{"title":"在高性能Prolog体系结构中裁剪功能单元和内存","authors":"A. Singhal, Y. Patt","doi":"10.1109/HICSS.1989.47179","DOIUrl":null,"url":null,"abstract":"A description is given of PLUM, a Prolog machine with multiple specialized functional units and memory ports that operate in parallel using data-driven control. Unification parallelism is utilized by multiple unification units. Bookkeeping operations, such as choicepoint and environment manipulation, are executed by special functional units in parallel with unification. The performance of the system is limited mainly by the time spent on unification operations. By using the parallelism among bookkeeping and unification operations, it is estimated that PLUM can achieve a speedup of at least a factor of 4 over the Berkeley PLM, assuming the same cycle time.<<ETX>>","PeriodicalId":300182,"journal":{"name":"[1989] Proceedings of the Twenty-Second Annual Hawaii International Conference on System Sciences. Volume 1: Architecture Track","volume":"64 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1989-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Tailoring functional units and memory in a high performance Prolog architecture\",\"authors\":\"A. Singhal, Y. Patt\",\"doi\":\"10.1109/HICSS.1989.47179\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"A description is given of PLUM, a Prolog machine with multiple specialized functional units and memory ports that operate in parallel using data-driven control. Unification parallelism is utilized by multiple unification units. Bookkeeping operations, such as choicepoint and environment manipulation, are executed by special functional units in parallel with unification. The performance of the system is limited mainly by the time spent on unification operations. By using the parallelism among bookkeeping and unification operations, it is estimated that PLUM can achieve a speedup of at least a factor of 4 over the Berkeley PLM, assuming the same cycle time.<<ETX>>\",\"PeriodicalId\":300182,\"journal\":{\"name\":\"[1989] Proceedings of the Twenty-Second Annual Hawaii International Conference on System Sciences. Volume 1: Architecture Track\",\"volume\":\"64 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1989-01-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"[1989] Proceedings of the Twenty-Second Annual Hawaii International Conference on System Sciences. Volume 1: Architecture Track\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/HICSS.1989.47179\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"[1989] Proceedings of the Twenty-Second Annual Hawaii International Conference on System Sciences. Volume 1: Architecture Track","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/HICSS.1989.47179","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Tailoring functional units and memory in a high performance Prolog architecture
A description is given of PLUM, a Prolog machine with multiple specialized functional units and memory ports that operate in parallel using data-driven control. Unification parallelism is utilized by multiple unification units. Bookkeeping operations, such as choicepoint and environment manipulation, are executed by special functional units in parallel with unification. The performance of the system is limited mainly by the time spent on unification operations. By using the parallelism among bookkeeping and unification operations, it is estimated that PLUM can achieve a speedup of at least a factor of 4 over the Berkeley PLM, assuming the same cycle time.<>
京公网安备 11010802042870号
京ICP备2023020795号-1
分享
![[1989] Proceedings of the Twenty-Second Annual Hawaii International Conference on System Sciences. Volume 1: Architecture Track](/Content/css/sci/img/zetp.jpg)
求助内容：
应助结果提醒方式：
扫码关注我们
