{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T10:26:48Z","timestamp":1725791208486},"reference-count":14,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,9]]},"DOI":"10.1109\/cahpc.2018.8645848","type":"proceedings-article","created":{"date-parts":[[2019,2,21]],"date-time":"2019-02-21T23:19:26Z","timestamp":1550791166000},"page":"442-449","source":"Crossref","is-referenced-by-count":2,"title":["Automated GPU Grid Geometry Selection for OPENMP Kernels"],"prefix":"10.1109","author":[{"given":"Taylor","family":"Lloyd","sequence":"first","affiliation":[]},{"given":"Artem","family":"Chikin","sequence":"additional","affiliation":[]},{"given":"Sanket","family":"Kedia","sequence":"additional","affiliation":[]},{"given":"Dhruv","family":"Jain","sequence":"additional","affiliation":[]},{"given":"Jose Nelson","family":"Amaral","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICPC.2010.36"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1542476.1542496"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2808091.2808092"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.1145\/1504176.1504189","article-title":"Mapping parallelism to multicores: A machine learning based approach","author":"wang","year":"2009","journal-title":"Principles and Practice of Parallel Programming (PPoPP)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2014.6835939"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/99.660313"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1454115.1454122"},{"journal-title":"SPEC ACCEL A Standard Application Suite for Measuring Hardware Accelerator Performance","year":"2015","author":"juckeland","key":"ref6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/InPar.2012.6339595"},{"journal-title":"Nvidia NVIDIA TESLA V100 GPU ARCHITECTURE","year":"0","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2010.36"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2833157.2833161"},{"key":"ref9","article-title":"Portable mapping of data parallel programs to opencl for heterogeneous systems","author":"o'boyle","year":"2013","journal-title":"Proceedings of Code Generation and Optimization (CGO)"}],"event":{"name":"2018 30th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD)","start":{"date-parts":[[2018,9,24]]},"location":"Lyon, France","end":{"date-parts":[[2018,9,27]]}},"container-title":["2018 30th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8638685\/8645847\/08645848.pdf?arnumber=8645848","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:42:33Z","timestamp":1721004153000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8645848\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,9]]},"references-count":14,"URL":"https:\/\/doi.org\/10.1109\/cahpc.2018.8645848","relation":{},"subject":[],"published":{"date-parts":[[2018,9]]}}}