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

Use plain llvmcall calling convention for WMMA intrinsics. #1709

Merged
merged 1 commit into from
Dec 28, 2022
Merged

Use plain llvmcall calling convention for WMMA intrinsics. #1709

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
6 changes: 3 additions & 3 deletions src/device/intrinsics/wmma.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -191,7 +191,7 @@ for ops in all_ldst_ops,
# Determine types + size for this (matrix, elem_type) combination
arr_ty, frag_ty, sz = get_frag_info(mat, elem_type, shape)

ccall_name = "extern $llvm_intr"
ccall_name = "$llvm_intr"

ptr_ty = LLVMPtr{arr_ty, addr_space_int}

Expand Down Expand Up @@ -257,7 +257,7 @@ export llvm_wmma_store
# Determine types + size for this (matrix, elem_type) combination
arr_ty, frag_ty, sz = get_frag_info(mat, elem_type, shape)

ccall_name = "extern $llvm_intr"
ccall_name = "$llvm_intr"
frag_types = ntuple(i -> frag_ty, sz)
frag_vars = ntuple(i -> :(data[$i]), sz)

Expand Down Expand Up @@ -329,7 +329,7 @@ for ops in all_wmma_ops,
c_arr_ty, c_frag_ty, c_sz = get_frag_info("c", c_elem_type, shape)
d_arr_ty, d_frag_ty, d_sz = get_frag_info("d", d_elem_type, shape)

ccall_name = "extern $llvm_intr"
ccall_name = "$llvm_intr"

a_types = ntuple(i -> a_frag_ty, a_sz)
b_types = ntuple(i -> b_frag_ty, b_sz)
Expand Down