{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T15:14:06Z","timestamp":1776784446713,"version":"3.51.2"},"reference-count":27,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,2]]},"DOI":"10.1109\/cgo.2015.7054184","type":"proceedings-article","created":{"date-parts":[[2015,3,10]],"date-time":"2015-03-10T17:47:12Z","timestamp":1426009632000},"page":"23-33","source":"Crossref","is-referenced-by-count":18,"title":["Automatic data placement into GPU on-chip memory resources"],"prefix":"10.1109","author":[{"given":"Chao","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhen","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huiyang","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2013.6618813"},{"key":"ref11","article-title":"Programming Massively Parallel Processors: A Hands-on Approach","author":"kirk","year":"2010"},{"key":"ref12","article-title":"Performance upper bound analysis and optimization of SGEMM on FERMI and KEPLER GPUs","author":"lai","year":"2013","journal-title":"CGO"},{"key":"ref13","article-title":"Cetus-An extensible compiler infrastructure for source-to-source transformation","author":"lee","year":"0","journal-title":"LCPC 2004"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2014.6844487"},{"key":"ref15","article-title":"GLES: A Practical GPGPU Optimizing Compiler Using Data Sharing and Thread Coarsening","author":"lin","year":"2014","journal-title":"LCPC"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1375527.1375562"},{"key":"ref17","year":"2011","journal-title":"NVIDIA Nvidia's Next Generation CUDA Compute Architecture Fermi"},{"key":"ref18","year":"2012","journal-title":"NVIDIA Kepler GK110 White Paper"},{"key":"ref19","year":"2011","journal-title":"NVIDIA CUDA C\/C++ SDK Code Samples 2011"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2370816.2370858"},{"key":"ref3","year":"0","journal-title":"CUDA Programming Guide"},{"key":"ref6","article-title":"Energy-efficient mechanisms for managing thread context in throughput processors","author":"gebhart","year":"2012","journal-title":"ISCA"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.1145\/314403.314414","article-title":"Optimzing for reduced code space using generic algorithms","author":"cooper","year":"1999","journal-title":"LCTES"},{"key":"ref8","article-title":"Unified On-Chip Mmeory Allocation for SIMT Architecture","author":"hayes","year":"2014","journal-title":"ICS"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2012.18"},{"key":"ref2","author":"bakhoda","year":"2009","journal-title":"Analyzing CUDA Workloads Using A Detailed GPU Simulator"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2304576.2304582"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2013.6522337"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/781131.781141"},{"key":"ref22","article-title":"Automatic Restructuring of GPU Kernels for Exploiting Inter-thread Data Locality","author":"unkule","year":"0","journal-title":"CCC 2012"},{"key":"ref21","article-title":"MCUDA: An efficient implementation of CUDA kernels on multi-cores","author":"stratton","year":"0","journal-title":"LCPC 2008"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2555243.2555255"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2442516.2442523"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/1806596.1806606"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2555243.2555254"}],"event":{"name":"2015 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO)","location":"San Francisco, CA, USA","start":{"date-parts":[[2015,2,7]]},"end":{"date-parts":[[2015,2,11]]}},"container-title":["2015 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7041249\/7054173\/07054184.pdf?arnumber=7054184","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,21]],"date-time":"2019-08-21T17:07:56Z","timestamp":1566407276000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7054184\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,2]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/cgo.2015.7054184","relation":{},"subject":[],"published":{"date-parts":[[2015,2]]}}}