OpenCL code generation for low energy wide SIMD architectures with explicit datapath

Dongrui She, Yifan He, Luc Waeijen, H. Corporaal
{"title":"OpenCL code generation for low energy wide SIMD architectures with explicit datapath","authors":"Dongrui She, Yifan He, Luc Waeijen, H. Corporaal","doi":"10.1109/SAMOS.2013.6621141","DOIUrl":null,"url":null,"abstract":"Energy efficiency is one of the most important aspects in designing embedded processors. The use of a wide SIMD processor architecture is a promising approach to build energy-efficient high performance embedded processors. In this paper, we propose a configurable wide SIMD architecture that utilizes explicit datapath to achieve high energy efficiency. To efficiently program the proposed architecture with a standard parallel programming language, we introduce a tool flow that can compile and map OpenCL programs onto it. The compiler in the proposed tool flow is able to analyze the static access patterns in OpenCL kernels and generate efficient mapping and code that utilizes the explicit datapath. Experimental results show that the proposed architecture is efficient. In a 128-PE processor, the proposed architecture is able to achieve over 200 times speed-up and reduce the energy consumption of register file and memory by over 90% compared to a RISC processor.","PeriodicalId":382307,"journal":{"name":"2013 International Conference on Embedded Computer Systems: Architectures, Modeling, and Simulation (SAMOS)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2013-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"11","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2013 International Conference on Embedded Computer Systems: Architectures, Modeling, and Simulation (SAMOS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SAMOS.2013.6621141","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 11

Abstract

Energy efficiency is one of the most important aspects in designing embedded processors. The use of a wide SIMD processor architecture is a promising approach to build energy-efficient high performance embedded processors. In this paper, we propose a configurable wide SIMD architecture that utilizes explicit datapath to achieve high energy efficiency. To efficiently program the proposed architecture with a standard parallel programming language, we introduce a tool flow that can compile and map OpenCL programs onto it. The compiler in the proposed tool flow is able to analyze the static access patterns in OpenCL kernels and generate efficient mapping and code that utilizes the explicit datapath. Experimental results show that the proposed architecture is efficient. In a 128-PE processor, the proposed architecture is able to achieve over 200 times speed-up and reduce the energy consumption of register file and memory by over 90% compared to a RISC processor.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
具有显式数据路径的低能耗宽SIMD架构的OpenCL代码生成
能效是嵌入式处理器设计中最重要的方面之一。采用宽SIMD处理器体系结构是构建高效节能的高性能嵌入式处理器的一种很有前途的方法。在本文中,我们提出了一种可配置的宽SIMD架构,该架构利用显式数据路径来实现高能效。为了使用标准的并行编程语言对所提出的体系结构进行高效编程,我们引入了一个工具流,可以将OpenCL程序编译并映射到该体系结构上。该工具流中的编译器能够分析OpenCL内核中的静态访问模式,并生成利用显式数据路径的高效映射和代码。实验结果表明,该结构是有效的。在128-PE处理器中,与RISC处理器相比,该架构能够实现200倍以上的加速,并将寄存器文件和内存的能耗降低90%以上。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Workload-dependent relative fault sensitivity and error contribution factor of GPU onchip memory structures TimeCube: A manycore embedded processor with interference-agnostic progress tracking An effective model extraction method with state space compression for model checking SystemC TLM designs A just-in-time modulo scheduling for virtual coarse-grained reconfigurable architectures An embedded hardware-efficient architecture for real-time cascade Support Vector Machine classification
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1