Skip to content

[NVPTX] Fix generic address in st.bulk intrinsic #130740

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
Wolfram70 merged 1 commit into from
Mar 12, 2025
Merged

[NVPTX] Fix generic address in st.bulk intrinsic #130740

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 llvm/include/llvm/IR/IntrinsicsNVVM.td
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5274,7 +5274,7 @@ foreach shape = ["16x64b", "16x128b", "16x256b", "32x32b", "16x32bx2"] in {
//

def int_nvvm_st_bulk: DefaultAttrsIntrinsic<[],
[llvm_global_ptr_ty, llvm_i64_ty, llvm_i64_ty],
[llvm_ptr_ty, llvm_i64_ty, llvm_i64_ty],
[IntrArgMemOnly, IntrWriteMem,
WriteOnly<ArgIndex<0>>, NoCapture<ArgIndex<0>>, ImmArg<ArgIndex<2>>]>;

Expand Down
6 changes: 3 additions & 3 deletions llvm/test/CodeGen/NVPTX/st_bulk.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,8 +4,8 @@
; RUN: %if ptxas-12.8 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_100 -mattr=+ptx86 | %ptxas-verify -arch=sm_100 %}
; RUN: %if ptxas-12.8 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_100 -mattr=+ptx86 --nvptx-short-ptr | %ptxas-verify -arch=sm_100 %}

declare void @llvm.nvvm.st.bulk(ptr addrspace(1), i64, i64)
define void @st_bulk(ptr addrspace(1) %dest_addr, i64 %size) {
declare void @llvm.nvvm.st.bulk(ptr, i64, i64)
define void @st_bulk(ptr %dest_addr, i64 %size) {
; CHECK-LABEL: st_bulk(
; CHECK: {
; CHECK-NEXT: .reg .b64 %rd<3>;
Expand All @@ -15,7 +15,7 @@ define void @st_bulk(ptr addrspace(1) %dest_addr, i64 %size) {
; CHECK-NEXT: ld.param.u64 %rd2, [st_bulk_param_1];
; CHECK-NEXT: st.bulk [%rd1], %rd2, 0;
; CHECK-NEXT: ret;
call void @llvm.nvvm.st.bulk(ptr addrspace(1) %dest_addr, i64 %size, i64 0)
call void @llvm.nvvm.st.bulk(ptr %dest_addr, i64 %size, i64 0)
ret void
}

Expand Down