[PATCH] D128700: [AMDGPU][Clang] Skip adding noundef attribute to AMDGPU HIP device functions

[krishna chaitanya sankisa via Phabricator via cfe-commits]

skc7 created this revision.
Herald added subscribers: kosarev, kerbowa, t-tye, tpr, dstuttard, yaxunl, 
jvesely, kzhuravl.
Herald added a project: All.
skc7 requested review of this revision.
Herald added subscribers: llvm-commits, cfe-commits, wdng.
Herald added projects: clang, LLVM.

Noundef attribute has been enabled by default in clang. This is causing 
execution issues, when kernel has uninitialized variables passed to cuda 
cross-lane APIs.
This patch skips adding noundef attribute to function arguments and return 
values for HIP device functions.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D128700

Files:
  clang/lib/CodeGen/CGCall.cpp
  clang/test/CodeGenCUDA/builtins-amdgcn.cu
  clang/test/CodeGenCUDA/lambda.cu
  clang/test/CodeGenCUDA/unnamed-types.cu
  clang/test/CodeGenHIP/hipspv-addr-spaces.cpp
  clang/test/CodeGenHIP/noundef-attribute-hip-device-verify.hip
  llvm/test/CodeGen/AMDGPU/lower-lds-struct-aa-memcpy.ll

Index: llvm/test/CodeGen/AMDGPU/lower-lds-struct-aa-memcpy.ll
===
--- llvm/test/CodeGen/AMDGPU/lower-lds-struct-aa-memcpy.ll
+++ llvm/test/CodeGen/AMDGPU/lower-lds-struct-aa-memcpy.ll
@@ -18,19 +18,19 @@
 
 ; CHECK-LABEL: @test
 ; CHECK: store i8 3, i8 addrspace(3)* %0, align 4, !alias.scope !0, !noalias !3
-; CHECK: tail call void @llvm.memcpy.p3i8.p3i8.i64(i8 addrspace(3)* noundef align 1 dereferenceable(3) %2, i8 addrspace(3)* noundef align 1 dereferenceable(3) %1, i64 3, i1 false), !alias.scope !6, !noalias !7
+; CHECK: tail call void @llvm.memcpy.p3i8.p3i8.i64(i8 addrspace(3)* align 1 dereferenceable(3) %2, i8 addrspace(3)* align 1 dereferenceable(3) %1, i64 3, i1 false), !alias.scope !6, !noalias !7
 ; CHECK: %4 = load i8, i8 addrspace(3)* %3, align 4, !alias.scope !8, !noalias !9
-; CHECK: tail call void @llvm.memcpy.p3i8.p3i8.i64(i8 addrspace(3)* noundef align 1 dereferenceable(3) %7, i8 addrspace(3)* noundef align 1 dereferenceable(3) %6, i64 3, i1 false), !alias.scope !6, !noalias !7
+; CHECK: tail call void @llvm.memcpy.p3i8.p3i8.i64(i8 addrspace(3)* align 1 dereferenceable(3) %7, i8 addrspace(3)* align 1 dereferenceable(3) %6, i64 3, i1 false), !alias.scope !6, !noalias !7
 ; CHECK: %9 = load i8, i8 addrspace(3)* %8, align 4, !alias.scope !8, !noalias !9
 
 define protected amdgpu_kernel void @test(i8 addrspace(1)* nocapture %ptr.coerce) local_unnamed_addr #0 {
 entry:
   store i8 3, i8 addrspace(3)* getelementptr inbounds (%vec_type, %vec_type addrspace(3)* @_f1, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0), align 1
-  tail call void @llvm.memcpy.p3i8.p3i8.i64(i8 addrspace(3)* noundef align 1 dereferenceable(3) getelementptr inbounds (%vec_type, %vec_type addrspace(3)* @_f2, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0), i8 addrspace(3)* noundef align 1 dereferenceable(3) getelementptr inbounds (%vec_type, %vec_type addrspace(3)* @_f1, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0), i64 3, i1 false)
+  tail call void @llvm.memcpy.p3i8.p3i8.i64(i8 addrspace(3)* align 1 dereferenceable(3) getelementptr inbounds (%vec_type, %vec_type addrspace(3)* @_f2, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0), i8 addrspace(3)* align 1 dereferenceable(3) getelementptr inbounds (%vec_type, %vec_type addrspace(3)* @_f1, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0), i64 3, i1 false)
   %0 = load i8, i8 addrspace(3)* getelementptr inbounds (%vec_type, %vec_type addrspace(3)* @_f2, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0), align 1
   %cmp.i.i = icmp eq i8 %0, 3
   store i8 2, i8 addrspace(3)* getelementptr inbounds (%vec_type, %vec_type addrspace(3)* @_f1, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0), align 1
-  tail call void @llvm.memcpy.p3i8.p3i8.i64(i8 addrspace(3)* noundef align 1 dereferenceable(3) getelementptr inbounds (%vec_type, %vec_type addrspace(3)* @_f2, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0), i8 addrspace(3)* noundef align 1 dereferenceable(3) getelementptr inbounds (%vec_type, %vec_type addrspace(3)* @_f1, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0), i64 3, i1 false)
+  tail call void @llvm.memcpy.p3i8.p3i8.i64(i8 addrspace(3)* align 1 dereferenceable(3) getelementptr inbounds (%vec_type, %vec_type addrspace(3)* @_f2, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0), i8 addrspace(3)* align 1 dereferenceable(3) getelementptr inbounds (%vec_type, %vec_type addrspace(3)* @_f1, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0), i64 3, i1 false)
   %1 = load i8, i8 addrspace(3)* getelementptr inbounds (%vec_type, %vec_type addrspace(3)* @_f2, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0), align 1
   %cmp.i.i19 = icmp eq i8 %1, 2
   %2 = and i1 %cmp.i.i19, %cmp.i.i
Index: clang/test/CodeGenHIP/noundef-attribute-hip-device-verify.hip
===
--- /dev/null
+++ clang/test/CodeGenHIP/noundef-attribute-hip-device-verify.hip
@@ -0,0 +1,38 @@
+// RUN: %clang_cc1 -no-opaque-pointers -triple amdgcn-amd-amdhsa -target-cpu gfx906 -x hip -fcuda-is-device -emit-llvm %s \
+// RUN:   -o - 

[PATCH] D128907: [Clang] Disable noundef attribute for languages which allow uninitialized function arguments

[krishna chaitanya sankisa via Phabricator via cfe-commits]

skc7 created this revision.
skc7 added reviewers: arsenm, sameerds, cdevadas, ronlieb, yaxunl, b-sumner, 
bcahoon.
Herald added subscribers: kosarev, mattd, asavonic, ThomasRaoux, jdoerfert, 
kerbowa, kbarton, jvesely, nemanjai.
Herald added a project: All.
skc7 requested review of this revision.
Herald added subscribers: llvm-commits, cfe-commits, sstefan1, wdng.
Herald added a reviewer: jdoerfert.
Herald added projects: clang, LLVM.

