Bryan Donyanavard, Amir Mahdi Hosseini Monazzah, T. Mück, N. Dutt
{"title":"探索HMP核心类型中的快存储器和慢存储器:正在进行中","authors":"Bryan Donyanavard, Amir Mahdi Hosseini Monazzah, T. Mück, N. Dutt","doi":"10.1145/3125502.3125545","DOIUrl":null,"url":null,"abstract":"Studies have shown memory and computational needs vary independently across applications. Recent work has explored using hybrid memory technology (SRAM+NVM) in on-chip memories of multicore processors (CMPs) to support the varied needs of diverse workloads. Such works suggest architectural modifications that require supplemental management in the memory hierarchy. Instead, we propose to deploy hybrid memory in a manner that integrates seamlessly with the existing heterogeneous multicore (HMP) architectural model, and therefore does not require any architectural modification, simply the integration of different memory technologies on-chip. We evaluate platforms with a combination of fast (SRAM cache) and slow (STT-MRAM cache) core-types for mobile workloads.","PeriodicalId":350509,"journal":{"name":"Proceedings of the Twelfth IEEE/ACM/IFIP International Conference on Hardware/Software Codesign and System Synthesis Companion","volume":"29 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Exploring fast and slow memories in HMP core types: work-in-progress\",\"authors\":\"Bryan Donyanavard, Amir Mahdi Hosseini Monazzah, T. Mück, N. Dutt\",\"doi\":\"10.1145/3125502.3125545\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Studies have shown memory and computational needs vary independently across applications. Recent work has explored using hybrid memory technology (SRAM+NVM) in on-chip memories of multicore processors (CMPs) to support the varied needs of diverse workloads. Such works suggest architectural modifications that require supplemental management in the memory hierarchy. Instead, we propose to deploy hybrid memory in a manner that integrates seamlessly with the existing heterogeneous multicore (HMP) architectural model, and therefore does not require any architectural modification, simply the integration of different memory technologies on-chip. We evaluate platforms with a combination of fast (SRAM cache) and slow (STT-MRAM cache) core-types for mobile workloads.\",\"PeriodicalId\":350509,\"journal\":{\"name\":\"Proceedings of the Twelfth IEEE/ACM/IFIP International Conference on Hardware/Software Codesign and System Synthesis Companion\",\"volume\":\"29 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2017-10-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the Twelfth IEEE/ACM/IFIP International Conference on Hardware/Software Codesign and System Synthesis Companion\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3125502.3125545\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the Twelfth IEEE/ACM/IFIP International Conference on Hardware/Software Codesign and System Synthesis Companion","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3125502.3125545","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Exploring fast and slow memories in HMP core types: work-in-progress
Studies have shown memory and computational needs vary independently across applications. Recent work has explored using hybrid memory technology (SRAM+NVM) in on-chip memories of multicore processors (CMPs) to support the varied needs of diverse workloads. Such works suggest architectural modifications that require supplemental management in the memory hierarchy. Instead, we propose to deploy hybrid memory in a manner that integrates seamlessly with the existing heterogeneous multicore (HMP) architectural model, and therefore does not require any architectural modification, simply the integration of different memory technologies on-chip. We evaluate platforms with a combination of fast (SRAM cache) and slow (STT-MRAM cache) core-types for mobile workloads.