{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T03:47:56Z","timestamp":1769658476382,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":102,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,1,28]]},"DOI":"10.1145\/3774934.3786456","type":"proceedings-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T15:25:57Z","timestamp":1769613957000},"page":"687-701","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Characterizing Matrix Multiplication Units across General Parallel Patterns in Scientific Computing"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-6387-8116","authenticated-orcid":false,"given":"Yuechen","family":"Lu","sequence":"first","affiliation":[{"name":"China University of Petroleum-Beijing, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7504-4758","authenticated-orcid":false,"given":"Hongwei","family":"Zeng","sequence":"additional","affiliation":[{"name":"China University of Petroleum-Beijing, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4564-2093","authenticated-orcid":false,"given":"Marc","family":"Casas","sequence":"additional","affiliation":[{"name":"Barcelona Supercomputing Center, Barcelona, Spain"},{"name":"Universitat Polit\u00e8cnica de Catalunya, Barcelona, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2150-5759","authenticated-orcid":false,"given":"Weifeng","family":"Liu","sequence":"additional","affiliation":[{"name":"China University of Petroleum-Beijing, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,1,28]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"2024. The top500 list.. https:\/\/top500.org\/"},{"key":"e_1_3_2_2_2_1","unstructured":"Krste Asanovic Ras Bodik Bryan Catanzaro Joseph Gebis Parry Husbands Kurt Keutzer David Patterson William Plishker John Shalf and Samuel Webb Williams. 2006. The landscape of parallel computing research: A view from berkeley. https:\/\/escholarship.org\/uc\/item\/1z50m2xt"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1562764.1562783"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","unstructured":"D. H. Bailey E. Barszcz J. T. Barton D. S. Browning R. L. Carter L. Dagum R. A. Fatoohi P. O. Frederickson T. A. Lasinski R. S. Schreiber H. D. Simon V. Venkatakrishnan and S. K. Weeratunga. 1991. The NAS parallel benchmarks\u2014summary and preliminary results. In SC \u201991. https:\/\/doi.org\/10.1145\/125826.125925 10.1145\/125826.125925","DOI":"10.1145\/125826.125925"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","unstructured":"N. Bell and M. Garland. 2009. Implementing sparse matrix-vector multiplication on throughput-oriented processors. In SC \u201909. https:\/\/doi.org\/10.1145\/1654059.1654078 10.1145\/1654059.1654078","DOI":"10.1145\/1654059.1654078"},{"key":"e_1_3_2_2_6_1","unstructured":"Jay P Boris. 1970. Relativistic plasma simulation-optimization of a hybrid code. In CNSP \u201970."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","unstructured":"John Burgess. 2019. Rtx on\u2014the nvidia turing gpu. In HCS \u201919. https:\/\/doi.org\/10.1109\/HOTCHIPS.2019.8875651 10.1109\/HOTCHIPS.2019.8875651","DOI":"10.1109\/HOTCHIPS.2019.8875651"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","unstructured":"Jou-An Chen Hsin-Hsuan Sung Ruifeng Zhang Ang Li and Xipeng Shen. 2025. Accelerating GNNs on GPU Sparse Tensor Cores through N: M Sparsity-Oriented Graph Reordering. In PPoPP \u201925. https:\/\/doi.org\/10.1145\/3710848.3710881 10.1145\/3710848.3710881","DOI":"10.1145\/3710848.3710881"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","unstructured":"Tianshi Chen Zidong Du Ninghui Sun Jia Wang Chengyong Wu Yunji Chen and Olivier Temam. 