一种具有类cpu可编程性的高能效顺序可重构阵列

IF 2.4 Q2 ENGINEERING, ELECTRICAL & ELECTRONIC
Tobias Kaiser;Esther Gottschalk;Kai Biethahn;Friedel Gerfers
{"title":"一种具有类cpu可编程性的高能效顺序可重构阵列","authors":"Tobias Kaiser;Esther Gottschalk;Kai Biethahn;Friedel Gerfers","doi":"10.1109/OJCAS.2024.3518110","DOIUrl":null,"url":null,"abstract":"This work presents Pasithea-1, a coarse-grained reconfigurable array (CGRA) that combines energy efficiency with CPU-like programmability. Its extensible instruction set uses sequential control flow in code fragments of up to 64 RISC-like instructions, which encode control and dataflow graphs in adjacency lists. Combined with dedicated, uniform processing elements, this enables fast compilation from C source code (1.4 s mean compile time). Demonstrator measurements reveal energy efficiency of up to 601 int32 MIPS/mW at 0.59V and performance of up to 148 MIPS at 0.90 V. Compared to a RISC reference system, mean energy efficiency is improved by 2.24× with 1.71× higher execution times across 12 of 14 benchmarks. Program-dependent factors underlying variations in energy efficiency are identified using dynamic program analysis. To reduce operand transfer energy, seven interconnect topologies are evaluated: a flat bus, five crossbar variants and a logarithmic network. Best results are obtained for a crossbar topology, reducing mean dynamic tile energy by 19 %. Furthermore, floating-point (FP) support is added to the instruction set and evaluated using three binary-compatible microarchitectures, presenting distinct area-performance-energy tradeoffs. The interconnect and FP microarchitecture explorations demonstrate that, unlike CGRAs utilizing low-level bitstreams, Pasithea’s instruction set hides microarchitectural details, which makes it possible to optimize hardware without severing binary compatibility.","PeriodicalId":93442,"journal":{"name":"IEEE open journal of circuits and systems","volume":"6 ","pages":"1-13"},"PeriodicalIF":2.4000,"publicationDate":"2024-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10802954","citationCount":"0","resultStr":"{\"title\":\"Pasithea-1: An Energy-Efficient Sequential Reconfigurable Array With CPU-Like Programmability\",\"authors\":\"Tobias Kaiser;Esther Gottschalk;Kai Biethahn;Friedel Gerfers\",\"doi\":\"10.1109/OJCAS.2024.3518110\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This work presents Pasithea-1, a coarse-grained reconfigurable array (CGRA) that combines energy efficiency with CPU-like programmability. Its extensible instruction set uses sequential control flow in code fragments of up to 64 RISC-like instructions, which encode control and dataflow graphs in adjacency lists. Combined with dedicated, uniform processing elements, this enables fast compilation from C source code (1.4 s mean compile time). Demonstrator measurements reveal energy efficiency of up to 601 int32 MIPS/mW at 0.59V and performance of up to 148 MIPS at 0.90 V. Compared to a RISC reference system, mean energy efficiency is improved by 2.24× with 1.71× higher execution times across 12 of 14 benchmarks. Program-dependent factors underlying variations in energy efficiency are identified using dynamic program analysis. To reduce operand transfer energy, seven interconnect topologies are evaluated: a flat bus, five crossbar variants and a logarithmic network. Best results are obtained for a crossbar topology, reducing mean dynamic tile energy by 19 %. Furthermore, floating-point (FP) support is added to the instruction set and evaluated using three binary-compatible microarchitectures, presenting distinct area-performance-energy tradeoffs. The interconnect and FP microarchitecture explorations demonstrate that, unlike CGRAs utilizing low-level bitstreams, Pasithea’s instruction set hides microarchitectural details, which makes it possible to optimize hardware without severing binary compatibility.\",\"PeriodicalId\":93442,\"journal\":{\"name\":\"IEEE open journal of circuits and systems\",\"volume\":\"6 \",\"pages\":\"1-13\"},\"PeriodicalIF\":2.4000,\"publicationDate\":\"2024-12-16\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10802954\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE open journal of circuits and systems\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://ieeexplore.ieee.org/document/10802954/\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ENGINEERING, ELECTRICAL & ELECTRONIC\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE open journal of circuits and systems","FirstCategoryId":"1085","ListUrlMain":"https://ieeexplore.ieee.org/document/10802954/","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
引用次数: 0

摘要

这项工作提出了Pasithea-1,一种粗粒度可重构阵列(CGRA),它结合了能源效率和类似cpu的可编程性。它的可扩展指令集在多达64个类似risc指令的代码片段中使用顺序控制流,这些指令在邻接表中编码控制和数据流图。结合专用的、统一的处理元素,这使得从C源代码快速编译(平均编译时间1.4秒)成为可能。演示测量显示,在0.59V时,能量效率高达601 int32 MIPS/mW,在0.90 V时,性能高达148 MIPS。与RISC参考系统相比,在14个基准测试中的12个基准测试中,平均能源效率提高了2.24倍,执行时间提高了1.71倍。利用动态程序分析确定了能源效率变化的程序依赖因素。为了减少操作数传递能量,评估了7种互连拓扑:扁平总线、5种交叉杆变体和对数网络。横条拓扑的效果最好,平均动态能量降低了19%。此外,在指令集中添加了浮点(FP)支持,并使用三种二进制兼容的微体系结构进行评估,呈现出不同的面积-性能-能量权衡。互连和FP微架构的探索表明,与使用低级比特流的CGRAs不同,Pasithea的指令集隐藏了微架构细节,这使得在不切断二进制兼容性的情况下优化硬件成为可能。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Pasithea-1: An Energy-Efficient Sequential Reconfigurable Array With CPU-Like Programmability
This work presents Pasithea-1, a coarse-grained reconfigurable array (CGRA) that combines energy efficiency with CPU-like programmability. Its extensible instruction set uses sequential control flow in code fragments of up to 64 RISC-like instructions, which encode control and dataflow graphs in adjacency lists. Combined with dedicated, uniform processing elements, this enables fast compilation from C source code (1.4 s mean compile time). Demonstrator measurements reveal energy efficiency of up to 601 int32 MIPS/mW at 0.59V and performance of up to 148 MIPS at 0.90 V. Compared to a RISC reference system, mean energy efficiency is improved by 2.24× with 1.71× higher execution times across 12 of 14 benchmarks. Program-dependent factors underlying variations in energy efficiency are identified using dynamic program analysis. To reduce operand transfer energy, seven interconnect topologies are evaluated: a flat bus, five crossbar variants and a logarithmic network. Best results are obtained for a crossbar topology, reducing mean dynamic tile energy by 19 %. Furthermore, floating-point (FP) support is added to the instruction set and evaluated using three binary-compatible microarchitectures, presenting distinct area-performance-energy tradeoffs. The interconnect and FP microarchitecture explorations demonstrate that, unlike CGRAs utilizing low-level bitstreams, Pasithea’s instruction set hides microarchitectural details, which makes it possible to optimize hardware without severing binary compatibility.
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
审稿时长
19 weeks
×
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:481959085
Book学术官方微信