{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T02:04:10Z","timestamp":1729649050111,"version":"3.28.0"},"reference-count":41,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,10]]},"DOI":"10.1109\/iiswc.2017.8167754","type":"proceedings-article","created":{"date-parts":[[2017,12,7]],"date-time":"2017-12-07T18:28:15Z","timestamp":1512671295000},"page":"32-42","source":"Crossref","is-referenced-by-count":7,"title":["AutoMatch: An automated framework for relative performance estimation and workload distribution on heterogeneous HPC systems"],"prefix":"10.1109","author":[{"given":"Ahmed E.","family":"Helal","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wu-chun","family":"Feng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changhee","family":"Jung","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yasser Y.","family":"Hanafy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Commanalyzer: Automated estimation of communication cost on hpc clusters using sequential code","author":"helal","year":"2017","journal-title":"Tech Rep"},{"journal-title":"Finite Difference Methods in Heat Transfer","year":"1994","author":"ozisik","key":"ref38"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/2049662.2049663"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/166955.166974"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/1810479.1810519"},{"key":"ref37","article-title":"Minighost: a miniapp for exploring boundary exchange strategies using stencil computations in scientific parallel computing","author":"barrett","year":"2011","journal-title":"Tech Rep"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2012.300"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1137\/0910073"},{"journal-title":"Cache-conscious data structures design and implementation","year":"1999","author":"chilimbi","key":"ref34"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"451","DOI":"10.1145\/1816038.1816021","article-title":"Debunking the 100x gpu vs. cpu myth: An evaluation of throughput computing on cpu and gpu","author":"lee","year":"2010","journal-title":"Proceedings of the 37th Annual International Symposium on Computer Architecture"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/1555754.1555775"},{"key":"ref11","article-title":"Parboil: A revised benchmark suite for scientific and commercial throughput computing","volume":"127","author":"stratton","year":"2012","journal-title":"Center for Reliable and High-Performance Computing"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2016.10"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2014.07.003"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.2172\/1169830"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/48529.48535"},{"key":"ref16","first-page":"9","article-title":"Balance principles for algorithm-architecture codesign","author":"czechowski","year":"2011","journal-title":"Proceedings of the 3rd USENIX Conference on Hot Topic in Parallelism"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2010.5470477"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2010.5537722"},{"key":"ref19","first-page":"129","article-title":"Roofline model toolkit: A practical tool for architectural and program analysis","author":"lo","year":"2014","journal-title":"International Workshop on Performance Modeling Benchmarking and Simulation of High Performance Computer Systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2010.49"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2012.128"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/379605.379671"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2048066.2048108"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44898-5_24"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1147\/sj.92.0078"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2751205.2751220"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830780"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/186025.186041"},{"journal-title":"ExaScale Computing Study Technology Challenges in Achieving Exascale Systems","year":"2008","author":"bergman","key":"ref2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SBAC-PAD.2014.30"},{"journal-title":"Free Lunch Is Over A Fundamental Turn Towards Concurrency in Software","year":"2005","author":"sutter","key":"ref1"},{"key":"ref20","first-page":"23","article-title":"lmbench: portable tools for performance analysis","author":"mcvoy","year":"1996","journal-title":"Proceedings of the 1996 Annual Conference on USENIX Annual Technical Conference"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2744769.2744888"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2010.5452013"},{"key":"ref24","first-page":"75","author":"lattner","year":"2004","journal-title":"LLVM A Compilation Framework for Lifelong Program Analysis and Transformation"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2015.2509972"},{"journal-title":"Parallel Computer Architecture A Hardware\/Software Approach","year":"1996","author":"culler","key":"ref23"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/227234.227246"},{"journal-title":"Advanced Compiler Design Implementation","year":"1997","author":"muchnick","key":"ref25"}],"event":{"name":"2017 IEEE International Symposium on Workload Characterization (IISWC)","start":{"date-parts":[[2017,10,1]]},"location":"Seattle, WA","end":{"date-parts":[[2017,10,3]]}},"container-title":["2017 IEEE International Symposium on Workload Characterization (IISWC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8122074\/8167743\/08167754.pdf?arnumber=8167754","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,7]],"date-time":"2019-10-07T13:37:33Z","timestamp":1570455453000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8167754\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,10]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/iiswc.2017.8167754","relation":{},"subject":[],"published":{"date-parts":[[2017,10]]}}}