2014. DianNao: a small-footprint high-throughput accelerator for ubiquitous machine-learning. In ASPLOS \u201914. https:\/\/doi.org\/10.1145\/2541940.2541967 10.1145\/2541940.2541967","DOI":"10.1145\/2541940.2541967"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","unstructured":"Yuetao Chen Kun Li Yuhao Wang Donglin Bai Lei Wang Lingxiao Ma Liang Yuan Yunquan Zhang Ting Cao and Mao Yang. 2024. ConvStencil: Transform stencil computation to matrix multiplication on tensor cores. In PPoPP \u201924. https:\/\/doi.org\/10.1145\/3627535.3638476 10.1145\/3627535.3638476","DOI":"10.1145\/3627535.3638476"},{"key":"e_1_3_2_2_12_1","unstructured":"Jack Choquette. 2017. Nvidia\u2019s volta gpu: Programmability and performance for gpu computing. In HCS \u201917."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","unstructured":"Jack Choquette. 2022. Nvidia hopper gpu: Scaling performance. In HCS \u201922. https:\/\/doi.org\/10.1109\/HCS55958.2022.9895592 10.1109\/HCS55958.2022.9895592","DOI":"10.1109\/HCS55958.2022.9895592"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","unstructured":"Jack Choquette and Wish Gandhi. 2020. Nvidia a100 gpu: Performance & innovation for gpu computing. In HCS \u201920. https:\/\/doi.org\/10.1109\/HCS49909.2020.9220622 10.1109\/HCS49909.2020.9220622","DOI":"10.1109\/HCS49909.2020.9220622"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2021.3061394"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1147\/rd.341.0004"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","unstructured":"Abdul Dakkak Cheng Li Jinjun Xiong Isaac Gelado and Wen-mei Hwu. 2019. Accelerating reduction and scan using tensor core units. In ICS \u201919. https:\/\/doi.org\/10.1145\/3330345.3331057 10.1145\/3330345.3331057","DOI":"10.1145\/3330345.3331057"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","unstructured":"Anthony Danalis Gabriel Marin Collin McCurdy Jeremy S Meredith Philip C Roth Kyle Spafford Vinod Tipparaju and Jeffrey S Vetter. 2010. The scalable heterogeneous computing (SHOC) benchmark suite. In GPGPU \u201910. https:\/\/doi.org\/10.1145\/1735688.1735702 10.1145\/1735688.1735702","DOI":"10.1145\/1735688.1735702"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2049662.2049663"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132710"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","unstructured":"Jens Domke Emil Vatai Aleksandr Drozd Peng ChenT Yosuke Oyama Lingqi Zhang Shweta Salaria Daichi Mukunoki Artur Podobas Mohamed WahibT and Satoshi Matsuoka. 2021. Matrix engines for high performance computing: A paragon of performance or grasping at straws? In IPDPS \u201921. https:\/\/doi.org\/10.1109\/IPDPS49936.2021.00114 10.1109\/IPDPS49936.2021.00114","DOI":"10.1109\/IPDPS49936.2021.00114"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.728"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/PACT52795.2021.00032"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476157"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3576933"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","unstructured":"Xixhou Feng Rong Ge and Kirk W Cameron. 