Skip to content

[Bugfix] Fix a bug when simplifying warp combination for T.gemm #540

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

Merged
merged 1 commit into from
May 31, 2025
Merged

[Bugfix] Fix a bug when simplifying warp combination for T.gemm #540

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
4 changes: 0 additions & 4 deletions src/op/gemm.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -197,10 +197,6 @@ std::pair<int, int> Gemm::ComputeWarpPartition(int num_warps, Target target,
// Try all possible combinations that satisfy the constraints
for (int m = 1; m <= max_m_warps && m <= num_warps; m++) {
int n = num_warps / m;
if (n > max_n_warps)
continue;
if (m * n != num_warps)
continue;

// Calculate how balanced this partition is
float m_per_warp = static_cast<float>(this->M) / (m * kMPerWarp);
Expand Down
3 changes: 3 additions & 0 deletions tilelang/jit/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -181,6 +181,9 @@ def wrapper(*args: _P.args, **kwargs: _P.kwargs) -> Any:
else:
raise ValueError(f"Invalid function type: {type(program_result_source)}")

if self.verbose:
logger.info(f"Verbose: Compiling for program \n {program_result.script()}")

kernel_result = compile(
program_result,
out_idx=self.out_idx,
Expand Down