FLOVA:一个带有SIMD指令和光照加速单元的四问题VLIW几何处理器

Proceedings of the IEEE 2000 Custom Integrated Circuits Conference (Cat. No.00CH37044) Pub Date : 2000-05-21 DOI:10.1109/CICC.2000.852728

S. Nam, Byoung-Woon Kim, Y. Im, Young-Su Kwon, Jun-Hee Lee, Young-Wook Cheon, Sung-Jae Byun, Dae-Hyun Lee, C. Kyung

{"title":"FLOVA:一个带有SIMD指令和光照加速单元的四问题VLIW几何处理器","authors":"S. Nam, Byoung-Woon Kim, Y. Im, Young-Su Kwon, Jun-Hee Lee, Young-Wook Cheon, Sung-Jae Byun, Dae-Hyun Lee, C. Kyung","doi":"10.1109/CICC.2000.852728","DOIUrl":null,"url":null,"abstract":"This paper describes a VLIW (very long instruction word) geometry processor called FLOVA (FLOating-Point VLIW Architecture) which was developed to accelerate the geometry stage of 3D graphics. FLOVA executes four instructions in one cycle and supports 136 instructions including 35 SIMD (single instruction multiple data) instructions to accelerate the geometry stage. Special features to accelerate transformation and lighting operations in 3D graphics geometry stage are described. FLOVA can calculate the power value of two floating-point numbers in only four clock cycles with a negligible loss of accuracy, compared to over 150 clock cycles in other processors.","PeriodicalId":20702,"journal":{"name":"Proceedings of the IEEE 2000 Custom Integrated Circuits Conference (Cat. No.00CH37044)","volume":"30 1","pages":"551-554"},"PeriodicalIF":0.0000,"publicationDate":"2000-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"FLOVA: A four-issue VLIW geometry processor with SIMD instructions and lighting acceleration unit\",\"authors\":\"S. Nam, Byoung-Woon Kim, Y. Im, Young-Su Kwon, Jun-Hee Lee, Young-Wook Cheon, Sung-Jae Byun, Dae-Hyun Lee, C. Kyung\",\"doi\":\"10.1109/CICC.2000.852728\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper describes a VLIW (very long instruction word) geometry processor called FLOVA (FLOating-Point VLIW Architecture) which was developed to accelerate the geometry stage of 3D graphics. FLOVA executes four instructions in one cycle and supports 136 instructions including 35 SIMD (single instruction multiple data) instructions to accelerate the geometry stage. Special features to accelerate transformation and lighting operations in 3D graphics geometry stage are described. FLOVA can calculate the power value of two floating-point numbers in only four clock cycles with a negligible loss of accuracy, compared to over 150 clock cycles in other processors.\",\"PeriodicalId\":20702,\"journal\":{\"name\":\"Proceedings of the IEEE 2000 Custom Integrated Circuits Conference (Cat. No.00CH37044)\",\"volume\":\"30 1\",\"pages\":\"551-554\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2000-05-21\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the IEEE 2000 Custom Integrated Circuits Conference (Cat. No.00CH37044)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/CICC.2000.852728\",\"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 of the IEEE 2000 Custom Integrated Circuits Conference (Cat. No.00CH37044)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CICC.2000.852728","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 2

摘要

本文介绍了一种名为FLOVA (FLOating-Point VLIW Architecture)的VLIW (very long instruction word)几何处理器，它是为加速三维图形的几何阶段而开发的。FLOVA在一个周期内执行4条指令，支持136条指令，其中包括35条SIMD(单指令多数据)指令，以加速几何阶段。描述了在3D图形几何阶段加速转换和照明操作的特殊功能。FLOVA可以在四个时钟周期内计算两个浮点数的功率值，精度损失可以忽略不计，而其他处理器则需要超过150个时钟周期。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

FLOVA: A four-issue VLIW geometry processor with SIMD instructions and lighting acceleration unit

This paper describes a VLIW (very long instruction word) geometry processor called FLOVA (FLOating-Point VLIW Architecture) which was developed to accelerate the geometry stage of 3D graphics. FLOVA executes four instructions in one cycle and supports 136 instructions including 35 SIMD (single instruction multiple data) instructions to accelerate the geometry stage. Special features to accelerate transformation and lighting operations in 3D graphics geometry stage are described. FLOVA can calculate the power value of two floating-point numbers in only four clock cycles with a negligible loss of accuracy, compared to over 150 clock cycles in other processors.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Proceedings of the IEEE 2000 Custom Integrated Circuits Conference (Cat. No.00CH37044)

自引率

0.00%

发文量