2005. Power and energy profiling of scientific applications on distributed systems. In IPDPS \u201905. https:\/\/doi.org\/10.1109\/IPDPS.2005.346 10.1109\/IPDPS.2005.346","DOI":"10.1109\/IPDPS.2005.346"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2009.76"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","unstructured":"Haozhi Han Kun Li Wei Cui Donglin Bai Yiwei Zhang Liang Yuan Yifeng Chen Yunquan Zhang Ting Cao and Mao Yang. 2025. FlashFFTStencil: Bridging fast fourier transforms to memory-efficient stencil computations on tensor core units. In PPoPP \u201925. https:\/\/doi.org\/10.1145\/3710848.3710897 10.1145\/3710848.3710897","DOI":"10.1145\/3710848.3710897"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3093239"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","unstructured":"Guyue Huang Haoran Li Minghai Qin Fei Sun Yufei Ding and Yuan Xie. 2022. Shfl-BW: Accelerating deep neural network inference with tensor-core aware weight pruning. In DAC \u201922. https:\/\/doi.org\/10.1145\/3489517.3530588 10.1145\/3489517.3530588","DOI":"10.1145\/3489517.3530588"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2016.2582151"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071058"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","unstructured":"Zhuoran Ji and Cho-Li Wang. 2022. Efficient exact k-nearest neighbor graph construction for billion-scale datasets using GPUs with tensor cores. In ICS \u201922. https:\/\/doi.org\/10.1145\/3524059.3532368 10.1145\/3524059.3532368","DOI":"10.1145\/3524059.3532368"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","unstructured":"Hong Jiang. 2022. Intel\u2019s Ponte Vecchio GPU : Architecture Systems & Software. In HCS \u201922. https:\/\/doi.org\/10.1109\/HCS55958.2022.9895631 10.1109\/HCS55958.2022.9895631","DOI":"10.1109\/HCS55958.2022.9895631"},{"key":"e_1_3_2_2_35_1","unstructured":"Peng Jiang Lihan Hu and Shihui Song. 2022. Exposing and exploiting fine-grained block structures for fast and accurate sparse training. In NeurIPS \u201922. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/hash\/fa69e968b7319fd42524febd41475fb3-Abstract-Conference.html"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","unstructured":"Norman P. Jouppi Cliff Young Nishant Patil David Patterson Gaurav Agrawal Raminder Bajwa Sarah Bates Suresh Bhatia Nan Boden Al Borchers Rick Boyle Pierre-luc Cantin Clifford Chao Chris Clark Jeremy Coriell Mike Daley Matt Dau Jeffrey Dean Ben Gelb Tara Vazir Ghaemmaghami Rajendra Gottipati William Gulland Robert Hagmann C. Richard Ho Doug Hogberg John Hu Robert Hundt Dan Hurt Julian Ibarz Aaron Jaffey Alek Jaworski Alexander Kaplan Harshit Khaitan Daniel Killebrew Andy Koch Naveen Kumar Steve Lacy James Laudon James Law Diemthu Le Chris Leary Zhuyuan Liu Kyle Lucke Alan Lundin Gordon MacKean Adriana Maggiore Maire Mahony Kieran Miller Rahul Nagarajan Ravi Narayanaswami Ray Ni Kathy Nix Thomas Norrie Mark Omernick Narayana Penukonda Andy Phelps Jonathan Ross Matt Ross Amir Salek Emad Samadiani Chris Severn Gregory Sizikov Matthew Snelham Jed Souter Dan Steinberg Andy Swing Mercedes Tan Gregory Thorson Bo Tian Horia Toma Erick Tuttle Vijay Vasudevan Richard Walter Walter Wang Eric Wilcox and Doe Hyun Yoon. 2017. In-datacenter performance analysis of a tensor processing unit. In ISCA \u201917. https:\/\/doi.org\/10.1145\/3079856.3080246 10.1145\/3079856.3080246","DOI":"10.1145\/3079856.3080246"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","unstructured":"Jeremy Kepner Peter Aaltonen David Bader Aydin Bulu\u00e7 Franz Franchetti John Gilbert Dylan Hutchison Manoj Kumar Andrew Lumsdaine Henning Meyerhenke Scott McMillan Carl Yang John D. Owens Marcin Zalewski Timothy Mattson and Jose Moreira. 