Skip to content

[AMDGPU] Propagate alias information in AMDGPULowerKernelArguments. #161375

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

Jump to bottom
Merged
PeddleSpam merged 12 commits into from
Dec 21, 2025
Merged

[AMDGPU] Propagate alias information in AMDGPULowerKernelArguments. #161375

PeddleSpam merged 12 commits into from
Dec 21, 2025

Conversation

@PeddleSpam
Copy link
Contributor

@PeddleSpam PeddleSpam commented Sep 30, 2025 •
edited
Loading

Emit !noalias and alias.scope metadata for noalias kernel arguments.

@llvmbot
Copy link
Member

llvmbot commented Sep 30, 2025

@llvm/pr-subscribers-backend-amdgpu

Author: Leon Clark (PeddleSpam)

Changes

Emit !noalias metadata for noalias kernel arguments.

Patch is 50.28 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/161375.diff

1 Files Affected:

  • (added) llvm/test/CodeGen/AMDGPU/lower-noalias-kernargs.ll (+620)
diff --git a/llvm/test/CodeGen/AMDGPU/lower-noalias-kernargs.ll b/llvm/test/CodeGen/AMDGPU/lower-noalias-kernargs.ll
new file mode 100644
index 0000000000000..313ae3b883e56
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/lower-noalias-kernargs.ll
@@ -0,0 +1,620 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 6
+; RUN: opt -mtriple=amdgcn-- -S -o - -passes=amdgpu-lower-kernel-arguments %s | FileCheck %s
+
+define amdgpu_kernel void @aliasinfo_2i32(ptr addrspace(1) %out, ptr addrspace(1) %in) nounwind {
+; CHECK-LABEL: define amdgpu_kernel void @aliasinfo_2i32(
+; CHECK-SAME: ptr addrspace(1) [[OUT:%.*]], ptr addrspace(1) [[IN:%.*]]) #[[ATTR0:[0-9]+]] {
+; CHECK-NEXT:  [[ENTRY:.*:]]
+; CHECK-NEXT:    [[ALIASINFO_2I32_KERNARG_SEGMENT:%.*]] = call nonnull align 16 dereferenceable(272) ptr addrspace(4) @llvm.amdgcn.kernarg.segment.ptr()
+; CHECK-NEXT:    [[OUT_KERNARG_OFFSET:%.*]] = getelementptr inbounds i8, ptr addrspace(4) [[ALIASINFO_2I32_KERNARG_SEGMENT]], i64 36
+; CHECK-NEXT:    [[OUT_LOAD:%.*]] = load ptr addrspace(1), ptr addrspace(4) [[OUT_KERNARG_OFFSET]], align 4, !invariant.load [[META0:![0-9]+]]
+; CHECK-NEXT:    [[IN_KERNARG_OFFSET:%.*]] = getelementptr inbounds i8, ptr addrspace(4) [[ALIASINFO_2I32_KERNARG_SEGMENT]], i64 44
+; CHECK-NEXT:    [[IN_LOAD:%.*]] = load ptr addrspace(1), ptr addrspace(4) [[IN_KERNARG_OFFSET]], align 4, !invariant.load [[META0]]
+; CHECK-NEXT:    [[TID:%.*]] = call i32 @llvm.amdgcn.workitem.id.x()
+; CHECK-NEXT:    [[IN_GEP:%.*]] = getelementptr i32, ptr addrspace(1) [[IN_LOAD]], i32 [[TID]]
+; CHECK-NEXT:    [[VAL:%.*]] = load i32, ptr addrspace(1) [[IN_GEP]], align 4
+; CHECK-NEXT:    [[CTLZ:%.*]] = call i32 @llvm.ctlz.i32(i32 [[VAL]], i1 false) #[[ATTR5:[0-9]+]]
+; CHECK-NEXT:    store i32 [[CTLZ]], ptr addrspace(1) [[OUT_LOAD]], align 4
+; CHECK-NEXT:    ret void
+;
+entry:
+  %tid = call i32 @llvm.amdgcn.workitem.id.x()
+  %in.gep = getelementptr i32, ptr addrspace(1) %in, i32 %tid
+  %val = load i32, ptr addrspace(1) %in.gep, align 4
+  %ctlz = call i32 @llvm.ctlz.i32(i32 %val, i1 false) nounwind readnone
+  store i32 %ctlz, ptr addrspace(1) %out, align 4
+  ret void
+}
+
+define amdgpu_kernel void @aliasinfo_2i32_NA(ptr addrspace(1) noalias %out, ptr addrspace(1) noalias %in) nounwind {
+; CHECK-LABEL: define amdgpu_kernel void @aliasinfo_2i32_NA(
+; CHECK-SAME: ptr addrspace(1) noalias [[OUT:%.*]], ptr addrspace(1) noalias [[IN:%.*]]) #[[ATTR0]] {
+; CHECK-NEXT:  [[ENTRY:.*:]]
+; CHECK-NEXT:    [[ALIASINFO_2I32_NA_KERNARG_SEGMENT:%.*]] = call nonnull align 16 dereferenceable(272) ptr addrspace(4) @llvm.amdgcn.kernarg.segment.ptr()
+; CHECK-NEXT:    [[TID:%.*]] = call i32 @llvm.amdgcn.workitem.id.x()
+; CHECK-NEXT:    [[IN_GEP:%.*]] = getelementptr i32, ptr addrspace(1) [[IN]], i32 [[TID]]
+; CHECK-NEXT:    [[VAL:%.*]] = load i32, ptr addrspace(1) [[IN_GEP]], align 4
+; CHECK-NEXT:    [[CTLZ:%.*]] = call i32 @llvm.ctlz.i32(i32 [[VAL]], i1 false) #[[ATTR5]]
+; CHECK-NEXT:    store i32 [[CTLZ]], ptr addrspace(1) [[OUT]], align 4
+; CHECK-NEXT:    ret void
+;
+entry:
+  %tid = call i32 @llvm.amdgcn.workitem.id.x()
+  %in.gep = getelementptr i32, ptr addrspace(1) %in, i32 %tid
+  %val = load i32, ptr addrspace(1) %in.gep, align 4
+  %ctlz = call i32 @llvm.ctlz.i32(i32 %val, i1 false) nounwind readnone
+  store i32 %ctlz, ptr addrspace(1) %out, align 4
+  ret void
+}
+
+define amdgpu_kernel void @aliasinfo_2i32_AS(ptr addrspace(1) %out, ptr addrspace(1) %in) nounwind {
+; CHECK-LABEL: define amdgpu_kernel void @aliasinfo_2i32_AS(
+; CHECK-SAME: ptr addrspace(1) [[OUT:%.*]], ptr addrspace(1) [[IN:%.*]]) #[[ATTR0]] {
+; CHECK-NEXT:  [[ENTRY:.*:]]
+; CHECK-NEXT:    [[ALIASINFO_2I32_AS_KERNARG_SEGMENT:%.*]] = call nonnull align 16 dereferenceable(272) ptr addrspace(4) @llvm.amdgcn.kernarg.segment.ptr()
+; CHECK-NEXT:    [[OUT_KERNARG_OFFSET:%.*]] = getelementptr inbounds i8, ptr addrspace(4) [[ALIASINFO_2I32_AS_KERNARG_SEGMENT]], i64 36
+; CHECK-NEXT:    [[OUT_LOAD:%.*]] = load ptr addrspace(1), ptr addrspace(4) [[OUT_KERNARG_OFFSET]], align 4, !invariant.load [[META0]]
+; CHECK-NEXT:    [[IN_KERNARG_OFFSET:%.*]] = getelementptr inbounds i8, ptr addrspace(4) [[ALIASINFO_2I32_AS_KERNARG_SEGMENT]], i64 44
+; CHECK-NEXT:    [[IN_LOAD:%.*]] = load ptr addrspace(1), ptr addrspace(4) [[IN_KERNARG_OFFSET]], align 4, !invariant.load [[META0]]
+; CHECK-NEXT:    [[TID:%.*]] = call i32 @llvm.amdgcn.workitem.id.x()
