Speculative trivialization point advancing in high-performance processors

被引:0
|
作者
Atoofian, Ehsan [1 ]
Baniasadi, Amirali [1 ]
机构
[1] Univ Victoria, ECE Dept, Victoria, BC V8P5C2, Canada
基金
加拿大自然科学与工程研究理事会;
关键词
high-performance processors; trivial instructions; value prediction;
D O I
10.1016/j.sysarc.2006.12.009
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Trivial instruct ions are those instructions whose output can be determined without performing the actual computation. This is due to the fact that for these instructions the output is often either one of the source operands or zero (e.g., addition with or multiplication by zero). In this work we study trivial instructions and use our findings to improve performance in high-performance processors. In particular, we introduce speculative trivialization point advancing to detect and bypass trivial instructions as soon as possible and as early as the decode stage. Consequently, we improve performance over a conventional processor (up to 30%) and a processor that detects and bypasses trivial instructions at their conventional point of trivialization. (up to 5%). (c) 2007 Elsevier B.V. All rights reserved.
引用
收藏
页码:587 / 601
页数:15
相关论文
共 50 条
  • [1] DESIGN HIGH-PERFORMANCE PROCESSORS
    LAU, SY
    ELECTRONIC DESIGN, 1977, 25 (07) : 86 - 95
  • [2] Cost-Effective Speculative Scheduling in High Performance Processors
    Perais, Arthur
    Seznec, Andre
    Michaud, Pierre
    Sembrant, Andreas
    Hagersten, Erik
    2015 ACM/IEEE 42ND ANNUAL INTERNATIONAL SYMPOSIUM ON COMPUTER ARCHITECTURE (ISCA), 2015, : 247 - 259
  • [3] Vying for the lead in high-performance processors
    Lauterbach, G
    COMPUTER, 1999, 32 (06) : 38 - +
  • [4] Blueprint for Advancing High-Performance Homes
    Turner, James H., Jr.
    Vaughan, Ellen Larson
    ISSUES IN SCIENCE AND TECHNOLOGY, 2012, 28 (02) : 67 - 76
  • [5] Adaptive cache compression for high-performance processors
    Alameldeen, AR
    Wood, DA
    31ST ANNUAL INTERNATIONAL SYMPOSIUM ON COMPUTER ARCHITECTURE, PROCEEDINGS, 2004, : 212 - 223
  • [6] Statistical Power Analysis for High-Performance Processors
    Chen, Howard
    Neely, Scott
    Xiong, Jinjun
    Zolotov, Vladimir
    Visweswariah, Chandu
    JOURNAL OF LOW POWER ELECTRONICS, 2009, 5 (01) : 70 - 76
  • [7] High-performance Graph Analytics on Manycore Processors
    Slota, George M.
    Rajamanickam, Sivasankaran
    Madduri, Kamesh
    2015 IEEE 29TH INTERNATIONAL PARALLEL AND DISTRIBUTED PROCESSING SYMPOSIUM (IPDPS), 2015, : 17 - 27
  • [8] Clock Design Technology for High-Performance Processors
    Ishizaka, Kinya
    Komatsu, Hiroaki
    FUJITSU SCIENTIFIC & TECHNICAL JOURNAL, 2011, 47 (02): : 136 - 141
  • [9] FOURIER FAST TRANSFORMATION PROCESSORS WITH HIGH-PERFORMANCE
    FEDOROVSKAYA, TN
    RADIOTEKHNIKA I ELEKTRONIKA, 1988, 33 (07): : 1481 - 1486
  • [10] Performance Analysis of Timing-Speculative Processors
    Assare, Omid
    Gupta, Rajesh K.
    IEEE TRANSACTIONS ON COMPUTERS, 2022, 71 (02) : 407 - 420