Skip to content

Commit

Permalink
Merge branch 'amd-staging' into spatial-multiplexing
Browse files Browse the repository at this point in the history
  • Loading branch information
ywang103-amd authored Dec 17, 2024
2 parents 9c7e6cf + b2ee53f commit 691794a
Show file tree
Hide file tree
Showing 4 changed files with 3 additions and 3 deletions.
Binary file added docs/data/profile/sample-roof-plot.jpg
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file removed docs/data/profile/sample-roof-plot.png
Binary file not shown.
4 changes: 2 additions & 2 deletions docs/how-to/profile/mode.rst
Original file line number Diff line number Diff line change
Expand Up @@ -445,10 +445,10 @@ successfully.
clutter. One chart plots FP32/FP64 performance while the other plots I8/FP16
performance.

The following image is a sample ``empirRoof_gpu-ALL_fp32_fp64.pdf`` roofline
The following image is a sample ``empirRoof_gpu-0_int8_fp16.pdf`` roofline
plot.

.. image:: ../../data/profile/sample-roof-plot.png
.. image:: ../../data/profile/sample-roof-plot.jpg
:align: center
:alt: Sample ROCm Compute Profiler roofline output
:width: 800
2 changes: 1 addition & 1 deletion src/roofline.py
Original file line number Diff line number Diff line change
Expand Up @@ -96,7 +96,7 @@ def roof_setup(self):
self.__run_parameters["workload_dir"] = os.path.join(
self.__run_parameters["workload_dir"],
self.__args.name,
self.__mspec.gpu_series,
self.__mspec.gpu_model,
)
# create new directory for roofline if it doesn't exist
if not os.path.isdir(self.__run_parameters["workload_dir"]):
Expand Down

0 comments on commit 691794a

Please sign in to comment.