+; CHECK-NEXT:    [[IN_GEP:%.*]] = getelementptr i32, ptr addrspace(1) [[IN_LOAD]], i32 [[TID]]
+; CHECK-NEXT:    [[VAL:%.*]] = load i32, ptr addrspace(1) [[IN_GEP]], align 4, !alias.scope [[META1:![0-9]+]], !noalias [[META4:![0-9]+]]
+; CHECK-NEXT:    [[CTLZ:%.*]] = call i32 @llvm.ctlz.i32(i32 [[VAL]], i1 false) #[[ATTR5]]
+; CHECK-NEXT:    store i32 [[CTLZ]], ptr addrspace(1) [[OUT_LOAD]], align 4, !alias.scope [[META4]], !noalias [[META1]]
+; CHECK-NEXT:    ret void
+;
+entry:
+  %tid = call i32 @llvm.amdgcn.workitem.id.x()
+  %in.gep = getelementptr i32, ptr addrspace(1) %in, i32 %tid
+  %val = load i32, ptr addrspace(1) %in.gep, align 4, !alias.scope !4, !noalias !2
+  %ctlz = call i32 @llvm.ctlz.i32(i32 %val, i1 false) nounwind readnone
+  store i32 %ctlz, ptr addrspace(1) %out, align 4, !alias.scope !2, !noalias !4
+  ret void
+}
+
+define amdgpu_kernel void @aliasinfo_2i32_NA_AS(ptr addrspace(1) noalias %out, ptr addrspace(1) noalias %in) nounwind {
+; CHECK-LABEL: define amdgpu_kernel void @aliasinfo_2i32_NA_AS(
+; CHECK-SAME: ptr addrspace(1) noalias [[OUT:%.*]], ptr addrspace(1) noalias [[IN:%.*]]) #[[ATTR0]] {
+; CHECK-NEXT:  [[ENTRY:.*:]]
+; CHECK-NEXT:    [[ALIASINFO_2I32_NA_AS_KERNARG_SEGMENT:%.*]] = call nonnull align 16 dereferenceable(272) ptr addrspace(4) @llvm.amdgcn.kernarg.segment.ptr()
+; CHECK-NEXT:    [[TID:%.*]] = call i32 @llvm.amdgcn.workitem.id.x()
+; CHECK-NEXT:    [[IN_GEP:%.*]] = getelementptr i32, ptr addrspace(1) [[IN]], i32 [[TID]]
+; CHECK-NEXT:    [[VAL:%.*]] = load i32, ptr addrspace(1) [[IN_GEP]], align 4, !alias.scope [[META1]], !noalias [[META4]]
+; CHECK-NEXT:    [[CTLZ:%.*]] = call i32 @llvm.ctlz.i32(i32 [[VAL]], i1 false) #[[ATTR5]]
+; CHECK-NEXT:    store i32 [[CTLZ]], ptr addrspace(1) [[OUT]], align 4, !alias.scope [[META4]], !noalias [[META1]]
+; CHECK-NEXT:    ret void
+;
+entry:
+  %tid = call i32 @llvm.amdgcn.workitem.id.x()
+  %in.gep = getelementptr i32, ptr addrspace(1) %in, i32 %tid
+  %val = load i32, ptr addrspace(1) %in.gep, align 4, !alias.scope !4, !noalias !2
+  %ctlz = call i32 @llvm.ctlz.i32(i32 %val, i1 false) nounwind readnone
+  store i32 %ctlz, ptr addrspace(1) %out, align 4, !alias.scope !2, !noalias !4
+  ret void
+}
+
+define amdgpu_kernel void @aliasinfo_v4f32_3v4i8(ptr addrspace(1) %out, ptr addrspace(1) %out1, ptr addrspace(1) %in, ptr addrspace(1) %in1) nounwind {
+; CHECK-LABEL: define amdgpu_kernel void @aliasinfo_v4f32_3v4i8(
+; CHECK-SAME: ptr addrspace(1) [[OUT:%.*]], ptr addrspace(1) [[OUT1:%.*]], ptr addrspace(1) [[IN:%.*]], ptr addrspace(1) [[IN1:%.*]]) #[[ATTR0]] {
+; CHECK-NEXT:  [[ENTRY:.*:]]
+; CHECK-NEXT:    [[ALIASINFO_V4F32_3V4I8_KERNARG_SEGMENT:%.*]] = call nonnull align 16 dereferenceable(288) ptr addrspace(4) @llvm.amdgcn.kernarg.segment.ptr()
+; CHECK-NEXT:    [[OUT_KERNARG_OFFSET:%.*]] = getelementptr inbounds i8, ptr addrspace(4) [[ALIASINFO_V4F32_3V4I8_KERNARG_SEGMENT]], i64 36
+; CHECK-NEXT:    [[OUT_LOAD:%.*]] = load ptr addrspace(1), ptr addrspace(4) [[OUT_KERNARG_OFFSET]], align 4, !invariant.load [[META0]]
+; CHECK-NEXT:    [[OUT1_KERNARG_OFFSET:%.*]] = getelementptr inbounds i8, ptr addrspace(4) [[ALIASINFO_V4F32_3V4I8_KERNARG_SEGMENT]], i64 44
+; CHECK-NEXT:    [[OUT1_LOAD:%.*]] = load ptr addrspace(1), ptr addrspace(4) [[OUT1_KERNARG_OFFSET]], align 4, !invariant.load [[META0]]
+; CHECK-NEXT:    [[IN_KERNARG_OFFSET:%.*]] = getelementptr inbounds i8, ptr addrspace(4) [[ALIASINFO_V4F32_3V4I8_KERNARG_SEGMENT]], i64 52
+; CHECK-NEXT:    [[IN_LOAD:%.*]] = load ptr addrspace(1), ptr addrspace(4) [[IN_KERNARG_OFFSET]], align 4, !invariant.load [[META0]]
+; CHECK-NEXT:    [[IN1_KERNARG_OFFSET:%.*]] = getelementptr inbounds i8, ptr addrspace(4) [[ALIASINFO_V4F32_3V4I8_KERNARG_SEGMENT]], i64 60
+; CHECK-NEXT:    [[IN1_LOAD:%.*]] = load ptr addrspace(1), ptr addrspace(4) [[IN1_KERNARG_OFFSET]], align 4, !invariant.load [[META0]]
+; CHECK-NEXT:    [[TID:%.*]] = call i32 @llvm.amdgcn.workitem.id.x()
+; CHECK-NEXT:    [[GEP:%.*]] = getelementptr <4 x i8>, ptr addrspace(1) [[IN_LOAD]], i32 [[TID]]
+; CHECK-NEXT:    [[GEP1:%.*]] = getelementptr <4 x i8>, ptr addrspace(1) [[IN1_LOAD]], i32 [[TID]]
+; CHECK-NEXT:    [[LOAD:%.*]] = load <4 x i8>, ptr addrspace(1) [[GEP]], align 1
+; CHECK-NEXT:    [[LOAD1:%.*]] = load <4 x i8>, ptr addrspace(1) [[GEP1]], align 1
+; CHECK-NEXT:    [[SHUFFLE0_0:%.*]] = shufflevector <4 x i8> [[LOAD]], <4 x i8> [[LOAD1]], <4 x i32> <i32 3, i32 2, i32 6, i32 2>
+; CHECK-NEXT:    [[CVT:%.*]] = uitofp <4 x i8> [[SHUFFLE0_0]] to <4 x float>
+; CHECK-NEXT:    store <4 x float> [[CVT]], ptr addrspace(1) [[OUT_LOAD]], align 16
+; CHECK-NEXT:    store <4 x i8> [[SHUFFLE0_0]], ptr addrspace(1) [[OUT1_LOAD]], align 4
+; CHECK-NEXT:    ret void
+;
+entry:
+  %tid = call i32 @llvm.amdgcn.workitem.id.x()
+  %gep = getelementptr <4 x i8>, ptr addrspace(1) %in, i32 %tid
+  %gep1 = getelementptr <4 x i8>, ptr addrspace(1) %in1, i32 %tid
+  %load = load <4 x i8>, ptr addrspace(1) %gep, align 1
+  %load1 = load <4 x i8>, ptr addrspace(1) %gep1, align 1
+  %shuffle0_0 = shufflevector <4 x i8> %load, <4 x i8> %load1, <4 x i32> <i32 3, i32 2, i32 6, i32 2>
+  %cvt = uitofp <4 x i8> %shuffle0_0 to <4 x float>
+  store <4 x float> %cvt, ptr addrspace(1) %out, align 16
+  store <4 x i8> %shuffle0_0, ptr addrspace(1) %out1, align 4
+  ret void
+}
+
