{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T23:37:38Z","timestamp":1783035458386,"version":"3.54.6"},"reference-count":63,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,19]]},"DOI":"10.1109\/ccgrid64434.2025.00035","type":"proceedings-article","created":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T17:36:08Z","timestamp":1751304968000},"page":"549-558","source":"Crossref","is-referenced-by-count":3,"title":["Evaluating Energy Efficiency of Ai Accelerators Using Two Mlperf Benchmarks"],"prefix":"10.1109","author":[{"given":"Farah","family":"Ferdaus","sequence":"first","affiliation":[{"name":"Mathematics and Computer Science Division,Argonne National Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingfu","family":"Wu","sequence":"additional","affiliation":[{"name":"Mathematics and Computer Science Division,Argonne National Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Valerie","family":"Taylor","sequence":"additional","affiliation":[{"name":"Mathematics and Computer Science Division,Argonne National Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiling","family":"Lan","sequence":"additional","affiliation":[{"name":"University of Illinois Chicago,Argonne National Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sanjif","family":"Shanmugavelu","sequence":"additional","affiliation":[{"name":"Groq Inc."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Venkatram","family":"Vishwanath","sequence":"additional","affiliation":[{"name":"Argonne Leadership Computing Facility, Argonne National Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael E.","family":"Papka","sequence":"additional","affiliation":[{"name":"University of Illinois Chicago,Argonne National Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1126\/science.aaa8685"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2020.2975764"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMp1606181"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41582-020-0377-8"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/s41524-019-0221-0"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1085\/2\/022008"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1039\/C9TA02356A"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref10","first-page":"645","article-title":"Pattern recognition and machine learning","volume":"2","author":"Bishop","year":"2006","journal-title":"Springer google schola"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511973000"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/s41573-019-0024-5"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.2172\/1604756"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/PMBS56514.2022.00007"},{"key":"ref16","year":"2024","journal-title":"\u201cTOP500 LIST - JUNE 2024"},{"key":"ref17","author":"Wang","year":"2019","journal-title":"Benchmarking TPU, GPU, and CPU platforms for deep learning"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3282307"},{"key":"ref19","article-title":"Multi-horizon forecasting for limit order books: Novel deep learning approaches and hardware acceleration using intelligent processing units","author":"Zhang","year":"2021","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Using the graphcore ipu for traditional hpc applications","volume-title":"3rd Workshop on Accelerated Machine Learning (AccML)","author":"Louw","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s41781-021-00057-z"},{"key":"ref22","volume-title":"MLPerf."},{"key":"ref23","volume-title":"ALCF AI Testbed."},{"key":"ref24","volume-title":"Graphcore Intelligent Processing Unit."},{"key":"ref25","volume-title":"Frontier."},{"key":"ref26","volume-title":"Aurora Supercomputing System."},{"key":"ref27","article-title":"Productive computational science in the era of extreme heterogeneity","volume-title":"Report for DOE ASCR Basic Research Needs Workshop on Extreme Heterogeneity","author":"Vetter","year":"2019"},{"key":"ref28","volume-title":"AI for Science: Report on the Department of Energy (DOE) Town Halls on Artificial Intelligence (AI) for Science","author":"Stevens","year":"2020"},{"key":"ref29","article-title":"Mlperf power: Benchmarking the energy efficiency of machine learning systems from microwatts to megawatts for sustainable ai","author":"Tschand","year":"2024","journal-title":"arXiv preprint"},{"key":"ref30","volume-title":"Sofia."},{"key":"ref31","article-title":"Quantifying the carbon emissions of machine learning","author":"Lacoste","year":"2019","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"Carbon emissions and large neural network training","author":"Patterson","year":"2021","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i09.7123"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid49817.2020.00-15"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/SCW63240.2024.00178"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC55821.2022.9926296"},{"key":"ref37","first-page":"119","article-title":"Zeus: Understanding and optimizing \\{GPU\\} energy consumption of \\{DNN\\} training","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"You","year":"2023"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/PMBS56514.2022.00010"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid49817.2020.00-15"},{"key":"ref40","article-title":"Graphcore c2 card performance for image-based deep learning application: A report","author":"Kacher","year":"2020","journal-title":"arXiv preprint"},{"key":"ref41","article-title":"Dissecting the graphcore ipu architecture via microbenchmarking","author":"Jia","year":"2019","journal-title":"arXiv preprint"},{"key":"ref42","volume-title":"Second-Gen Habana Gaudi2 Outperforms Nvidia A100","year":"2022"},{"key":"ref43","first-page":"2","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of naacL-HLT","volume":"1","author":"Kenton","year":"2019"},{"key":"ref44","volume-title":"Truepoint technology."},{"key":"ref45","article-title":"Large batch optimization for deep learning: Training bert in 76 minutes","author":"You","year":"2019","journal-title":"arXiv preprint"},{"key":"ref46","volume-title":"BOW POD64","year":"2024"},{"key":"ref47","volume-title":"Intel gaudi ai accelerator","year":"2024"},{"key":"ref48","volume-title":"Groqcard accelerator","year":"2024"},{"key":"ref49","volume-title":"Power measurement."},{"key":"ref50","volume-title":"gcipuinfo."},{"key":"ref51","volume-title":"pyhlml."},{"key":"ref52","volume-title":"NVML."},{"key":"ref53","year":"2024","journal-title":"Groqware suite"},{"key":"ref54","year":"2024","journal-title":"CUDA COMPILER DRIVER NVCC"},{"key":"ref55","volume-title":"Poplar SDK."},{"key":"ref56","volume-title":"Intel\u00ae Gaudi\u00ae Support Matrix."},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref58","volume-title":"Deeplearningexamples."},{"key":"ref59","volume-title":"Graphcore application examples."},{"key":"ref60","volume-title":"Intel gaudi ai accelerator examples.","author":"Gaudi"},{"key":"ref61","volume-title":"Automatic mixed precision package - torch.amp","year":"2024"},{"key":"ref62","article-title":"Efficient sequence packing without cross-contamination: Accelerating large language models without impacting performance","author":"Krell","year":"2021","journal-title":"arXiv preprint"},{"issue":"1","key":"ref63","doi-asserted-by":"crossref","DOI":"10.1002\/cpe.8322","article-title":"ytopt: Autotuning scientific applications for energy efficiency at large scales","volume":"37","author":"Wu","year":"2025","journal-title":"Concurrency and Computation: Practice and Experience"}],"event":{"name":"2025 IEEE 25th International Symposium on Cluster, Cloud and Internet Computing (CCGrid)","location":"Troms\u00f8, Norway","start":{"date-parts":[[2025,5,19]]},"end":{"date-parts":[[2025,5,22]]}},"container-title":["2025 IEEE 25th International Symposium on Cluster, Cloud and Internet Computing (CCGrid)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11044421\/11044790\/11044796.pdf?arnumber=11044796","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T05:33:38Z","timestamp":1751348018000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11044796\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/ccgrid64434.2025.00035","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}