Compare with Previous Result

You optimized your code to apply a loop interchange mechanism that gave you 3 seconds of improvement in the application execution time. To understand whether you got rid of the hotspot and what kind of optimization you got per function, re-run the Basic Hotspots analysis on the optimized code and compare results:

  1. Compare results before and after optimization.

  2. Identify the performance gain.

Compare Results Before and After Optimization

  1. Run the Basic Hotspots analysis on the modified code.

    VTune Amplifier collects data and opens the result in the Result tab. Make sure to close the results before comparison.

  2. Click the Compare Results button on the Intel® VTune™ Amplifier toolbar.

    The Compare Results window opens.

  3. Specify the Basic Hotspots analysis results you want to compare and click the Compare Results button:

    The Hotspots Bottom-up window opens, showing the CPU time usage across the two results and the differences side by side.

Difference in CPU time between the two results in the following format: <Difference CPU Time> = <Result 1 CPU Time> – <Result 2 CPU Time>.

CPU time for the initial version of the tachyon_find_hotspots application.

CPU time for the optimized version of the tachyon_find_hotspots.

Identify the Performance Gain

Explore the Bottom-up pane to compare CPU time data for the first hotspot: CPU Time:r001hs - CPU Time:r002hs = CPU Time: Difference. 8.719s - 5.564s = 3.154s, which means that you got the optimization of ~3 seconds for the initialize_2D_buffer function.

If you switch to the Summary window, you see that the Elapsed time also shows 3.392 seconds of optimization for the whole application execution:

Einzelheiten zur Compiler-Optimierung finden Sie in unserem Optimierungshinweis.