+define amdgpu_kernel void @aliasinfo_v4f32_3v4i8_NA(ptr addrspace(1) noalias %out, ptr addrspace(1) noalias %out1, ptr addrspace(1) noalias %in, ptr addrspace(1) noalias %in1) nounwind {
+; CHECK-LABEL: define amdgpu_kernel void @aliasinfo_v4f32_3v4i8_NA(
+; CHECK-SAME: ptr addrspace(1) noalias [[OUT:%.*]], ptr addrspace(1) noalias [[OUT1:%.*]], ptr addrspace(1) noalias [[IN:%.*]], ptr addrspace(1) noalias [[IN1:%.*]]) #[[ATTR0]] {
+; CHECK-NEXT:  [[ENTRY:.*:]]
+; CHECK-NEXT:    [[ALIASINFO_V4F32_3V4I8_NA_KERNARG_SEGMENT:%.*]] = call nonnull align 16 dereferenceable(288) ptr addrspace(4) @llvm.amdgcn.kernarg.segment.ptr()
+; CHECK-NEXT:    [[TID:%.*]] = call i32 @llvm.amdgcn.workitem.id.x()
+; CHECK-NEXT:    [[GEP:%.*]] = getelementptr <4 x i8>, ptr addrspace(1) [[IN]], i32 [[TID]]
+; CHECK-NEXT:    [[GEP1:%.*]] = getelementptr <4 x i8>, ptr addrspace(1) [[IN1]], i32 [[TID]]
+; CHECK-NEXT:    [[LOAD:%.*]] = load <4 x i8>, ptr addrspace(1) [[GEP]], align 1
+; CHECK-NEXT:    [[LOAD1:%.*]] = load <4 x i8>, ptr addrspace(1) [[GEP1]], align 1
+; CHECK-NEXT:    [[SHUFFLE0_0:%.*]] = shufflevector <4 x i8> [[LOAD]], <4 x i8> [[LOAD1]], <4 x i32> <i32 3, i32 2, i32 6, i32 2>
+; CHECK-NEXT:    [[CVT:%.*]] = uitofp <4 x i8> [[SHUFFLE0_0]] to <4 x float>
+; CHECK-NEXT:    store <4 x float> [[CVT]], ptr addrspace(1) [[OUT]], align 16
+; CHECK-NEXT:    store <4 x i8> [[SHUFFLE0_0]], ptr addrspace(1) [[OUT1]], align 4
+; CHECK-NEXT:    ret void
+;
+entry:
+  %tid = call i32 @llvm.amdgcn.workitem.id.x()
+  %gep = getelementptr <4 x i8>, ptr addrspace(1) %in, i32 %tid
+  %gep1 = getelementptr <4 x i8>, ptr addrspace(1) %in1, i32 %tid
+  %load = load <4 x i8>, ptr addrspace(1) %gep, align 1
+  %load1 = load <4 x i8>, ptr addrspace(1) %gep1, align 1
+  %shuffle0_0 = shufflevector <4 x i8> %load, <4 x i8> %load1, <4 x i32> <i32 3, i32 2, i32 6, i32 2>
+  %cvt = uitofp <4 x i8> %shuffle0_0 to <4 x float>
+  store <4 x float> %cvt, ptr addrspace(1) %out, align 16
+  store <4 x i8> %shuffle0_0, ptr addrspace(1) %out1, align 4
+  ret void
+}
+
+define amdgpu_kernel void @aliasinfo_v4f32_3v4i8_AS(ptr addrspace(1) %out, ptr addrspace(1) %out1, ptr addrspace(1) %in, ptr addrspace(1) %in1) nounwind {
+; CHECK-LABEL: define amdgpu_kernel void @aliasinfo_v4f32_3v4i8_AS(
+; CHECK-SAME: ptr addrspace(1) [[OUT:%.*]], ptr addrspace(1) [[OUT1:%.*]], ptr addrspace(1) [[IN:%.*]], ptr addrspace(1) [[IN1:%.*]]) #[[ATTR0]] {
+; CHECK-NEXT:  [[ENTRY:.*:]]
+; CHECK-NEXT:    [[ALIASINFO_V4F32_3V4I8_AS_KERNARG_SEGMENT:%.*]] = call nonnull align 16 dereferenceable(288) ptr addrspace(4) @llvm.amdgcn.kernarg.segment.ptr()
+; CHECK-NEXT:    [[OUT_KERNARG_OFFSET:%.*]] = getelementptr inbounds i8, ptr addrspace(4) [[ALIASINFO_V4F32_3V4I8_AS_KERNARG_SEGMENT]], i64 36
+; CHECK-NEXT:    [[OUT_LOAD:%.*]] = load ptr addrspace(1), ptr addrspace(4) [[OUT_KERNARG_OFFSET]], align 4, !invariant.load [[META0]]
+; CHECK-NEXT:    [[OUT1_KERNARG_OFFSET:%.*]] = getelementptr inbounds i8, ptr addrspace(4) [[ALIASINFO_V4F32_3V4I8_AS_KERNARG_SEGMENT]], i64 44
+; CHECK-NEXT:    [[OUT1_LOAD:%.*]] = load ptr addrspace(1), ptr addrspace(4) [[OUT1_KERNARG_OFFSET]], align 4, !invariant.load [[META0]]
+; CHECK-NEXT:    [[IN_KERNARG_OFFSET:%.*]] = getelementptr inbounds i8, ptr addrspace(4) [[ALIASINFO_V4F32_3V4I8_AS_KERNARG_SEGMENT]], i64 52
+; CHECK-NEXT:    [[IN_LOAD:%.*]] = load ptr addrspace(1), ptr addrspace(4) [[IN_KERNARG_OFFSET]], align 4, !invariant.load [[META0]]
+; CHECK-NEXT:    [[IN1_KERNARG_OFFSET:%.*]] = getelementptr inbounds i8, ptr addrspace(4) [[ALIASINFO_V4F32_3V4I8_AS_KERNARG_SEGMENT]], i64 60
+; CHECK-NEXT:    [[IN1_LOAD:%.*]] = load ptr addrspace(1), ptr addrspace(4) [[IN1_KERNARG_OFFSET]], align 4, !invariant.load [[META0]]
+; CHECK-NEXT:    [[TID:%.*]] = call i32 @llvm.amdgcn.workitem.id.x()
+; CHECK-NEXT:    [[GEP:%.*]] = getelementptr <4 x i8>, ptr addrspace(1) [[IN_LOAD]], i32 [[TID]]
+; CHECK-NEXT:    [[GEP1:%.*]] = getelementptr <4 x i8>, ptr addrspace(1) [[IN1_LOAD]], i32 [[TID]]
+; CHECK-NEXT:    [[LOAD:%.*]] = load <4 x i8>, ptr addrspace(1) [[GEP]], align 1, !alias.scope [[META1]], !noalias [[META4]]
+; CHECK-NEXT:    [[LOAD1:%.*]] = load <4 x i8>, ptr addrspace(1) [[GEP1]], align 1, !alias.scope [[META1]], !noalias [[META4]]
+; CHECK-NEXT:    [[SHUFFLE0_0:%.*]] = shufflevector <4 x i8> [[LOAD]], <4 x i8> [[LOAD1]], <4 x i32> <i32 3, i32 2, i32 6, i32 2>
+; CHECK-NEXT:    [[CVT:%.*]] = uitofp <4 x i8> [[SHUFFLE0_0]] to <4 x float>
+; CHECK-NEXT:    store <4 x float> [[CVT]], ptr addrspace(1) [[OUT_LOAD]], align 16, !alias.scope [[META4]], !noalias [[META1]]
+; CHECK-NEXT:    store <4 x i8> [[SHUFFLE0_0]], ptr addrspace(1) [[OUT1_LOAD]], align 4, !alias.scope [[META4]], !noalias [[META1]]
+; CHECK-NEXT:    ret void
+;
+entry:
+  %tid = call i32 @llvm.amdgcn.workitem.id.x()
+  %gep = getelementptr <4 x i8>, ptr addrspace(1) %in, i32 %tid
+  %gep1 = getelementptr <4 x i8>, ptr addrspace(1) %in1, i32 %tid
+  %load = load <4 x i8>, ptr addrspace(1) %gep, align 1, !alias.scope !4, !noalias !2
+  %load1 = load <4 x i8>, ptr addrspace(1) %gep1, align 1, !alias.scope !4, !noalias !2
+  %shuffle0_0 = shufflevector <4 x i8> %load, <4 x i8> %load1, <4 x i32> <i32 3, i32 2, i32 6, i32 2>
+  %cvt = uitofp <4 x i8> %shuffle0_0 to <4 x float>
+  store <4 x float> %cvt, ptr addrspace(1) %out, align 16, !alias.scope !2, !noalias !4
