Intel® Xeon Phi™ Coprocessor Analysis Workflow

1.

Prepare your coprocessor system for analysis

• Install the sampling server and driver on an Intel Xeon Phi coprocessor card to be sampled.

• For native application analysis, copy the binary to the Intel Xeon Phi coprocessor. For offload applications, no copying is required.

• To communicate with the Intel Xeon Phi coprocessor cards, you may use any of the following mechanisms:

  • Mount an NFS share. See the NFS Mounting a Host Export topic in the Intel Manycore Platform Software Stack (MPSS) help for details.

  • Use existing SSH tools. Make sure to configure SSH to work in a password-less mode.

3.

Specify and configure your analysis target from the host system

• In the Analysis Target window, select a target system and specify target options:

  • Intel Xeon Phi Coprocessor (native) - Launch Application

  • Intel Xeon Phi Coprocessor (host launch) - Launch Application

  • Intel Xeon Phi Coprocessor - Profile System

• For proper symbol resolution, specify search paths for Intel Xeon Phi coprocessor modules in the Binary/Symbol Search and Source Search dialog boxes. Symbol resolution for Intel Xeon Phi coprocessor modules is done on the host during collection post-processing. You can also specify search paths after collection, but, if you do that, the result should be re-resolved to get the symbol information from the binaries after the symbol paths have been established.

4.

Configure and run an analysis type

• From the performance analysis tree in the Analysis Type window, choose and configure an analysis type. If you selected an Intel Xeon Phi coprocessor (native) or Intel Xeon Phi coprocessor (host launch) target system in the Analysis Target window, the VTune Amplifier updates the analysis tree in the Analysis Type window to display the analysis types supported for the Intel Xeon Phi coprocessor:

  • Advanced Hotspots

  • General Exploration

  • Memory Access

  • HPC Performance Characterization

  Note

  For Intel Xeon Phi coprocessor codenamed Knights Corner, the call stack data collection is supported only for the Intel Xeon Phi Coprocessor (native) target type.

• Click Start to run the analysis.

5.

Open and interpret analysis results

Intel® VTune™ Amplifier generates a data collection result and, by default, opens it in the default viewpoint. Switch between available viewpoints to identify code regions that took most of the CPU time and experienced potentially significant architectural bottlenecks.