Experience with a performance analyzer for multithreaded applications

Authors:
Gilbert J. Hansen;Charles A. Linthicum;Gary Brooks
Affiliations:
CONVEX Computer Corporation, P.O. Box 833851, Richardson, TX;CONVEX Computer Corporation, P.O. Box 833851, Richardson, TX;CONVEX Computer Corporation, P.O. Box 833851, Richardson, TX
Venue:
Proceedings of the 1990 ACM/IEEE conference on Supercomputing
Year:
1990

Citing 4
Cited 3

Non-intrusive and interactive profiling in parasight

PPEALS '88 Proceedings of the ACM/SIGPLAN conference on Parallel programming: experience with applications, languages and systems
The convex C240 architecture

Proceedings of the 1988 ACM/IEEE conference on Supercomputing
Multiprocessor instrumentation: approaches for Cedar

Instrumentation for future parallel computing systems
Gprof: A call graph execution profiler

SIGPLAN '82 Proceedings of the 1982 SIGPLAN symposium on Compiler construction

A bibliography of parallel debuggers, 1993 edition

PADD '93 Proceedings of the 1993 ACM/ONR workshop on Parallel and distributed debugging
An API for Runtime Code Patching

International Journal of High Performance Computing Applications
Analyzing lock contention in multithreaded applications

Proceedings of the 15th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming

Quantified Score

Hi-index	0.00

Visualization

Abstract

Determining the effectiveness of parallelization requires performance data about elapsed process time and total CPU time. Furthermore, it is desirable not to have to run a parallel application in a stand-alone environment in order to obtain the profile. This paper describes the CONVEX performance analyzer, CXpa, with the capability to monitor parallel regions of code, in particular loops, executed in a time-sharing environment. The means by which profiling information is measured for a parallel region is described along with the operating system facilities required to support it. The effectiveness of the approach is evaluated and suggestions for improvement made.The profiling of parallel regions is implemented on the CONVEX C200 Series™ computers, a tightly coupled, shared-memory, parallel/multiprocessor systems running ConvexOS™ V8.0, a UNIX® based operating system.