+  store <4 x i8> %shuffle0_0, ptr addrspace(1) %out1, align 4, !alias.scope !2, !noalias !4
+  ret void
+}
+
+define amdgpu_kernel void @aliasinfo_v4f32_3v4i8_NA_AS(ptr addrspace(1) noalias %out, ptr addrspace(1) noalias %out1, ptr addrspace(1) noalias %in, ptr addrspace(1) noalias %in1) nounwind {
+; CHECK-LABEL: define amdgpu_kernel void @aliasinfo_v4f32_3v4i8_NA_AS(
+; CHECK-SAME: ptr addrspace(1) noalias [[OUT:%.*]], ptr addrspace(1) noalias [[OUT1:%.*]], ptr addrspace(1) noalias [[IN:%.*]], ptr addrspace(1) noalias [[IN1:%.*]]) #[[ATTR0]] {
+; CHECK-NEXT:  [[ENTRY:.*:]]
+; CHECK-NEXT:    [[ALIASINFO_V4F32_3V4I8_NA_AS_KERNARG_SEGMENT:%.*]] = call nonnull align 16 dereferenceable(288) ptr addrspace(4) @llvm.amdgcn.kernarg.segment.ptr()
+; CHECK-NEXT:    [[TID:%.*]] = call i32 @llvm.amdgcn.workitem.id.x()
+; CHECK-NEXT:    [[GEP:%.*]] = getelementptr <4 x i8>, ptr addrspace(1) [[IN]], i32 [[TID]]
+; CHECK-NEXT:    [[GEP1:%.*]] = getelementptr <4 x i8>, ptr addrspace(1) [[IN1]], i32 [[TID]]
+; CHECK-NEXT:    [[LOAD:%.*]] = load <4 x i8>, ptr addrspace(1) [[GEP]], align 1, !alias.scope [[META1]], !noalias [[META4]]
+; CHECK-NEXT:    [[LOAD1:%.*]] = load <4 x i8>, ptr addrspace(1) [[GEP1]], align 1, !alias.scope [[META1]], !noalias [[META4]]
+; CHECK-NEXT:    [[SHUFFLE0_0:%.*]] = shufflevector <4 x i8> [[LOAD]], <4 x i8> [[LOAD1]], <4 x i32> <i32 3, i32 2, i32 6, i32 2>
+; CHECK-NEXT:    [[CVT:%.*]] = uitofp <4 x i8> [[SHUFFLE0_0]] to <4 x float>
+; CHECK-NEXT:    store <4 x float> [[CVT]], ptr addrspace(1) [[OUT]], align 16, !alias.scope [[META4]], !noalias [[META1]]
+; CHECK-NEXT:    store <4 x i8> [[SHUFFLE0_0]], ptr addrspace(1) [[OUT1]], align 4, !alias.scope [[META4]], !noalias [[META1]]
+; CHECK-NEXT:    ret void
+;
+entry:
+  %tid = call i32 @llvm.amdgcn.workitem.id.x()
+  %gep = getelementptr <4 x i8>, ptr addrspace(1) %in, i32 %tid
+  %gep1 = getelementptr <4 x i8>, ptr addrspace(1) %in1, i32 %tid
+  %load = load <4 x i8>, ptr addrspace(1) %gep, align 1, !alias.scope !4, !noalias !2
+  %load1 = load <4 x i8>, ptr addrspace(1) %gep1, align 1, !alias.scope !4, !noalias !2
+  %shuffle0_0 = shufflevector <4 x i8> %load, <4 x i8> %load1, <4 x i32> <i32 3, i32 2, i32 6, i32 2>
+  %cvt = uitofp <4 x i8> %shuffle0_0 to <4 x float>
+  store <4 x float> %cvt, ptr addrspace(1) %out, align 16, !alias.scope !2, !noalias !4
+  store <4 x i8> %shuffle0_0, ptr addrspace(1) %out1, align 4, !alias.scope !2, !noalias !4
+  ret void
+}
+
+define amdgpu_kernel void @aliasinfo_10v16f16(ptr addrspace(3) %in, ptr addrspace(3) %out) #0 {
+; CHECK-LABEL: define amdgpu_kernel void @aliasinfo_10v16f16(
+; CHECK-SAME: ptr addrspace(3) [[IN:%.*]], ptr addrspace(3) [[OUT:%.*]]) #[[ATTR1:[0-9]+]] {
+; CHECK-NEXT:  [[ENTRY:.*:]]
+; CHECK-NEXT:    [[ALIASINFO_10V16F16_KERNARG_SEGMENT:%.*]] = call nonnull align 16 dereferenceable(264) ptr addrspace(4) @llvm.amdgcn.kernarg.segment.ptr()
+; CHECK-NEXT:    [[IDX:%.*]] = call i32 @llvm.amdgcn.workitem.id.x()
+; CHECK-NEXT:    [[LOAD_0_ADDR:%.*]] = getelementptr <16 x half>, ptr addrspace(3) [[IN]], i32 [[IDX]]
+; CHECK-NEXT:    [[LOAD_0:%.*]] = load <16 x half>, ptr addrspace(3) [[LOAD_0_ADDR]], align 32
+; CHECK-NEXT:    [[LOAD_1_ADDR:%.*]] = getelementptr <16 x half>, ptr addrspace(3) [[LOAD_0_ADDR]], i32 64
+; CHECK-NEXT:    [[LOAD_1:%.*]] = load <16 x half>, ptr addrspace(3) [[LOAD_1_ADDR]], align 32
+; CHECK-NEXT:    [[LOAD_2_ADDR:%.*]] = getelementptr <16 x half>, ptr addrspace(3) [[LOAD_1_ADDR]], i32 128
+; CHECK-NEXT:    [[LOAD_2:%.*]] = load <16 x half>, ptr addrspace(3) [[LOAD_2_ADDR]], align 32
+; CHECK-NEXT:    [[LOAD_3_ADDR:%.*]] = getelementptr <16 x half>, ptr addrspace(3) [[LOAD_2_ADDR]], i32 192
+; CHECK-NEXT:    [[LOAD_3:%.*]] = load <16 x half>, ptr addrspace(3) [[LOAD_3_ADDR]], align 32
+; CHECK-NEXT:    [[LOAD_4_ADDR:%.*]] = getelementptr <16 x half>, ptr addrspace(3) [[LOAD_3_ADDR]], i32 256
+; CHECK-NEXT:    [[LOAD_4:%.*]] = load <16 x half>, ptr addrspace(3) [[LOAD_4_ADDR]], align 32
+; CHECK-NEXT:    [[MAI_0:%.*]] = call <16 x half> @llvm.amdgcn.wmma.f16.16x16x16.f16.v16f16.v16f16(<16 x half> [[LOAD_0]], <16 x half> [[LOAD_0]], <16 x half> [[LOAD_0]], i1 false)
+; CHECK-NEXT:    [[MAI_1:%.*]] = call <16 x half> @llvm.amdgcn.wmma.f16.16x16x16.f16.v16f16.v16f16(<16 x half> [[LOAD_1]], <16 x half> [[LOAD_1]], <16 x half> [[LOAD_1]], i1 false)
+; CHECK-NEXT:    [[MAI_2:%.*]] = call <16 x half> @llvm.amdgcn.wmma.f16.16x16x16.f16.v16f16.v16f16(<16 x half> [[LOAD_2]], <16 x half> [[LOAD_2]], <16 x half> [[LOAD_2]], i1 false)
+; CHECK-NEXT:    [[MAI_3:%.*]] = call <16 x half> @llvm.amdgcn.wmma.f16.16x16x16.f16.v16f16.v16f16(<16 x half> [[LOAD_3]], <16 x half> [[LOAD_3]], <16 x half> [[LOAD_3]], i1 false)
+; CHECK-NEXT:    [[MAI_4:%.*]] = call <16 x half> @llvm.amdgcn.wmma.f16.16x16x16.f16.v16f16.v16f16(<16 x half> [[LOAD_4]], <16 x half> [[LOAD_4]], <16 x half> [[LOAD_4]], i1 false)
+; CHECK-NEXT:    [[STORE_0_ADDR:%.*]] = getelementptr <16 x half>, ptr addrspace(3) [[OUT]], i32 [[IDX]]
+; CHECK-NEXT:    store <16 x half> [[MAI_0]], ptr addrspace(3) [[STORE_0_ADDR]], align 32
+; CHECK-NEXT:    [[STORE_1_ADDR:%.*]] = getelementptr <16 x half>, ptr addrspace(3) [[OUT]], i32 64
+; CHECK-NEXT:    store <16 x half> [[MAI_1]], ptr addrspace(3) [[STORE_1_ADDR]], align ...
[truncated]