Languages like CUDA, HIP etc. have APIs which accept uninitialized function 
arguments.
With D105169 , noundef-analysis has been 
enabled by default and
we are forced to assume very strict constraints for the mentioned languages.
So, the proposed change is to skip adding noundef attribute to function
arguments and return values for such languages.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D128907

Files:
  clang/include/clang/Basic/LangOptions.h
  clang/lib/CodeGen/CGCall.cpp
  clang/test/CodeGen/PowerPC/ppc64le-varargs-f128.c
  clang/test/CodeGenCUDA/address-spaces.cu
  clang/test/CodeGenCUDA/builtins-amdgcn.cu
  clang/test/CodeGenCUDA/cuda-builtin-vars.cu
  clang/test/CodeGenCUDA/kernel-args-alignment.cu
  clang/test/CodeGenCUDA/kernel-args.cu
  clang/test/CodeGenCUDA/lambda.cu
  clang/test/CodeGenCUDA/redux-builtins.cu
  clang/test/CodeGenCUDA/surface.cu
  clang/test/CodeGenCUDA/unnamed-types.cu
  clang/test/CodeGenCUDA/usual-deallocators.cu
  clang/test/CodeGenCUDA/vtbl.cu
  clang/test/CodeGenCUDASPIRV/kernel-argument.cu
  clang/test/CodeGenHIP/hipspv-addr-spaces.cpp
  clang/test/CodeGenHIP/noundef-attribute-hip-device-verify.hip
  clang/test/CodeGenOpenCL/addr-space-struct-arg.cl
  clang/test/CodeGenOpenCL/address-spaces.cl
  clang/test/CodeGenOpenCL/amdgcn-automatic-variable.cl
  clang/test/CodeGenOpenCL/amdgpu-abi-struct-coerce.cl
  clang/test/CodeGenOpenCL/amdgpu-call-kernel.cl
  clang/test/CodeGenOpenCL/amdgpu-printf.cl
  clang/test/CodeGenOpenCL/as_type.cl
  clang/test/CodeGenOpenCL/atomic-ops-libcall.cl
  clang/test/CodeGenOpenCL/blocks.cl
  clang/test/CodeGenOpenCL/byval.cl
  clang/test/CodeGenOpenCL/const-str-array-decay.cl
  clang/test/CodeGenOpenCL/constant-addr-space-globals.cl
  clang/test/CodeGenOpenCL/convergent.cl
  clang/test/CodeGenOpenCL/fpmath.cl
  clang/test/CodeGenOpenCL/half.cl
  clang/test/CodeGenOpenCL/kernel-param-alignment.cl
  clang/test/CodeGenOpenCL/kernels-have-spir-cc-by-default.cl
  clang/test/CodeGenOpenCL/no-half.cl
  clang/test/CodeGenOpenCL/overload.cl
  clang/test/CodeGenOpenCL/size_t.cl
  clang/test/CodeGenOpenCL/spir-calling-conv.cl
  clang/test/CodeGenOpenCLCXX/address-space-deduction.clcpp
  clang/test/CodeGenOpenCLCXX/addrspace-derived-base.clcpp
  clang/test/CodeGenOpenCLCXX/addrspace-new-delete.clcpp
  clang/test/CodeGenOpenCLCXX/addrspace-of-this.clcpp
  clang/test/CodeGenOpenCLCXX/addrspace-operators.clcpp
  clang/test/CodeGenOpenCLCXX/addrspace-references.clcpp
  clang/test/CodeGenOpenCLCXX/addrspace-with-class.clcpp
  clang/test/CodeGenOpenCLCXX/template-address-spaces.clcpp
  clang/test/CodeGenSYCL/address-space-conversions.cpp
  clang/test/CodeGenSYCL/address-space-mangling.cpp
  clang/test/CodeGenSYCL/functionptr-addrspace.cpp
  clang/test/CodeGenSYCL/unique_stable_name.cpp
  clang/test/OpenMP/amdgcn-attributes.cpp
  clang/test/OpenMP/amdgcn_target_global_constructor.cpp
  clang/test/OpenMP/assumes_include_nvptx.cpp
  clang/test/OpenMP/declare_target_codegen.cpp
  clang/test/OpenMP/declare_target_codegen_globalization.cpp
  clang/test/OpenMP/declare_target_link_codegen.cpp
  clang/test/OpenMP/declare_variant_mixed_codegen.c
  clang/test/OpenMP/distribute_codegen.cpp
  clang/test/OpenMP/distribute_simd_codegen.cpp
  clang/test/OpenMP/nvptx_allocate_codegen.cpp
  clang/test/OpenMP/nvptx_data_sharing.cpp
  clang/test/OpenMP/nvptx_declare_target_var_ctor_dtor_codegen.cpp
  clang/test/OpenMP/nvptx_declare_variant_name_mangling.cpp
  clang/test/OpenMP/nvptx_distribute_parallel_generic_mode_codegen.cpp
  clang/test/OpenMP/nvptx_lambda_capturing.cpp
  clang/test/OpenMP/nvptx_multi_target_parallel_codegen.cpp
  clang/test/OpenMP/nvptx_nested_parallel_codegen.cpp
  clang/test/OpenMP/nvptx_parallel_codegen.cpp
  clang/test/OpenMP/nvptx_parallel_for_codegen.cpp
  clang/test/OpenMP/nvptx_target_firstprivate_codegen.cpp
  clang/test/OpenMP/nvptx_target_parallel_codegen.cpp
  clang/test/OpenMP/nvptx_target_parallel_num_threads_codegen.cpp
  clang/test/OpenMP/nvptx_target_parallel_reduction_codegen.cpp
  clang/test/OpenMP/nvptx_target_printf_codegen.c
  clang/test/OpenMP/nvptx_target_teams_codegen.cpp
  clang/test/OpenMP/nvptx_target_teams_distribute_codegen.cpp
  clang/test/OpenMP/nvptx_target_teams_distribute_parallel_for_codegen.cpp
  
clang/test/OpenMP/nvptx_target_teams_distribute_parallel_for_generic_mode_codegen.cpp
  clang/test/OpenMP/nvptx_target_teams_distribute_parallel_for_simd_codegen.cpp
  clang/test/OpenMP/nvptx_teams_codegen.cpp
  clang/test/OpenMP/nvptx_teams_re

[PATCH] D128700: [AMDGPU][Clang] Skip adding noundef attribute to AMDGPU HIP device functions

[krishna chaitanya sankisa via Phabricator via cfe-commits]

skc7 added inline comments.



Comment at: clang/lib/CodeGen/CGCall.cpp:2309
+  bool EnableNoundefAttrs = CodeGenOpts.EnableNoundefAttrs &&
+!(getLangOpts().HIP && getLangOpts().CUDAIsDevice);
+

arsenm wrote:
> Shouldn't be limited to HIP. All languages with convergent operations
With this above suggested change to include all languages with convergent 
operations, lot of tests had to be updated. Created this new patch D128907 for 
same.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D128700/new/

https://reviews.llvm.org/D128700

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D128907: [Clang] Disable noundef attribute for languages which allow uninitialized function arguments

[krishna chaitanya sankisa via Phabricator via cfe-commits]

skc7 updated this revision to Diff 441409.
skc7 added a comment.

