Tutorial

Analyze MPI Applications with Intel® Trace Analyzer and Collector and Intel® VTune™ Profiler

Download PDF
ID 773180
Date 3/31/2023
Public
Document Table of Contents
Document Table of Contents x
Analyze MPI Applications with Intel® Trace Analyzer and Collector and Intel® VTune™ Profiler
Analyze MPI Applications with Intel® Trace Analyzer and Collector and Intel® VTune™ Profiler x
Prerequisites Starting Intel® Trace Analyzer Starting Intel® VTune™ Profiler Analyzing an MPI Application Summary Notices and Disclaimers
Analyzing an MPI Application x
Optimizing MPI Communications Improving Intra-process Performance
Optimizing MPI Communications x
Prepare for Analysis Ungroup MPI Functions Detect Serialization in Function Profile and Message Profile Compare Original Trace File With Idealized Trace File Remove Serialization Compare Two Trace Files Analyze Optimized Communications
Improving Intra-process Performance x
Run Basic Hotspots Analysis Interpret Results
Analyze MPI Applications with Intel® Trace Analyzer and Collector and Intel® VTune™ Profiler

Run Basic Hotspots Analysis

Open the Summary Page in Intel® Trace Analyzer and copy the command line for Intel® VTune™ Profiler:

Use the following command line to run Intel VTune Profiler for the most CPU-bound rank: 

& mpirun -gtool "vtune -collect hotspots -r result:1" -n 4 ./poisson inp
NOTE:
This information is available only for tracefiles generated on Linux* OS. On Windows* OS, make up the command line manually, see the example below.

Run the command line to perform the hotspot analysis with VTune Profiler.

Linux OS:

& mpirun -gtool "vtune -collect hotspots -r result:1" -n 16 ./poisson inp

Windows OS:

> mpiexec -gtool "vtune -collect hotspots -r result:1" -n 16 ./poisson inp

Navigate to the result.1 directory and open the poisson.1.vtune file in VTune Profiler.

Parent topic: Improving Intra-process Performance
Level Two Title