arsenm
arsenm requested changes Oct 10, 2025
View reviewed changes
Copy link
Contributor

@arsenm arsenm left a comment

Choose a reason for hiding this comment

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

Is this supposed to just be a baseline test? The title sounds like it should be the actual change, but that's missing?

@PeddleSpam PeddleSpam mentioned this pull request Nov 20, 2025
Merged
PeddleSpam added a commit that referenced this pull request Nov 24, 2025
@PeddleSpam
[AMDGPU] Propagate AA info in vector load/store splitting. (#168871)
ee4f647 
Fixes a bug in `AMDGPUISelLowering` where alias analysis info is not
propagated to split loads and stores.

This is required for #161375

---------

Co-authored-by: Leon Clark <[email protected]>
@github-actions
Copy link

github-actions bot commented Nov 24, 2025 •
edited
Loading

✅ With the latest revision this PR passed the C/C++ code formatter.

arsenm
arsenm reviewed Nov 24, 2025
View reviewed changes
arsenm
arsenm reviewed Nov 25, 2025
View reviewed changes
aadeshps-mcw pushed a commit to aadeshps-mcw/llvm-project that referenced this pull request Nov 26, 2025
@PeddleSpam @aadeshps-mcw
[AMDGPU] Propagate AA info in vector load/store splitting. (llvm#168871)
2aea285 
Fixes a bug in `AMDGPUISelLowering` where alias analysis info is not
propagated to split loads and stores.

This is required for llvm#161375

---------

Co-authored-by: Leon Clark <[email protected]>
Priyanshu3820 pushed a commit to Priyanshu3820/llvm-project that referenced this pull request Nov 26, 2025
@PeddleSpam @Priyanshu3820
[AMDGPU] Propagate AA info in vector load/store splitting. (llvm#168871)
4fd84c5 
Fixes a bug in `AMDGPUISelLowering` where alias analysis info is not
propagated to split loads and stores.

This is required for llvm#161375

---------

Co-authored-by: Leon Clark <[email protected]>
@PeddleSpam PeddleSpam requested a review from arsenm November 27, 2025 04:28
augusto2112 pushed a commit to augusto2112/llvm-project that referenced this pull request Dec 3, 2025
@PeddleSpam @augusto2112
[AMDGPU] Propagate AA info in vector load/store splitting. (llvm#168871)
7f8febf 
Fixes a bug in `AMDGPUISelLowering` where alias analysis info is not
propagated to split loads and stores.

This is required for llvm#161375

---------

Co-authored-by: Leon Clark <[email protected]>
arsenm
arsenm reviewed Dec 8, 2025
View reviewed changes
@PeddleSpam PeddleSpam mentioned this pull request Dec 17, 2025
Closed
@PeddleSpam PeddleSpam requested a review from arsenm December 18, 2025 15:44
@PeddleSpam PeddleSpam merged commit 9f4f13a into llvm:main Dec 21, 2025
10 checks passed
@llvm-ci
Copy link
Collaborator

llvm-ci commented Dec 21, 2025

LLVM Buildbot has detected a new failure on builder sanitizer-aarch64-linux-bootstrap-ubsan running on sanitizer-buildbot9 while building llvm at step 2 "annotate".

Full details are available at: https://lab.llvm.org/buildbot/#/builders/85/builds/16928

Here is the relevant piece of the build log for the reference 
Step 2 (annotate) failure: 'python ../sanitizer_buildbot/sanitizers/zorg/buildbot/builders/sanitizers/buildbot_selector.py' (failure)
...
llvm-lit: /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/utils/lit/lit/llvm/config.py:564: note: using lld-link: /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/lld-link
llvm-lit: /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/utils/lit/lit/llvm/config.py:564: note: using ld64.lld: /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/ld64.lld
llvm-lit: /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/utils/lit/lit/llvm/config.py:564: note: using wasm-ld: /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/wasm-ld
llvm-lit: /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/utils/lit/lit/llvm/config.py:564: note: using ld.lld: /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/ld.lld
llvm-lit: /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/utils/lit/lit/llvm/config.py:564: note: using lld-link: /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/lld-link
llvm-lit: /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/utils/lit/lit/llvm/config.py:564: note: using ld64.lld: /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/ld64.lld
llvm-lit: /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/utils/lit/lit/llvm/config.py:564: note: using wasm-ld: /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/wasm-ld
llvm-lit: /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/utils/lit/lit/main.py:74: note: The test suite configuration requested an individual test timeout of 0 seconds but a timeout of 900 seconds was requested on the command line. Forcing timeout to be 900 seconds.
-- Testing: 93499 tests, 72 workers --
Testing:  0.. 10.. 20.. 30
FAIL: LLVM :: CodeGen/AMDGPU/lower-kernargs.ll (32785 of 93499)
******************** TEST 'LLVM :: CodeGen/AMDGPU/lower-kernargs.ll' FAILED ********************
Exit Code: 2

