{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T12:07:43Z","timestamp":1730290063795,"version":"3.28.0"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"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":[[2021,11]]},"DOI":"10.1109\/pmbs54543.2021.00007","type":"proceedings-article","created":{"date-parts":[[2021,12,28]],"date-time":"2021-12-28T21:29:40Z","timestamp":1640726980000},"page":"7-17","source":"Crossref","is-referenced-by-count":8,"title":["Architectural Requirements for Deep Learning Workloads in HPC Environments"],"prefix":"10.1109","author":[{"given":"Khaled Z.","family":"Ibrahim","sequence":"first","affiliation":[]},{"given":"Tan","family":"Nguyen","sequence":"additional","affiliation":[]},{"given":"Hai Ah","family":"Nam","sequence":"additional","affiliation":[]},{"given":"Wahid","family":"Bhimji","sequence":"additional","affiliation":[]},{"given":"Steven","family":"Farrell","sequence":"additional","affiliation":[]},{"given":"Leonid","family":"Oliker","sequence":"additional","affiliation":[]},{"given":"Michael","family":"Rowan","sequence":"additional","affiliation":[]},{"given":"Nicholas J.","family":"Wright","sequence":"additional","affiliation":[]},{"given":"Samuel","family":"Williams","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/PMBS49563.2019.00017"},{"volume":"7","journal-title":"The Design Deployment and Evaluation of the CORAL Pre-Exascale Systems","year":"2018","author":"vazhkudai","key":"ref38"},{"journal-title":"Intel SSD DC P4500 Series","year":"2021","key":"ref33"},{"journal-title":"Cori GPU Nodes","year":"2021","key":"ref32"},{"key":"ref31","first-page":"108","article-title":"V100 gpu architecture. the world's most advanced data center gpu. version wp-08608-001_v1. 1","author":"nvidia","year":"2017","journal-title":"NVIDIA Aug"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"journal-title":"NVIDIA data loading library (DALI)","year":"2021","key":"ref37"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356183"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/215399.215427"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/1498765.1498785"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref11","first-page":"336","article-title":"MLPerf Training Benchmark","volume":"2","author":"mattson","year":"0","journal-title":"Proceedings of Machine Learning and Systems"},{"journal-title":"Tensorflow model garden","year":"2021","key":"ref12"},{"journal-title":"NVIDIA Deep Learning Examples for Tensor Cores","year":"2021","key":"ref13"},{"journal-title":"HPE Deep Learning Benchmarking Suite","year":"2021","key":"ref14"},{"journal-title":"DAWNBench An End-to-End Deep Learning Bench-mark and Competition","year":"2021","key":"ref15"},{"journal-title":"Hpl-ai mixed-precision benchmark","year":"2021","author":"dongarra","key":"ref16"},{"journal-title":"Deepbench","year":"2021","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2016.7581275"},{"key":"ref19","article-title":"Benchmarking TPU, GPU, and CPU platforms for deep learning","volume":"abs 1907 10701","author":"wang","year":"2019","journal-title":"CoRR"},{"key":"ref28","article-title":"Hierarchical roofline performance analysis for deep learning applications","volume":"abs 2009 5257","author":"wang","year":"2020","journal-title":"CoRR"},{"journal-title":"Benchmarking & workload characterization","year":"2021","key":"ref4"},{"journal-title":"Deep Learning Climate Segmentation Benchmark","year":"2021","key":"ref27"},{"journal-title":"What is CORAL?","year":"2021","key":"ref3"},{"volume":"2","journal-title":"Workshop Report on Basic Research Needs for Scientific Machine Learning Core Technologies for Artificial Intelligence","year":"0","author":"baker","key":"ref6"},{"journal-title":"NCAR Community Atmosphere Model (CAM 5 0)","year":"2021","key":"ref29"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10214-6_3"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00054"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00068"},{"journal-title":"2021","article-title":"Top 500","year":"0","key":"ref2"},{"journal-title":"MLPerf Training HPC","year":"2021","key":"ref9"},{"journal-title":"Hyperion Research","year":"2021","key":"ref1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS47924.2020.00042"},{"key":"ref22","article-title":"HPC AI500: the methodology, tools, roofline performance models, and metrics for benchmarking HPC AI systems","volume":"abs 2007 279","author":"jiang","year":"2020","journal-title":"CoRR"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2019.00018"},{"journal-title":"Cosmoflow datasets","year":"2021","key":"ref24"},{"journal-title":"CosmoFlow TensorFlow Keras benchmark implementation","year":"2021","key":"ref23"},{"key":"ref26","article-title":"Encoder-decoder with atrous separable convolution for semantic image segmentation","volume":"abs 1802 2611","author":"chen","year":"2018","journal-title":"CoRR"},{"journal-title":"TFRecord and tf train Example","year":"2021","key":"ref25"}],"event":{"name":"2021 International Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS)","start":{"date-parts":[[2021,11,15]]},"location":"St. Louis, MO, USA","end":{"date-parts":[[2021,11,15]]}},"container-title":["2021 International Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9652586\/9652659\/09652793.pdf?arnumber=9652793","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:59:55Z","timestamp":1652201995000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9652793\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/pmbs54543.2021.00007","relation":{},"subject":[],"published":{"date-parts":[[2021,11]]}}}