{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T08:27:55Z","timestamp":1725784075919},"reference-count":57,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"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":[[2019,11]]},"DOI":"10.1109\/iiswc47752.2019.9041977","type":"proceedings-article","created":{"date-parts":[[2020,3,20]],"date-time":"2020-03-20T08:55:14Z","timestamp":1584694514000},"page":"243-248","source":"Crossref","is-referenced-by-count":4,"title":["Optimizing GPU Cache Policies for MI Workloads"],"prefix":"10.1109","author":[{"given":"Johnathan","family":"Alsop","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthew D.","family":"Sinclair","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Srikant","family":"Bharadwaj","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexandru","family":"Dutu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anthony","family":"Gutierrez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Onur","family":"Kayiran","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"LeBeane","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brandon","family":"Potter","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sooraj","family":"Puthoor","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xianwei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tsung Tai","family":"Yeh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bradford M.","family":"Beckmann","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"951","article-title":"DeepCPU: Serving RNN-based Deep Learning Models 10x Faster","author":"zhang","year":"0","journal-title":"2018 USENIX Annual Technical Conference (Usenix ATC)"},{"journal-title":"AMD Graphics Core Next (GCN) Architecture","year":"2012","key":"ref38"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080254"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00017"},{"journal-title":"Graphics Core Next Arcitecture Generation 3","year":"2016","key":"ref31"},{"journal-title":"Radeon's next-generation vega architecture","year":"2017","key":"ref30"},{"journal-title":"Inside volta The world's most advanced data center gpu","year":"2017","author":"durant","key":"ref37"},{"key":"ref36","article-title":"Proteus: Exploiting Numerical Precision Variability in Deep Neural Networks","author":"judd","year":"0","journal-title":"Proceedings of the 2016 International Conference on Supercomputing"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123982"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.30"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1145\/2370816.2370865","article-title":"Multi2Sim: A Simulation Framework for CPU-GPU Computing","author":"rafael ubal","year":"2012","journal-title":"In International Conference on Parallel Architectures and Compilation Techniques (PACT)"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.40"},{"journal-title":"MIOpen An open source library for deep learning primitives","year":"2019","author":"khan","key":"ref29"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.1145\/2024716.2024718","article-title":"The gem5 Simulator","author":"binkert","year":"2011","journal-title":"ACM SIGARCH Computer Architecture News"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC47752.2019.9041977"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080215"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001138"},{"key":"ref21","first-page":"561","article-title":"Understanding and Optimizing Asynchronous Low-Precision Stochastic Gradient Descent","author":"de sa","year":"2017","journal-title":"Proceedings of the 44th Annual International Symposium on Computer Architecture ISCA ‘17"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.12"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001163"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00059"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001165"},{"key":"ref50","first-page":"457","article-title":"Heterogeneous system coherence for integrated CPU -GPU systems","author":"jason","year":"0","journal-title":"Proceedings of the 46th Annual IEEE\/ACM International Symposium on Microarchitecture"},{"key":"ref51","first-page":"1","article-title":"Fusion coherence: scalable cache coherence for heterogeneous kilo-core system.","author":"pei","year":"2014","journal-title":"Advanced Computer Architecture"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807606"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/2751205.2751237"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00027"},{"key":"ref54","first-page":"261","article-title":"Spandex: a flexible interface for efficient heterogeneous coherence","author":"johnathan","year":"0","journal-title":"Proc of the 45th International Symposium on Computer Architecture"},{"key":"ref53","first-page":"26","article-title":"Lazy release consistency for GPUs","author":"johnathan","year":"0","journal-title":"49th IEEE\/ACM Int Symp Microarchitecture"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/2694344.2694350"},{"journal-title":"HCC An open source C++ compiler for heterogeneous devices","year":"0","key":"ref10"},{"key":"ref11","article-title":"HCC: A C++ Compiler for Heterogenous Computing","author":"sander","year":"2015","journal-title":"Tech Report"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/2716282.2716283"},{"journal-title":"HIP Heterogeneous-computing Interface for Portability","year":"0","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00060"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00070"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00012"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080244"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080254"},{"key":"ref19","first-page":"535","article-title":"Maximizing CNN Accelerator Efficiency Through Resource Partitioning","author":"shen","year":"0","journal-title":"Proceedings of Annual International Symposium on Computer Architecture (ISCA)"},{"key":"ref4","article-title":"AMD gem5 APU simulator: Modeling GPU s Using the Machine ISA","author":"gutierrez","year":"0","journal-title":"Tutorial at International Symposium on Computer Architecture"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00058"},{"journal-title":"Deepbench","year":"2016","author":"narang","key":"ref6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3038228.3038239"},{"journal-title":"MIOpen-benchmarks","year":"2017","author":"flick","key":"ref8"},{"journal-title":"An update to DeepBench with a focus on deep learning inference","year":"2017","author":"narang","key":"ref7"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2013.6522351"},{"journal-title":"The unreasonable effectiveness of recurrent neural networks","year":"2015","author":"karpathy","key":"ref9"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2019.00028"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322230"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2014.6835930"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830821"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/1815961.1815972"},{"key":"ref41","article-title":"Eager writeback - a technique for improving bandwidth utilization","author":"lee","year":"0","journal-title":"Proc of the IEEE\/ACM International Symposium on Microarchitecture (MICRO)"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2014.6853204"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/2541228.2555300"}],"event":{"name":"2019 IEEE International Symposium on Workload Characterization (IISWC)","start":{"date-parts":[[2019,11,3]]},"location":"Orlando, FL, USA","end":{"date-parts":[[2019,11,5]]}},"container-title":["2019 IEEE International Symposium on Workload Characterization (IISWC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9027808\/9041927\/09041977.pdf?arnumber=9041977","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:19:26Z","timestamp":1657855166000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9041977\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/iiswc47752.2019.9041977","relation":{},"subject":[],"published":{"date-parts":[[2019,11]]}}}