A Top-Down Method for Performance Analysis and Counters Architecture

被引：0
作者：
Yasin, Ahmad [1 ]
机构：
[1] Intel Corp, Architecture Grp, Santa Clara, CA 95051 USA
来源：
2014 IEEE INTERNATIONAL SYMPOSIUM ON PERFORMANCE ANALYSIS OF SYSTEMS AND SOFTWARE (ISPASS) | 2014年
关键词：
D O I：
暂无
中图分类号：
TP3 [计算技术、计算机技术];
学科分类号：
0812 ;
摘要：
Optimizing an application's performance for a given microarchitecture has become painfully difficult. Increasing microarchitecture complexity, workload diversity, and the unmanageable volume of data produced by performance tools increase the optimization challenges. At the same time resource and time constraints get tougher with recently emerged segments. This further calls for accurate and prompt analysis methods.
引用
收藏
页码：35 / 44
页数：10
相关论文
共 13 条
  • [1] Ailamaki A, 1999, PROCEEDINGS OF THE TWENTY-FIFTH INTERNATIONAL CONFERENCE ON VERY LARGE DATA BASES, P266
  • [2] Allam O., 2012, GLSVLSI
  • [3] [Anonymous], INT 64 IA 32 ARCH SO
  • [4] Carvalho A., 2010, LIN K
  • [5] Eklov D., 2012, A Profiling Method for Analyzing Scalability Bottlenecks on Multicores
  • [6] A top-down approach to architecting CPI component performance counters
    Eyerman, Stijn
    Eeckhout, Lieven
    Karkhanis, Tejas
    Smith, James E.
    [J]. IEEE MICRO, 2007, 27 (01) : 84 - 93
  • [7] A performance counter architecture for computing accurate CPI components
    Eyerman, Stijn
    Eeckhout, Lieven
    Karkhanis, Tejas
    Smith, James E.
    [J]. ACM SIGPLAN NOTICES, 2006, 41 (11) : 175 - 184
  • [8] Intel corporation, INT 64 IA 32 ARCH OP
  • [9] Intel Corporation, 2013, INT VTUNE AMPL XE 20
  • [10] Jaleel A., 2010, MEMORY CHRACTERIZATI
12