{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T23:22:22Z","timestamp":1776468142478,"version":"3.51.2"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/V007092\/1"],"award-info":[{"award-number":["EP\/V007092\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Leverhulme Trust Doctoral Scholarships programme in Material Social Futures","award":["DS-2017-036"],"award-info":[{"award-number":["DS-2017-036"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2023,7]]},"DOI":"10.1109\/tpds.2023.3279233","type":"journal-article","created":{"date-parts":[[2023,5,23]],"date-time":"2023-05-23T18:45:55Z","timestamp":1684867555000},"page":"2208-2220","source":"Crossref","is-referenced-by-count":8,"title":["DOPpler: Parallel Measurement Infrastructure for Auto-Tuning Deep Learning Tensor Programs"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4287-0752","authenticated-orcid":false,"given":"Damian","family":"Borowiec","sequence":"first","affiliation":[{"name":"Lancaster University, Lancaster, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3845-0686","authenticated-orcid":false,"given":"Gingfung","family":"Yeung","sequence":"additional","affiliation":[{"name":"Lancaster University, Lancaster, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9228-7365","authenticated-orcid":false,"given":"Adrian","family":"Friday","sequence":"additional","affiliation":[{"name":"Lancaster University, Lancaster, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8838-2012","authenticated-orcid":false,"given":"Richard","family":"Harper","sequence":"additional","affiliation":[{"name":"Lancaster University, Lancaster, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7103-2515","authenticated-orcid":false,"given":"Peter","family":"Garraghan","sequence":"additional","affiliation":[{"name":"Lancaster University, Lancaster, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"14807","article-title":"AdaTune: Adaptive tensor program compilation made efficient","author":"li","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3337821.3337839"},{"key":"ref12","first-page":"3389","article-title":"Learning to optimize tensor programs","author":"chen","year":"2018","journal-title":"Proc 32nd Annu Conf Neural Inf Process Syst"},{"key":"ref34","article-title":"Accelerating neural architecture search using performance prediction","author":"baker","year":"2017"},{"key":"ref15","article-title":"CUDA streams and concurrency, NVIDIA","author":"rennich","year":"2022"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2011.03.041"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2008.31"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2010.5470423"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.23919\/DATE51398.2021.9473984"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.peva.2021.102234"},{"key":"ref11","year":"2022"},{"key":"ref33","year":"2022"},{"key":"ref10","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref32","year":"2022"},{"key":"ref2","first-page":"578","article-title":"TVM: An automated end-to-end optimizing compiler for deep learning","author":"chen","year":"2018","journal-title":"Proc 13th USENIX Symp Operating Syst Des Implementation"},{"key":"ref1","article-title":"Deep learning inference in facebook data centers: Characterization, performance optimizations and hardware implications","author":"park","year":"2018"},{"key":"ref17","article-title":"SqueezeNet: Alexnet-level accuracy with 50x fewer parameters and< 0.5 mb model size","author":"iandola","year":"2016"},{"key":"ref39","article-title":"Intel nGraph: An intermediate representation, compiler, and executor for deep learning","author":"cyphers","year":"2018"},{"key":"ref16","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017"},{"key":"ref38","article-title":"MXNet","year":"2022"},{"key":"ref19","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref18","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014"},{"key":"ref24","volume":"16","author":"iglewicz","year":"1993","journal-title":"How to Detect and Handle Outliers"},{"key":"ref23","author":"berg","year":"1936","journal-title":"Heaviside's Operational Calculus as applied to engineering and physics"},{"key":"ref45","first-page":"181","article-title":"A deep learning based cost model for automatic code optimization","volume":"3","author":"baghdadi","year":"2021","journal-title":"Proc Mach Learn Syst"},{"key":"ref26","article-title":"Cupti :: Cupti documentation, NVIDIA","year":"2022"},{"key":"ref25","article-title":"Python multiprocessing &#x2014; process-based parallelism, Python software foundation","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/2490301.2451160"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/2499370.2462176"},{"key":"ref22","article-title":"NVIDIA Nsight systems, NVIDIA","year":"2022"},{"key":"ref44","first-page":"323","article-title":"Value learning for throughput optimization of deep learning workloads","volume":"3","author":"steiner","year":"2021","journal-title":"Proc Mach Learn Syst"},{"key":"ref21","article-title":"Multi-process service - MPS, NVIDIA","year":"2022"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3079202"},{"key":"ref28","first-page":"2514","article-title":"Binary increase congestion control (BIC) for fast long-distance networks","author":"xu","year":"2004","journal-title":"Proc IEEE InfoCom"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.jesp.2013.03.013"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref8","year":"2023"},{"key":"ref7","year":"2023"},{"key":"ref9","author":"borowiec","year":"2023"},{"key":"ref4","first-page":"863","article-title":"Ansor: Generating high-performance tensor programs for deep learning","author":"zheng","year":"2020","journal-title":"Proc 14th USENIX Symp Operating Syst Des Implementation"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3322967"},{"key":"ref6","year":"2022"},{"key":"ref5","article-title":"Chameleon: Adaptive code optimization for expedited deep neural network compilation","author":"ahn","year":"2020","journal-title":"arXiv 2001 08743"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2019.8661197"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/10132303\/10132048.pdf?arnumber=10132048","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,26]],"date-time":"2023-06-26T18:51:22Z","timestamp":1687805482000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10132048\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7]]},"references-count":45,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2023.3279233","relation":{},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"value":"1045-9219","type":"print"},{"value":"1558-2183","type":"electronic"},{"value":"2161-9883","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7]]}}}