{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T12:33:33Z","timestamp":1776774813483,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Advanced Scientific Computing Research","award":["DE-AC02-06CH11357"],"award-info":[{"award-number":["DE-AC02-06CH11357"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1145\/3725798.3725803","type":"proceedings-article","created":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T10:40:50Z","timestamp":1747132850000},"page":"28-34","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Can Tensor Cores Benefit Memory-Bound Kernels? (NO!)"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2452-1551","authenticated-orcid":false,"given":"Lingqi","family":"Zhang","sequence":"first","affiliation":[{"name":"RIKEN Center for Computational Science, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5092-3987","authenticated-orcid":false,"given":"Jiajun","family":"Huang","sequence":"additional","affiliation":[{"name":"University of California, Riverside, Riverside, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9935-5674","authenticated-orcid":false,"given":"Sheng","family":"Di","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory, Lemont, Illinois, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1910-8532","authenticated-orcid":false,"given":"Satoshi","family":"Matsuoka","sequence":"additional","affiliation":[{"name":"RIKEN Center for Computational Science, Kobe, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7165-2095","authenticated-orcid":false,"given":"Mohamed","family":"Wahib","sequence":"additional","affiliation":[{"name":"RIKEN Center for Computational Science, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,5,13]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC55821.2022.9926299"},{"key":"e_1_3_3_2_3_2","unstructured":"Hartwig Anzt Stanimire Tomov and Jack Dongarra. 2014. Implementing a Sparse Matrix Vector Product for the SELL-C\/SELL-C-\u03c3 formats on NVIDIA GPUs. University of Tennessee Tech. Rep. ut-eecs-14-727 (2014)."},{"key":"e_1_3_3_2_4_2","volume-title":"PMBS24: The 15th International Workshop on Performance Modeling, Benchmarking, and Simulation of High-Performance Computer Systems","author":"Austin Brian","year":"2024","unstructured":"Brian Austin, Dhruva Kulkarni, Brandon Cook, Samuel Williams, and Nicholas\u00a0J Wright. 2024. System-Wide Roofline Profiling-a Case Study on NERSC\u2019s Perlmutter Supercomputer. In PMBS24: The 15th International Workshop on Performance Modeling, Benchmarking, and Simulation of High-Performance Computer Systems."},{"key":"e_1_3_3_2_5_2","unstructured":"Somashekaracharya\u00a0G. Bhaskaracharya Julien Demouth and Vinod Grover. 2020. Automatic Kernel Generation for Volta Tensor Cores. arxiv:https:\/\/arXiv.org\/abs\/2006.12645\u00a0[cs.PL] https:\/\/arxiv.org\/abs\/2006.12645"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3627535.3638476"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","unstructured":"Jack Choquette Olivier Giroux and Denis Foley. 2018. Volta: Performance and Programmability. IEEE Micro 38 2 (2018) 42\u201352. 10.1109\/MM.2018.022071134","DOI":"10.1109\/MM.2018.022071134"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"crossref","unstructured":"Timothy\u00a0A Davis and Yifan Hu. 2011. The University of Florida sparse matrix collection. ACM Transactions on Mathematical Software (TOMS) 38 1 (2011) 1\u201325.","DOI":"10.1145\/2049662.2049663"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS49936.2021.00114"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/PACT52795.2021.00032"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651378"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3168824"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00050"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","unstructured":"Moritz Kreutzer Georg Hager Gerhard Wellein Holger Fehske and Alan\u00a0R. Bishop. 2014. A Unified Sparse Matrix Data Format for Efficient General Sparse Matrix-Vector Multiplication on Modern Processors with Wide SIMD Units. SIAM Journal on Scientific Computing 36 5 (2014) C401\u2013C423. 10.1137\/130930352 arXiv:10.1137\/130930352","DOI":"10.1137\/130930352"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","unstructured":"Victor\u00a0W. Lee Changkyu Kim Jatin Chhugani Michael Deisher Daehyun Kim Anthony\u00a0D. Nguyen Nadathur Satish Mikhail Smelyanskiy Srinivas Chennupaty Per Hammarlund Ronak Singhal and Pradeep Dubey. 2010. Debunking the 100X GPU vs. CPU myth: an evaluation of throughput computing on CPU and GPU. SIGARCH Comput. Archit. News 38 3 (June 2010) 451\u2013460. 