2016. Mathematical foundations of the GraphBLAS. In HPEC \u201916. https:\/\/doi.org\/10.1109\/HPEC.2016.7761646 10.1109\/HPEC.2016.7761646","DOI":"10.1109\/HPEC.2016.7761646"},{"key":"e_1_3_2_2_38_1","volume-title":"Mathematical methods in large-scale computing units. The Annals of","author":"Lehmer D.H.","year":"1951","unstructured":"D.H. Lehmer. 1951. Mathematical methods in large-scale computing units. The Annals of\u2019 the Computation Laboratory of Harvard University, 26 (1951)."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2024.3522776"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3045828"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","unstructured":"Binrui Li Shenggan Cheng and James Lin. 2021. tcfft: A fast half-precision fft library for nvidia tensor cores. In CLUSTER \u201921. https:\/\/doi.org\/10.1109\/Cluster48925.2021.00035 10.1109\/Cluster48925.2021.00035","DOI":"10.1109\/Cluster48925.2021.00035"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","unstructured":"Guangli Li Jingling Xue Lei Liu Xueying Wang Xiu Ma Xiao Dong Jiansong Li and Xiaobing Feng. 2021. Unleashing the Low-Precision Computation Potential of Tensor Cores on GPUs. In CGO \u201921. https:\/\/doi.org\/10.1109\/CGO51591.2021.9370335 10.1109\/CGO51591.2021.9370335","DOI":"10.1109\/CGO51591.2021.9370335"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","unstructured":"Qi Li Kun Li Haozhi Han Liang Yuan Junshi Chen Yunquan Zhang Yifeng Chen Hong An Ting Cao and Mao Yang. 2025. SparStencil: Retargeting Sparse Tensor Cores to Scientific Stencil Computations via Structured Sparsity Transformation. In SC \u201925. https:\/\/doi.org\/10.1145\/3712285.3759820 10.1145\/3712285.3759820","DOI":"10.1145\/3712285.3759820"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","unstructured":"Shigang Li Kazuki Osawa and Torsten Hoefler. 2022. Efficient quantized sparse matrix operations on tensor cores. In SC \u201922. https:\/\/doi.org\/10.1109\/SC41404.2022.00042 10.1109\/SC41404.2022.00042","DOI":"10.1109\/SC41404.2022.00042"},{"key":"e_1_3_2_2_45_1","unstructured":"Haocheng Lian Qiyue Zhang Xinran Zhao Meichen Dong Yijie Nie Zhengyi Zhao Junzhong Shen Wei Guo Chun Huang Bingcai Sui and Weifeng Liu. 2026. Uni-STC: Unified Sparse Tensor Core. In HPCA \u201926."},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD57390.2023.10323775"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","unstructured":"Weifeng Liu and Brian Vinter. 2015. CSR5: An efficient storage format for cross-platform sparse matrix-vector multiplication. In ICS \u201915. https:\/\/doi.org\/10.1145\/2751205.2751209 10.1145\/2751205.2751209","DOI":"10.1145\/2751205.2751209"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","unstructured":"Xiaoyan Liu Yi Liu Hailong Yang Jianjin Liao Mingzhen Li Zhongzhi Luan and Depei Qian. 2022. Toward accelerated stencil computation by adapting tensor core unit on gpu. In ICS \u201922. https:\/\/doi.org\/10.1145\/3524059.3532392 10.1145\/3524059.3532392","DOI":"10.1145\/3524059.3532392"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","unstructured":"Yiwei Liu and Olin Johnson. 