Skip to content

[PERF IMPROVEMENT] Add amdgpu-waves-per-eu fn_attrs to 4 rigid/constraint kernels. #39

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

Open
kevinjosephamd wants to merge 1 commit into
base: amd-integration
Choose a base branch
from
+3 −4
Open

[PERF IMPROVEMENT] Add amdgpu-waves-per-eu fn_attrs to 4 rigid/constraint kernels. #39

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
2 changes: 1 addition & 1 deletion genesis/engine/solvers/rigid/constraint/solver.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2929,7 +2929,7 @@ def initialize_Ma(
# ======================================================= Core ========================================================


@qd.kernel(fastcache=gs.use_fastcache)
@qd.kernel(fastcache=gs.use_fastcache, fn_attrs={"amdgpu": {"amdgpu-waves-per-eu": "2,4"}})
def func_solve_init(
dofs_info: array_class.DofsInfo,
dofs_state: array_class.DofsState,
Expand Down
5 changes: 2 additions & 3 deletions genesis/engine/solvers/rigid/rigid_solver.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2626,7 +2626,7 @@ def equalities(self):
return gs.List(equality for entity in self._entities for equality in entity.equalities)


@qd.kernel(fastcache=gs.use_fastcache)
@qd.kernel(fastcache=gs.use_fastcache, fn_attrs={"amdgpu": {"amdgpu-waves-per-eu": "3,4"}})
def kernel_step_1(
links_state: array_class.LinksState,
links_info: array_class.LinksInfo,
Expand Down Expand Up @@ -2690,7 +2690,7 @@ def kernel_step_1(
)


@qd.kernel(fastcache=gs.use_fastcache)
@qd.kernel(fastcache=gs.use_fastcache, fn_attrs={"amdgpu": {"amdgpu-waves-per-eu": "1,4"}})
def kernel_step_2(
dofs_state: array_class.DofsState,
dofs_info: array_class.DofsInfo,
Expand Down Expand Up @@ -2799,4 +2799,3 @@ def kernel_step_2(
static_rigid_sim_config=static_rigid_sim_config,
is_backward=is_backward,
)