Command Output (stdout):
--
# RUN: at line 2
/home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/opt -mtriple=amdgcn-amd-amdhsa -S -o - -passes=amdgpu-lower-kernel-arguments /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/test/CodeGen/AMDGPU/lower-kernargs.ll | /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/FileCheck -check-prefixes=GCN,HSA /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/test/CodeGen/AMDGPU/lower-kernargs.ll
# executed command: /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/opt -mtriple=amdgcn-amd-amdhsa -S -o - -passes=amdgpu-lower-kernel-arguments /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/test/CodeGen/AMDGPU/lower-kernargs.ll
# .---command stderr------------
# | PLEASE submit a bug report to https://github.com/llvm/llvm-project/issues/ and include the crash backtrace and instructions to reproduce the bug.
# | Stack dump:
# | 0.	Program arguments: /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/opt -mtriple=amdgcn-amd-amdhsa -S -o - -passes=amdgpu-lower-kernel-arguments /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/test/CodeGen/AMDGPU/lower-kernargs.ll
# | 1.	Running pass "function(amdgpu-lower-kernel-arguments)" on module "/home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/test/CodeGen/AMDGPU/lower-kernargs.ll"
# | 2.	Running pass "amdgpu-lower-kernel-arguments" on function "kern_noargs"
# |  #0 0x0000c57a10fdef2c llvm::sys::PrintStackTrace(llvm::raw_ostream&, int) /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/lib/Support/Unix/Signals.inc:842:13
# |  #1 0x0000c57a10fdbe30 __cxx_atomic_store<CallbackAndCookie::Status> /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/libcxx_install_ubsan/include/c++/v1/__atomic/support/c11.h:68:3
# |  #2 0x0000c57a10fdbe30 store /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/libcxx_install_ubsan/include/c++/v1/__atomic/atomic.h:63:5
# |  #3 0x0000c57a10fdbe30 llvm::sys::RunSignalHandlers() /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/lib/Support/Signals.cpp:110:16
# |  #4 0x0000c57a10fe0a08 SignalHandler(int, siginfo_t*, void*) /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/lib/Support/Unix/Signals.inc:429:38
# |  #5 0x0000fec7e6df59c0 (linux-vdso.so.1+0x9c0)
# |  #6 0x0000fec7e67ba460 (/lib/aarch64-linux-gnu/libc.so.6+0x8a460)
# |  #7 0x0000fec7e67676c0 raise (/lib/aarch64-linux-gnu/libc.so.6+0x376c0)
# |  #8 0x0000fec7e6751ac8 abort (/lib/aarch64-linux-gnu/libc.so.6+0x21ac8)
# |  #9 0x0000c57a10f4b008 __sanitizer::Atexit(void (*)()) /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/compiler-rt/lib/sanitizer_common/sanitizer_posix_libcdep.cpp:170:10
# | #10 0x0000c57a10f48eb0 __sanitizer::Die() /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/compiler-rt/lib/sanitizer_common/sanitizer_termination.cpp:52:5
# | #11 0x0000c57a10f5a6b4 __ubsan_handle_alignment_assumption /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/compiler-rt/lib/ubsan/ubsan_handlers.cpp:195:0
# | #12 0x0000c57a1428427c llvm::AMDGPULowerKernelArgumentsPass::run(llvm::Function&, llvm::AnalysisManager<llvm::Function>&) /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/lib/Target/AMDGPU/AMDGPULowerKernelArguments.cpp:0:0
# | #13 0x0000c57a112cfec4 llvm::PassManager<llvm::Function, llvm::AnalysisManager<llvm::Function>>::run(llvm::Function&, llvm::AnalysisManager<llvm::Function>&) /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/include/llvm/IR/PassManagerImpl.h:80:8
# | #14 0x0000c57a112d5cc4 llvm::ModuleToFunctionPassAdaptor::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/lib/IR/PassManager.cpp:132:23
# | #15 0x0000c57a112ceeb4 llvm::PassManager<llvm::Module, llvm::AnalysisManager<llvm::Module>>::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/include/llvm/IR/PassManagerImpl.h:80:8
# | #16 0x0000c57a12c01e5c isSmall /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/include/llvm/ADT/SmallPtrSet.h:248:33
# | #17 0x0000c57a12c01e5c ~SmallPtrSetImplBase /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/include/llvm/ADT/SmallPtrSet.h:89:10
# | #18 0x0000c57a12c01e5c ~PreservedAnalyses /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/include/llvm/IR/Analysis.h:112:7
# | #19 0x0000c57a12c01e5c llvm::runPassPipeline(llvm::StringRef, llvm::Module&, llvm::TargetMachine*, llvm::TargetLibraryInfoImpl*, llvm::ToolOutputFile*, llvm::ToolOutputFile*, llvm::ToolOutputFile*, llvm::StringRef, llvm::ArrayRef<llvm::PassPlugin>, llvm::ArrayRef<std::__1::function<void (llvm::PassBuilder&)>>, llvm::opt_tool::OutputKind, llvm::opt_tool::VerifierKind, bool, bool, bool, bool, bool, bool, bool, bool) /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/tools/opt/NewPMDriver.cpp:574:3
# | #20 0x0000c57a10f63d64 optMain /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/tools/opt/optdriver.cpp:758:9
# | #21 0x0000fec7e67522dc (/lib/aarch64-linux-gnu/libc.so.6+0x222dc)
# | #22 0x0000fec7e67523bc __libc_start_main (/lib/aarch64-linux-gnu/libc.so.6+0x223bc)
# | #23 0x0000c57a10f33e30 _start (/home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/opt+0x7a83e30)
Step 11 (stage2/ubsan check) failure: stage2/ubsan check (failure)
...
llvm-lit: /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/utils/lit/lit/llvm/config.py:564: note: using lld-link: /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/lld-link
llvm-lit: /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/utils/lit/lit/llvm/config.py:564: note: using ld64.lld: /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/ld64.lld
llvm-lit: /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/utils/lit/lit/llvm/config.py:564: note: using wasm-ld: /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/wasm-ld
llvm-lit: /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/utils/lit/lit/llvm/config.py:564: note: using ld.lld: /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/ld.lld
llvm-lit: /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/utils/lit/lit/llvm/config.py:564: note: using lld-link: /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/lld-link
llvm-lit: /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/utils/lit/lit/llvm/config.py:564: note: using ld64.lld: /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/ld64.lld
llvm-lit: /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/utils/lit/lit/llvm/config.py:564: note: using wasm-ld: /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/wasm-ld
llvm-lit: /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/utils/lit/lit/main.py:74: note: The test suite configuration requested an individual test timeout of 0 seconds but a timeout of 900 seconds was requested on the command line. Forcing timeout to be 900 seconds.
-- Testing: 93499 tests, 72 workers --
Testing:  0.. 10.. 20.. 30
FAIL: LLVM :: CodeGen/AMDGPU/lower-kernargs.ll (32785 of 93499)
******************** TEST 'LLVM :: CodeGen/AMDGPU/lower-kernargs.ll' FAILED ********************
Exit Code: 2

Command Output (stdout):
--
# RUN: at line 2
/home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/opt -mtriple=amdgcn-amd-amdhsa -S -o - -passes=amdgpu-lower-kernel-arguments /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/test/CodeGen/AMDGPU/lower-kernargs.ll | /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/FileCheck -check-prefixes=GCN,HSA /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/test/CodeGen/AMDGPU/lower-kernargs.ll
# executed command: /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/opt -mtriple=amdgcn-amd-amdhsa -S -o - -passes=amdgpu-lower-kernel-arguments /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/test/CodeGen/AMDGPU/lower-kernargs.ll
# .---command stderr------------
# | PLEASE submit a bug report to https://github.com/llvm/llvm-project/issues/ and include the crash backtrace and instructions to reproduce the bug.
# | Stack dump:
# | 0.	Program arguments: /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/opt -mtriple=amdgcn-amd-amdhsa -S -o - -passes=amdgpu-lower-kernel-arguments /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/test/CodeGen/AMDGPU/lower-kernargs.ll
# | 1.	Running pass "function(amdgpu-lower-kernel-arguments)" on module "/home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/test/CodeGen/AMDGPU/lower-kernargs.ll"
# | 2.	Running pass "amdgpu-lower-kernel-arguments" on function "kern_noargs"
# |  #0 0x0000c57a10fdef2c llvm::sys::PrintStackTrace(llvm::raw_ostream&, int) /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/lib/Support/Unix/Signals.inc:842:13
# |  #1 0x0000c57a10fdbe30 __cxx_atomic_store<CallbackAndCookie::Status> /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/libcxx_install_ubsan/include/c++/v1/__atomic/support/c11.h:68:3
# |  #2 0x0000c57a10fdbe30 store /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/libcxx_install_ubsan/include/c++/v1/__atomic/atomic.h:63:5
# |  #3 0x0000c57a10fdbe30 llvm::sys::RunSignalHandlers() /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/lib/Support/Signals.cpp:110:16
# |  #4 0x0000c57a10fe0a08 SignalHandler(int, siginfo_t*, void*) /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/lib/Support/Unix/Signals.inc:429:38
# |  #5 0x0000fec7e6df59c0 (linux-vdso.so.1+0x9c0)
# |  #6 0x0000fec7e67ba460 (/lib/aarch64-linux-gnu/libc.so.6+0x8a460)
# |  #7 0x0000fec7e67676c0 raise (/lib/aarch64-linux-gnu/libc.so.6+0x376c0)
# |  #8 0x0000fec7e6751ac8 abort (/lib/aarch64-linux-gnu/libc.so.6+0x21ac8)
# |  #9 0x0000c57a10f4b008 __sanitizer::Atexit(void (*)()) /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/compiler-rt/lib/sanitizer_common/sanitizer_posix_libcdep.cpp:170:10
# | #10 0x0000c57a10f48eb0 __sanitizer::Die() /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/compiler-rt/lib/sanitizer_common/sanitizer_termination.cpp:52:5
# | #11 0x0000c57a10f5a6b4 __ubsan_handle_alignment_assumption /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/compiler-rt/lib/ubsan/ubsan_handlers.cpp:195:0
# | #12 0x0000c57a1428427c llvm::AMDGPULowerKernelArgumentsPass::run(llvm::Function&, llvm::AnalysisManager<llvm::Function>&) /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/lib/Target/AMDGPU/AMDGPULowerKernelArguments.cpp:0:0
# | #13 0x0000c57a112cfec4 llvm::PassManager<llvm::Function, llvm::AnalysisManager<llvm::Function>>::run(llvm::Function&, llvm::AnalysisManager<llvm::Function>&) /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/include/llvm/IR/PassManagerImpl.h:80:8
# | #14 0x0000c57a112d5cc4 llvm::ModuleToFunctionPassAdaptor::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/lib/IR/PassManager.cpp:132:23
# | #15 0x0000c57a112ceeb4 llvm::PassManager<llvm::Module, llvm::AnalysisManager<llvm::Module>>::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/include/llvm/IR/PassManagerImpl.h:80:8
# | #16 0x0000c57a12c01e5c isSmall /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/include/llvm/ADT/SmallPtrSet.h:248:33
# | #17 0x0000c57a12c01e5c ~SmallPtrSetImplBase /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/include/llvm/ADT/SmallPtrSet.h:89:10
# | #18 0x0000c57a12c01e5c ~PreservedAnalyses /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/include/llvm/IR/Analysis.h:112:7
# | #19 0x0000c57a12c01e5c llvm::runPassPipeline(llvm::StringRef, llvm::Module&, llvm::TargetMachine*, llvm::TargetLibraryInfoImpl*, llvm::ToolOutputFile*, llvm::ToolOutputFile*, llvm::ToolOutputFile*, llvm::StringRef, llvm::ArrayRef<llvm::PassPlugin>, llvm::ArrayRef<std::__1::function<void (llvm::PassBuilder&)>>, llvm::opt_tool::OutputKind, llvm::opt_tool::VerifierKind, bool, bool, bool, bool, bool, bool, bool, bool) /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/tools/opt/NewPMDriver.cpp:574:3
# | #20 0x0000c57a10f63d64 optMain /home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm-project/llvm/tools/opt/optdriver.cpp:758:9
# | #21 0x0000fec7e67522dc (/lib/aarch64-linux-gnu/libc.so.6+0x222dc)
# | #22 0x0000fec7e67523bc __libc_start_main (/lib/aarch64-linux-gnu/libc.so.6+0x223bc)
# | #23 0x0000c57a10f33e30 _start (/home/b/sanitizer-aarch64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/opt+0x7a83e30)

