面向容错应用的高性能节能混合冗余MAC

Sunil Dutt, Anshu Chauhan, Rahul Bhadoriya, Sukumar Nandi, G. Trivedi
{"title":"面向容错应用的高性能节能混合冗余MAC","authors":"Sunil Dutt, Anshu Chauhan, Rahul Bhadoriya, Sukumar Nandi, G. Trivedi","doi":"10.1109/VLSID.2015.65","DOIUrl":null,"url":null,"abstract":"In the majority of Digital Signal Processing (DSP) applications, such as image, audio and video processing, the final result is interpreted by human senses, and, the fact of confined perception of human senses declines the strict restriction on accuracy. Thus, by adopting the emerging concept of approximate computing, we propose an approximate radix-2 hybrid redundant Multiply-and-Accumulate (Approx MAC) unit which stems a novel Speed-Power-Accuracy-Area (SPAA) metrics. The Approx MAC unit attains tremendous improvements in computational performance, energy efficiency and silicon area with a trivial degradation in the output quality. To inspect the effectiveness of the proposed approach in real-time DSP applications, we demonstrate an Approx MAC unit embedded JPEG-E-X IP core architecture. The Approx MAC unit with 40 approximate LSBs ensures 7.177x and 1.526x speedup, 1.594x and 4.163x energy efficiency, and 1.131x and 1.277x silicon area improvements over binary and hybrid redundant MAC units, respectively. Moreover, the Approx MAC unit with 40 approximate LSBs decorates power precision and delay-precision metrics by 14.71% and 32.95%, respectively.","PeriodicalId":123635,"journal":{"name":"2015 28th International Conference on VLSI Design","volume":"13 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"6","resultStr":"{\"title\":\"A High-Performance Energy-Efficient Hybrid Redundant MAC for Error-Resilient Applications\",\"authors\":\"Sunil Dutt, Anshu Chauhan, Rahul Bhadoriya, Sukumar Nandi, G. Trivedi\",\"doi\":\"10.1109/VLSID.2015.65\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In the majority of Digital Signal Processing (DSP) applications, such as image, audio and video processing, the final result is interpreted by human senses, and, the fact of confined perception of human senses declines the strict restriction on accuracy. Thus, by adopting the emerging concept of approximate computing, we propose an approximate radix-2 hybrid redundant Multiply-and-Accumulate (Approx MAC) unit which stems a novel Speed-Power-Accuracy-Area (SPAA) metrics. The Approx MAC unit attains tremendous improvements in computational performance, energy efficiency and silicon area with a trivial degradation in the output quality. To inspect the effectiveness of the proposed approach in real-time DSP applications, we demonstrate an Approx MAC unit embedded JPEG-E-X IP core architecture. The Approx MAC unit with 40 approximate LSBs ensures 7.177x and 1.526x speedup, 1.594x and 4.163x energy efficiency, and 1.131x and 1.277x silicon area improvements over binary and hybrid redundant MAC units, respectively. Moreover, the Approx MAC unit with 40 approximate LSBs decorates power precision and delay-precision metrics by 14.71% and 32.95%, respectively.\",\"PeriodicalId\":123635,\"journal\":{\"name\":\"2015 28th International Conference on VLSI Design\",\"volume\":\"13 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1900-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"6\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2015 28th International Conference on VLSI Design\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/VLSID.2015.65\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2015 28th International Conference on VLSI Design","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/VLSID.2015.65","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 6

摘要

在大多数数字信号处理(DSP)应用中,如图像、音频和视频处理,最终结果都是由人的感官来解释的,而人的感官有限的感知事实拒绝了对精度的严格限制。因此,通过采用新兴的近似计算概念,我们提出了一个近似基数-2混合冗余乘法和累加(近似MAC)单元,它形成了一个新的速度-功率-精度-面积(SPAA)指标。近似MAC单元在计算性能、能源效率和硅面积方面取得了巨大的进步,而输出质量却有轻微的下降。为了检验所提出的方法在实时DSP应用中的有效性,我们展示了一个嵌入JPEG-E-X IP核架构的大约MAC单元。与二进制和混合冗余MAC单元相比,具有40个近似lsb的Approx MAC单元分别确保了7.177倍和1.526倍的加速,1.594倍和4.163倍的能源效率,以及1.131倍和1.277倍的硅面积改进。此外,具有40个近似lsb的近似MAC单元将功率精度和延迟精度指标分别提高了14.71%和32.95%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
A High-Performance Energy-Efficient Hybrid Redundant MAC for Error-Resilient Applications
In the majority of Digital Signal Processing (DSP) applications, such as image, audio and video processing, the final result is interpreted by human senses, and, the fact of confined perception of human senses declines the strict restriction on accuracy. Thus, by adopting the emerging concept of approximate computing, we propose an approximate radix-2 hybrid redundant Multiply-and-Accumulate (Approx MAC) unit which stems a novel Speed-Power-Accuracy-Area (SPAA) metrics. The Approx MAC unit attains tremendous improvements in computational performance, energy efficiency and silicon area with a trivial degradation in the output quality. To inspect the effectiveness of the proposed approach in real-time DSP applications, we demonstrate an Approx MAC unit embedded JPEG-E-X IP core architecture. The Approx MAC unit with 40 approximate LSBs ensures 7.177x and 1.526x speedup, 1.594x and 4.163x energy efficiency, and 1.131x and 1.277x silicon area improvements over binary and hybrid redundant MAC units, respectively. Moreover, the Approx MAC unit with 40 approximate LSBs decorates power precision and delay-precision metrics by 14.71% and 32.95%, respectively.
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
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信