1988. Optimal scheduling policies for mixed scalar-vector multiprocessor supercomputers. In SC \u201988. https:\/\/doi.org\/10.1109\/SUPERC.1988.44661 10.1109\/SUPERC.1988.44661","DOI":"10.1109\/SUPERC.1988.44661"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","unstructured":"Andr\u00e9 Lopes Frederico Pratas Leonel Sousa and Aleksandar Ilic. 2017. Exploring GPU performance power and energy-efficiency bounds with Cache-aware Roofline Modeling. In ISPASS \u201917. https:\/\/doi.org\/10.1109\/ISPASS.2017.7975297 10.1109\/ISPASS.2017.7975297","DOI":"10.1109\/ISPASS.2017.7975297"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607051"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","unstructured":"Yuechen Lu Hongwei Zeng Marc Casas and Weifeng Liu. 2025. Cubie. https:\/\/doi.org\/10.5281\/zenodo.17725527 10.5281\/zenodo.17725527","DOI":"10.5281\/zenodo.17725527"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00058"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2018.00091"},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2020.01.044"},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","unstructured":"Timothy G Mattson Carl Yang Scott McMillan Aydin Bulu\u00e7 and Jos\u00e9 E Moreira. 2017. GraphBLAS C API: Ideas for future versions of the specification. In HPEC \u201917. https:\/\/doi.org\/10.1109\/HPEC.2017.8091095 10.1109\/HPEC.2017.8091095","DOI":"10.1109\/HPEC.2017.8091095"},{"key":"e_1_3_2_2_57_1","unstructured":"Vishal Mehta. 2019. Particle in Cell using Tensor Core. https:\/\/github.com\/vishalmehta1991\/pictc"},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42614.2022.9731107"},{"key":"e_1_3_2_2_59_1","doi-asserted-by":"publisher","unstructured":"Yuyao Niu and Marc Casas. 2025. BerryBees: Breadth first search by bit-tensor-cores. In PPoPP \u201925. https:\/\/doi.org\/10.1145\/3710848.3710859 10.1145\/3710848.3710859","DOI":"10.1145\/3710848.3710859"},{"key":"e_1_3_2_2_60_1","unstructured":"NVIDIA. 2020. NVIDIA A100 Tensor Core GPU Architecture. https:\/\/images.nvidia.com\/aem-dam\/en-zz\/Solutions\/data-center\/nvidia-ampere-architecture-whitepaper.pdf"},{"key":"e_1_3_2_2_61_1","unstructured":"NVIDIA. 2023. NVIDIA H100 Tensor Core GPU Architecture. https:\/\/resources.nvidia.com\/en-us-hopper-architecture\/nvidia-h100-tensor-c"},{"key":"e_1_3_2_2_62_1","unstructured":"NVIDIA. 2024. NVIDIA Blackwell Architecture Technical Brief. https:\/\/resources.nvidia.com\/en-us-blackwell-architecture"},{"key":"e_1_3_2_2_63_1","unstructured":"NVIDIA. 2024. NVIDIA GH200 Grace Hopper Superchip Architecture. https:\/\/nvdam.widen.net\/s\/c9lts6msjj\/nvidia-grace-hopper-superchip-architecture-whitepaper"},{"key":"e_1_3_2_2_64_1","unstructured":"NVIDIA. 2025. The API reference for CUB. https:\/\/docs.nvidia.com\/cuda\/cub\/"},{"key":"e_1_3_2_2_65_1","unstructured":"NVIDIA. 2025. The API Reference guide for cuBLAS the CUDA Basic Linear Algebra Subroutine library.. https:\/\/docs.nvidia.com\/cuda\/cublas\/"},{"key":"e_1_3_2_2_66_1","unstructured":"NVIDIA. 2025. The API reference guide for cuFFT the CUDA Fast Fourier Transform library.. https:\/\/docs.nvidia.com\/cuda\/cufft\/"},{"key":"e_1_3_2_2_67_1","unstructured":"NVIDIA. 