Bureaucrats, cc_docs_admin, cc_staff
337
edits
OpenACC Tutorial - Profiling: Difference between revisions
Jump to navigation
Jump to search
no edit summary
No edit summary |
No edit summary |
||
| Line 94: | Line 94: | ||
======== Data collected at 100Hz frequency | ======== Data collected at 100Hz frequency | ||
}} | }} | ||
== NVIDIA NVPROF Command Line Profiler == | |||
Before working on the routine, we need to understand what the compiler is actually doing. Several questions we got to ask ourselves: | |||
* What optimizations were applied ? | |||
* What prevented further optimizations ? | |||
* Can very minor modification of the code affect the performance ? | |||