Scalable Detection of MPI-2 Remote Memory Access Inefficiency Patterns

Authors:
Marc-André Hermanns;Markus Geimer;Bernd Mohr;Felix Wolf
Affiliations:
Jülich Supercomputing Centre, Forschungszentrum Jülich, Germany;Jülich Supercomputing Centre, Forschungszentrum Jülich, Germany;Jülich Supercomputing Centre, Forschungszentrum Jülich, Germany;Jülich Supercomputing Centre, Forschungszentrum Jülich, Germany and Department of Computer Science, RWTH Aachen University, Germany
Venue:
Proceedings of the 16th European PVM/MPI Users' Group Meeting on Recent Advances in Parallel Virtual Machine and Message Passing Interface
Year:
2009

Citing 10
Cited 1

NAS Parallel Benchmark Results

IEEE Parallel & Distributed Technology: Systems & Technology
Automatic performance analysis of hybrid MPI/OpenMP applications

Journal of Systems Architecture: the EUROMICRO Journal - Special issue: Evolutions in parallel distributed and network-based processing
Performance Tool Support for MPI-2 on Linux

Proceedings of the 2004 ACM/IEEE conference on Supercomputing
A Scalable Implementation of a Finite-Volume Dynamical Core in the Community Atmosphere Model

International Journal of High Performance Computing Applications
The Tau Parallel Performance System

International Journal of High Performance Computing Applications
Parallel performance wizard: a performance analysis tool for partitioned global-address-space programming models

Proceedings of the 2006 ACM/IEEE conference on Supercomputing
Replay-Based Synchronization of Timestamps in Event Traces of Massively Parallel Applications

ICPPW '08 Proceedings of the 2008 International Conference on Parallel Processing - Workshops
A scalable tool architecture for diagnosing wait states in massively parallel applications

Parallel Computing
Scalable parallel trace-based performance analysis

EuroPVM/MPI'06 Proceedings of the 13th European PVM/MPI User's Group conference on Recent advances in parallel virtual machine and message passing interface
Specification of inefficiency patterns for MPI-2 one-sided communication

Euro-Par'06 Proceedings of the 12th international conference on Parallel Processing

A scalable infrastructure for the performance analysis of passive target synchronization

Parallel Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Wait states in parallel applications can be identified by scanning event traces for characteristic patterns. In our earlier work, we have defined such patterns for mpi -2 one-sided communication, although still based on a trace-analysis scheme with limited scalability. Taking advantage of a new scalable trace-analysis approach based on a parallel replay, which was originally developed for mpi -1 point-to-point and collective communication, we show how wait states in one-sided communications can be detected in a more scalable fashion. We demonstrate the scalability of our method and its usefulness for the optimization cycle with applications running on up to 8,192 cores.