Add description for allowUninitializedFunctionsArgs


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D128907/new/

https://reviews.llvm.org/D128907

Files:
  clang/include/clang/Basic/LangOptions.h
  clang/lib/CodeGen/CGCall.cpp
  clang/test/CodeGen/PowerPC/ppc64le-varargs-f128.c
  clang/test/CodeGenCUDA/address-spaces.cu
  clang/test/CodeGenCUDA/builtins-amdgcn.cu
  clang/test/CodeGenCUDA/cuda-builtin-vars.cu
  clang/test/CodeGenCUDA/kernel-args-alignment.cu
  clang/test/CodeGenCUDA/kernel-args.cu
  clang/test/CodeGenCUDA/lambda.cu
  clang/test/CodeGenCUDA/redux-builtins.cu
  clang/test/CodeGenCUDA/surface.cu
  clang/test/CodeGenCUDA/unnamed-types.cu
  clang/test/CodeGenCUDA/usual-deallocators.cu
  clang/test/CodeGenCUDA/vtbl.cu
  clang/test/CodeGenCUDASPIRV/kernel-argument.cu
  clang/test/CodeGenHIP/hipspv-addr-spaces.cpp
  clang/test/CodeGenHIP/noundef-attribute-hip-device-verify.hip
  clang/test/CodeGenOpenCL/addr-space-struct-arg.cl
  clang/test/CodeGenOpenCL/address-spaces.cl
  clang/test/CodeGenOpenCL/amdgcn-automatic-variable.cl
  clang/test/CodeGenOpenCL/amdgpu-abi-struct-coerce.cl
  clang/test/CodeGenOpenCL/amdgpu-call-kernel.cl
  clang/test/CodeGenOpenCL/amdgpu-printf.cl
  clang/test/CodeGenOpenCL/as_type.cl
  clang/test/CodeGenOpenCL/atomic-ops-libcall.cl
  clang/test/CodeGenOpenCL/blocks.cl
  clang/test/CodeGenOpenCL/byval.cl
  clang/test/CodeGenOpenCL/const-str-array-decay.cl
  clang/test/CodeGenOpenCL/constant-addr-space-globals.cl
  clang/test/CodeGenOpenCL/convergent.cl
  clang/test/CodeGenOpenCL/fpmath.cl
  clang/test/CodeGenOpenCL/half.cl
  clang/test/CodeGenOpenCL/kernel-param-alignment.cl
  clang/test/CodeGenOpenCL/kernels-have-spir-cc-by-default.cl
  clang/test/CodeGenOpenCL/no-half.cl
  clang/test/CodeGenOpenCL/overload.cl
  clang/test/CodeGenOpenCL/size_t.cl
  clang/test/CodeGenOpenCL/spir-calling-conv.cl
  clang/test/CodeGenOpenCLCXX/address-space-deduction.clcpp
  clang/test/CodeGenOpenCLCXX/addrspace-derived-base.clcpp
  clang/test/CodeGenOpenCLCXX/addrspace-new-delete.clcpp
  clang/test/CodeGenOpenCLCXX/addrspace-of-this.clcpp
  clang/test/CodeGenOpenCLCXX/addrspace-operators.clcpp
  clang/test/CodeGenOpenCLCXX/addrspace-references.clcpp
  clang/test/CodeGenOpenCLCXX/addrspace-with-class.clcpp
  clang/test/CodeGenOpenCLCXX/template-address-spaces.clcpp
  clang/test/CodeGenSYCL/address-space-conversions.cpp
  clang/test/CodeGenSYCL/address-space-mangling.cpp
  clang/test/CodeGenSYCL/functionptr-addrspace.cpp
  clang/test/CodeGenSYCL/unique_stable_name.cpp
  clang/test/OpenMP/amdgcn-attributes.cpp
  clang/test/OpenMP/amdgcn_target_global_constructor.cpp
  clang/test/OpenMP/assumes_include_nvptx.cpp
  clang/test/OpenMP/declare_target_codegen.cpp
  clang/test/OpenMP/declare_target_codegen_globalization.cpp
  clang/test/OpenMP/declare_target_link_codegen.cpp
  clang/test/OpenMP/declare_variant_mixed_codegen.c
  clang/test/OpenMP/distribute_codegen.cpp
  clang/test/OpenMP/distribute_simd_codegen.cpp
  clang/test/OpenMP/nvptx_allocate_codegen.cpp
  clang/test/OpenMP/nvptx_data_sharing.cpp
  clang/test/OpenMP/nvptx_declare_target_var_ctor_dtor_codegen.cpp
  clang/test/OpenMP/nvptx_declare_variant_name_mangling.cpp
  clang/test/OpenMP/nvptx_distribute_parallel_generic_mode_codegen.cpp
  clang/test/OpenMP/nvptx_lambda_capturing.cpp
  clang/test/OpenMP/nvptx_multi_target_parallel_codegen.cpp
  clang/test/OpenMP/nvptx_nested_parallel_codegen.cpp
  clang/test/OpenMP/nvptx_parallel_codegen.cpp
  clang/test/OpenMP/nvptx_parallel_for_codegen.cpp
  clang/test/OpenMP/nvptx_target_firstprivate_codegen.cpp
  clang/test/OpenMP/nvptx_target_parallel_codegen.cpp
  clang/test/OpenMP/nvptx_target_parallel_num_threads_codegen.cpp
  clang/test/OpenMP/nvptx_target_parallel_reduction_codegen.cpp
  clang/test/OpenMP/nvptx_target_printf_codegen.c
  clang/test/OpenMP/nvptx_target_teams_codegen.cpp
  clang/test/OpenMP/nvptx_target_teams_distribute_codegen.cpp
  clang/test/OpenMP/nvptx_target_teams_distribute_parallel_for_codegen.cpp
  
clang/test/OpenMP/nvptx_target_teams_distribute_parallel_for_generic_mode_codegen.cpp
  clang/test/OpenMP/nvptx_target_teams_distribute_parallel_for_simd_codegen.cpp
  clang/test/OpenMP/nvptx_teams_codegen.cpp
  clang/test/OpenMP/nvptx_teams_reduction_codegen.cpp
  clang/test/OpenMP/nvptx_unsupported_type_codegen.cpp
  clang/test/OpenMP/openmp_offload_codegen.cpp
  clang/test/OpenMP/reduction_implicit_map.cpp
  clang/test/OpenMP/target_firstprivate_codegen.cpp
  clang/test/OpenMP/target_parallel_codegen.cpp
  clang/test/OpenMP/target_parallel_debug_codegen.cpp
  clang/test/OpenMP/target_parallel_for_codegen.cpp
  clang/test/OpenMP/target_parallel_for_debug_codegen.cpp
  clang/test/OpenMP/target_parallel_for_simd_codegen.cpp
  clang/test/OpenMP/target_parallel_if_codegen.cpp
  clang/test/OpenMP/target_parallel_num_threads_codegen.cpp
  clang/test/OpenMP/target_private_cod

[PATCH] D130224: [Clang][Attribute] Introduce maybe_undef attribute for function arguments which accepts undef values

[krishna chaitanya sankisa via Phabricator via cfe-commits]

skc7 updated this revision to Diff 447993.
skc7 added a comment.

Changes for code review comments from @aaron.ballman


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D130224/new/

https://reviews.llvm.org/D130224

Files:
  clang/include/clang/Basic/Attr.td
  clang/include/clang/Basic/AttrDocs.td
  clang/lib/CodeGen/CGCall.cpp
  clang/lib/Sema/SemaDeclAttr.cpp
  clang/test/CodeGen/attr-maybeundef-template.cpp
  clang/test/CodeGen/attr-maybeundef.c
  clang/test/CodeGenHIP/maybe_undef-attr-verify.hip
  clang/test/Misc/pragma-attribute-supported-attributes-list.test
  clang/test/Sema/attr-maybeundef.c

