Speculative trace scheduling in VLIW processors

被引:0
|
作者
Agarwal, M [1 ]
Nandy, SK [1 ]
von Eijndhoven, J [1 ]
Balakrishnan, S [1 ]
机构
[1] Indian Inst Sci, SERC, CADL, Bangalore 560012, Karnataka, India
来源
ICCD'2002: IEEE INTERNATIONAL CONFERENCE ON COMPUTER DESIGN: VLSI IN COMPUTERS AND PROCESSORS, PROCEEDINGS | 2002年
关键词
D O I
10.1109/ICCD.2002.1106803
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
VLIW processors are statically scheduled processors and their performance depends on the quality of schedules generated by the compiler's scheduler. We propose a new scheduling scheme where the application is first divided into decision trees and then further split into traces. Traces are speculatively scheduled on the processor based on their probability of execution. We have developed a tool "SpliTree" to generate traces automatically. Using dynamic branch prediction for scheduling traces our scheme achieves approximately 1.4x performance improvement over that using decision trees for Spec92 benchmarks simulated on TriMedia(TM).
引用
收藏
页码:408 / 413
页数:6
相关论文
共 50 条
  • [31] Code compression for VLIW processors
    Xie, Y
    Lekatsas, H
    Wolf, W
    DCC 2001: DATA COMPRESSION CONFERENCE, PROCEEDINGS, 2001, : 525 - 525
  • [32] Dynamically scheduling the trace produced during program execution into VLIW instructions
    Univ Coll London, London, United Kingdom
    Proc Int Parall Process Symp IPPS, (248-257):
  • [33] Dynamically scheduling the trace produced during program execution into VLIW instructions
    de Souza, AF
    Rounce, P
    IPPS/SPDP 1999: 13TH INTERNATIONAL PARALLEL PROCESSING SYMPOSIUM & 10TH SYMPOSIUM ON PARALLEL AND DISTRIBUTED PROCESSING, PROCEEDINGS, 1999, : 248 - 257
  • [34] Speculative multithreaded processors
    Sohi, GS
    Roth, A
    COMPUTER, 2001, 34 (04) : 66 - +
  • [35] Speculative multithreaded processors
    Sohi, GS
    Roth, A
    HIGH PERFORMANCE COMPUTING - HIPC 2000, PROCEEDINGS, 2001, 1970 : 259 - 270
  • [36] ADDRESSING MECHANISMS FOR VLIW AND SUPERSCALAR PROCESSORS
    STEVEN, FL
    ADAMS, RG
    STEVEN, GB
    WANG, L
    WHALE, DJ
    MICROPROCESSING AND MICROPROGRAMMING, 1993, 39 (2-5): : 75 - 78
  • [37] Instruction scheduling methods and phase ordering framework for VLIW DSP processors with distributed register files
    Chung-Ju Wu
    Yu-Te Lin
    Jenq-Kuen Lee
    The Journal of Supercomputing, 2012, 61 : 1024 - 1047
  • [38] Compiler-assisted leakage-aware loop scheduling for embedded VLIW DSP processors
    Wang, Meng
    Wang, Yi
    Liu, Duo
    Qin, Zhiwei
    Shao, Zili
    JOURNAL OF SYSTEMS AND SOFTWARE, 2010, 83 (05) : 772 - 785
  • [39] A rough programming approach to power-aware VLIW instruction scheduling for digital signal processors
    Xiao, S
    Lai, EMK
    2005 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1-5: SPEECH PROCESSING, 2005, : 141 - 144
  • [40] A rough programming approach to power-balanced instruction scheduling for VLIW digital signal processors
    Xiao, Shu
    Lai, Edmund M. -K.
    IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2008, 56 (04) : 1698 - 1709