@llvm-ci
Copy link
Collaborator

llvm-ci commented Dec 21, 2025

LLVM Buildbot has detected a new failure on builder sanitizer-x86_64-linux-bootstrap-ubsan running on sanitizer-buildbot4 while building llvm at step 2 "annotate".

Full details are available at: https://lab.llvm.org/buildbot/#/builders/25/builds/14230

Here is the relevant piece of the build log for the reference 
Step 2 (annotate) failure: 'python ../sanitizer_buildbot/sanitizers/zorg/buildbot/builders/sanitizers/buildbot_selector.py' (failure)
...
llvm-lit: /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/utils/lit/lit/llvm/config.py:564: note: using lld-link: /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/lld-link
llvm-lit: /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/utils/lit/lit/llvm/config.py:564: note: using ld64.lld: /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/ld64.lld
llvm-lit: /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/utils/lit/lit/llvm/config.py:564: note: using wasm-ld: /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/wasm-ld
llvm-lit: /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/utils/lit/lit/llvm/config.py:564: note: using ld.lld: /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/ld.lld
llvm-lit: /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/utils/lit/lit/llvm/config.py:564: note: using lld-link: /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/lld-link
llvm-lit: /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/utils/lit/lit/llvm/config.py:564: note: using ld64.lld: /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/ld64.lld
llvm-lit: /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/utils/lit/lit/llvm/config.py:564: note: using wasm-ld: /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/wasm-ld
llvm-lit: /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/utils/lit/lit/main.py:74: note: The test suite configuration requested an individual test timeout of 0 seconds but a timeout of 900 seconds was requested on the command line. Forcing timeout to be 900 seconds.
-- Testing: 94794 tests, 64 workers --
Testing:  0.. 10.. 20.. 30.
FAIL: LLVM :: CodeGen/AMDGPU/lower-kernargs.ll (34237 of 94794)
******************** TEST 'LLVM :: CodeGen/AMDGPU/lower-kernargs.ll' FAILED ********************
Exit Code: 2

Command Output (stdout):
--
# RUN: at line 2
/home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/opt -mtriple=amdgcn-amd-amdhsa -S -o - -passes=amdgpu-lower-kernel-arguments /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/test/CodeGen/AMDGPU/lower-kernargs.ll | /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/FileCheck -check-prefixes=GCN,HSA /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/test/CodeGen/AMDGPU/lower-kernargs.ll
# executed command: /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/opt -mtriple=amdgcn-amd-amdhsa -S -o - -passes=amdgpu-lower-kernel-arguments /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/test/CodeGen/AMDGPU/lower-kernargs.ll
# .---command stderr------------
# | PLEASE submit a bug report to https://github.com/llvm/llvm-project/issues/ and include the crash backtrace and instructions to reproduce the bug.
# | Stack dump:
# | 0.	Program arguments: /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/opt -mtriple=amdgcn-amd-amdhsa -S -o - -passes=amdgpu-lower-kernel-arguments /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/test/CodeGen/AMDGPU/lower-kernargs.ll
# | 1.	Running pass "function(amdgpu-lower-kernel-arguments)" on module "/home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/test/CodeGen/AMDGPU/lower-kernargs.ll"
# | 2.	Running pass "amdgpu-lower-kernel-arguments" on function "kern_noargs"
# |  #0 0x00005a1404da319e llvm::sys::PrintStackTrace(llvm::raw_ostream&, int) /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/lib/Support/Unix/Signals.inc:842:13
# |  #1 0x00005a1404d9fc3f llvm::sys::RunSignalHandlers() /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/lib/Support/Signals.cpp:109:18
# |  #2 0x00005a1404da4bb8 SignalHandler(int, siginfo_t*, void*) /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/lib/Support/Unix/Signals.inc:429:38
# |  #3 0x0000743dfcc458d0 (/lib/x86_64-linux-gnu/libc.so.6+0x458d0)
# |  #4 0x0000743dfcca49bc pthread_kill (/lib/x86_64-linux-gnu/libc.so.6+0xa49bc)
# |  #5 0x0000743dfcc4579e raise (/lib/x86_64-linux-gnu/libc.so.6+0x4579e)
# |  #6 0x0000743dfcc288cd abort (/lib/x86_64-linux-gnu/libc.so.6+0x288cd)
# |  #7 0x00005a1404d0b60c (/home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/opt+0x798160c)
# |  #8 0x00005a1404d0949e __sanitizer::Die() /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/compiler-rt/lib/sanitizer_common/sanitizer_termination.cpp:52:5
# |  #9 0x00005a1404d1b629 (/home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/opt+0x7991629)
# | #10 0x00005a14083440f3 llvm::AMDGPULowerKernelArgumentsPass::run(llvm::Function&, llvm::AnalysisManager<llvm::Function>&) /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/lib/Target/AMDGPU/AMDGPULowerKernelArguments.cpp:0:0
# | #11 0x00005a140509e850 llvm::PassManager<llvm::Function, llvm::AnalysisManager<llvm::Function>>::run(llvm::Function&, llvm::AnalysisManager<llvm::Function>&) /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/include/llvm/IR/PassManagerImpl.h:80:8
# | #12 0x00005a14050a48b1 llvm::ModuleToFunctionPassAdaptor::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/lib/IR/PassManager.cpp:132:23
# | #13 0x00005a140509d690 llvm::PassManager<llvm::Module, llvm::AnalysisManager<llvm::Module>>::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/include/llvm/IR/PassManagerImpl.h:80:8
# | #14 0x00005a1406b0b796 isSmall /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/include/llvm/ADT/SmallPtrSet.h:248:33
# | #15 0x00005a1406b0b796 ~SmallPtrSetImplBase /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/include/llvm/ADT/SmallPtrSet.h:89:10
# | #16 0x00005a1406b0b796 ~PreservedAnalyses /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/include/llvm/IR/Analysis.h:112:7
# | #17 0x00005a1406b0b796 llvm::runPassPipeline(llvm::StringRef, llvm::Module&, llvm::TargetMachine*, llvm::TargetLibraryInfoImpl*, llvm::ToolOutputFile*, llvm::ToolOutputFile*, llvm::ToolOutputFile*, llvm::StringRef, llvm::ArrayRef<llvm::PassPlugin>, llvm::ArrayRef<std::__1::function<void (llvm::PassBuilder&)>>, llvm::opt_tool::OutputKind, llvm::opt_tool::VerifierKind, bool, bool, bool, bool, bool, bool, bool, bool) /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/tools/opt/NewPMDriver.cpp:574:3
# | #18 0x00005a1404d26bdc optMain /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/tools/opt/optdriver.cpp:0:10
# | #19 0x0000743dfcc2a578 (/lib/x86_64-linux-gnu/libc.so.6+0x2a578)
# | #20 0x0000743dfcc2a63b __libc_start_main (/lib/x86_64-linux-gnu/libc.so.6+0x2a63b)
# | #21 0x00005a1404cf38e5 _start (/home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/opt+0x79698e5)
# `-----------------------------
# error: command failed with exit status: -6
Step 11 (stage2/ubsan check) failure: stage2/ubsan check (failure)
...
llvm-lit: /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/utils/lit/lit/llvm/config.py:564: note: using lld-link: /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/lld-link
llvm-lit: /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/utils/lit/lit/llvm/config.py:564: note: using ld64.lld: /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/ld64.lld
llvm-lit: /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/utils/lit/lit/llvm/config.py:564: note: using wasm-ld: /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/wasm-ld
llvm-lit: /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/utils/lit/lit/llvm/config.py:564: note: using ld.lld: /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/ld.lld
llvm-lit: /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/utils/lit/lit/llvm/config.py:564: note: using lld-link: /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/lld-link
llvm-lit: /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/utils/lit/lit/llvm/config.py:564: note: using ld64.lld: /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/ld64.lld
llvm-lit: /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/utils/lit/lit/llvm/config.py:564: note: using wasm-ld: /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/wasm-ld
llvm-lit: /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/utils/lit/lit/main.py:74: note: The test suite configuration requested an individual test timeout of 0 seconds but a timeout of 900 seconds was requested on the command line. Forcing timeout to be 900 seconds.
-- Testing: 94794 tests, 64 workers --
Testing:  0.. 10.. 20.. 30.
FAIL: LLVM :: CodeGen/AMDGPU/lower-kernargs.ll (34237 of 94794)
******************** TEST 'LLVM :: CodeGen/AMDGPU/lower-kernargs.ll' FAILED ********************
Exit Code: 2

