Performance profiling

If you want to make your application faster then you will probably need to profile it to find out where it spends most of its time.

Profiling an MPI code can be done using the Intel Trace Analyser and Collector (see ProfilingMPI). This will show you how much time is spent in MPI calls in addition to the time spent in the application's functions and subroutines.

Profiling a non-MPI code can be done using gprof. This article demonstrates how to use gprof to profile your code.

There is more information on general code optimisation in the code optimisation check list on the Hector website. Some of this document is specific to Hector but it gives an overview of things to consider when optimising code.

-- DavidAcreman - 01 Nov 2012

This topic: Zen > WebHome > CodeDevelopment > PerformanceProfiling
History: r1 - 01 Nov 2012 - 14:34:57 - DavidAcreman
 
This site is powered by the TWiki collaboration platformCopyright © by the contributing authors. All material on this collaboration platform is the property of the contributing authors.
Ideas, requests, problems regarding Astrophysics Wiki? Send feedback