{"title":"用于多集群应用加速器的自定义本地存储器的自动合成","authors":"M. Kudlur, Kevin Fan, Michael L. Chu, S. Mahlke","doi":"10.1109/ASAP.2004.10030","DOIUrl":null,"url":null,"abstract":"Distributed local memories, or scratchpads, have been shown to effectively reduce cost and power consumption of application-specific accelerators while maintaining performance. The design of the local memory organization must take several factors into account, including the memory bandwidth and size requirements of the program and the distribution of program data among the memories. In addition, when register structures and function units in the accelerator are clustered, the effects of intercluster communication should be taken into account. This work proposes a technique to synthesize the local memory architecture of a clustered accelerator using a phase-ordered approach. First, the dataflow graph is pre-partitioned to define a performance-centric grouping of the operations. Second, memory synthesis is performed by combining multiple data structures into a set of physical memories that minimizes cost while maintaining a performance threshold. Finally, post-partitioning is performed to determine the final assignment of operations to clusters given the memory organization. Results show that customization reduces memory cost from 2% to 59% over a naive scheme that utilizes one physical memory per program data structure. Further, pre-partitioning is shown to reduce the intercluster communication required to achieve a fixed performance.","PeriodicalId":120245,"journal":{"name":"Proceedings. 15th IEEE International Conference on Application-Specific Systems, Architectures and Processors, 2004.","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2004-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"7","resultStr":"{\"title\":\"Automatic synthesis of customized local memories for multicluster application accelerators\",\"authors\":\"M. Kudlur, Kevin Fan, Michael L. Chu, S. Mahlke\",\"doi\":\"10.1109/ASAP.2004.10030\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Distributed local memories, or scratchpads, have been shown to effectively reduce cost and power consumption of application-specific accelerators while maintaining performance. The design of the local memory organization must take several factors into account, including the memory bandwidth and size requirements of the program and the distribution of program data among the memories. In addition, when register structures and function units in the accelerator are clustered, the effects of intercluster communication should be taken into account. This work proposes a technique to synthesize the local memory architecture of a clustered accelerator using a phase-ordered approach. First, the dataflow graph is pre-partitioned to define a performance-centric grouping of the operations. Second, memory synthesis is performed by combining multiple data structures into a set of physical memories that minimizes cost while maintaining a performance threshold. Finally, post-partitioning is performed to determine the final assignment of operations to clusters given the memory organization. Results show that customization reduces memory cost from 2% to 59% over a naive scheme that utilizes one physical memory per program data structure. Further, pre-partitioning is shown to reduce the intercluster communication required to achieve a fixed performance.\",\"PeriodicalId\":120245,\"journal\":{\"name\":\"Proceedings. 15th IEEE International Conference on Application-Specific Systems, Architectures and Processors, 2004.\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2004-09-27\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"7\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings. 15th IEEE International Conference on Application-Specific Systems, Architectures and Processors, 2004.\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ASAP.2004.10030\",\"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. 15th IEEE International Conference on Application-Specific Systems, Architectures and Processors, 2004.","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ASAP.2004.10030","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Automatic synthesis of customized local memories for multicluster application accelerators
Distributed local memories, or scratchpads, have been shown to effectively reduce cost and power consumption of application-specific accelerators while maintaining performance. The design of the local memory organization must take several factors into account, including the memory bandwidth and size requirements of the program and the distribution of program data among the memories. In addition, when register structures and function units in the accelerator are clustered, the effects of intercluster communication should be taken into account. This work proposes a technique to synthesize the local memory architecture of a clustered accelerator using a phase-ordered approach. First, the dataflow graph is pre-partitioned to define a performance-centric grouping of the operations. Second, memory synthesis is performed by combining multiple data structures into a set of physical memories that minimizes cost while maintaining a performance threshold. Finally, post-partitioning is performed to determine the final assignment of operations to clusters given the memory organization. Results show that customization reduces memory cost from 2% to 59% over a naive scheme that utilizes one physical memory per program data structure. Further, pre-partitioning is shown to reduce the intercluster communication required to achieve a fixed performance.