AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs update: highlight location of example workload source code

Browse Source 
Signed-off-by: Karl W. Schulz <karl.schulz@amd.com>


[ROCm/rocprofiler-compute commit: 0c1cd70864]
This commit is contained in:
Karl W. Schulz
2022-11-04 17:48:04 -05:00
parent b551420c80
commit 8576ca0b53
1 changed files with 9 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
projects/rocprofiler-compute/src/docs/performance_analysis.md
+9 -2
View File
@@ -6,9 +6,16 @@
:maxdepth: 4
```
The [Omniperf](https://github.com/AMDResearch/omniperf) repository comes with a sample GPU compute workload, *vcopy*. This workload is used throughout the following sections to demonstrate the use of Omniperf in MI GPU performance analysis.
The [Omniperf](https://github.com/AMDResearch/omniperf) repository
includes source code for a sample GPU compute workload,
__vcopy.cpp__. A copy of this file is available in the `share/sample`
subdirectory after a normal Omniperf installation, or via the
`$OMNIPERF_SHARE/sample` directory when using the supplied modulefile.
Unless otherwise noted, the performance analysis is done on the MI200 platform.
A compiled version of this workload is used throughout the following
sections to demonstrate the use of Omniperf in MI GPU performance
analysis. Unless otherwise noted, the performance analysis is done on
the MI200 platform.
## Workload Compilation
**vcopy compilation:**