Mapping of Processes

Assume that run A had A.P0, A.P1 and run B had B.P0, B.P1, B.P2, B.P3 and assume that A.P0 did the same work as B.P0 and B.P1 and A.P1 did the same work as B.P2 and B.P3.

To get a meaningful Comparison Message Profile under these assumptions, choose the aggregation as shown in here and here:

Intel® Trace Analyzer

This image demonstrates the comparison of Run A (with 2 processes) with Run B (with 4 processes).

The message profile shows the average transfer rate quotient B/A. The Comparison Message Profile (and in fact the whole Comparison View) maps the senders and receivers of the two runs onto each other in the following way: child number i of run A's process aggregation is always mapped to (compared with) child number i of run B's process aggregation.

For more complete information about compiler optimizations, see our Optimization Notice.