2025. The API reference guide for cuSPARSE the CUDA sparse matrix library.. https:\/\/docs.nvidia.com\/cuda\/cusparse\/"},{"key":"e_1_3_2_2_68_1","unstructured":"NVIDIA. 2025. CUDA Samples. https:\/\/docs.nvidia.com\/cuda\/cuda-samples\/"},{"key":"e_1_3_2_2_69_1","unstructured":"NVIDIA. 2025. CUDA Templates for Linear Algebra Subroutines and Solvers. https:\/\/nvidia.github.io\/cutlass\/"},{"key":"e_1_3_2_2_70_1","unstructured":"NVIDIA. 2025. Nsight Compute.. https:\/\/docs.nvidia.com\/nsight-compute\/"},{"key":"e_1_3_2_2_71_1","unstructured":"NVIDIA. 2025. NVIDIA Management Library.. https:\/\/developer.nvidia.com\/management-library-nvml"},{"key":"e_1_3_2_2_72_1","unstructured":"NVIDIA. 2025. NVIDIA Parallel Thread Execution ISA. https:\/\/docs.nvidia.com\/cuda\/parallel-thread-execution\/"},{"key":"e_1_3_2_2_73_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00060"},{"key":"e_1_3_2_2_74_1","doi-asserted-by":"publisher","DOI":"10.1177\/10943420241239588"},{"key":"e_1_3_2_2_75_1","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","author":"Pedregosa Fabian","year":"2011","unstructured":"Fabian Pedregosa, Ga\u00ebl Varoquaux, Alexandre Gramfort, Vincent Michel, Bertrand Thirion, Olivier Grisel, Mathieu Blondel, Peter Prettenhofer, Ron Weiss, Vincent Dubourg, Jake Vanderplas, Alexandre Passos, David Cournapeau, Matthieu Brucher, Matthieu Perrot, and \u00c9douard Duchesnay. 2011. Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research, 12, 85 (2011), https:\/\/www.jmlr.org\/papers\/volume12\/pedregosa11a\/pedregosa11a.pdf","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_2_76_1","doi-asserted-by":"publisher","unstructured":"Louis Pisha and \u0141 ukasz Ligowski. 2021. Accelerating non-power-of-2 size Fourier transforms with GPU tensor cores. In IPDPS \u201921. https:\/\/doi.org\/10.1109\/IPDPS49936.2021.00059 10.1109\/IPDPS49936.2021.00059","DOI":"10.1109\/IPDPS49936.2021.00059"},{"key":"e_1_3_2_2_77_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00015"},{"key":"e_1_3_2_2_78_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS61541.2024.00022"},{"key":"e_1_3_2_2_79_1","doi-asserted-by":"publisher","unstructured":"Gabin Schieffer Jacob Wahlgren Jie Ren Jennifer Faj and Ivy Peng. 2024. Harnessing integrated cpu-gpu system memory for hpc: a first look into grace hopper. In ICPP \u201924. https:\/\/doi.org\/10.1145\/3673038.3673110 10.1145\/3673038.3673110","DOI":"10.1145\/3673038.3673110"},{"key":"e_1_3_2_2_80_1","doi-asserted-by":"publisher","DOI":"10.1145\/3710848.3710858"},{"key":"e_1_3_2_2_81_1","doi-asserted-by":"publisher","unstructured":"Andrew Siegel Erik W Draeger Jack Deslippe Thomas Evans Marianne M Francois Timothy C Germann Daniel F Martin and William Hart. 2021. Map applications to target exascale architecture with machine-specific performance analysis including challenges and projections. Oak Ridge National Laboratory (ORNL) Oak Ridge TN (United States). https:\/\/doi.org\/10.2172\/1838979 10.2172\/1838979","DOI":"10.2172\/1838979"},{"key":"e_1_3_2_2_82_1","doi-asserted-by":"publisher","unstructured":"Prasoon Sinha Akhil Guliani Rutwik Jain Brandon Tran Matthew D Sinclair and Shivaram Venkataraman. 2022. Not all gpus are created equal: characterizing variability in large-scale accelerator-rich systems. In SC \u201922. https:\/\/doi.org\/10.1109\/SC41404.2022.00070 10.1109\/SC41404.2022.00070","DOI":"10.1109\/SC41404.2022.00070"},{"key":"e_1_3_2_2_83_1","doi-asserted-by":"publisher","unstructured":"Alan Smith and Norman James. 