{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T05:24:40Z","timestamp":1787203480328,"version":"build-2736575974"},"reference-count":57,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"U.S. Department of Energy"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/ipdpsw71298.2026.00025","type":"proceedings-article","created":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T19:13:15Z","timestamp":1787166795000},"page":"149-156","source":"Crossref","is-referenced-by-count":0,"title":["A Benchmark Suite for Evaluating Scientific AI Workloads on GPUs"],"prefix":"10.1109","author":[{"given":"Zheming","family":"Jin","sequence":"first","affiliation":[{"name":"Oak Ridge National Laboratory","place":["Oak Ridge, TN, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Bernholdt","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory","place":["Oak Ridge, TN, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feiyi","family":"Wang","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory","place":["Oak Ridge, TN, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junqi","family":"Yin","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory","place":["Oak Ridge, TN, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2008.917757"},{"key":"ref2","first-page":"32","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2023.3256796"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-18991-2_27"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8191(05)80029-8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8191(05)80033-X"},{"key":"ref8","volume-title":"Transaction processing performance council","year":"2005"},{"key":"ref9","author":"Narang","year":"2016","journal-title":"DeepBench: Benchmarking deep learning operations on different hardware"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2016.7581275"},{"issue":"101","key":"ref11","first-page":"102","article-title":"Dawnbench: An end-to-end deep learning benchmark and competition","volume":"100","author":"Coleman","year":"2017","journal-title":"Training"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2020.2974843"},{"key":"ref13","volume-title":"Ai for science: Report on the Department of Energy (DOE) Town Halls on Artificial Intelligence (AI) for Science (No. ANL-20\/17)","author":"Stevens","year":"2020"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.2172\/1081802","volume-title":"Scientific application requirements for leadership computing at the exascale (No. ORNL\/TM-2011\/250)","author":"Ahern","year":"2007"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2005.1555942"},{"key":"ref17","article-title":"Fourier neural operator for parametric partial differential equations","author":"Li","year":"2020"},{"key":"ref18","volume-title":"About MLCommons Benchmarks"},{"key":"ref19","volume-title":"MI300X vs H100 vs H200 Benchmark Part 1: Training - CUDA Moat Still Alive"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.tbench.2021.100005"},{"key":"ref21","article-title":"Kernelbench: Can LLMs write efficient GPU kernels?","author":"Ouyang","year":"2025"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.1183"},{"key":"ref23","article-title":"Geak: Introducing triton kernel ai agent & evaluation benchmarks","author":"Wang","year":"2025"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/vl\/N19-142"},{"issue":"8","key":"ref25","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1615\/JMachLearnModelComput.2023048607"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00007"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1200\/CCI.23.00148"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3774934.3786444"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1189"},{"key":"ref31","article-title":"FlashAttention-2: Faster attention with better parallelism and work partitioning","author":"Dao","year":"2023"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2193"},{"key":"ref33","article-title":"The lastest PyTorch Reference Application Programming Interface"},{"key":"ref34","article-title":"NVIDIA CUDA Deep Neural Network (cuDNN)"},{"key":"ref35","first-page":"7","article-title":"FlexAttention: A Programming Model for Generating Fused Attention Variants","volume-title":"Proceedings of Machine Learning and Systems","author":"Dong"},{"key":"ref36","article-title":"AI Tensor Engine for ROCm"},{"key":"ref37","article-title":"tritonBLAS: Triton-based Analytical Approach for GEMM Kernel Parameter Selection","author":"Swann","year":"2025"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ARITH.2019.00022"},{"key":"ref39","article-title":"Fp8 formats for deep learning","author":"Micikevicius","year":"2022"},{"key":"ref40","article-title":"TorchAO: PyTorch-Native Training-to-Serving Model Optimization","author":"Or","year":"2025"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmgm.2023.108506"},{"key":"ref42","article-title":"Graph neural networks in particle physics: Implementations, innovations, and challenges","author":"Thais","year":"2022"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10375-2"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/springerreference_33509"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1038\/s42254-024-00712-5"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-96208-y"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3337857"},{"key":"ref48","article-title":"Fourcastnet: A global data-driven high-resolution weather model using adaptive fourier neural operators","author":"Pathak","year":"2022"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3592979.3593412"},{"key":"ref50","article-title":"Interconnect bandwidth heterogeneity on AMD MI250x and infinity fabric","author":"Pearson","year":"2023"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC49657.2024.10454441"},{"key":"ref52","article-title":"The lastest PyTorch Reference Application Programming Interface"},{"key":"ref53","article-title":"A lightweight library for PyTorch training tools and utilities"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3613215"},{"key":"ref55","article-title":"Fast and memory-efficient exact attention"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3673038.3673136"},{"key":"ref57","volume-title":"HydraGNN","author":"Lupo Pasini","year":"2021"}],"event":{"name":"2026 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)","location":"New Orleans, LA, USA","start":{"date-parts":[[2026,5,25]]},"end":{"date-parts":[[2026,5,29]]}},"container-title":["2026 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11651886\/11651887\/11652033.pdf?arnumber=11652033","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T04:51:48Z","timestamp":1787201508000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11652033\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/ipdpsw71298.2026.00025","relation":{},"subject":[],"published":{"date-parts":[[2026,5]]}}}