{"title":"自定时数据路径中块级松弛的完全综合方法","authors":"W. Toms, D. A. Edwards","doi":"10.1109/ACSD.2010.29","DOIUrl":null,"url":null,"abstract":"Self-timed circuits present an attractive solution to the problem of process variation. However, implementing self-timed combinational logic can be complex and expensive. This paper presents a complete synthesis flow that generates self-timed combinational networks from conventional Boolean networks. The Boolean network is partitioned into small function blocks which are then synthesised using self-timed techniques. The procedure employs relaxation optimisations to distribute the overheads associated with self-timed networks between function-blocks. Relaxation is incorporated into the function block synthesis procedures, meaning the optimisations can be applied at a much finer granularity than previously possible. The new techniques are demonstrated on a range of benchmarks showing average reduction of 5% in area, 26% in latency and 48% in energy over gate-level relaxation techniques and 17% in area, 8% in latency and 20% in energy consumption over other block-level relaxation techniques.","PeriodicalId":169191,"journal":{"name":"2010 10th International Conference on Application of Concurrency to System Design","volume":"19 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2010-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"11","resultStr":"{\"title\":\"A Complete Synthesis Method for Block-Level Relaxation in Self-Timed Datapaths\",\"authors\":\"W. Toms, D. A. Edwards\",\"doi\":\"10.1109/ACSD.2010.29\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Self-timed circuits present an attractive solution to the problem of process variation. However, implementing self-timed combinational logic can be complex and expensive. This paper presents a complete synthesis flow that generates self-timed combinational networks from conventional Boolean networks. The Boolean network is partitioned into small function blocks which are then synthesised using self-timed techniques. The procedure employs relaxation optimisations to distribute the overheads associated with self-timed networks between function-blocks. Relaxation is incorporated into the function block synthesis procedures, meaning the optimisations can be applied at a much finer granularity than previously possible. The new techniques are demonstrated on a range of benchmarks showing average reduction of 5% in area, 26% in latency and 48% in energy over gate-level relaxation techniques and 17% in area, 8% in latency and 20% in energy consumption over other block-level relaxation techniques.\",\"PeriodicalId\":169191,\"journal\":{\"name\":\"2010 10th International Conference on Application of Concurrency to System Design\",\"volume\":\"19 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2010-06-21\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"11\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2010 10th International Conference on Application of Concurrency to System Design\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ACSD.2010.29\",\"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 10th International Conference on Application of Concurrency to System Design","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ACSD.2010.29","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
A Complete Synthesis Method for Block-Level Relaxation in Self-Timed Datapaths
Self-timed circuits present an attractive solution to the problem of process variation. However, implementing self-timed combinational logic can be complex and expensive. This paper presents a complete synthesis flow that generates self-timed combinational networks from conventional Boolean networks. The Boolean network is partitioned into small function blocks which are then synthesised using self-timed techniques. The procedure employs relaxation optimisations to distribute the overheads associated with self-timed networks between function-blocks. Relaxation is incorporated into the function block synthesis procedures, meaning the optimisations can be applied at a much finer granularity than previously possible. The new techniques are demonstrated on a range of benchmarks showing average reduction of 5% in area, 26% in latency and 48% in energy over gate-level relaxation techniques and 17% in area, 8% in latency and 20% in energy consumption over other block-level relaxation techniques.