Bureaucrats, cc_docs_admin, cc_staff
337
edits
OpenACC Tutorial - Profiling: Difference between revisions
no edit summary
No edit summary |
No edit summary |
||
| Line 58: | Line 58: | ||
}} | }} | ||
[[File:Pgprof-pic1.png|thumbnail|300px|Starting new session|right ]] | |||
Bellow are several snapshots demonstrating how to start with the PGPROF profiler. First step is to initiate a new session. | |||
Then browse for an executable file of the code you want to profile. | Then browse for an executable file of the code you want to profile. | ||
[[File:Pgprof-pic2.png|thumbnail| | [[File:Pgprof-pic2.png|thumbnail|300px|Browse for executable you want to profile|right ]] | ||
Then specify the profiling options. For example, if you need to profile CPU activity then set the "Profile execution of the CPU" box. | Then specify the profiling options. For example, if you need to profile CPU activity then set the "Profile execution of the CPU" box. | ||
[[File:Pgprof-pic2.png|thumbnail| | [[File:Pgprof-pic2.png|thumbnail|300px|Browse for executable you want to profile|right ]] | ||
== NVIDIA Visual Profiller == | |||
Another profiler available for OpenACC applications is NVIDIA Visual Profiler. It's a cross-platform analyzing tool for the codes written with OpenACC and CUDA C/C++ instructions. | |||
[[File:Nvvp-pic0.png|thumbnail|300px|The NVVP profiler|right ]] | |||
[[File:Nvvp-pic1.png|thumbnail|300px|Browse for executable you want to profile|right ]] | |||