Overview Report
default report divided into five main areas of concern
The Overview Report is the default report. Whenever a data file is opened, this is the first report displayed (with the exception of when --cg is used).
The Overview Report provides a high-level view of the program's performance characteristics, and is divided into five main areas. These are:
- Profile: The center of the Overview window displays a bar graph designed to give a high-level assessment of how much CPU time (as a percentage of wall-clock time) the program spent doing actual computation, versus Programming Model overhead (i.e., MPI communication, UPC or SHMEM data movement, OpenMP parallel region work, etc.) and I/O.
- If the program uses GPUs, a second bar graph is displayed showing GPU time relative to wall-clock time. The numbers in the GPU bar graph are the percentages of total time that were spent in the specified GPU functions, and thus are not expected to equal 100% of the wall-clock time.
- Function/Region Profile: The Function/Region Profile in the upper-left corner of the Overview Report highlights the top time-consuming functions or regions in the code. Click on the pie chart to jump to the Profile Report.
- Load Imbalance: The Load Imbalance summary in the lower-left corner of the Overview Report highlights load imbalance, if detected, as a percentage of wall-clock time. Click on the scales to jump to the Call Tree Report, if available (Call Tree is not available for samp_pc_time experiments).
- If an "i" ("information") icon is displayed, use the cursor to hover over it to see additional grid detection information and rank placement suggestions.
- Memory Utilization: The Memory Utilization summary in the upper-right corner of the Overview Report highlights poor memory hierarchy utilization, if detected, including TLB and cache utilization.
- If an "i" ("information") icon is displayed, use the cursor to hover over it to see additional observations.
- Data Movement: The Data Movement summary in the lower-right corner of the Overview Report identifies data movement bottlenecks, if detected.