Skip to content

[AMDGPU] Fix an invalid cast in AMDGPULateCodeGenPrepare::visitLoadInst #122494

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
Jan 13, 2025
Merged

[AMDGPU] Fix an invalid cast in AMDGPULateCodeGenPrepare::visitLoadInst #122494

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
7 changes: 5 additions & 2 deletions llvm/lib/Target/AMDGPU/AMDGPULateCodeGenPrepare.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -464,8 +464,11 @@ bool AMDGPULateCodeGenPrepare::visitLoadInst(LoadInst &LI) {
NewLd->setMetadata(LLVMContext::MD_range, nullptr);

unsigned ShAmt = Adjust * 8;
auto *NewVal = IRB.CreateBitCast(
IRB.CreateTrunc(IRB.CreateLShr(NewLd, ShAmt), IntNTy), LI.getType());
Value *NewVal = IRB.CreateBitCast(
IRB.CreateTrunc(IRB.CreateLShr(NewLd, ShAmt),
DL.typeSizeEqualsStoreSize(LI.getType()) ? IntNTy
: LI.getType()),
LI.getType());
LI.replaceAllUsesWith(NewVal);
DeadInsts.emplace_back(&LI);

Expand Down
37 changes: 37 additions & 0 deletions llvm/test/CodeGen/AMDGPU/invalid-cast-load-i1.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,37 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx90a %s -o - | FileCheck %s

define amdgpu_kernel void @load_idx_idy(ptr addrspace(4) %disp, ptr %g) {
; CHECK-LABEL: load_idx_idy:
; CHECK: ; %bb.0: ; %entry
; CHECK-NEXT: s_load_dword s6, s[4:5], 0x4
; CHECK-NEXT: s_load_dwordx4 s[0:3], s[8:9], 0x0
; CHECK-NEXT: v_mov_b32_e32 v0, 0
; CHECK-NEXT: s_waitcnt lgkmcnt(0)
; CHECK-NEXT: s_lshr_b32 s4, s6, 16
; CHECK-NEXT: s_bfe_i64 s[4:5], s[4:5], 0x10000
; CHECK-NEXT: s_lshl_b64 s[4:5], s[4:5], 6
; CHECK-NEXT: s_add_u32 s0, s0, s4
; CHECK-NEXT: s_addc_u32 s1, s1, s5
; CHECK-NEXT: global_load_ubyte v2, v0, s[0:1] offset:4
; CHECK-NEXT: v_mov_b32_e32 v0, s2
; CHECK-NEXT: v_mov_b32_e32 v1, s3
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: flat_store_byte v[0:1], v2
; CHECK-NEXT: s_endpgm
entry:
%disp1 = tail call ptr addrspace(4) @llvm.amdgcn.dispatch.ptr()
Copy link
Contributor

@arsenm arsenm Jan 13, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Should be able to use a pointer argument and avoid the special intrinsic. Also can you merge this in with an existing test for this function?

Copy link
Contributor Author

@shiltian shiltian Jan 13, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Should be able to use a pointer argument and avoid the special intrinsic.

The current version was from llvm-reduce. I did try to get rid of the intrinsic but failed to do so, then I didn't dig more into that.

Also can you merge this in with an existing test for this function?

I'm not sure which existing test can be a good fit for this one.

Copy link
Contributor

@arsenm arsenm Jan 13, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

You probably missed adding the dereferenceable and align attributes to the pointer, which are implied by the intrinsic declaration

%gep_y = getelementptr i8, ptr addrspace(4) %disp1, i64 6
%L = load i1, ptr addrspace(4) %gep_y, align 1
%idxprom = sext i1 %L to i64
%gep0 = getelementptr <32 x i16>, ptr addrspace(4) %disp, i64 %idxprom
%gep1 = getelementptr i8, ptr addrspace(4) %gep0, i64 4
%L1 = load i8, ptr addrspace(4) %gep1
store i8 %L1, ptr %g
ret void
}

; Function Attrs: nocallback nofree nosync nounwind speculatable willreturn memory(none)
declare noundef nonnull align 4 ptr addrspace(4) @llvm.amdgcn.dispatch.ptr() #0

attributes #0 = { nocallback nofree nosync nounwind speculatable willreturn memory(none) }
Loading