{"title":"用于3D图形物理引擎的浮点重构阵列处理器","authors":"Hoonmo Yang","doi":"10.1109/ASPDAC.2008.4483956","DOIUrl":null,"url":null,"abstract":"We implemented an RTL model of the proposed RA and perform simulation in RealView coverification environment by executing examples using physics engine. We discovered if the physics engine part is accelerated by RA, the workloads run over 20 times faster than the pure software without FPU and over 4 times faster than the pure software with FPU. If codes are well partitioned and optimized for the proposed RA, which now remains for future study, even more improvement can be expected.","PeriodicalId":277556,"journal":{"name":"2008 Asia and South Pacific Design Automation Conference","volume":"27 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2008-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"Floating-point reconfiguration array processor for 3D graphics physics engine\",\"authors\":\"Hoonmo Yang\",\"doi\":\"10.1109/ASPDAC.2008.4483956\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We implemented an RTL model of the proposed RA and perform simulation in RealView coverification environment by executing examples using physics engine. We discovered if the physics engine part is accelerated by RA, the workloads run over 20 times faster than the pure software without FPU and over 4 times faster than the pure software with FPU. If codes are well partitioned and optimized for the proposed RA, which now remains for future study, even more improvement can be expected.\",\"PeriodicalId\":277556,\"journal\":{\"name\":\"2008 Asia and South Pacific Design Automation Conference\",\"volume\":\"27 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2008-01-21\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2008 Asia and South Pacific Design Automation Conference\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ASPDAC.2008.4483956\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2008 Asia and South Pacific Design Automation Conference","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ASPDAC.2008.4483956","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Floating-point reconfiguration array processor for 3D graphics physics engine
We implemented an RTL model of the proposed RA and perform simulation in RealView coverification environment by executing examples using physics engine. We discovered if the physics engine part is accelerated by RA, the workloads run over 20 times faster than the pure software without FPU and over 4 times faster than the pure software with FPU. If codes are well partitioned and optimized for the proposed RA, which now remains for future study, even more improvement can be expected.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