Index: clang/test/Sema/attr-maybeundef.c
===
--- /dev/null
+++ clang/test/Sema/attr-maybeundef.c
@@ -0,0 +1,15 @@
+// RUN: %clang_cc1  -fsyntax-only -verify %s
+
+// Decl annotations.
+void f(int __attribute__((maybe_undef)) *a);
+void (*fp)(int __attribute__((maybe_undef)) handle);
+__attribute__((maybe_undef)) int i(); // expected-warning {{'maybe_undef' attribute only applies to parameters}}
+int __attribute__((maybe_undef)) a; // expected-warning {{'maybe_undef' attribute only applies to parameters}}
+int (* __attribute__((maybe_undef)) fpt)(char *); // expected-warning {{'maybe_undef' attribute only applies to parameters}}
+void h(int *a __attribute__((maybe_undef("RandomString"; // expected-error {{'maybe_undef' attribute takes no arguments}}
+
+// Type annotations.
+int __attribute__((maybe_undef)) ta; // expected-warning {{'maybe_undef' attribute only applies to parameters}}
+
+// Typedefs.
+typedef int callback(char *) __attribute__((maybe_undef)); // expected-warning {{'maybe_undef' attribute only applies to parameters}}
Index: clang/test/Misc/pragma-attribute-supported-attributes-list.test
===
--- clang/test/Misc/pragma-attribute-supported-attributes-list.test
+++ clang/test/Misc/pragma-attribute-supported-attributes-list.test
@@ -83,6 +83,7 @@
 // CHECK-NEXT: Lockable (SubjectMatchRule_record)
 // CHECK-NEXT: MIGServerRoutine (SubjectMatchRule_function, SubjectMatchRule_objc_method, SubjectMatchRule_block)
 // CHECK-NEXT: MSStruct (SubjectMatchRule_record)
+// CHECK-NEXT: MaybeUndef (SubjectMatchRule_variable_is_parameter)
 // CHECK-NEXT: MicroMips (SubjectMatchRule_function)
 // CHECK-NEXT: MinSize (SubjectMatchRule_function, SubjectMatchRule_objc_method)
 // CHECK-NEXT: MinVectorWidth (SubjectMatchRule_function)
Index: clang/test/CodeGenHIP/maybe_undef-attr-verify.hip
===
--- /dev/null
+++ clang/test/CodeGenHIP/maybe_undef-attr-verify.hip
@@ -0,0 +1,44 @@
+// RUN: %clang_cc1 -no-opaque-pointers -triple amdgcn-amd-amdhsa -target-cpu gfx906 -x hip -fcuda-is-device -emit-llvm  %s \
+// RUN:   -o - | FileCheck %s
+
+// CHECK: define dso_local amdgpu_kernel void @_Z13shufflekernelv()
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:[[TMP1:%.*]] = alloca i32, align 4, addrspace(5)
+// CHECK-NEXT:[[TMP2:%.*]] = alloca i32, align 4, addrspace(5)
+// CHECK-NEXT:[[TMP3:%.*]] = addrspacecast i32 addrspace(5)* [[TMP1:%.*]] to i32*
+// CHECK-NEXT:[[TMP4:%.*]] = addrspacecast i32 addrspace(5)* [[TMP2:%.*]] to i32*
+// CHECK-NEXT:[[TMP5:%.*]] = load i32, i32* [[TMP3:%.*]], align 4
+// CHECK-NEXT:[[TMP6:%.*]] = freeze i32 [[TMP5:%.*]]
+// CHECK-NEXT:%call = call noundef i32 @_Z11__shfl_synciii(i32 noundef [[TMP6:%.*]], i32 noundef 64, i32 noundef 0) #4
+// CHECK-NEXT:store i32 %call, i32* [[TMP4:%.*]], align 4
+// CHECK-NEXT:  ret void
+
+// CHECK: define linkonce_odr noundef i32 @_Z11__shfl_synciii(i32 noundef [[TMP1:%.*]], i32 noundef [[TMP2:%.*]], i32 noundef [[TMP3:%.*]])
+
+#define __global__ __attribute__((global))
+#define __device__ __attribute__((device))
+#define __maybe_undef __attribute__((maybe_undef))
+#define WARP_SIZE 64
+
+static constexpr int warpSize = __AMDGCN_WAVEFRONT_SIZE;
+
+__device__ static inline unsigned int __lane_id() {
+return  __builtin_amdgcn_mbcnt_hi(
+-1, __builtin_amdgcn_mbcnt_lo(-1, 0));
+}
+
+__device__
+inline
+int __shfl_sync(int __maybe_undef var, int src_lane, int width = warpSize) {
+int self = __lane_id();
+int index = src_lane + (self & ~(width-1));
+return __builtin_amdgcn_ds_bpermute(index<<2, var);
+}
+
+__global__ void
+shufflekernel()
+{
+int t;
+int res;
+res = __shfl_sync(t, WARP_SIZE, 0);
+}
Index: clang/test/CodeGen/attr-maybeundef.c
===
--- /dev/null
+++ clang/test/CodeGen/attr-maybeundef.c
@@ -0,0 +1,110 @@
+// RUN: %clang_cc1 -no-opaque-pointers -emit-llvm %s -o - | FileCheck %s
+
+#define __maybe_undef __attribute__((maybe_undef))
+
+// CHECK:  define dso_local void @t1(i32 noundef [[TMP1:%.*]], i32 noundef [[TMP2:%.*]], float noundef [[TMP3:%.*]])
+// CHECK-NEXT: entry:
+// CHECK-NEXT:   [[TMP4:%.*]] = alloca i32, align 4
+// CHECK-

[PATCH] D130224: [Clang][Attribute] Introduce maybe_undef attribute for function arguments which accepts undef values

[krishna chaitanya sankisa via Phabricator via cfe-commits]

skc7 added inline comments.



Comment at: clang/lib/CodeGen/CGCall.cpp:2050-2066
+static bool IsArgumentMayBeUndef(const Decl *TargetDecl, unsigned ArgNo) {
+  if (!TargetDecl)
+return false;
+
+  bool ArgHasMayBeUndefAttr = false;
+  if (TargetDecl) {
+if (const FunctionDecl *FD = dyn_cast(TargetDecl)) {

aaron.ballman wrote:
> One question I have is whether you ever need to mark the variadic arguments 
> as being maybe undef. e.g., `void func(int i, ...);` do you need to signal 
> that arguments passed to `...` are maybe undef?
> 
Current change assumes variadic arguments will not have "maybe_undef" 
attribute. If its a function attribute, variadic arguments can inherit them 
(Have seen such cases in clang codebase). But "maybe_undef" is function 
argument attribute and I'm not sure on how to add it to variadic arguments.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D130224/new/

https://reviews.llvm.org/D130224

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D130224: [Clang][Attribute] Introduce maybe_undef attribute for function arguments which accepts undef values

[krishna chaitanya sankisa via Phabricator via cfe-commits]

skc7 updated this revision to Diff 448330.
skc7 marked an inline comment as not done.
skc7 added a comment.

Fix tests failures.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D130224/new/

https://reviews.llvm.org/D130224

Files:
  clang/include/clang/Basic/Attr.td
  clang/include/clang/Basic/AttrDocs.td
  clang/lib/CodeGen/CGCall.cpp
  clang/lib/Sema/SemaDeclAttr.cpp
  clang/test/CodeGen/attr-maybeundef-template.cpp
  clang/test/CodeGen/attr-maybeundef.c
  clang/test/CodeGenHIP/maybe_undef-attr-verify.hip
  clang/test/Misc/pragma-attribute-supported-attributes-list.test
  clang/test/Sema/attr-maybeundef.c

