{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T07:14:02Z","timestamp":1772694842807,"version":"3.50.1"},"reference-count":96,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T00:00:00Z","timestamp":1769817600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T00:00:00Z","timestamp":1769817600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U23A20301,62372467,62202481"],"award-info":[{"award-number":["U23A20301,62372467,62202481"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1,31]]},"DOI":"10.1109\/hpca68181.2026.11408500","type":"proceedings-article","created":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T20:47:22Z","timestamp":1772657242000},"page":"1-18","source":"Crossref","is-referenced-by-count":0,"title":["Uni-STC: Unified Sparse Tensor Core"],"prefix":"10.1109","author":[{"given":"Haocheng","family":"Lian","sequence":"first","affiliation":[{"name":"China University of Petroleum-Beijing,Super Scientific Software Laboratory,Department of CST,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiyue","family":"Zhang","sequence":"additional","affiliation":[{"name":"China University of Petroleum-Beijing,Super Scientific Software Laboratory,Department of CST,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinran","family":"Zhao","sequence":"additional","affiliation":[{"name":"China University of Petroleum-Beijing,Super Scientific Software Laboratory,Department of CST,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meichen","family":"Dong","sequence":"additional","affiliation":[{"name":"China University of Petroleum-Beijing,Super Scientific Software Laboratory,Department of CST,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yijie","family":"Nie","sequence":"additional","affiliation":[{"name":"China University of Petroleum-Beijing,Super Scientific Software Laboratory,Department of CST,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengyi","family":"Zhao","sequence":"additional","affiliation":[{"name":"China University of Petroleum-Beijing,Super Scientific Software Laboratory,Department of CST,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junzhong","family":"Shen","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Guo","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chun","family":"Huang","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bingcai","family":"Sui","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weifeng","family":"Liu","sequence":"additional","affiliation":[{"name":"China University of Petroleum-Beijing,Super Scientific Software Laboratory,Department of CST,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1562764.1562783"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00034"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3085572"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/HCS52781.2021.9566865"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2011.73"},{"key":"ref6","article-title":"Avalanche: Optimizing cache utilization via matrix reordering for sparse matrix multiplication accelerator","author":"Byeon","year":"2025","journal-title":"ISCA"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00044"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3605573.3605611"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/HCS55958.2022.9895592"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2049662.2049663"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00090"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3614263"},{"key":"ref13","article-title":"Recg: Reramaccelerated sparse conjugate gradient","author":"Fan","year":"2024","journal-title":"DAC"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/DAC56929.2023.10247881"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3689031.3717481"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589040"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00091"},{"key":"ref18","article-title":"Dpacs: Hardware accelerated dynamic neural network pruning through algorithm-architecture codesign","author":"Gao","year":"2023","journal-title":"ASPLOS"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00081"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589054"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358291"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3614312"},{"key":"ref23","year":"2020","journal-title":"Deep learning matrix collection(dlmc)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00069"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001163"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527419"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358275"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00017"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3623775"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10070983"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00011"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071058"},{"key":"ref34","article-title":"Tilespmspv: A tiled algorithm for sparse matrix-sparse vector multiplication on gpus","author":"Ji","year":"2023","journal-title":"ICPP"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00010"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3140659.3080246"},{"key":"ref37","article-title":"Smash: Codesigning software compression and hardware-accelerated indexing for efficient sparse matrix operations","author":"Kanellopoulos","year":"2019","journal-title":"MICRO"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00047"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3623790"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527404"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00065"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER52292.2023.00025"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575706"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00075"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s10766-018-0604-8"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2014.47"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/2751205.2751209"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2015.06.010"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2015.04.004"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00049"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651381"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607051"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00058"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00069"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid57682.2023.00056"},{"key":"ref56","article-title":"Berrybees: Breadth first search by bit-tensorcores","author":"Niu","year":"2025","journal-title":"PPoPP"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS49936.2021.00016"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3503221.3508431"},{"key":"ref59","article-title":"Flexagon: A multi-dataflow sparse-sparse matrix multiplication accelerator for efficient dnn processing","author":"noz Mart\u00ednez","year":"2023","journal-title":"ASPLOS"},{"key":"ref60","article-title":"NVIDIA A100 Tensor Core GPU Architecture","volume-title":"Nvidia","year":"2020"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3582016.3582064"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICECS.2016.7841286"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00067"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080254"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00081"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00015"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10070977"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00068"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00073"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3614284"},{"key":"ref71","article-title":"Amd instinct ${}^{\\text {TM}}$ mi200 series accelerator and node architectures","author":"Smith","year":"2022","journal-title":"HCS"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530420"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00024"},{"key":"ref74","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00018"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1145\/3712285.3759895"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00093"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00088"},{"key":"ref79","volume-title":"Yosys open synthesis suite","author":"Wolf"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00096"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00055"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1145\/3330345.3330354"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3090328"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3623793"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575738"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322271"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00072"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1145\/3676536.3676773"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.23919\/DATE58400.2024.10546672"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071102"},{"key":"ref91","article-title":"Scalpel: Customizing dnn pruning to the underlying hardware parallelism","author":"Yu","year":"2017","journal-title":"ISCA"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/tc.2024.3475814"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446702"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00030"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651336"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358269"}],"event":{"name":"2026 IEEE International Symposium on High Performance Computer Architecture (HPCA)","location":"Sydney, Australia","start":{"date-parts":[[2026,1,31]]},"end":{"date-parts":[[2026,2,4]]}},"container-title":["2026 IEEE International Symposium on High Performance Computer Architecture (HPCA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11408404\/11408433\/11408500.pdf?arnumber=11408500","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T06:35:20Z","timestamp":1772692520000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11408500\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,31]]},"references-count":96,"URL":"https:\/\/doi.org\/10.1109\/hpca68181.2026.11408500","relation":{},"subject":[],"published":{"date-parts":[[2026,1,31]]}}}