Wei Huang, K. Skadron, S. Gurumurthi, R. J. Ribando, M. Stan
{"title":"探讨热对多核处理器性能的影响","authors":"Wei Huang, K. Skadron, S. Gurumurthi, R. J. Ribando, M. Stan","doi":"10.1109/STHERM.2010.5444293","DOIUrl":null,"url":null,"abstract":"Performance of processors with many simple parallel cores is limited by the serial part of the workload, requiring an asymmetric core organization with one or more aggressive “primary” cores for better serial performance. A primary core introduces power-hungry microarchitectural structures and usually causes severe local hot spots. This paper explores the thermal impact on manycore processor architecture and evaluates its performance. Preliminary results show that thermal constraints reduce performance as expected, but also make performance almost insensitive to the complexity of the primary core across a diverse degrees of parallelism, which greatly reduces design complexity.","PeriodicalId":111882,"journal":{"name":"2010 26th Annual IEEE Semiconductor Thermal Measurement and Management Symposium (SEMI-THERM)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2010-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"26","resultStr":"{\"title\":\"Exploring the thermal impact on manycore processor performance\",\"authors\":\"Wei Huang, K. Skadron, S. Gurumurthi, R. J. Ribando, M. Stan\",\"doi\":\"10.1109/STHERM.2010.5444293\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Performance of processors with many simple parallel cores is limited by the serial part of the workload, requiring an asymmetric core organization with one or more aggressive “primary” cores for better serial performance. A primary core introduces power-hungry microarchitectural structures and usually causes severe local hot spots. This paper explores the thermal impact on manycore processor architecture and evaluates its performance. Preliminary results show that thermal constraints reduce performance as expected, but also make performance almost insensitive to the complexity of the primary core across a diverse degrees of parallelism, which greatly reduces design complexity.\",\"PeriodicalId\":111882,\"journal\":{\"name\":\"2010 26th Annual IEEE Semiconductor Thermal Measurement and Management Symposium (SEMI-THERM)\",\"volume\":\"1 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2010-04-08\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"26\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2010 26th Annual IEEE Semiconductor Thermal Measurement and Management Symposium (SEMI-THERM)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/STHERM.2010.5444293\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2010 26th Annual IEEE Semiconductor Thermal Measurement and Management Symposium (SEMI-THERM)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/STHERM.2010.5444293","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Exploring the thermal impact on manycore processor performance
Performance of processors with many simple parallel cores is limited by the serial part of the workload, requiring an asymmetric core organization with one or more aggressive “primary” cores for better serial performance. A primary core introduces power-hungry microarchitectural structures and usually causes severe local hot spots. This paper explores the thermal impact on manycore processor architecture and evaluates its performance. Preliminary results show that thermal constraints reduce performance as expected, but also make performance almost insensitive to the complexity of the primary core across a diverse degrees of parallelism, which greatly reduces design complexity.