{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T15:51:14Z","timestamp":1758124274759,"version":"3.37.3"},"reference-count":18,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2017,7,1]],"date-time":"2017-07-01T00:00:00Z","timestamp":1498867200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology of Taiwan","doi-asserted-by":"publisher","award":["MOST-105-2221-E-002-156-MY2","MOST-105-2622-8-002-002","MOST-105-2218-E-002-025"],"award-info":[{"award-number":["MOST-105-2221-E-002-156-MY2","MOST-105-2622-8-002-002","MOST-105-2218-E-002-025"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004164","name":"MediaTek Inc.","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004164","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Comput. Arch. Lett."],"published-print":{"date-parts":[[2017,7,1]]},"DOI":"10.1109\/lca.2017.2693371","type":"journal-article","created":{"date-parts":[[2017,4,12]],"date-time":"2017-04-12T18:32:26Z","timestamp":1492021946000},"page":"127-131","source":"Crossref","is-referenced-by-count":15,"title":["Improving GPGPU Performance via Cache Locality Aware Thread Block Scheduling"],"prefix":"10.1109","volume":"16","author":[{"given":"Li-Jhan","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hsiang-Yun","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Po-Han","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0091-5027","authenticated-orcid":false,"given":"Chia-Lin","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"volume":"1","journal-title":"6th Generation Intel CoreTM Processor Family Datasheet","year":"2016","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2009.4919648"},{"article-title":"Scheduling and execution of compute tasks","year":"2013","author":"abdalla","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"journal-title":"CUDA C\/C++ SDK CODE Samples","year":"2011","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2451116.2451158"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2485922.2485951"},{"key":"ref17","first-page":"157","article-title":"Neither more nor less:\n Optimizing thread-level parallelism for GPGPUs","author":"kay?ran","year":"2013","journal-title":"Proc Int Conf Parallel Archit Compilation Tech"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001199"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2540708.2540718"},{"journal-title":"NVIDIAs Next Generation CUDA Compute Architecture Fermi","year":"2009","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2012.16"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2014.6835937"},{"key":"ref7","first-page":"89","article-title":"Priority-based cache allocation in throughput processors","author":"li et","year":"2015","journal-title":"Proc IEEE 21st Int Symp High Perform Comput Archit"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2304576.2304582"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2010.41"},{"journal-title":"Kepler The Fastest Most Efficient HPC Architecture Ever Built","year":"2012","key":"ref9"}],"container-title":["IEEE Computer Architecture Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10208\/8240814\/07898501.pdf?arnumber=7898501","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:25:04Z","timestamp":1642004704000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7898501\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,7,1]]},"references-count":18,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/lca.2017.2693371","relation":{},"ISSN":["1556-6056"],"issn-type":[{"type":"print","value":"1556-6056"}],"subject":[],"published":{"date-parts":[[2017,7,1]]}}}