Index: clang/test/Sema/attr-maybeundef.c
===
--- /dev/null
+++ clang/test/Sema/attr-maybeundef.c
@@ -0,0 +1,15 @@
+// RUN: %clang_cc1  -fsyntax-only -verify %s
+
+// Decl annotations.
+void f(int __attribute__((maybe_undef)) *a);
+void (*fp)(int __attribute__((maybe_undef)) handle);
+__attribute__((maybe_undef)) int i(); // expected-warning {{'maybe_undef' attribute only applies to parameters}}
+int __attribute__((maybe_undef)) a; // expected-warning {{'maybe_undef' attribute only applies to parameters}}
+int (* __attribute__((maybe_undef)) fpt)(char *); // expected-warning {{'maybe_undef' attribute only applies to parameters}}
+void h(int *a __attribute__((maybe_undef("RandomString"; // expected-error {{'maybe_undef' attribute takes no arguments}}
+
+// Type annotations.
+int __attribute__((maybe_undef)) ta; // expected-warning {{'maybe_undef' attribute only applies to parameters}}
+
+// Typedefs.
+typedef int callback(char *) __attribute__((maybe_undef)); // expected-warning {{'maybe_undef' attribute only applies to parameters}}
Index: clang/test/Misc/pragma-attribute-supported-attributes-list.test
===
--- clang/test/Misc/pragma-attribute-supported-attributes-list.test
+++ clang/test/Misc/pragma-attribute-supported-attributes-list.test
@@ -83,6 +83,7 @@
 // CHECK-NEXT: Lockable (SubjectMatchRule_record)
 // CHECK-NEXT: MIGServerRoutine (SubjectMatchRule_function, SubjectMatchRule_objc_method, SubjectMatchRule_block)
 // CHECK-NEXT: MSStruct (SubjectMatchRule_record)
+// CHECK-NEXT: MaybeUndef (SubjectMatchRule_variable_is_parameter)
 // CHECK-NEXT: MicroMips (SubjectMatchRule_function)
 // CHECK-NEXT: MinSize (SubjectMatchRule_function, SubjectMatchRule_objc_method)
 // CHECK-NEXT: MinVectorWidth (SubjectMatchRule_function)
Index: clang/test/CodeGenHIP/maybe_undef-attr-verify.hip
===
--- /dev/null
+++ clang/test/CodeGenHIP/maybe_undef-attr-verify.hip
@@ -0,0 +1,44 @@
+// RUN: %clang_cc1 -no-opaque-pointers -triple amdgcn-amd-amdhsa -target-cpu gfx906 -x hip -fcuda-is-device -emit-llvm  %s \
+// RUN:   -o - | FileCheck %s
+
+// CHECK: define dso_local amdgpu_kernel void @_Z13shufflekernelv()
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:[[TMP1:%.*]] = alloca i32, align 4, addrspace(5)
+// CHECK-NEXT:[[TMP2:%.*]] = alloca i32, align 4, addrspace(5)
+// CHECK-NEXT:[[TMP3:%.*]] = addrspacecast i32 addrspace(5)* [[TMP1:%.*]] to i32*
+// CHECK-NEXT:[[TMP4:%.*]] = addrspacecast i32 addrspace(5)* [[TMP2:%.*]] to i32*
+// CHECK-NEXT:[[TMP5:%.*]] = load i32, i32* [[TMP3:%.*]], align 4
+// CHECK-NEXT:[[TMP6:%.*]] = freeze i32 [[TMP5:%.*]]
+// CHECK-NEXT:%call = call noundef i32 @_Z11__shfl_synciii(i32 noundef [[TMP6:%.*]], i32 noundef 64, i32 noundef 0) #4
+// CHECK-NEXT:store i32 %call, i32* [[TMP4:%.*]], align 4
+// CHECK-NEXT:  ret void
+
+// CHECK: define linkonce_odr noundef i32 @_Z11__shfl_synciii(i32 noundef [[TMP1:%.*]], i32 noundef [[TMP2:%.*]], i32 noundef [[TMP3:%.*]])
+
+#define __global__ __attribute__((global))
+#define __device__ __attribute__((device))
+#define __maybe_undef __attribute__((maybe_undef))
+#define WARP_SIZE 64
+
+static constexpr int warpSize = __AMDGCN_WAVEFRONT_SIZE;
+
+__device__ static inline unsigned int __lane_id() {
+return  __builtin_amdgcn_mbcnt_hi(
+-1, __builtin_amdgcn_mbcnt_lo(-1, 0));
+}
+
+__device__
+inline
+int __shfl_sync(int __maybe_undef var, int src_lane, int width = warpSize) {
+int self = __lane_id();
+int index = src_lane + (self & ~(width-1));
+return __builtin_amdgcn_ds_bpermute(index<<2, var);
+}
+
+__global__ void
+shufflekernel()
+{
+int t;
+int res;
+res = __shfl_sync(t, WARP_SIZE, 0);
+}
Index: clang/test/CodeGen/attr-maybeundef.c
===
--- /dev/null
+++ clang/test/CodeGen/attr-maybeundef.c
@@ -0,0 +1,109 @@
+// RUN: %clang_cc1 -no-opaque-pointers -emit-llvm %s -o - | FileCheck %s
+
+#define __maybe_undef __attribute__((maybe_undef))
+
+// CHECK:  define dso_local void @t1(i32 noundef [[TMP1:%.*]], i32 noundef [[TMP2:%.*]], i32 noundef [[TMP3:%.*]])
+// CHECK-NEXT: entry:
+// CHECK-NEXT:   [[TMP4:%.*]] = alloca i32, align 4
+/

[PATCH] D130224: [Clang][Attribute] Introduce maybe_undef attribute for function arguments which accepts undef values

[krishna chaitanya sankisa via Phabricator via cfe-commits]

skc7 updated this revision to Diff 448361.
skc7 added a comment.

Fix windows tests failure


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D130224/new/

https://reviews.llvm.org/D130224

Files:
  clang/include/clang/Basic/Attr.td
  clang/include/clang/Basic/AttrDocs.td
  clang/lib/CodeGen/CGCall.cpp
  clang/lib/Sema/SemaDeclAttr.cpp
  clang/test/CodeGen/attr-maybeundef-template.cpp
  clang/test/CodeGen/attr-maybeundef.c
  clang/test/CodeGenHIP/maybe_undef-attr-verify.hip
  clang/test/Misc/pragma-attribute-supported-attributes-list.test
  clang/test/Sema/attr-maybeundef.c

