Parallel Region Time is the total duration for all instances of all lexical parallel regions.
Total amount of time spent within a task.
The normalized sum of all cycles on all cores spent actively executing instructions.
Memory read from Shared Local Memory bandwidth.
Energy analysis is provided by the Intel® VTune™ Amplifier for Systems only. Energy analysis collection is supported for target Android*, Windows* or Linux* devices.
Displays the timeline for all features in the same time scale.
Other Time is unclassified Spin or Overhead time spent in a threading runtime library.
The Total Iteration Count metric provides a statistical estimation of the total number of iterations of the loop over entire profiling time.
Total number of bytes transferred directly between EUs and L3 caches.