2022. AMD Instinct\u2122 MI200 Series Accelerator and Node Architectures. In HCS \u201922. https:\/\/doi.org\/10.1109\/HCS55958.2022.9895477 10.1109\/HCS55958.2022.9895477","DOI":"10.1109\/HCS55958.2022.9895477"},{"key":"e_1_3_2_2_84_1","doi-asserted-by":"publisher","unstructured":"Zhuoran Song Jianfei Wang Tianjian Li Li Jiang Jing Ke Xiaoyao Liang and Naifeng Jing. 2020. GPNPU: Enabling Efficient Hardware-Based Direct Convolution with Multi-Precision Support in GPU Tensor Cores. In DAC \u201920. https:\/\/doi.org\/10.1109\/DAC18072.2020.9218566 10.1109\/DAC18072.2020.9218566","DOI":"10.1109\/DAC18072.2020.9218566"},{"key":"e_1_3_2_2_85_1","first-page":"7","article-title":"Parboil: A revised benchmark suite for scientific and commercial throughput computing","volume":"127","author":"Stratton John A","year":"2012","unstructured":"John A Stratton, Christopher Rodrigues, I-Jui Sung, Nady Obeid, Li-Wen Chang, Nasser Anssari, Geng Daniel Liu, and Wen-mei W Hwu. 2012. Parboil: A revised benchmark suite for scientific and commercial throughput computing. Center for Reliable and High-Performance Computing, 127, 7.2 (2012), http:\/\/impact.crhc.illinois.edu\/Shared\/Report\/impact-12-01.parboil.pdf","journal-title":"Center for Reliable and High-Performance Computing"},{"key":"e_1_3_2_2_86_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3217824"},{"key":"e_1_3_2_2_87_1","doi-asserted-by":"publisher","unstructured":"Ajay Tirumala and Raymond Wong. 2024. Nvidia blackwell platform: Advancing generative ai and accelerated computing. In HCS \u201924. https:\/\/doi.org\/10.1109\/HCS61935.2024.10665247 10.1109\/HCS61935.2024.10665247","DOI":"10.1109\/HCS61935.2024.10665247"},{"key":"e_1_3_2_2_88_1","doi-asserted-by":"publisher","unstructured":"Hansheng Wang Zhekai Duan Zitian Zhao Siqi Wu Saiqi Zheng Qiao Li Xu Jiang and Shaoshuai Zhang. 2025. Improving Tridiagonalization Performance on GPU Architectures. In PPoPP \u201925. https:\/\/doi.org\/10.1145\/3710848.3710894 10.1145\/3710848.3710894","DOI":"10.1145\/3710848.3710894"},{"key":"e_1_3_2_2_89_1","doi-asserted-by":"publisher","DOI":"10.1145\/2851141.2851145"},{"key":"e_1_3_2_2_90_1","doi-asserted-by":"publisher","unstructured":"Yuke Wang Boyuan Feng and Yufei Ding. 2022. QGTC: accelerating quantized graph neural networks via GPU tensor core. In PPoPP \u201922. https:\/\/doi.org\/10.1145\/3503221.3508408 10.1145\/3503221.3508408","DOI":"10.1145\/3503221.3508408"},{"key":"e_1_3_2_2_91_1","unstructured":"Yuke Wang Boyuan Feng Zheng Wang Guyue Huang and Yufei Ding. 2023. TC-GNN: Bridging sparse GNN computation and dense tensor cores on GPUs. In USENIX ATC \u201923. https:\/\/www.usenix.org\/conference\/atc23\/presentation\/wang-yuke"},{"key":"e_1_3_2_2_92_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2024.3365941"},{"key":"e_1_3_2_2_93_1","doi-asserted-by":"publisher","unstructured":"Yang Wang Chen Zhang Zhiqiang Xie Cong Guo Yunxin Liu and Jingwen Leng. 2021. Dual-side sparse tensor core. In ISCA \u201921. https:\/\/doi.org\/10.1109\/ISCA52012.2021.00088 10.1109\/ISCA52012.2021.00088","DOI":"10.1109\/ISCA52012.2021.00088"},{"key":"e_1_3_2_2_94_1","unstructured":"Martin Weidmann. 