MTOOL - AN INTEGRATED SYSTEM FOR PERFORMANCE DEBUGGING SHARED MEMORY MULTIPROCESSOR APPLICATIONS

被引:35
|
作者
GOLDBERG, AJ [1 ]
HENNESSY, JL [1 ]
机构
[1] STANFORD UNIV,COMP SYST LAB,STANFORD,CA 94305
关键词
MEMORY SYSTEM BEHAVIOR; PARALLEL PROGRAMMING; PERFORMANCE DEBUGGING; SHARED MEMORY MULTIPROCESSOR; SOFTWARE INSTRUMENTATION;
D O I
10.1109/71.205651
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
This paper describes Mtool, a software tool for analyzing performance losses in shared memory parallel programs. Mtool augments a program with low overhead instrumentation which perturbs the program's execution as little as possible while generating enough information to isolate memory and synchronization bottlenecks. After running the instrumented version of the parallel program, the programmer can use Mtool's window-based user interface to view compute time, memory, and synchronization bottlenecks at increasing levels of detail from a whole program level down to the level of individual procedures, loops, and synchronization objects. The paper describes Mtool's low overhead instrumentation methods, memory bottleneck detection technique, and attention focusing mechanisms, contrasts Mtool with other approaches, and offers a case study to demonstrate the effectiveness of Mtool.
引用
收藏
页码:28 / 40
页数:13
相关论文
共 50 条
  • [31] Designing a standardized model for a shared-memory multiprocessor computing system
    Nikol'skii, VA
    AUTOMATIC CONTROL AND COMPUTER SCIENCES, 2001, 35 (02) : 47 - 51
  • [32] Parallel scheduler for a shared memory (tightly-coupled) multiprocessor system
    Sharma, G
    Gupta, B
    COMPUTER SYSTEMS SCIENCE AND ENGINEERING, 1998, 13 (04): : 241 - 247
  • [33] PERFORMANCE-MEASUREMENT AND MODELING TO EVALUATE VARIOUS EFFECTS ON A SHARED MEMORY MULTIPROCESSOR
    ZHANG, XD
    IEEE TRANSACTIONS ON SOFTWARE ENGINEERING, 1991, 17 (01) : 87 - 93
  • [34] A HARDWARE INSTRUMENTATION APPROACH FOR PERFORMANCE-MEASUREMENT OF A SHARED-MEMORY MULTIPROCESSOR
    NACHT, G
    MINK, A
    MODELING TECHNIQUES AND TOOLS FOR COMPUTER PERFORMANCE EVALUATION, 1989, : 249 - 264
  • [35] PERFORMANCE ANALYSIS OF MR-1, A CLUSTERED SHARED-MEMORY MULTIPROCESSOR
    MABBS, SA
    FORWARD, KE
    JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING, 1994, 20 (02) : 158 - 175
  • [36] Strings: A high-performance distributed shared memory for symmetrical multiprocessor clusters
    Roy, S
    Chaudhary, V
    SEVENTH INTERNATIONAL SYMPOSIUM ON HIGH PERFORMANCE DISTRIBUTED COMPUTING - PROCEEDINGS, 1998, : 90 - 97
  • [37] COMBINATOR REDUCTION IN A SHARED-MEMORY MULTIPROCESSOR
    BURKIMSHER, PC
    COMPUTER JOURNAL, 1987, 30 (03): : 214 - 222
  • [38] MULTIPROCESSOR SHARED-MEMORY INFORMATION EXCHANGE
    SANTOLINE, LL
    BOWERS, MD
    CREW, AW
    ROSLUND, CJ
    GHRIST, WD
    IEEE TRANSACTIONS ON NUCLEAR SCIENCE, 1989, 36 (01) : 626 - 633
  • [39] A shared-memory multiprocessor scheduling algorithm
    Zuccar, Irene
    Solar, Mauricio
    Kri, Fernanda
    Parada, Victor
    PROFESSIONAL PRACTICE IN ARTIFICIAL INTELLIGENCE, 2006, 218 : 313 - +
  • [40] APPLICATIVE PARALLELISM ON A SHARED-MEMORY MULTIPROCESSOR
    OLDEHOEFT, RR
    CANN, DC
    IEEE SOFTWARE, 1988, 5 (01) : 62 - 70