Documentation

Parallel Profiler and Code Improvement

Locate problematic areas in parallel code; work around common errors

Functions

mpiprofile Profile parallel communication and execution times

Examples and How To

Profiling Parallel Code

Describes how to use the parallel profile to determine the calculation and communications time for each worker

Job Monitor

Manage your jobs using the Job Monitor

Concepts

Troubleshooting and Debugging

Describes common programming errors and how to avoid them

Featured Examples

Profiling Explicit Parallel Communication

Profiling Explicit Parallel Communication

This example shows how to profile explicit communication to the nearest neighbor lab. It illustrates the use of labSend, labReceive, and labSendReceive, showing both the slow (incorrect) and the fast (optimal) way of implementing this algorithm. The problem is explored using the parallel profiler.

Profiling Parallel Work Distribution

Profiling Parallel Work Distribution

This example shows how to solve an embarrassingly parallel problem with uneven work distribution using for drange. The for drange splits iterations equally. As a result it can do suboptimal load balancing, which is visible using the parallel profiler. The procedures described here are also applicable to other work distribution problems.

Profiling Load Unbalanced Codistributed Arrays

Profiling Load Unbalanced Codistributed Arrays

This example shows how to profile the implicit communication that occurs when using an unevenly distributed array.

Was this topic helpful?

Parallel Computing Toolbox Documentation

Other Documentation

Support