{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T07:14:02Z","timestamp":1725693242786},"reference-count":43,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,10]]},"DOI":"10.1109\/micro.2016.7783760","type":"proceedings-article","created":{"date-parts":[[2016,12,19]],"date-time":"2016-12-19T17:11:05Z","timestamp":1482167465000},"page":"1-12","source":"Crossref","is-referenced-by-count":20,"title":["Improving bank-level parallelism for irregular applications"],"prefix":"10.1109","author":[{"given":"Xulong","family":"Tang","sequence":"first","affiliation":[]},{"given":"Mahmut","family":"Kandemir","sequence":"additional","affiliation":[]},{"given":"Praveen","family":"Yedlapalli","sequence":"additional","affiliation":[]},{"given":"Jagadish","family":"Kotra","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","article-title":"Cooperative Paral-lelization","author":"yedlapalli","year":"2011","journal-title":"Proceedings of the International Conference on Computer-Aided Design"},{"key":"ref38","article-title":"How Much Parallelism is There in Irregular Applications?","author":"kulkarni","year":"2009","journal-title":"Proceedings of the 14th ACM SIGPLAN Symposium on Principles and Practice of Parallel Prozrammine"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/301618.301670"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/1111037.1111040"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/503272.503283"},{"key":"ref30","article-title":"Meeting midway: Improving cmp performance with memory-side prefetching","author":"yedlapalli","year":"2013","journal-title":"Proceedings of the 22nd International Conference on Parallel Architectures and Compilation Techniques"},{"key":"ref37","article-title":"Automatically enhancing locality for tree traver-sals with traversal splicing","author":"jo","year":"2012","journal-title":"Proc Conf Object-Oriented Programming Systems Languages and Applications"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/781131.781142"},{"key":"ref35","article-title":"Localizing non-affine array ref-erences","author":"mitchell","year":"1999","journal-title":"Proc Parallel Architectures and Compilation Techniques (PACT)"},{"key":"ref34","article-title":"Improving Memory Hierarchy Performance for Irregular Applications Using Data and Computation Reorderings","author":"mellor","year":"2001","journal-title":"International Journal of Parallel Programming"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.1999.809452"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/12.902753"},{"year":"2014","key":"ref11","article-title":"Intel Xeon Processor E5 v2 and E7 v2 Product Families Uncore Performance Monitoring Reference Manual"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2004.1281665"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1021\/ci00037a006"},{"article-title":"HPCG: Toward a New Metric for Ranking High Performance Computing Systems","year":"2013","author":"dongarra","key":"ref14"},{"year":"0","key":"ref15","article-title":"Minife"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.1007\/3-540-44587-0_1","article-title":"SPEComp: A New Benchmark Suite for Measuring Parallel Computer Performance","author":"aslot","year":"2001"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IFITA.2009.339"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.1145\/2024716.2024718","article-title":"The Gem5 Simulator","author":"binkert","year":"2011","journal-title":"SIGARCH Comout Archit News"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2628071.2628082"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2540708.2540730"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1669112.1669155"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2006.5"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2591635.2591646"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.1145\/1394608.1382128","article-title":"Parallelism-aware batch scheduling: Enhancing both performance and fairness of shared dram systems","author":"mutlu","year":"2008","journal-title":"SIGARCH Comput Archit News"},{"key":"ref29","article-title":"Adaptive history-based memory schedulers","author":"hur","year":"2004","journal-title":"Proceedings of the 37th annual IEEE\/ACM International Symposium on Microarchitecture"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.1145\/2366231.2337202","article-title":"A Case for Ex-ploiting Subarray-level Parallelism (SALP) in DRAM","author":"kim","year":"2012","journal-title":"Proceedings of the 39th International Symposium on Computer Architecture"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2004.22"},{"key":"ref7","doi-asserted-by":"crossref","DOI":"10.1006\/jpdc.1994.1104","article-title":"Communication Opti-mizations for Irregular Scientific Computations on Distributed Memory Architectures","author":"das","year":"1994","journal-title":"J Parallel Distrib Comput"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2682585"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/342001.339668"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2540708.2540734"},{"key":"ref20","article-title":"Exploiting Locality for Irregular Scientific Codes","author":"han","year":"2006","journal-title":"IEEE Trans Parallel Distrib Syst"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2155620.2155663"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2010.51"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45574-4_12"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.34"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/335231.335238"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2370816.2370869"},{"key":"ref26","article-title":"A Memory-Level Parallelism Aware Fetch Policy for SMT Processors","author":"eyerman","year":"2007","journal-title":"Proceedings of the 13th International Symposium on Higli Performance ComputerArchitecture"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/996841.996872"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.1145\/1028176.1006708","article-title":"Micro architecture optimizations for exploiting memory-level parallelism","author":"chou","year":"2004","journal-title":"Proceedings of the 31st Annual International Symposium on Computer Architecture"}],"event":{"name":"2016 49th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO)","start":{"date-parts":[[2016,10,15]]},"location":"Taipei, Taiwan","end":{"date-parts":[[2016,10,19]]}},"container-title":["2016 49th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7777315\/7783693\/07783760.pdf?arnumber=7783760","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,16]],"date-time":"2019-09-16T14:51:43Z","timestamp":1568645503000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7783760\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,10]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/micro.2016.7783760","relation":{},"subject":[],"published":{"date-parts":[[2016,10]]}}}