Index: clang/test/Sema/attr-maybeundef.c
===
--- /dev/null
+++ clang/test/Sema/attr-maybeundef.c
@@ -0,0 +1,15 @@
+// RUN: %clang_cc1  -fsyntax-only -verify %s
+
+// Decl annotations.
+void f(int __attribute__((maybe_undef)) *a);
+void (*fp)(int __attribute__((maybe_undef)) handle);
+__attribute__((maybe_undef)) int i(); // expected-warning {{'maybe_undef' attribute only applies to parameters}}
+int __attribute__((maybe_undef)) a; // expected-warning {{'maybe_undef' attribute only applies to parameters}}
+int (* __attribute__((maybe_undef)) fpt)(char *); // expected-warning {{'maybe_undef' attribute only applies to parameters}}
+void h(int *a __attribute__((maybe_undef("RandomString"; // expected-error {{'maybe_undef' attribute takes no arguments}}
+
+// Type annotations.
+int __attribute__((maybe_undef)) ta; // expected-warning {{'maybe_undef' attribute only applies to parameters}}
+
+// Typedefs.
+typedef int callback(char *) __attribute__((maybe_undef)); // expected-warning {{'maybe_undef' attribute only applies to parameters}}
Index: clang/test/Misc/pragma-attribute-supported-attributes-list.test
===
--- clang/test/Misc/pragma-attribute-supported-attributes-list.test
+++ clang/test/Misc/pragma-attribute-supported-attributes-list.test
@@ -83,6 +83,7 @@
 // CHECK-NEXT: Lockable (SubjectMatchRule_record)
 // CHECK-NEXT: MIGServerRoutine (SubjectMatchRule_function, SubjectMatchRule_objc_method, SubjectMatchRule_block)
 // CHECK-NEXT: MSStruct (SubjectMatchRule_record)
+// CHECK-NEXT: MaybeUndef (SubjectMatchRule_variable_is_parameter)
 // CHECK-NEXT: MicroMips (SubjectMatchRule_function)
 // CHECK-NEXT: MinSize (SubjectMatchRule_function, SubjectMatchRule_objc_method)
 // CHECK-NEXT: MinVectorWidth (SubjectMatchRule_function)
Index: clang/test/CodeGenHIP/maybe_undef-attr-verify.hip
===
--- /dev/null
+++ clang/test/CodeGenHIP/maybe_undef-attr-verify.hip
@@ -0,0 +1,44 @@
+// RUN: %clang_cc1 -no-opaque-pointers -triple amdgcn-amd-amdhsa -target-cpu gfx906 -x hip -fcuda-is-device -emit-llvm  %s \
+// RUN:   -o - | FileCheck %s
+
+// CHECK: define dso_local amdgpu_kernel void @_Z13shufflekernelv()
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:[[TMP1:%.*]] = alloca i32, align 4, addrspace(5)
+// CHECK-NEXT:[[TMP2:%.*]] = alloca i32, align 4, addrspace(5)
+// CHECK-NEXT:[[TMP3:%.*]] = addrspacecast i32 addrspace(5)* [[TMP1:%.*]] to i32*
+// CHECK-NEXT:[[TMP4:%.*]] = addrspacecast i32 addrspace(5)* [[TMP2:%.*]] to i32*
+// CHECK-NEXT:[[TMP5:%.*]] = load i32, i32* [[TMP3:%.*]], align 4
+// CHECK-NEXT:[[TMP6:%.*]] = freeze i32 [[TMP5:%.*]]
+// CHECK-NEXT:%call = call noundef i32 @_Z11__shfl_synciii(i32 noundef [[TMP6:%.*]], i32 noundef 64, i32 noundef 0) #4
+// CHECK-NEXT:store i32 %call, i32* [[TMP4:%.*]], align 4
+// CHECK-NEXT:  ret void
+
+// CHECK: define linkonce_odr noundef i32 @_Z11__shfl_synciii(i32 noundef [[TMP1:%.*]], i32 noundef [[TMP2:%.*]], i32 noundef [[TMP3:%.*]])
+
+#define __global__ __attribute__((global))
+#define __device__ __attribute__((device))
+#define __maybe_undef __attribute__((maybe_undef))
+#define WARP_SIZE 64
+
+static constexpr int warpSize = __AMDGCN_WAVEFRONT_SIZE;
+
+__device__ static inline unsigned int __lane_id() {
+return  __builtin_amdgcn_mbcnt_hi(
+-1, __builtin_amdgcn_mbcnt_lo(-1, 0));
+}
+
+__device__
+inline
+int __shfl_sync(int __maybe_undef var, int src_lane, int width = warpSize) {
+int self = __lane_id();
+int index = src_lane + (self & ~(width-1));
+return __builtin_amdgcn_ds_bpermute(index<<2, var);
+}
+
+__global__ void
+shufflekernel()
+{
+int t;
+int res;
+res = __shfl_sync(t, WARP_SIZE, 0);
+}
Index: clang/test/CodeGen/attr-maybeundef.c
===
--- /dev/null
+++ clang/test/CodeGen/attr-maybeundef.c
@@ -0,0 +1,109 @@
+// RUN: %clang_cc1 -no-opaque-pointers -emit-llvm %s -o - | FileCheck %s
+
+#define __maybe_undef __attribute__((maybe_undef))
+
+// CHECK:  define{{.*}} void @t1(i32 noundef [[TMP1:%.*]], i32 noundef [[TMP2:%.*]], i32 noundef [[TMP3:%.*]])
+// CHECK-NEXT: entry:
+// CHECK-NEXT:   [[TMP4:%.*]] = alloca i32, align 4
+// CHECK-NEXT:   [[TMP5:%.*]] = alloca i32

[PATCH] D130224: [Clang][Attribute] Introduce maybe_undef attribute for function arguments which accepts undef values

[krishna chaitanya sankisa via Phabricator via cfe-commits]

skc7 added inline comments.



Comment at: clang/test/CodeGen/attr-maybeundef.c:48
+
+// CHECK: declare void @VariadicFunction(i32 noundef, ...)
+

aaron.ballman wrote:
> It looks like dso_local is missing here on Windows and expected to be missing 
> on Linux? Not certain what's up with that...
On Linux, dso_local isn't present.
declare void @VariadicFunction(i32 noundef, ...)


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D130224/new/

https://reviews.llvm.org/D130224

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D130224: [Clang][Attribute] Introduce maybe_undef attribute for function arguments which accepts undef values

[krishna chaitanya sankisa via Phabricator via cfe-commits]

This revision was automatically updated to reflect the committed changes.
Closed by commit rGa35c64ce23b7: [Clang][Attribute] Introduce maybe_undef 
attribute for function arguments which… (authored by skc7).

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D130224/new/

https://reviews.llvm.org/D130224

Files:
  clang/include/clang/Basic/Attr.td
  clang/include/clang/Basic/AttrDocs.td
  clang/lib/CodeGen/CGCall.cpp
  clang/lib/Sema/SemaDeclAttr.cpp
  clang/test/CodeGen/attr-maybeundef-template.cpp
  clang/test/CodeGen/attr-maybeundef.c
  clang/test/CodeGenHIP/maybe_undef-attr-verify.hip
  clang/test/Misc/pragma-attribute-supported-attributes-list.test
  clang/test/Sema/attr-maybeundef.c

Index: clang/test/Sema/attr-maybeundef.c
===
--- /dev/null
+++ clang/test/Sema/attr-maybeundef.c
@@ -0,0 +1,15 @@
+// RUN: %clang_cc1  -fsyntax-only -verify %s
+
+// Decl annotations.
+void f(int __attribute__((maybe_undef)) *a);
+void (*fp)(int __attribute__((maybe_undef)) handle);
+__attribute__((maybe_undef)) int i(); // expected-warning {{'maybe_undef' attribute only applies to parameters}}
+int __attribute__((maybe_undef)) a; // expected-warning {{'maybe_undef' attribute only applies to parameters}}
+int (* __attribute__((maybe_undef)) fpt)(char *); // expected-warning {{'maybe_undef' attribute only applies to parameters}}
+void h(int *a __attribute__((maybe_undef("RandomString"; // expected-error {{'maybe_undef' attribute takes no arguments}}
+
+// Type annotations.
+int __attribute__((maybe_undef)) ta; // expected-warning {{'maybe_undef' attribute only applies to parameters}}
+
+// Typedefs.
+typedef int callback(char *) __attribute__((maybe_undef)); // expected-warning {{'maybe_undef' attribute only applies to parameters}}
Index: clang/test/Misc/pragma-attribute-supported-attributes-list.test
===
--- clang/test/Misc/pragma-attribute-supported-attributes-list.test
+++ clang/test/Misc/pragma-attribute-supported-attributes-list.test
@@ -83,6 +83,7 @@
 // CHECK-NEXT: Lockable (SubjectMatchRule_record)
 // CHECK-NEXT: MIGServerRoutine (SubjectMatchRule_function, SubjectMatchRule_objc_method, SubjectMatchRule_block)
 // CHECK-NEXT: MSStruct (SubjectMatchRule_record)
+// CHECK-NEXT: MaybeUndef (SubjectMatchRule_variable_is_parameter)
 // CHECK-NEXT: MicroMips (SubjectMatchRule_function)
 // CHECK-NEXT: MinSize (SubjectMatchRule_function, SubjectMatchRule_objc_method)
 // CHECK-NEXT: MinVectorWidth (SubjectMatchRule_function)
Index: clang/test/CodeGenHIP/maybe_undef-attr-verify.hip
===
--- /dev/null
+++ clang/test/CodeGenHIP/maybe_undef-attr-verify.hip
@@ -0,0 +1,44 @@
+// RUN: %clang_cc1 -no-opaque-pointers -triple amdgcn-amd-amdhsa -target-cpu gfx906 -x hip -fcuda-is-device -emit-llvm  %s \
+// RUN:   -o - | FileCheck %s
+
+// CHECK: define dso_local amdgpu_kernel void @_Z13shufflekernelv()
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:[[TMP1:%.*]] = alloca i32, align 4, addrspace(5)
+// CHECK-NEXT:[[TMP2:%.*]] = alloca i32, align 4, addrspace(5)
+// CHECK-NEXT:[[TMP3:%.*]] = addrspacecast i32 addrspace(5)* [[TMP1:%.*]] to i32*
+// CHECK-NEXT:[[TMP4:%.*]] = addrspacecast i32 addrspace(5)* [[TMP2:%.*]] to i32*
+// CHECK-NEXT:[[TMP5:%.*]] = load i32, i32* [[TMP3:%.*]], align 4
+// CHECK-NEXT:[[TMP6:%.*]] = freeze i32 [[TMP5:%.*]]
+// CHECK-NEXT:%call = call noundef i32 @_Z11__shfl_synciii(i32 noundef [[TMP6:%.*]], i32 noundef 64, i32 noundef 0) #4
+// CHECK-NEXT:store i32 %call, i32* [[TMP4:%.*]], align 4
+// CHECK-NEXT:  ret void
+
+// CHECK: define linkonce_odr noundef i32 @_Z11__shfl_synciii(i32 noundef [[TMP1:%.*]], i32 noundef [[TMP2:%.*]], i32 noundef [[TMP3:%.*]])
+
+#define __global__ __attribute__((global))
+#define __device__ __attribute__((device))
+#define __maybe_undef __attribute__((maybe_undef))
+#define WARP_SIZE 64
+
+static constexpr int warpSize = __AMDGCN_WAVEFRONT_SIZE;
+
+__device__ static inline unsigned int __lane_id() {
+return  __builtin_amdgcn_mbcnt_hi(
+-1, __builtin_amdgcn_mbcnt_lo(-1, 0));
+}
+
+__device__
+inline
+int __shfl_sync(int __maybe_undef var, int src_lane, int width = warpSize) {
+int self = __lane_id();
+int index = src_lane + (self & ~(width-1));
+return __builtin_amdgcn_ds_bpermute(index<<2, var);
+}
+
+__global__ void
+shufflekernel()
+{
+int t;
+int res;
+res = __shfl_sync(t, WARP_SIZE, 0);
+}
Index: clang/test/CodeGen/attr-maybeundef.c
===
--- /dev/null
+++ clang/test/CodeGen/attr-maybeundef.c
@@ -0,0 +1,109 @@
+// RUN: %clang_cc1 -no-opaque-pointers -emit-llvm %s -o - | FileCheck %s
+
+#define __maybe_undef __attribute__((maybe_undef))
+
+// CHECK:  define{{.*}} void @t1(i32 noundef [[TMP1:%.*]], i32 noundef [[TM