10.1145\/1816038.1816021","DOI":"10.1145\/1816038.1816021"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607051"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00058"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS57955.2024.00064"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3368826.3377904"},{"key":"e_1_3_3_2_20_2","volume-title":"STREAM: Sustainable Memory Bandwidth in High Performance Computers","author":"McCalpin John\u00a0D.","year":"1991","unstructured":"John\u00a0D. McCalpin. 1991-2007. STREAM: Sustainable Memory Bandwidth in High Performance Computers. Technical Report. University of Virginia, Charlottesville, Virginia. http:\/\/www.cs.virginia.edu\/stream\/ A continually updated technical report. http:\/\/www.cs.virginia.edu\/stream\/."},{"key":"e_1_3_3_2_21_2","unstructured":"John\u00a0D McCalpin et\u00a0al. 1995. Memory bandwidth and machine balance in current high performance computers. IEEE computer society technical committee on computer architecture (TCCA) newsletter 2 19-25 (1995)."},{"key":"e_1_3_3_2_22_2","volume-title":"GPU Technology Conference","volume":"12","author":"Naumov Maxim","year":"2010","unstructured":"Maxim Naumov, L Chien, Philippe Vandermersch, and Ujval Kapasi. 2010. Cusparse library. In GPU Technology Conference, Vol.\u00a012."},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"crossref","unstructured":"Crist\u00f3bal\u00a0A Navarro Roberto Carrasco Ricardo\u00a0J Barrientos Javier\u00a0A Riquelme and Raimundo Vega. 2020. GPU tensor cores for fast arithmetic reductions. IEEE Transactions on Parallel and Distributed Systems 32 1 (2020) 72\u201384.","DOI":"10.1109\/TPDS.2020.3011893"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2014.6844463"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00060"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"crossref","unstructured":"Hiroyuki Ootomo Katsuhisa Ozaki and Rio Yokota. 2024. DGEMM on integer matrix multiplication unit. The International Journal of High Performance Computing Applications (2024) 10943420241239588.","DOI":"10.1177\/10943420241239588"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"crossref","unstructured":"Hiroyuki Ootomo and Rio Yokota. 2022. Recovering single precision accuracy from Tensor Cores while surpassing the FP32 theoretical peak performance. The International Journal of High Performance Computing Applications 36 4 (2022) 475\u2013491.","DOI":"10.1177\/10943420221090256"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS49936.2021.00059"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/2884045.2884047"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","unstructured":"Wei Sun Ang Li Tong Geng Sander Stuijk and Henk Corporaal. 2023. Dissecting Tensor Cores via Microbenchmarks: Latency Throughput and Numeric Behaviors. IEEE Transactions on Parallel and Distributed Systems 34 1 (2023) 246\u2013261. 10.1109\/TPDS.2022.3217824","DOI":"10.1109\/TPDS.2022.3217824"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"crossref","unstructured":"Samuel Williams Andrew Waterman and David Patterson. 2009. Roofline: an insightful visual performance model for multicore architectures. Commun. ACM 52 4 (2009) 65\u201376.","DOI":"10.1145\/1498765.1498785"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3650200.3656634"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"crossref","unstructured":"Charlene Yang Thorsten Kurth and Samuel Williams. 2020. Hierarchical Roofline analysis for GPUs: Accelerating performance optimization for the NERSC-9 Perlmutter system. Concurrency and Computation: Practice and Experience 32 20 (2020) e5547.","DOI":"10.1002\/cpe.5547"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3577193.3593705"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3577193.3593716"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00059"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356210"}],"event":{"name":"GPGPU 2025: 17th Workshop on General Purpose Processing Using GPU","location":"Las Vegas NV USA","acronym":"GPGPU 2025"},"container-title":["Proceedings of the 17th Workshop on General Purpose Processing Using GPU"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3725798.3725803","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3725798.3725803","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3725798.3725803","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:57:04Z","timestamp":1750298224000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3725798.3725803"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":36,"alternative-id":["10.1145\/3725798.3725803","10.1145\/3725798"],"URL":"https:\/\/doi.org\/10.1145\/3725798.3725803","relation":{},"subject":[],"published":{"date-parts":[[2025,3]]},"assertion":[{"value":"2025-05-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}