Sangyeun Cho, Socrates Demetriades, Shayne Evans, Lei Jin, Hyunjin Lee, Kiyeon Lee, Michael Moeng
{"title":"TPTS:一种快速多核处理器架构模拟的新框架","authors":"Sangyeun Cho, Socrates Demetriades, Shayne Evans, Lei Jin, Hyunjin Lee, Kiyeon Lee, Michael Moeng","doi":"10.1109/ICPP.2008.7","DOIUrl":null,"url":null,"abstract":"The slow speed of conventional execution-driven architecture simulators is a serious impediment to obtaining desirable research productivity. This paper proposes and evaluates a fast manycore processor simulation framework called two-phase trace-driven simulation (TPTS), which splits detailed timing simulation into a trace generation phase and a trace simulation phase. Much of the simulation overhead caused by uninteresting architectural events is only incurred once during the trace generation phase and can be omitted in the repeated trace-driven simulations. We design and implement tsim, an event-driven manycore processor simulator that models detailed memory hierarchy, interconnect, and coherence protocol models based on the proposed TPTS framework. By applying aggressive event filtering, tsim achieves an impressive simulation speed of 146 MIPS, when running 16-thread parallel applications.","PeriodicalId":388408,"journal":{"name":"2008 37th International Conference on Parallel Processing","volume":"350 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2008-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"37","resultStr":"{\"title\":\"TPTS: A Novel Framework for Very Fast Manycore Processor Architecture Simulation\",\"authors\":\"Sangyeun Cho, Socrates Demetriades, Shayne Evans, Lei Jin, Hyunjin Lee, Kiyeon Lee, Michael Moeng\",\"doi\":\"10.1109/ICPP.2008.7\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The slow speed of conventional execution-driven architecture simulators is a serious impediment to obtaining desirable research productivity. This paper proposes and evaluates a fast manycore processor simulation framework called two-phase trace-driven simulation (TPTS), which splits detailed timing simulation into a trace generation phase and a trace simulation phase. Much of the simulation overhead caused by uninteresting architectural events is only incurred once during the trace generation phase and can be omitted in the repeated trace-driven simulations. We design and implement tsim, an event-driven manycore processor simulator that models detailed memory hierarchy, interconnect, and coherence protocol models based on the proposed TPTS framework. By applying aggressive event filtering, tsim achieves an impressive simulation speed of 146 MIPS, when running 16-thread parallel applications.\",\"PeriodicalId\":388408,\"journal\":{\"name\":\"2008 37th International Conference on Parallel Processing\",\"volume\":\"350 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2008-09-09\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"37\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2008 37th International Conference on Parallel Processing\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICPP.2008.7\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2008 37th International Conference on Parallel Processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICPP.2008.7","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
TPTS: A Novel Framework for Very Fast Manycore Processor Architecture Simulation
The slow speed of conventional execution-driven architecture simulators is a serious impediment to obtaining desirable research productivity. This paper proposes and evaluates a fast manycore processor simulation framework called two-phase trace-driven simulation (TPTS), which splits detailed timing simulation into a trace generation phase and a trace simulation phase. Much of the simulation overhead caused by uninteresting architectural events is only incurred once during the trace generation phase and can be omitted in the repeated trace-driven simulations. We design and implement tsim, an event-driven manycore processor simulator that models detailed memory hierarchy, interconnect, and coherence protocol models based on the proposed TPTS framework. By applying aggressive event filtering, tsim achieves an impressive simulation speed of 146 MIPS, when running 16-thread parallel applications.