[PATCH] D130790: Fix failing tests for "[Clang][Attribute] Introduce maybe_undef attribute for function arguments which accepts undef values"

[krishna chaitanya sankisa via Phabricator via cfe-commits]

skc7 created this revision.
skc7 added reviewers: aaron.ballman, ronlieb, arsenm.
Herald added a subscriber: pengfei.
Herald added a project: All.
skc7 requested review of this revision.
Herald added subscribers: cfe-commits, wdng.
Herald added a project: clang.

Add target triple x86_64-gnu-linux for tests failing due to D130224 



Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D130790

Files:
  clang/test/CodeGen/attr-maybeundef-template.cpp
  clang/test/CodeGen/attr-maybeundef.c


Index: clang/test/CodeGen/attr-maybeundef.c
===
--- clang/test/CodeGen/attr-maybeundef.c
+++ clang/test/CodeGen/attr-maybeundef.c
@@ -1,4 +1,4 @@
-// RUN: %clang_cc1 -no-opaque-pointers -emit-llvm %s -o - | FileCheck %s
+// RUN: %clang_cc1 -no-opaque-pointers -triple x86_64-gnu-linux -emit-llvm %s 
-o - | FileCheck %s
 
 #define __maybe_undef __attribute__((maybe_undef))
 
Index: clang/test/CodeGen/attr-maybeundef-template.cpp
===
--- clang/test/CodeGen/attr-maybeundef-template.cpp
+++ clang/test/CodeGen/attr-maybeundef-template.cpp
@@ -1,4 +1,4 @@
-// RUN: %clang_cc1 -no-opaque-pointers -emit-llvm %s -o - | FileCheck %s
+// RUN: %clang_cc1 -no-opaque-pointers -triple x86_64-gnu-linux -emit-llvm %s 
-o - | FileCheck %s
 
 // CHECK-LABEL: define{{.*}} void @{{.*}}test4{{.*}}(float
 // CHECK-NEXT:  entry:


Index: clang/test/CodeGen/attr-maybeundef.c
===
--- clang/test/CodeGen/attr-maybeundef.c
+++ clang/test/CodeGen/attr-maybeundef.c
@@ -1,4 +1,4 @@
-// RUN: %clang_cc1 -no-opaque-pointers -emit-llvm %s -o - | FileCheck %s
+// RUN: %clang_cc1 -no-opaque-pointers -triple x86_64-gnu-linux -emit-llvm %s -o - | FileCheck %s
 
 #define __maybe_undef __attribute__((maybe_undef))
 
Index: clang/test/CodeGen/attr-maybeundef-template.cpp
===
--- clang/test/CodeGen/attr-maybeundef-template.cpp
+++ clang/test/CodeGen/attr-maybeundef-template.cpp
@@ -1,4 +1,4 @@
-// RUN: %clang_cc1 -no-opaque-pointers -emit-llvm %s -o - | FileCheck %s
+// RUN: %clang_cc1 -no-opaque-pointers -triple x86_64-gnu-linux -emit-llvm %s -o - | FileCheck %s
 
 // CHECK-LABEL: define{{.*}} void @{{.*}}test4{{.*}}(float
 // CHECK-NEXT:  entry:
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D130224: [Clang][Attribute] Introduce maybe_undef attribute for function arguments which accepts undef values

[krishna chaitanya sankisa via Phabricator via cfe-commits]

skc7 added a comment.

In D130224#3687907 , @aaron.ballman 
wrote:

> In D130224#3687860 , @amyk wrote:
>
>> In D130224#3687487 , @mubarizafzal 
>> wrote:
>>
>>> Hi, the test cases that this patch introduces are failing on some ppc64le 
>>> (Linux on Power) buildbots:
>>> https://lab.llvm.org/buildbot/#/builders/57
>>> https://lab.llvm.org/buildbot/#/builders/230
>>>
>>> Would you mind taking a look please?
>>
>> Thanks for pinging this patch. It appears it's affecting both little endian 
>> PPC:
>> https://lab.llvm.org/buildbot/#/builders/230/builds/1079
>> https://lab.llvm.org/buildbot/#/builders/121/builds/21978
>> https://lab.llvm.org/buildbot/#/builders/57/builds/20484
>> https://lab.llvm.org/buildbot/#/builders/36/builds/23702
>>
>> And big endian PPC bots:
>> https://lab.llvm.org/buildbot/#/builders/231/builds/842
>> https://lab.llvm.org/buildbot/#/builders/93/builds/10270
>
> If we don't hear from @skc7 in the next ~hour with a fix, feel free to revert 
> to get the bots back to green.

Issue is with missing target triple in the tests. Submitted D130790 
 for review, which should fix the tests.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D130224/new/

https://reviews.llvm.org/D130224

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D130224: [Clang][Attribute] Introduce maybe_undef attribute for function arguments which accepts undef values

[krishna chaitanya sankisa via Phabricator via cfe-commits]

skc7 added a comment.

In D130224#3688067 , @amyk wrote:

> In D130224#3688034 , @skc7 wrote:
>
>> In D130224#3687907 , 
>> @aaron.ballman wrote:
>>
>>> In D130224#3687860 , @amyk wrote:
>>>
 In D130224#3687487 , 
 @mubarizafzal wrote:

> Hi, the test cases that this patch introduces are failing on some ppc64le 
> (Linux on Power) buildbots:
> https://lab.llvm.org/buildbot/#/builders/57
> https://lab.llvm.org/buildbot/#/builders/230
> Would you mind taking a look please?

