Yuichiro Miyaoka, N. Togawa, M. Yanagisawa, T. Ohtsuki
{"title":"具有异构数据路径的应用程序特定处理器的协同合成算法","authors":"Yuichiro Miyaoka, N. Togawa, M. Yanagisawa, T. Ohtsuki","doi":"10.1109/ASPDAC.2004.1337575","DOIUrl":null,"url":null,"abstract":"We propose a hardware/software cosynthesis algorithm for processors with heterogeneous registers. Given a CDFG corresponding to an application program and a timing constraint, the algorithm generates a processor configuration minimizing area of the processor and an assembly code on the processor. First, the algorithm configures a datapath which can execute several DFG nodes with data dependency at one cycle. The datapath can execute the application program at the least number of cycles. The branch and bound algorithm is applied and all the number of functional units and memory banks are tried. For an assumed number of functional units and memory banks, an appropriate number of heterogeneous registers and connections to functional units and registers are explored. The experimental results show effectiveness and efficiency of the algorithm.","PeriodicalId":426349,"journal":{"name":"ASP-DAC 2004: Asia and South Pacific Design Automation Conference 2004 (IEEE Cat. No.04EX753)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2004-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A cosynthesis algorithm for application specific processors with heterogeneous datapaths\",\"authors\":\"Yuichiro Miyaoka, N. Togawa, M. Yanagisawa, T. Ohtsuki\",\"doi\":\"10.1109/ASPDAC.2004.1337575\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We propose a hardware/software cosynthesis algorithm for processors with heterogeneous registers. Given a CDFG corresponding to an application program and a timing constraint, the algorithm generates a processor configuration minimizing area of the processor and an assembly code on the processor. First, the algorithm configures a datapath which can execute several DFG nodes with data dependency at one cycle. The datapath can execute the application program at the least number of cycles. The branch and bound algorithm is applied and all the number of functional units and memory banks are tried. For an assumed number of functional units and memory banks, an appropriate number of heterogeneous registers and connections to functional units and registers are explored. The experimental results show effectiveness and efficiency of the algorithm.\",\"PeriodicalId\":426349,\"journal\":{\"name\":\"ASP-DAC 2004: Asia and South Pacific Design Automation Conference 2004 (IEEE Cat. No.04EX753)\",\"volume\":\"3 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2004-01-27\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"ASP-DAC 2004: Asia and South Pacific Design Automation Conference 2004 (IEEE Cat. No.04EX753)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ASPDAC.2004.1337575\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"ASP-DAC 2004: Asia and South Pacific Design Automation Conference 2004 (IEEE Cat. No.04EX753)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ASPDAC.2004.1337575","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
A cosynthesis algorithm for application specific processors with heterogeneous datapaths
We propose a hardware/software cosynthesis algorithm for processors with heterogeneous registers. Given a CDFG corresponding to an application program and a timing constraint, the algorithm generates a processor configuration minimizing area of the processor and an assembly code on the processor. First, the algorithm configures a datapath which can execute several DFG nodes with data dependency at one cycle. The datapath can execute the application program at the least number of cycles. The branch and bound algorithm is applied and all the number of functional units and memory banks are tried. For an assumed number of functional units and memory banks, an appropriate number of heterogeneous registers and connections to functional units and registers are explored. The experimental results show effectiveness and efficiency of the algorithm.