PresCount:有效分配登记册,减少银行冲突

Xiaofeng Guan, Hao Zhou, Guoqing Bao, Handong Li, Liang Zhu, Jianguo Yao
{"title":"PresCount:有效分配登记册,减少银行冲突","authors":"Xiaofeng Guan, Hao Zhou, Guoqing Bao, Handong Li, Liang Zhu, Jianguo Yao","doi":"10.1109/CGO57630.2024.10444841","DOIUrl":null,"url":null,"abstract":"Modern processors with large multi-banked register files often rely on hardware solutions to resolve bank conflicts efficiently. However, these hardware-based methods, while flexible, can incur runtime penalties and restrict the exploration of optimized hardware designs. In contrast, compiler-based methods for register bank assignments avoid runtime overhead. However, incorporating bank assignment into the complex register allocation process presents significant challenges, leading existing methods to adopt conservative approaches to avoid potential side effects. This paper introduces the novel register allocation method PresCount, which enhances the coloring strategy for the Register Conflict Graph (RCG) and incorporates a bank pressure tracking mechanism to improve performance. The integrated register bank assigner in PresCount effectively reduces bank conflicts, achieving remarkable reductions of 43.28% and 27.76%, respectively, compared to existing methods on platforms with rich register banks and limited register budgets, as demonstrated by SPECfp and CNN-KERNEL benchmarks. Furthermore, a subgroup splitting technique is introduced to facilitate register allocation under the bank-subgroup register file design, specifically our Domain-Specific Architecture (DSA) for AI computing. This technique demonstrates an impressive 99.85% reduction in bank conflicts for domain-specific kernel functions. By addressing the challenges of bank conflicts in register allocation, the proposed PresCount method showcases significant improvements in performance and efficiency for platforms with different register configurations and domain-specific workloads, allowing for more flexible exploration of optimized hardware designs.","PeriodicalId":517814,"journal":{"name":"2024 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)","volume":"58 1","pages":"170-181"},"PeriodicalIF":0.0000,"publicationDate":"2024-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"PresCount: Effective Register Allocation for Bank Conflict Reduction\",\"authors\":\"Xiaofeng Guan, Hao Zhou, Guoqing Bao, Handong Li, Liang Zhu, Jianguo Yao\",\"doi\":\"10.1109/CGO57630.2024.10444841\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Modern processors with large multi-banked register files often rely on hardware solutions to resolve bank conflicts efficiently. However, these hardware-based methods, while flexible, can incur runtime penalties and restrict the exploration of optimized hardware designs. In contrast, compiler-based methods for register bank assignments avoid runtime overhead. However, incorporating bank assignment into the complex register allocation process presents significant challenges, leading existing methods to adopt conservative approaches to avoid potential side effects. This paper introduces the novel register allocation method PresCount, which enhances the coloring strategy for the Register Conflict Graph (RCG) and incorporates a bank pressure tracking mechanism to improve performance. The integrated register bank assigner in PresCount effectively reduces bank conflicts, achieving remarkable reductions of 43.28% and 27.76%, respectively, compared to existing methods on platforms with rich register banks and limited register budgets, as demonstrated by SPECfp and CNN-KERNEL benchmarks. Furthermore, a subgroup splitting technique is introduced to facilitate register allocation under the bank-subgroup register file design, specifically our Domain-Specific Architecture (DSA) for AI computing. This technique demonstrates an impressive 99.85% reduction in bank conflicts for domain-specific kernel functions. By addressing the challenges of bank conflicts in register allocation, the proposed PresCount method showcases significant improvements in performance and efficiency for platforms with different register configurations and domain-specific workloads, allowing for more flexible exploration of optimized hardware designs.\",\"PeriodicalId\":517814,\"journal\":{\"name\":\"2024 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)\",\"volume\":\"58 1\",\"pages\":\"170-181\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-03-02\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2024 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/CGO57630.2024.10444841\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2024 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CGO57630.2024.10444841","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

具有大型多库寄存器文件的现代处理器通常依赖硬件解决方案来有效解决库冲突问题。然而,这些基于硬件的方法虽然灵活,但可能会在运行时产生代价,并限制了对优化硬件设计的探索。相比之下,基于编译器的寄存器组分配方法可避免运行时开销。然而,将寄存器组分配纳入复杂的寄存器分配过程会带来巨大的挑战,导致现有方法采用保守的方法来避免潜在的副作用。本文介绍了新颖的寄存器分配方法 PresCount,它增强了寄存器冲突图(RCG)的着色策略,并采用了库压力跟踪机制来提高性能。正如 SPECfp 和 CNN-KERNEL 基准测试所示,PresCount 中集成的寄存器组分配器有效地减少了寄存器组冲突,在寄存器组丰富而寄存器预算有限的平台上,与现有方法相比,分别显著降低了 43.28% 和 27.76%。此外,我们还引入了子组拆分技术,以促进寄存器组-子组寄存器文件设计下的寄存器分配,特别是针对人工智能计算的特定领域架构(DSA)。该技术显著减少了特定领域内核函数 99.85% 的库冲突。通过解决寄存器分配中的组冲突难题,所提出的 PresCount 方法显著提高了具有不同寄存器配置和特定领域工作负载的平台的性能和效率,从而可以更灵活地探索优化的硬件设计。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
PresCount: Effective Register Allocation for Bank Conflict Reduction
Modern processors with large multi-banked register files often rely on hardware solutions to resolve bank conflicts efficiently. However, these hardware-based methods, while flexible, can incur runtime penalties and restrict the exploration of optimized hardware designs. In contrast, compiler-based methods for register bank assignments avoid runtime overhead. However, incorporating bank assignment into the complex register allocation process presents significant challenges, leading existing methods to adopt conservative approaches to avoid potential side effects. This paper introduces the novel register allocation method PresCount, which enhances the coloring strategy for the Register Conflict Graph (RCG) and incorporates a bank pressure tracking mechanism to improve performance. The integrated register bank assigner in PresCount effectively reduces bank conflicts, achieving remarkable reductions of 43.28% and 27.76%, respectively, compared to existing methods on platforms with rich register banks and limited register budgets, as demonstrated by SPECfp and CNN-KERNEL benchmarks. Furthermore, a subgroup splitting technique is introduced to facilitate register allocation under the bank-subgroup register file design, specifically our Domain-Specific Architecture (DSA) for AI computing. This technique demonstrates an impressive 99.85% reduction in bank conflicts for domain-specific kernel functions. By addressing the challenges of bank conflicts in register allocation, the proposed PresCount method showcases significant improvements in performance and efficiency for platforms with different register configurations and domain-specific workloads, allowing for more flexible exploration of optimized hardware designs.
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:481959085
Book学术官方微信