中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
SnsBooster: Enhancing Sampling-based μArch Evaluation Efficiency through Online Performance Sensitivity Analysis

文献类型：期刊论文

作者Han, Chenji1,2; Zhang, Zifei1,2; Xue, Feng1,2; Li, Xinyu1,2; Wu, Yuxuan1,2; Zhang, Tingting1,3; Liu, Tianyi4; Guo, Qi1; Zhang, Fuxin1
刊名ACM TRANSACTIONS ON ARCHITECTURE AND CODE OPTIMIZATION
出版日期2025-06-01
卷号22期号:2页码:27
关键词Representative sampling microarchitecture-independent characteristic analysis
ISSN号1544-3566
DOI10.1145/3727637
英文摘要Sampling-based methods, such as SimPoint, are widely used for efficient pre-silicon mu Arch evaluations, where the costs are the number of simulation points multiplied by the number of evaluated mu Arch designs. However, these costs keep growing with an increasing number of simulation points and expanding mu Arch design space. Although techniques have been developed to accelerate the mu Arch design space exploration, less attention has been given to further reducing the simulation budget of each mu Arch evaluation. Common strategies like reducing simulation coverage or sampling fewer simulation points typically compromise estimation accuracy. Therefore, further reducing the simulation budget without compromising estimation accuracy remains a critical research problem. In this work, we propose SnsBooster to enhance sampling-based mu Arch evaluation efficiency, based on two insights: (a) large portions of simulation points' performance changes are typically insensitive to the evaluated mu Arch changes, and (b) simulation points' performance sensitivities under specific mu Arch change correlate with their inherent characteristics. By online building a mu Arch-specific performance sensitivity classifier via progressive simulation and continuous validation, SnsBooster can identify and selectively evaluate only performance-sensitive points, thus reducing the simulation budget without compromising estimation accuracy. When applied across various mu Arch changes, SnsBooster achieves an average simulation budget reduction of 39.04% with an accuracy loss of only 0.14%, compared to simulating all the sampled points. Under the same accuracy loss, SnsBooster's simulation budgets are only 64.73% and 65.60% of those required by methods of reducing simulation coverage or sampling fewer points. Besides, under identical simulation budgets, the average accuracy losses of these methods are 1.41% and 1.23%, which is substantially higher than that of SnsBooster.
资助项目National Key Research and Development Program of China[2022YFB3105100]
WOS研究方向Computer Science
语种英语
WOS记录号WOS:001533499400007
出版者ASSOC COMPUTING MACHINERY
源URL[http://119.78.100.204/handle/2XEOYT63/42080]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Han, Chenji
作者单位1.Univ Chinese Acad Sci, Inst Comp Technol, Chinese Acad Sci, Beijing, Peoples R China
2.Univ Chinese Acad Sci, Beijing, Peoples R China
3.Loongson Technol Co Ltd, Beijing, Peoples R China
4.Univ Texas San Antonio, Comp Sci, San Antonio, TX 78249 USA
推荐引用方式
GB/T 7714		 Han, Chenji,Zhang, Zifei,Xue, Feng,et al. SnsBooster: Enhancing Sampling-based μArch Evaluation Efficiency through Online Performance Sensitivity Analysis[J]. ACM TRANSACTIONS ON ARCHITECTURE AND CODE OPTIMIZATION,2025,22(2):27.
APA Han, Chenji.,Zhang, Zifei.,Xue, Feng.,Li, Xinyu.,Wu, Yuxuan.,...&Zhang, Fuxin.(2025).SnsBooster: Enhancing Sampling-based μArch Evaluation Efficiency through Online Performance Sensitivity Analysis.ACM TRANSACTIONS ON ARCHITECTURE AND CODE OPTIMIZATION,22(2),27.
MLA Han, Chenji,et al."SnsBooster: Enhancing Sampling-based μArch Evaluation Efficiency through Online Performance Sensitivity Analysis".ACM TRANSACTIONS ON ARCHITECTURE AND CODE OPTIMIZATION 22.2(2025):27.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。