Command Output (stdout):
--
# RUN: at line 2
/home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/opt -mtriple=amdgcn-amd-amdhsa -S -o - -passes=amdgpu-lower-kernel-arguments /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/test/CodeGen/AMDGPU/lower-kernargs.ll | /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/FileCheck -check-prefixes=GCN,HSA /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/test/CodeGen/AMDGPU/lower-kernargs.ll
# executed command: /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/opt -mtriple=amdgcn-amd-amdhsa -S -o - -passes=amdgpu-lower-kernel-arguments /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/test/CodeGen/AMDGPU/lower-kernargs.ll
# .---command stderr------------
# | PLEASE submit a bug report to https://github.com/llvm/llvm-project/issues/ and include the crash backtrace and instructions to reproduce the bug.
# | Stack dump:
# | 0.	Program arguments: /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/opt -mtriple=amdgcn-amd-amdhsa -S -o - -passes=amdgpu-lower-kernel-arguments /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/test/CodeGen/AMDGPU/lower-kernargs.ll
# | 1.	Running pass "function(amdgpu-lower-kernel-arguments)" on module "/home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/test/CodeGen/AMDGPU/lower-kernargs.ll"
# | 2.	Running pass "amdgpu-lower-kernel-arguments" on function "kern_noargs"
# |  #0 0x00005a1404da319e llvm::sys::PrintStackTrace(llvm::raw_ostream&, int) /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/lib/Support/Unix/Signals.inc:842:13
# |  #1 0x00005a1404d9fc3f llvm::sys::RunSignalHandlers() /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/lib/Support/Signals.cpp:109:18
# |  #2 0x00005a1404da4bb8 SignalHandler(int, siginfo_t*, void*) /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/lib/Support/Unix/Signals.inc:429:38
# |  #3 0x0000743dfcc458d0 (/lib/x86_64-linux-gnu/libc.so.6+0x458d0)
# |  #4 0x0000743dfcca49bc pthread_kill (/lib/x86_64-linux-gnu/libc.so.6+0xa49bc)
# |  #5 0x0000743dfcc4579e raise (/lib/x86_64-linux-gnu/libc.so.6+0x4579e)
# |  #6 0x0000743dfcc288cd abort (/lib/x86_64-linux-gnu/libc.so.6+0x288cd)
# |  #7 0x00005a1404d0b60c (/home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/opt+0x798160c)
# |  #8 0x00005a1404d0949e __sanitizer::Die() /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/compiler-rt/lib/sanitizer_common/sanitizer_termination.cpp:52:5
# |  #9 0x00005a1404d1b629 (/home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/opt+0x7991629)
# | #10 0x00005a14083440f3 llvm::AMDGPULowerKernelArgumentsPass::run(llvm::Function&, llvm::AnalysisManager<llvm::Function>&) /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/lib/Target/AMDGPU/AMDGPULowerKernelArguments.cpp:0:0
# | #11 0x00005a140509e850 llvm::PassManager<llvm::Function, llvm::AnalysisManager<llvm::Function>>::run(llvm::Function&, llvm::AnalysisManager<llvm::Function>&) /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/include/llvm/IR/PassManagerImpl.h:80:8
# | #12 0x00005a14050a48b1 llvm::ModuleToFunctionPassAdaptor::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/lib/IR/PassManager.cpp:132:23
# | #13 0x00005a140509d690 llvm::PassManager<llvm::Module, llvm::AnalysisManager<llvm::Module>>::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/include/llvm/IR/PassManagerImpl.h:80:8
# | #14 0x00005a1406b0b796 isSmall /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/include/llvm/ADT/SmallPtrSet.h:248:33
# | #15 0x00005a1406b0b796 ~SmallPtrSetImplBase /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/include/llvm/ADT/SmallPtrSet.h:89:10
# | #16 0x00005a1406b0b796 ~PreservedAnalyses /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/include/llvm/IR/Analysis.h:112:7
# | #17 0x00005a1406b0b796 llvm::runPassPipeline(llvm::StringRef, llvm::Module&, llvm::TargetMachine*, llvm::TargetLibraryInfoImpl*, llvm::ToolOutputFile*, llvm::ToolOutputFile*, llvm::ToolOutputFile*, llvm::StringRef, llvm::ArrayRef<llvm::PassPlugin>, llvm::ArrayRef<std::__1::function<void (llvm::PassBuilder&)>>, llvm::opt_tool::OutputKind, llvm::opt_tool::VerifierKind, bool, bool, bool, bool, bool, bool, bool, bool) /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/tools/opt/NewPMDriver.cpp:574:3
# | #18 0x00005a1404d26bdc optMain /home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm-project/llvm/tools/opt/optdriver.cpp:0:10
# | #19 0x0000743dfcc2a578 (/lib/x86_64-linux-gnu/libc.so.6+0x2a578)
# | #20 0x0000743dfcc2a63b __libc_start_main (/lib/x86_64-linux-gnu/libc.so.6+0x2a63b)
# | #21 0x00005a1404cf38e5 _start (/home/b/sanitizer-x86_64-linux-bootstrap-ubsan/build/llvm_build_ubsan/bin/opt+0x79698e5)
# `-----------------------------
# error: command failed with exit status: -6

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@arsenm arsenm arsenm approved these changes

@nikic nikic Awaiting requested review from nikic

@fhahn fhahn Awaiting requested review from fhahn

@SLTozer SLTozer Awaiting requested review from SLTozer

@shiltian shiltian Awaiting requested review from shiltian

@srpande srpande Awaiting requested review from srpande

@dobbelaj-snps dobbelaj-snps Awaiting requested review from dobbelaj-snps

Assignees

No one assigned

Labels

backend:AMDGPU

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

4 participants

@PeddleSpam @llvmbot @llvm-ci @arsenm