{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T04:07:27Z","timestamp":1747886847790,"version":"3.41.0"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2012,6,1]],"date-time":"2012-06-01T00:00:00Z","timestamp":1338508800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2012,6,1]],"date-time":"2012-06-01T00:00:00Z","timestamp":1338508800000},"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":[[2012,6]]},"DOI":"10.1109\/isca.2012.6237006","type":"proceedings-article","created":{"date-parts":[[2012,7,21]],"date-time":"2012-07-21T00:59:02Z","timestamp":1342832342000},"page":"61-71","source":"Crossref","is-referenced-by-count":4,"title":["CAPRI: Prediction of compaction-adequacy for handling control-divergence in GPGPU architectures"],"prefix":"10.1109","author":[{"given":"Minsoo","family":"Rhu","sequence":"first","affiliation":[{"name":"Electrical and Computer Engineering Department, The University of Texas at Austin, USA"}]},{"given":"Mattan","family":"Erez","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering Department, The University of Texas at Austin, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/567067.567085"},{"volume-title":"AMD Radeon HD 6900M Series Specifications","year":"2010","key":"ref2"},{"volume-title":"ATI Stream Computing OpenCL Programming Guide","year":"2010","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2009.4919648"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1972.8647"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"ref7","doi-asserted-by":"crossref","DOI":"10.1145\/2155620.2155676","article-title":"SIMD Re-Convergence At Thread Frontiers","volume-title":"44th International Symposium on Microarchitecture (MICRO-44)","author":"Diamos"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2011.5749714"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2007.30"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2010.51"},{"volume-title":"Jacobi iteration for a Laplace discretisation on a 3D structured grid","year":"2008","author":"Giles","key":"ref11"},{"volume-title":"Notes on using the NVIDIA 8800 GTX graphics card","year":"2008","author":"Giles","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-77220-0_21"},{"volume-title":"The Parboil Benchmark Suite","year":"2007","key":"ref14"},{"volume-title":"Intel AVX: New Frontiers in Performance Improvements and Energy Efficiency","year":"2009","key":"ref15"},{"volume-title":"Intel HD Graphics OpenSource Programmer Reference Manual","year":"2011","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2000.898067"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/1815961.1815992"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.1145\/2155620.2155656","article-title":"Improving GPU Performance via Large Warps and Two-Level Warp Scheduling","volume-title":"44th International Symposium on Microarchitecture (MICRO-44)","author":"Narasiman"},{"volume-title":"NVIDIA\u2019s Next Generation. CUDA Compute Architecture: Fermi","year":"2009","key":"ref20"},{"volume-title":"NVIDIA CUDA Programming Guide","year":"2011","key":"ref21"},{"volume-title":"PTX: Parallel Thread Execution ISA Version 2.3","year":"2011","key":"ref22"},{"volume-title":"CUDA C\/C++ SDK CODE Samples","year":"2011","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/359327.359336"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-8-474"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/1360612.1360617"},{"key":"ref27","doi-asserted-by":"crossref","DOI":"10.1145\/339647.339693","article-title":"Vector instruction set support for conditional operations","volume-title":"27th International Symposium on Computer Architecture (ISCA-27)","author":"Smith","year":"2000"},{"volume-title":"Advanced Compiler Design and Implementation","year":"1997","author":"Muchnick","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/1654059.1654082"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/1073204.1073211"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1177\/1094342011434814"}],"event":{"name":"2012 ACM\/IEEE 39th International Symposium on Computer Architecture (ISCA)","start":{"date-parts":[[2012,6,9]]},"location":"Portland, OR, USA","end":{"date-parts":[[2012,6,13]]}},"container-title":["2012 39th Annual International Symposium on Computer Architecture (ISCA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/6230820\/6236993\/06237006.pdf?arnumber=6237006","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T05:15:51Z","timestamp":1747804551000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/6237006\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,6]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/isca.2012.6237006","relation":{},"subject":[],"published":{"date-parts":[[2012,6]]}}}