Design, implementation and analysis of a run-time configurable Memory Management Unit on FPGA

Farid Shamani, Vida Fakour Sevom, J. Nurmi, T. Ahonen
{"title":"Design, implementation and analysis of a run-time configurable Memory Management Unit on FPGA","authors":"Farid Shamani, Vida Fakour Sevom, J. Nurmi, T. Ahonen","doi":"10.1109/NORCHIP.2015.7364375","DOIUrl":null,"url":null,"abstract":"In this paper, we describe the design of a configurable Memory Management Unit (MMU) and its prototype implementation on a Field Programmable Gate Array (FPGA). We present analytical results of scaling the size of the second level software-managed Unified Translation Lookaside Buffer (UTLB) in terms of effect on the overall hit rate. Three design-time configurations with 16, 32, and 64 entries were used for this study. Critical path analysis of the logical design running on Altera Stratix-V FPGA is presented together with a description of optimization techniques employed in order to improve static timing performance. These optimization techniques assist in reaching 22.75% speed-up compared to non-optimized design. Moreover, maximum operating frequencies of 265, 225 and 200 MHz were achieved for UTLB sizes of 16, 32, and 64 entries, respectively. We quote worst case energy consumption figures with random input stimuli together with FPGA resource utilization characteristics for the above mentioned configurations. For resource-constrained or speed-critical hardware designs the 32-entry UTLB configuration provides a decent trade-off while the 16-entry configuration poses unsatisfactory performance. However, our target operating frequency of 200 MHz was eventually reached also for the 64-entry UTLB and hence it is our preferred option for most instantiations.","PeriodicalId":428994,"journal":{"name":"2015 Nordic Circuits and Systems Conference (NORCAS): NORCHIP & International Symposium on System-on-Chip (SoC)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2015-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2015 Nordic Circuits and Systems Conference (NORCAS): NORCHIP & International Symposium on System-on-Chip (SoC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/NORCHIP.2015.7364375","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 5

Abstract

In this paper, we describe the design of a configurable Memory Management Unit (MMU) and its prototype implementation on a Field Programmable Gate Array (FPGA). We present analytical results of scaling the size of the second level software-managed Unified Translation Lookaside Buffer (UTLB) in terms of effect on the overall hit rate. Three design-time configurations with 16, 32, and 64 entries were used for this study. Critical path analysis of the logical design running on Altera Stratix-V FPGA is presented together with a description of optimization techniques employed in order to improve static timing performance. These optimization techniques assist in reaching 22.75% speed-up compared to non-optimized design. Moreover, maximum operating frequencies of 265, 225 and 200 MHz were achieved for UTLB sizes of 16, 32, and 64 entries, respectively. We quote worst case energy consumption figures with random input stimuli together with FPGA resource utilization characteristics for the above mentioned configurations. For resource-constrained or speed-critical hardware designs the 32-entry UTLB configuration provides a decent trade-off while the 16-entry configuration poses unsatisfactory performance. However, our target operating frequency of 200 MHz was eventually reached also for the 64-entry UTLB and hence it is our preferred option for most instantiations.
基于FPGA的运行时可配置内存管理单元的设计、实现与分析
本文描述了一种可配置内存管理单元(MMU)的设计及其在现场可编程门阵列(FPGA)上的原型实现。我们提出了扩展二级软件管理的统一翻译暂存缓冲区(UTLB)的大小对总体命中率的影响的分析结果。本研究使用了三种设计时间配置,分别为16、32和64个条目。提出了在Altera Stratix-V FPGA上运行的逻辑设计的关键路径分析,并描述了为提高静态时序性能而采用的优化技术。与非优化设计相比,这些优化技术有助于达到22.75%的加速。此外,当UTLB大小为16、32和64项时,最大工作频率分别为265、225和200 MHz。我们引用具有随机输入刺激的最坏情况下的能耗数据以及上述配置的FPGA资源利用特性。对于资源受限或速度关键的硬件设计,32项UTLB配置提供了不错的折衷,而16项配置的性能不令人满意。然而,64条目UTLB最终也达到了200 MHz的目标工作频率,因此它是我们大多数实例化的首选选项。
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 求助全文
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
小红书