Fourth International Conference on High-Performance Computing (1997)
Dec. 18, 1997 to Dec. 21, 1997
Lars Lundberg , University of Karlskrona/Ronneby
Mikael Roos , University of Karlskrona/Ronneby
In this paper we present a method an a set of tools for predicting the speedup of multithreaded Solaris programs. The predictions are based on recordings from a single-processor execution of the multithreaded program. The routines in the thread library are overloaded with an instrumented thread library developed by us. We do not need to have access to the source code of the multithreaded program and no recompilation is needed.<div></div> Using three multithreaded programs and a multiprocessor with 8 processors, we are able to show that the predictions are very reliable, particularly for programs with a coarse grained parallelism. The run-time overhead for the recordings is very small. The presented technique does not model I/O, and is therefore applicable only to CPU-intensive applications.
L. Lundberg and M. Roos, "Predicting the Speedup of Multithreaded Solaris Programs," Fourth International Conference on High-Performance Computing(HIPC), Bangalore, India, 1997, pp. 386.