Skip to content

[NFC][Clang][AMDGPU] Fix upstream and downstream difference #164304

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 2 commits into from
Oct 20, 2025
Merged

[NFC][Clang][AMDGPU] Fix upstream and downstream difference #164304

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
83ed49b
[NFC][Clang][AMDGPU] Fix upstream and downstream difference
shiltian Oct 20, 2025
b5503e0
fix test failure
shiltian Oct 20, 2025
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
1 change: 1 addition & 0 deletions clang/lib/Headers/__clang_hip_runtime_wrapper.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,7 @@
#define __managed__ __attribute__((managed))

#define __cluster_dims__(...) __attribute__((cluster_dims(__VA_ARGS__)))
#define __no_cluster__ __attribute__((no_cluster))

#if !defined(__cplusplus) || __cplusplus < 201103L
#define nullptr NULL;
Expand Down
47 changes: 47 additions & 0 deletions clang/test/CodeGenOpenCL/amdgpu-cluster-dims.cl
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,47 @@
// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --check-attributes --check-globals all --include-generated-funcs --prefix-filecheck-ir-name VAR --version 5
// RUN: %clang_cc1 -cl-std=CL2.0 -triple amdgcn-amd-amdhsa -target-cpu gfx1250 -disable-llvm-passes -fno-ident -emit-llvm %s -o - | FileCheck %s

kernel void foo(global int *p) { *p = 1; }
// CHECK: Function Attrs: convergent norecurse nounwind
// CHECK-LABEL: define dso_local amdgpu_kernel void @foo(
// CHECK-SAME: ptr addrspace(1) noundef align 4 [[P:%.*]]) #[[ATTR0:[0-9]+]] !kernel_arg_addr_space [[META3:![0-9]+]] !kernel_arg_access_qual [[META4:![0-9]+]] !kernel_arg_type [[META5:![0-9]+]] !kernel_arg_base_type [[META5]] !kernel_arg_type_qual [[META6:![0-9]+]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: [[P_ADDR:%.*]] = alloca ptr addrspace(1), align 8, addrspace(5)
// CHECK-NEXT: [[P_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[P_ADDR]] to ptr
// CHECK-NEXT: store ptr addrspace(1) [[P]], ptr [[P_ADDR_ASCAST]], align 8, !tbaa [[TBAA7:![0-9]+]]
// CHECK-NEXT: [[TMP0:%.*]] = load ptr addrspace(1), ptr [[P_ADDR_ASCAST]], align 8, !tbaa [[TBAA7]]
// CHECK-NEXT: call void @__clang_ocl_kern_imp_foo(ptr addrspace(1) noundef align 4 [[TMP0]]) #[[ATTR2:[0-9]+]]
// CHECK-NEXT: ret void
//
//
// CHECK: Function Attrs: alwaysinline convergent norecurse nounwind
// CHECK-LABEL: define dso_local void @__clang_ocl_kern_imp_foo(
// CHECK-SAME: ptr addrspace(1) noundef align 4 [[P:%.*]]) #[[ATTR1:[0-9]+]] !kernel_arg_addr_space [[META3]] !kernel_arg_access_qual [[META4]] !kernel_arg_type [[META5]] !kernel_arg_base_type [[META5]] !kernel_arg_type_qual [[META6]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: [[P_ADDR:%.*]] = alloca ptr addrspace(1), align 8, addrspace(5)
// CHECK-NEXT: [[P_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[P_ADDR]] to ptr
// CHECK-NEXT: store ptr addrspace(1) [[P]], ptr [[P_ADDR_ASCAST]], align 8, !tbaa [[TBAA7]]
// CHECK-NEXT: [[TMP0:%.*]] = load ptr addrspace(1), ptr [[P_ADDR_ASCAST]], align 8, !tbaa [[TBAA7]]
// CHECK-NEXT: store i32 1, ptr addrspace(1) [[TMP0]], align 4, !tbaa [[TBAA12:![0-9]+]]
// CHECK-NEXT: ret void
//
//.
// CHECK: attributes #[[ATTR0]] = { convergent norecurse nounwind "amdgpu-cluster-dims"="0,0,0" "amdgpu-flat-work-group-size"="1,256" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="gfx1250" "target-features"="+16-bit-insts,+ashr-pk-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-buffer-pk-add-bf16-inst,+atomic-ds-pk-add-16-insts,+atomic-fadd-rtn-insts,+atomic-flat-pk-add-16-insts,+atomic-fmin-fmax-global-f32,+atomic-fmin-fmax-global-f64,+atomic-global-pk-add-bf16-inst,+bf16-cvt-insts,+bf16-pk-insts,+bf16-trans-insts,+bitop3-insts,+ci-insts,+clusters,+dl-insts,+dot7-insts,+dot8-insts,+dpp,+fp8-conversion-insts,+fp8e5m3-insts,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx12-insts,+gfx1250-insts,+gfx8-insts,+gfx9-insts,+permlane16-swap,+prng-inst,+setprio-inc-wg-inst,+tanh-insts,+tensor-cvt-lut-insts,+transpose-load-f4f6-insts,+vmem-pref-insts,+wavefrontsize32" "uniform-work-group-size"="false" }
// CHECK: attributes #[[ATTR1]] = { alwaysinline convergent norecurse nounwind "amdgpu-cluster-dims"="0,0,0" "amdgpu-flat-work-group-size"="1,256" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="gfx1250" "target-features"="+16-bit-insts,+ashr-pk-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-buffer-pk-add-bf16-inst,+atomic-ds-pk-add-16-insts,+atomic-fadd-rtn-insts,+atomic-flat-pk-add-16-insts,+atomic-fmin-fmax-global-f32,+atomic-fmin-fmax-global-f64,+atomic-global-pk-add-bf16-inst,+bf16-cvt-insts,+bf16-pk-insts,+bf16-trans-insts,+bitop3-insts,+ci-insts,+clusters,+dl-insts,+dot7-insts,+dot8-insts,+dpp,+fp8-conversion-insts,+fp8e5m3-insts,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx12-insts,+gfx1250-insts,+gfx8-insts,+gfx9-insts,+permlane16-swap,+prng-inst,+setprio-inc-wg-inst,+tanh-insts,+tensor-cvt-lut-insts,+transpose-load-f4f6-insts,+vmem-pref-insts,+wavefrontsize32" }
// CHECK: attributes #[[ATTR2]] = { convergent nounwind }
//.
// CHECK: [[META0:![0-9]+]] = !{i32 1, !"amdhsa_code_object_version", i32 600}
// CHECK: [[META1:![0-9]+]] = !{i32 1, !"wchar_size", i32 4}
// CHECK: [[META2:![0-9]+]] = !{i32 2, i32 0}
// CHECK: [[META3]] = !{i32 1}
// CHECK: [[META4]] = !{!"none"}
// CHECK: [[META5]] = !{!"int*"}
// CHECK: [[META6]] = !{!""}
// CHECK: [[TBAA7]] = !{[[META8:![0-9]+]], [[META8]], i64 0}
// CHECK: [[META8]] = !{!"p1 int", [[META9:![0-9]+]], i64 0}
// CHECK: [[META9]] = !{!"any pointer", [[META10:![0-9]+]], i64 0}
// CHECK: [[META10]] = !{!"omnipotent char", [[META11:![0-9]+]], i64 0}
// CHECK: [[META11]] = !{!"Simple C/C++ TBAA"}
// CHECK: [[TBAA12]] = !{[[META13:![0-9]+]], [[META13]], i64 0}
// CHECK: [[META13]] = !{!"int", [[META10]], i64 0}
//.
Loading