EXPLORER: Supporting run-time parallelization of DO-ACROSS loops on general networks of workstations

被引:0
|
作者
Liu, YL [1 ]
King, CT [1 ]
机构
[1] Natl Tsing Hua Univ, Dept Comp Sci, Hsinchu 30043, Taiwan
关键词
DOACROSS loops; inspector/executor; multithreading; networks of workstations; run-time parallelization;
D O I
暂无
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Performing runtime parallelization on general networks of workstations (NOWs) without special hardware or system software supports is very difficult, especially for DOACROSS loops. With the high communication overhead on NOWs, there is hardly any performance gain for runtime parallelization, due to the latter's large amount of messages for dependence detection, data accesses, and computation scheduling. In this paper, we introduce the EXPLORER system for runtime parallelization of DOACROSS and DOALL loops on general NOWs. EXPLORER hides the communication overhead on NOWs through multithreading - a facility supported in almost all workstations. A preliminary version of EXPLORER was implemented on a NOW consisting of eight DEC Alpha workstations connected through an Ethernet. The Pthread package was used to support multithreading. Experiments on synthetic loops showed speedups of up to 6.5 in DOACROSS loops and 7 in DOALL Loops.
引用
收藏
页码:103 / 110
页数:8
相关论文
共 12 条
  • [1] EXPLORER: Supporting run-time parallelization of DOACROSS loops on general networks of workstations
    Liu, YL
    King, CT
    [J]. PARALLEL COMPUTING, 2000, 26 (2-3) : 355 - 375
  • [2] Efficient run-time parallelization for DO loops
    Yang, CT
    Tseng, SS
    Hsieh, MH
    Kao, SH
    [J]. JOURNAL OF INFORMATION SCIENCE AND ENGINEERING, 1998, 14 (01) : 237 - 253
  • [3] RUN-TIME PARALLELIZATION AND SCHEDULING OF LOOPS
    SALTZ, JH
    MIRCHANDANEY, R
    BAXTER, D
    [J]. SPAA 89: PROCEEDINGS OF THE 1989 ACM SYMPOSIUM ON PARALLEL ALGORITHMS AND ARCHITECTURES, 1989, : 303 - 312
  • [4] RUN-TIME PARALLELIZATION AND SCHEDULING OF LOOPS
    SALTZ, JH
    MIRCHANDANEY, R
    CROWLEY, K
    [J]. IEEE TRANSACTIONS ON COMPUTERS, 1991, 40 (05) : 603 - 612
  • [5] Run-time parallelization for partially parallel loops
    Yang, CT
    Tseng, SS
    Kao, SH
    Hsieh, MH
    Jiang, MF
    [J]. 1997 INTERNATIONAL CONFERENCE ON PARALLEL AND DISTRIBUTED SYSTEMS, PROCEEDINGS, 1997, : 308 - 313
  • [6] Effects of parallelism degree on run-time parallelization of loops
    Xu, CZ
    [J]. PROCEEDINGS OF THE THIRTY-FIRST HAWAII INTERNATIONAL CONFERENCE ON SYSTEM SCIENCES, VOL VII: SOFTWARE TECHNOLOGY TRACK, 1998, : 86 - 95
  • [7] Exploiting locality in the run-time parallelization of irregular loops
    Martín, MJ
    Singh, DE
    Touriño, J
    Rivera, FF
    [J]. 2002 INTERNATIONAL CONFERENCE ON PARALLEL PROCESSING, PROCEEDING, 2002, : 27 - 34
  • [8] Time-stamping algorithms for parallelization of loops at run-time
    Xu, CZ
    Chaudhary, V
    [J]. 11TH INTERNATIONAL PARALLEL PROCESSING SYMPOSIUM, PROCEEDINGS, 1997, : 443 - 450
  • [9] THE LRPD TEST - SPECULATIVE RUN-TIME PARALLELIZATION OF LOOPS WITH PRIVATIZATION AND REDUCTION PARALLELIZATION
    RAUCHWERGER, L
    PADUA, D
    [J]. SIGPLAN NOTICES, 1995, 30 (06): : 218 - 232
  • [10] The LRPD test: Speculative run-time parallelization of loops with privatization and reduction parallelization
    Rauchwerger, L
    Padua, DA
    [J]. IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 1999, 10 (02) : 160 - 180