{"title":"GPGPU微架构参数的未来","authors":"C. Nugteren, Gert-Jan van den Braak, H. Corporaal","doi":"10.7873/DATE.2013.089","DOIUrl":null,"url":null,"abstract":"As graphics processing units (GPUs) are becoming increasingly popular for general purpose workloads (GPGPU), the question arises how such processors will evolve architecturally in the near future. In this work, we identify and discuss trade-offs for three GPU architecture parameters: active thread count, compute-memory ratio, and cluster and warp sizing. For each parameter, we propose changes to improve GPU design, keeping in mind trends such as dark silicon and the increasing popularity of GPGPU architectures. A key-enabler is dynamism and workload-adaptiveness, enabling among others: dynamic register file sizing, latency aware scheduling, roofline-aware DVFS, run-time cluster fusion, and dynamic warp sizing.","PeriodicalId":6310,"journal":{"name":"2013 Design, Automation & Test in Europe Conference & Exhibition (DATE)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2013-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"6","resultStr":"{\"title\":\"Future of GPGPU micro-architectural parameters\",\"authors\":\"C. Nugteren, Gert-Jan van den Braak, H. Corporaal\",\"doi\":\"10.7873/DATE.2013.089\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"As graphics processing units (GPUs) are becoming increasingly popular for general purpose workloads (GPGPU), the question arises how such processors will evolve architecturally in the near future. In this work, we identify and discuss trade-offs for three GPU architecture parameters: active thread count, compute-memory ratio, and cluster and warp sizing. For each parameter, we propose changes to improve GPU design, keeping in mind trends such as dark silicon and the increasing popularity of GPGPU architectures. A key-enabler is dynamism and workload-adaptiveness, enabling among others: dynamic register file sizing, latency aware scheduling, roofline-aware DVFS, run-time cluster fusion, and dynamic warp sizing.\",\"PeriodicalId\":6310,\"journal\":{\"name\":\"2013 Design, Automation & Test in Europe Conference & Exhibition (DATE)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2013-03-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"6\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2013 Design, Automation & Test in Europe Conference & Exhibition (DATE)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.7873/DATE.2013.089\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2013 Design, Automation & Test in Europe Conference & Exhibition (DATE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.7873/DATE.2013.089","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
As graphics processing units (GPUs) are becoming increasingly popular for general purpose workloads (GPGPU), the question arises how such processors will evolve architecturally in the near future. In this work, we identify and discuss trade-offs for three GPU architecture parameters: active thread count, compute-memory ratio, and cluster and warp sizing. For each parameter, we propose changes to improve GPU design, keeping in mind trends such as dark silicon and the increasing popularity of GPGPU architectures. A key-enabler is dynamism and workload-adaptiveness, enabling among others: dynamic register file sizing, latency aware scheduling, roofline-aware DVFS, run-time cluster fusion, and dynamic warp sizing.