2021. Introducing the Scalable Matrix Extension for the Armv9-A Architecture.. https:\/\/community.arm.com\/arm-community-blogs\/b\/architectures-and-processors-blog\/posts\/scalable-matrix-extension-armv9-a-architecture"},{"key":"e_1_3_2_2_95_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO51591.2021.9370330"},{"key":"e_1_3_2_2_96_1","doi-asserted-by":"publisher","unstructured":"Shengen Yan Chao Li Yunquan Zhang and Huiyang Zhou. 2014. yaSpMV: Yet Another SpMV Framework on GPUs. In PPoPP \u201914. https:\/\/doi.org\/10.1145\/2555243.2555255 10.1145\/2555243.2555255","DOI":"10.1145\/2555243.2555255"},{"key":"e_1_3_2_2_97_1","doi-asserted-by":"publisher","unstructured":"Zihao Ye Ruihang Lai Junru Shao Tianqi Chen and Luis Ceze. 2023. SparseTIR: Composable Abstractions for Sparse Compilation in Deep Learning. In ASPLOS \u201923. https:\/\/doi.org\/10.1145\/3582016.3582047 10.1145\/3582016.3582047","DOI":"10.1145\/3582016.3582047"},{"key":"e_1_3_2_2_98_1","doi-asserted-by":"publisher","unstructured":"Xin You Hailong Yang Zhonghui Jiang Zhongzhi Luan and Depei Qian. 2021. DRStencil: Exploiting data reuse within low-order stencil on GPU. In HPCC \u201921. https:\/\/doi.org\/10.1109\/HPCC-DSS-SmartCity-DependSys53884.2021.00036 10.1109\/HPCC-DSS-SmartCity-DependSys53884.2021.00036","DOI":"10.1109\/HPCC-DSS-SmartCity-DependSys53884.2021.00036"},{"key":"e_1_3_2_2_99_1","doi-asserted-by":"publisher","DOI":"10.1145\/3673038.3673108"},{"key":"e_1_3_2_2_100_1","doi-asserted-by":"publisher","unstructured":"Ruge Zhang Haipeng Jia Yunquan Zhang Baicheng Yan Penghao Ma Long Wang and Wenxuan Zhao. 2024. OpenFFT-SME: An Efficient Outer Product Pattern FFT Library on ARM SME CPUs. In IPDPS \u201924. https:\/\/doi.org\/10.1109\/IPDPS57955.2024.00088 10.1109\/IPDPS57955.2024.00088","DOI":"10.1109\/IPDPS57955.2024.00088"},{"key":"e_1_3_2_2_101_1","doi-asserted-by":"publisher","unstructured":"Shaoshuai Zhang Ruchi Shah Hiroyuki Ootomo Rio Yokota and Panruo Wu. 2023. Fast symmetric eigenvalue decomposition via wy representation on tensor core. In PPoPP \u201923. https:\/\/doi.org\/10.1145\/3572848.3577516 10.1145\/3572848.3577516","DOI":"10.1145\/3572848.3577516"},{"key":"e_1_3_2_2_102_1","doi-asserted-by":"publisher","unstructured":"Yiwei Zhang Kun Li Liang Yuan Jiawen Cheng Yunquan Zhang Ting Cao and Mao Yang. 2024. LoRAStencil: Low-Rank Adaptation of Stencil Computation on Tensor Cores. In SC \u201924. https:\/\/doi.org\/10.1109\/SC41406.2024.00059 10.1109\/SC41406.2024.00059","DOI":"10.1109\/SC41406.2024.00059"}],"event":{"name":"PPoPP '26: 31st ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","location":"Sydney NSW Australia","acronym":"PPoPP '26","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","SIGPLAN ACM Special Interest Group on Programming Languages"]},"container-title":["Proceedings of the 31st ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3774934.3786456","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T15:26:33Z","timestamp":1769613993000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774934.3786456"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,28]]},"references-count":102,"alternative-id":["10.1145\/3774934.3786456","10.1145\/3774934"],"URL":"https:\/\/doi.org\/10.1145\/3774934.3786456","relation":{},"subject":[],"published":{"date-parts":[[2026,1,28]]},"assertion":[{"value":"2026-01-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}