Skip to content

[CuTe][SM70] Add comment clarifying signed cast requirement for blockIdx coords #3203

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
Flink-ddd wants to merge 1 commit into
base: main
Choose a base branch
from
+2 −2
Open

[CuTe][SM70] Add comment clarifying signed cast requirement for blockIdx coords #3203

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 include/cutlass/gemm/kernel/sm70_gemm.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -210,7 +210,7 @@ static_assert(is_valid_tile_scheduler, "SM70 kernel does not support specializin
int thread_idx = int(threadIdx.x);
auto blk_shape = TileShape{}; // (BLK_M,BLK_N,BLK_K)
auto [m_coord, n_coord, l_coord] = static_cast<uint3>(blockIdx);
auto blk_coord_mnkl = make_coord(int(m_coord), int(n_coord), _, int(l_coord)); // (m,n,k,l)
auto blk_coord_mnkl = make_coord(int(m_coord), int(n_coord), _, int(l_coord)); // (m,n,k,l) NOTE: int() cast needed; unsigned coords cause underflow in residue computation for small problem shapes.

// Represent the full tensors
Tensor mA_mkl = make_tensor(make_gmem_ptr(params.mainloop.ptr_A), make_shape(M,K,L), params.mainloop.dA); //(m,k,l)
Expand Down
2 changes: 1 addition & 1 deletion include/cutlass/gemm/kernel/sm70_gemm_array.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -217,7 +217,7 @@ static_assert(is_valid_tile_scheduler, "SM70 kernel does not support specializin
int thread_idx = int(threadIdx.x);
auto blk_shape = TileShape{}; // (BLK_M,BLK_N,BLK_K)
auto [m_coord, n_coord, l_coord] = static_cast<uint3>(blockIdx);
auto blk_coord_mnkl = make_coord(int(m_coord), int(n_coord), _, int(l_coord)); // (m,n,k,l)
auto blk_coord_mnkl = make_coord(int(m_coord), int(n_coord), _, int(l_coord)); // (m,n,k,l) NOTE: int() cast needed; unsigned coords cause underflow in residue computation for small problem shapes.

// Represent the full tensors
Tensor mA_mkl = make_tensor(make_gmem_ptr(params.mainloop.ptr_A[l_coord]), make_shape(M,K,1), params.mainloop.dA); //(m,k,l)
Expand Down