Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add broken mclk workaround for all arch #453 #556

Merged
merged 2 commits into from
Feb 7, 2025
Merged

Add broken mclk workaround for all arch #453 #556

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
48482e7
Add broken mclk workaround for all arch #453
vedithal-amd Feb 7, 2025
099e038
Remove unnecessary conditional and use 'is' operator
vedithal-amd Feb 7, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 3 additions & 2 deletions src/rocprof_compute_soc/soc_gfx908.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -65,8 +65,9 @@ def __init__(self, args, mspec):
self._mspec.lds_banks_per_cu = 32
self._mspec.pipes_per_gpu = 4
# --showmclkrange is broken in Mi100, hardcode freq
self._mspec.max_mclk = 1200
self._mspec.cur_mclk = 1200
if self._mspec.max_mclk is None or self._mspec.cur_mclk is None:
self._mspec.max_mclk = 1200
self._mspec.cur_mclk = 1200

@demarcate
def get_profiler_options(self):
Expand Down
6 changes: 6 additions & 0 deletions src/rocprof_compute_soc/soc_gfx90a.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -74,6 +74,12 @@ def __init__(self, args, mspec):
)
self.roofline_obj = Roofline(args, self._mspec)

# Workaround for broken --showmclkrange
# MI210/MI250/MI250X have 1600MHz mclk
if self._mspec.max_mclk is None or self._mspec.cur_mclk is None:
self._mspec.max_mclk = 1600
self._mspec.cur_mclk = 1600

# Set arch specific specs
self._mspec._l2_banks = 32
self._mspec.lds_banks_per_cu = 32
Expand Down
5 changes: 3 additions & 2 deletions src/rocprof_compute_soc/soc_gfx942.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -75,8 +75,9 @@ def __init__(self, args, mspec):
)
self.roofline_obj = Roofline(args, self._mspec)

# --showmclkrange is broken in MI308X, hardcode freq
if self._mspec.gpu_model == "MI308X":
# Workaround for broken --showmclkrange
# MI300X/MI300A/MI308X have 1300MHz mclk
if self._mspec.max_mclk is None or self._mspec.cur_mclk is None:
self._mspec.max_mclk = 1300
self._mspec.cur_mclk = 1300

Expand Down