{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T00:42:12Z","timestamp":1725583332466},"reference-count":11,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,1]]},"DOI":"10.1109\/aspdac.2017.7858307","type":"proceedings-article","created":{"date-parts":[[2017,2,20]],"date-time":"2017-02-20T21:36:54Z","timestamp":1487626614000},"page":"121-126","source":"Crossref","is-referenced-by-count":3,"title":["Enabling fast preemption via Dual-Kernel support on GPUs"],"prefix":"10.1109","author":[{"given":"Li-Wei","family":"Shieh","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kun-Chih","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hsueh-Chun","family":"Fu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Po-Han","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chia-Lin","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2016.7446078"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2694344.2694346"},{"key":"ref10","article-title":"Parboil: A revised benchmark suite for scientific and commercial throughput computing","author":"stratton","year":"2012","journal-title":"IMPACT Technical Report IMPACT-12-01 U of Illinois at Urbana-Champaign"},{"journal-title":"CUDA C Programming Guide","article-title":"NVIDIA","year":"2011","key":"ref6"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2366231.2337168"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2014.6853209"},{"journal-title":"Whitepaper","article-title":"NVIDIA's Next Generation CUDA Compute Architecture: Fermi","year":"2009","key":"ref8"},{"key":"ref7","first-page":"163","article-title":"Analyzing CUDA workloads using a detailed GPU simulator","author":"ali","year":"2009","journal-title":"IEEE Int Symp Performance Anal Syst Software"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1145\/2678373.2665702","article-title":"Enabling Preemptive Multiprogramming on GPUs","author":"tanastic","year":"2014","journal-title":"Proc Int Symp Computer Architecture (ISCA)"},{"key":"ref9","first-page":"44","article-title":"Rodinia: A benchmark suite for heterogeneous computing","author":"shuai","year":"2009","journal-title":"Proc IEEE Symp Workload Characterization"},{"year":"2012","key":"ref1","article-title":"Sharing a GPU between MPI processes: multi-process service (MPS)"}],"event":{"name":"2017 22nd Asia and South Pacific Design Automation Conference (ASP-DAC)","start":{"date-parts":[[2017,1,16]]},"location":"Chiba, Japan","end":{"date-parts":[[2017,1,19]]}},"container-title":["2017 22nd Asia and South Pacific Design Automation Conference (ASP-DAC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7847727\/7858249\/07858307.pdf?arnumber=7858307","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,18]],"date-time":"2019-09-18T22:13:49Z","timestamp":1568844829000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7858307\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,1]]},"references-count":11,"URL":"https:\/\/doi.org\/10.1109\/aspdac.2017.7858307","relation":{},"subject":[],"published":{"date-parts":[[2017,1]]}}}