{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T18:15:09Z","timestamp":1771956909402,"version":"3.50.1"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T00:00:00Z","timestamp":1709337600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T00:00:00Z","timestamp":1709337600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,3,2]]},"DOI":"10.1109\/cgo57630.2024.10444828","type":"proceedings-article","created":{"date-parts":[[2024,2,28]],"date-time":"2024-02-28T18:47:35Z","timestamp":1709146055000},"page":"119-132","source":"Crossref","is-referenced-by-count":8,"title":["Retargeting and Respecializing GPU Workloads for Performance Portability"],"prefix":"10.1109","author":[{"given":"Ivan R.","family":"Ivanov","sequence":"first","affiliation":[{"name":"Tokyo Institute of Technology, RIKEN R-CCS,Kobe,Japan"}]},{"given":"Oleksandr","family":"Zinenko","sequence":"additional","affiliation":[{"name":"Google DeepMind,Paris,France"}]},{"given":"Jens","family":"Domke","sequence":"additional","affiliation":[{"name":"RIKEN R-CCS,Kobe,Japan"}]},{"given":"Toshio","family":"Endo","sequence":"additional","affiliation":[{"name":"Tokyo Institute of Technology,Tokyo,Japan"}]},{"given":"William S.","family":"Moses","sequence":"additional","affiliation":[{"name":"University of Illinois Urhana-Champaign, Google DeepMind,Illinois,United States"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3315508.3329973"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2400682.2400713"},{"issue":"9","key":"ref3","article-title":"Compiling machine learning programs via high-level tracing","volume":"4","author":"Frostig","year":"2018","journal-title":"Systems for Machine Learning"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3355606"},{"key":"ref5","article-title":"TVM: An Automated End-to-End Optimizing Compiler for Deep Learning","author":"Chen","year":"2018","journal-title":"arXiv"},{"key":"ref6","first-page":"673","article-title":"SYCL: Single-source C++ accelerator programming","volume-title":"Parallel Computing: On the Road to Exascale","author":"Reyes","year":"2016"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/PACT52795.2021.00011"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3572848.3577475"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CGO51591.2021.9370308"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2011.10.002"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD53106.2021.00054"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3577193.3593705"},{"key":"ref13","volume-title":"How to Access Global Memory Efficiently in CUDA C \/C++ Kernels","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW52791.2021.00068"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3469030"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-31445-2_10"},{"key":"ref17","volume-title":"Understanding Latency Hiding on GPUs","author":"Volkov","year":"2016"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3243176.3243196"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2503210.2503268"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2628071.2628087"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ispass57527.2023.00041"},{"key":"ref23","volume-title":"HIPify","year":"2023"},{"key":"ref24","first-page":"21","volume-title":"Automatic Restructuring of GPU Kernels for Exploiting Inter-thread Data Locality","author":"Unkule","year":"2012"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3194242"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2014.07.003"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/P3HPC49587.2019.00012"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2491956.2462176"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/WACCPD.2014.10"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3559009.3569687"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/cgo.2004.1281665"},{"key":"ref32","volume-title":"Retarpeting and Respecializing GPU Workloads for Performance Portability - Artifact","author":"Ivanov","year":"2024"}],"event":{"name":"2024 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO)","location":"Edinburgh, United Kingdom","start":{"date-parts":[[2024,3,2]]},"end":{"date-parts":[[2024,3,6]]}},"container-title":["2024 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10444766\/10444770\/10444828.pdf?arnumber=10444828","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T15:41:29Z","timestamp":1710430889000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10444828\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,2]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/cgo57630.2024.10444828","relation":{},"subject":[],"published":{"date-parts":[[2024,3,2]]}}}