang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3676641.3716248"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/micro50266.2020.00082"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575745"}],"event":{"name":"2026 ACM\/IEEE 53rd Annual International Symposium on Computer Architecture (ISCA)","location":"Raleigh, NC, USA","start":{"date-parts":[[2026,6,27]]},"end":{"date-parts":[[2026,7,1]]}},"container-title":["2026 ACM\/IEEE 53rd Annual International Symposium on Computer Architecture (ISCA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11617393\/11617394\/11617725.pdf?arnumber=11617725","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T05:52:04Z","timestamp":1785909124000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11617725\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/isca66397.2026.00094","relation":{},"subject":[],"published":{"date-parts":[[2026,6]]}}}