全流水线的能量效率:一个矩阵乘法的案例研究

2016 IEEE 24th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM) Pub Date : 2016-05-01 DOI:10.1109/FCCM.2016.50

Peipei Zhou, Hyunseok Park, Zhenman Fang, J. Cong, A. DeHon

{"title":"全流水线的能量效率:一个矩阵乘法的案例研究","authors":"Peipei Zhou, Hyunseok Park, Zhenman Fang, J. Cong, A. DeHon","doi":"10.1109/FCCM.2016.50","DOIUrl":null,"url":null,"abstract":"Customized pipeline designs that minimize the pipeline initiation interval (II) maximize the throughput of FPGA accelerators designed with high-level synthesis (HLS). What is the impact of minimizing II on energy efficiency? Using a matrix-multiply accelerator, we show that matrix multiplies with II>1 can sometimes reduce dynamic energy below II=1 due to interconnect savings, but II=1 always achieves energy close to the minimum. We also identify sources of inefficient mapping in the commercial tool flow.","PeriodicalId":113498,"journal":{"name":"2016 IEEE 24th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2016-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"7","resultStr":"{\"title\":\"Energy Efficiency of Full Pipelining: A Case Study for Matrix Multiplication\",\"authors\":\"Peipei Zhou, Hyunseok Park, Zhenman Fang, J. Cong, A. DeHon\",\"doi\":\"10.1109/FCCM.2016.50\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Customized pipeline designs that minimize the pipeline initiation interval (II) maximize the throughput of FPGA accelerators designed with high-level synthesis (HLS). What is the impact of minimizing II on energy efficiency? Using a matrix-multiply accelerator, we show that matrix multiplies with II>1 can sometimes reduce dynamic energy below II=1 due to interconnect savings, but II=1 always achieves energy close to the minimum. We also identify sources of inefficient mapping in the commercial tool flow.\",\"PeriodicalId\":113498,\"journal\":{\"name\":\"2016 IEEE 24th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM)\",\"volume\":\"38 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2016-05-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"7\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2016 IEEE 24th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/FCCM.2016.50\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2016 IEEE 24th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/FCCM.2016.50","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 7

摘要

定制的管道设计，最大限度地减少了管道启动间隔(II)，最大限度地提高了FPGA加速器的吞吐量，设计了高级合成(HLS)。最小化II对能源效率的影响是什么?使用矩阵乘加速器，我们表明，由于互连节省，矩阵乘II>1有时可以将动态能量降低到II=1以下，但II=1总是达到接近最小值的能量。我们还确定了商业工具流中低效映射的来源。

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

Energy Efficiency of Full Pipelining: A Case Study for Matrix Multiplication

Customized pipeline designs that minimize the pipeline initiation interval (II) maximize the throughput of FPGA accelerators designed with high-level synthesis (HLS). What is the impact of minimizing II on energy efficiency? Using a matrix-multiply accelerator, we show that matrix multiplies with II>1 can sometimes reduce dynamic energy below II=1 due to interconnect savings, but II=1 always achieves energy close to the minimum. We also identify sources of inefficient mapping in the commercial tool flow.

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

2016 IEEE 24th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM)

自引率

0.00%

发文量

期刊最新文献

Spatial Predicates Evaluation in the Geohash Domain Using Reconfigurable Hardware Two-Hit Filter Synthesis for Genomic Database Search Initiation Interval Aware Resource Sharing for FPGA DSP Blocks Finding Space-Time Stream Permutations for Minimum Memory and Latency Runtime Parameterizable Regular Expression Operators for Databases