Scientific Reports:

S. Hunold, A. Carpen-Amarie, F. Lübbe, J. Träff:
"PGMPI: Automatically Verifying Self-Consistent MPI Performance Guidelines";
Report for CoRR - Computing Research Repository; Report No. arXiv:1606.00215, 2016; 13 pages.

English abstract:
The Message Passing Interface (MPI) is the most commonly used application programming interface for process communication on current large-scale parallel systems. Due to the scale and complexity of modern parallel architectures, it is becoming increasingly difficult to optimize MPI libraries, as many factors can influence the communication performance. To assist MPI developers and users, we propose an automatic way to check whether MPI libraries respect self-consistent performance guidelines. We introduce the PGMPI framework that can benchmark and detect violations of performance guidelines. Our experimental results show that PGMPI can indeed help to pinpoint undesired and often unexpected performance degradations of collective MPI operations. We demonstrate how to overcome these performance issues of several libraries by adapting the algorithmic implementations of their respective collective MPI calls.

MPI, performance guidelines, benchmarking

Related Projects:
Project Head Jesper Larsson Träff:

Project Head Jesper Larsson Träff:

Created from the Publication Database of the Vienna University of Technology.