{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:10:12Z","timestamp":1755911412041,"version":"3.44.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"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":[[2019,11]]},"DOI":"10.1109\/iiswc47752.2019.9042139","type":"proceedings-article","created":{"date-parts":[[2020,3,20]],"date-time":"2020-03-20T04:55:14Z","timestamp":1584680114000},"page":"155-166","source":"Crossref","is-referenced-by-count":4,"title":["One Size Doesn't Fit All: Quantifying Performance Portability of Graph Applications on GPUs"],"prefix":"10.1109","author":[{"given":"Tyler","family":"Sorensen","sequence":"first","affiliation":[{"name":"Princeton University, USA,UC Santa Cruz,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sreepathi","family":"Pai","sequence":"additional","affiliation":[{"name":"University of Rochester,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alastair F.","family":"Donaldson","sequence":"additional","affiliation":[{"name":"Imperial College London,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","first-page":"578","article-title":"TVM: an automated end-to-end optimizing compiler for deep learning","author":"chen","year":"2018","journal-title":"In OSDI Symposium on Operating Systems Design and Implementation"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-38750-0_11"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2013.133"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1037\/0033-2909.111.2.361"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/1508244.1508275"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2983990.2984015"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2668930.2688042"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2851141.2851145"},{"article-title":"nvGraph library user's guide","year":"2018","author":"nvidia","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177730491"},{"journal-title":"The OpenCL Specification","year":"2013","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2983990.2984032"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/InPar.2012.6339596"},{"key":"ref19","first-page":"1","article-title":"Inter-block GPU communication via fast barrier synchronization","author":"xiao","year":"2010","journal-title":"IPDPS"},{"journal-title":"The art of computer systems performance analysis - techniques for experimental design measurement simulation and modeling ser Wiley professional computing","year":"1991","author":"jain","key":"ref28"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2628071.2628092"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611972740.43"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2014.59"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/InPar.2012.6339597"},{"journal-title":"Inter-workgroup barrier synchronisation on graphics processing units","year":"2018","author":"sorensen","key":"ref29"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1542476.1542481"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2451116.2451141"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67630-2_38"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2737924.2737969"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2451116.2451140"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2872362.2872411"},{"article-title":"The OpenCL specification version: 2.0 (rev. 29)","year":"2015","author":"group","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2717511"},{"journal-title":"CUDA C Programming Guide Version 3 1","year":"2019","key":"ref21"},{"key":"ref24","article-title":"Auto-matically comparing memory consistency models","author":"wickerson","year":"2017","journal-title":"POPL"},{"year":"2017","key":"ref23","article-title":"Parallel thread execution ISA: Version 6.0"},{"article-title":"ARM Midgard architecture","year":"2011","author":"lokhmotov","key":"ref26"},{"article-title":"cl_intel_subgroups version 4","year":"2016","author":"ashbaugh","key":"ref25"}],"event":{"name":"2019 IEEE International Symposium on Workload Characterization (IISWC)","start":{"date-parts":[[2019,11,3]]},"location":"Orlando, FL, USA","end":{"date-parts":[[2019,11,5]]}},"container-title":["2019 IEEE International Symposium on Workload Characterization (IISWC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9027808\/9041927\/09042139.pdf?arnumber=9042139","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T00:48:00Z","timestamp":1755910080000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9042139\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/iiswc47752.2019.9042139","relation":{},"subject":[],"published":{"date-parts":[[2019,11]]}}}