 Thanks for pinging this patch. It appears it's affecting both little 
 endian PPC:
 https://lab.llvm.org/buildbot/#/builders/230/builds/1079
 https://lab.llvm.org/buildbot/#/builders/121/builds/21978
 https://lab.llvm.org/buildbot/#/builders/57/builds/20484
 https://lab.llvm.org/buildbot/#/builders/36/builds/23702

 And big endian PPC bots:
 https://lab.llvm.org/buildbot/#/builders/231/builds/842
 https://lab.llvm.org/buildbot/#/builders/93/builds/10270
>>>
>>> If we don't hear from @skc7 in the next ~hour with a fix, feel free to 
>>> revert to get the bots back to green.
>>
>> Issue is with missing target triple in the tests. Submitted D130790 
>>  for review, which should fix the tests.
>
> I realized I didn't happen to see this comment in time and had already 
> reverted the patch. My apologies on this.

Relanded the revert with fixes to tests. commit 



Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D130224/new/

https://reviews.llvm.org/D130224

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D124158: [Clang][Attr] Skip adding noundef attribute to arguments when function has convergent attribute

[krishna chaitanya sankisa via Phabricator via cfe-commits]

skc7 created this revision.
skc7 added reviewers: sameerds, cdevadas, ronlieb.
Herald added subscribers: mattd, asavonic, ThomasRaoux, jdoerfert, kerbowa, 
kbarton, jvesely, nemanjai.
Herald added a project: All.
skc7 requested review of this revision.
Herald added a reviewer: jdoerfert.
Herald added subscribers: llvm-commits, cfe-commits, sstefan1.
Herald added projects: clang, LLVM.

Change https://reviews.llvm.org/D105169 enables noundef attribute by default. 
This is causing issue with functions tagged with convergent attribute.

For Ex: SimplifyCFG pass removes the branch leading to a BB which has an 
incoming value that will always trigger undefined behavior. This basically 
modifies the CFG and combines the basic blocks. This works for CPU execution. 
But on a GPU, there are intrinsics like "__shfl_sync(unsigned mask, T var, int 
srcLane, int width=warpSize)", Where the exchange of variable occurs 
simultaneously for all active threads within the warp. So, here in the cuda/hip 
kernel, variable var in shuffl_sync may not be initialised, and LLVM IR treats 
it as undef. Currently all the arguments are tagged with noundef attribute and 
the above mentioned optimization by SimplifyCFG gets applied and the kernel 
execution becomes ambiguous. So, the proposed change is to skip adding noundef 
attribute to arguments when a function has been tagged with convergent 
attribute.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D124158

Files:
  clang/lib/CodeGen/CGCall.cpp
  clang/test/CodeGen/PowerPC/ppc64le-varargs-f128.c
  clang/test/CodeGenCUDA/address-spaces.cu
  clang/test/CodeGenCUDA/builtins-amdgcn.cu
  clang/test/CodeGenCUDA/cuda-builtin-vars.cu
  clang/test/CodeGenCUDA/kernel-args-alignment.cu
  clang/test/CodeGenCUDA/kernel-args.cu
  clang/test/CodeGenCUDA/redux-builtins.cu
  clang/test/CodeGenCUDA/usual-deallocators.cu
  clang/test/CodeGenCUDA/vtbl.cu
  clang/test/CodeGenCUDASPIRV/kernel-argument.cu
  clang/test/CodeGenOpenCL/addr-space-struct-arg.cl
  clang/test/CodeGenOpenCL/address-spaces.cl
  clang/test/CodeGenOpenCL/amdgcn-automatic-variable.cl
  clang/test/CodeGenOpenCL/amdgpu-abi-struct-coerce.cl
  clang/test/CodeGenOpenCL/amdgpu-call-kernel.cl
  clang/test/CodeGenOpenCL/amdgpu-printf.cl
  clang/test/CodeGenOpenCL/as_type.cl
  clang/test/CodeGenOpenCL/atomic-ops-libcall.cl
  clang/test/CodeGenOpenCL/blocks.cl
  clang/test/CodeGenOpenCL/byval.cl
  clang/test/CodeGenOpenCL/const-str-array-decay.cl
  clang/test/CodeGenOpenCL/constant-addr-space-globals.cl
  clang/test/CodeGenOpenCL/convergent.cl
  clang/test/CodeGenOpenCL/fpmath.cl
  clang/test/CodeGenOpenCL/half.cl
  clang/test/CodeGenOpenCL/kernel-param-alignment.cl
  clang/test/CodeGenOpenCL/kernels-have-spir-cc-by-default.cl
  clang/test/CodeGenOpenCL/no-half.cl
  clang/test/CodeGenOpenCL/overload.cl
  clang/test/CodeGenOpenCL/size_t.cl
  clang/test/CodeGenOpenCL/spir-calling-conv.cl
  clang/test/CodeGenOpenCLCXX/address-space-deduction.clcpp
  clang/test/CodeGenOpenCLCXX/addrspace-of-this.clcpp
  clang/test/CodeGenOpenCLCXX/addrspace-operators.clcpp
  clang/test/CodeGenOpenCLCXX/addrspace-references.clcpp
  clang/test/CodeGenOpenCLCXX/addrspace-with-class.clcpp
  clang/test/CodeGenSYCL/address-space-conversions.cpp
  clang/test/CodeGenSYCL/address-space-mangling.cpp
  clang/test/CodeGenSYCL/functionptr-addrspace.cpp
  clang/test/CodeGenSYCL/unique_stable_name.cpp
  clang/test/OpenMP/amdgcn-attributes.cpp
  clang/test/OpenMP/amdgcn_target_global_constructor.cpp
  clang/test/OpenMP/assumes_include_nvptx.cpp
  clang/test/OpenMP/declare_target_codegen.cpp
  clang/test/OpenMP/declare_target_codegen_globalization.cpp
  clang/test/OpenMP/declare_target_link_codegen.cpp
  clang/test/OpenMP/declare_variant_mixed_codegen.c
  clang/test/OpenMP/distribute_codegen.cpp
  clang/test/OpenMP/distribute_simd_codegen.cpp
  clang/test/OpenMP/nvptx_allocate_codegen.cpp
  clang/test/OpenMP/nvptx_data_sharing.cpp
  clang/test/OpenMP/nvptx_declare_target_var_ctor_dtor_codegen.cpp
  clang/test/OpenMP/nvptx_distribute_parallel_generic_mode_codegen.cpp
  clang/test/OpenMP/nvptx_multi_target_parallel_codegen.cpp
  clang/test/OpenMP/nvptx_nested_parallel_codegen.cpp
  clang/test/OpenMP/nvptx_parallel_codegen.cpp
  clang/test/OpenMP/nvptx_parallel_for_codegen.cpp
  clang/test/OpenMP/nvptx_target_firstprivate_codegen.cpp
  clang/test/OpenMP/nvptx_target_parallel_codegen.cpp
  clang/test/OpenMP/nvptx_target_parallel_num_threads_codegen.cpp
  clang/test/OpenMP/nvptx_target_parallel_reduction_codegen.cpp
  clang/test/OpenMP/nvptx_target_printf_codegen.c
  clang/test/OpenMP/nvptx_target_teams_codegen.cpp
  clang/test/OpenMP/nvptx_target_teams_distribute_codegen.cpp
  clang/test/OpenMP/nvptx_target_teams_distribute_parallel_for_codegen.cpp
  
clang/test/OpenMP/nvptx_target_teams_distribute_parallel_for_generic_mode_codegen.cpp
  clang/test/OpenMP/nvptx_target_teams_distribute_parallel_for_simd_codegen.cpp
  clang/test/OpenMP/nvptx_teams_codegen.cpp
  clang

[PATCH] D114533: LLVM IR should allow bitcast between address spaces with the same size.

[krishna chaitanya sankisa via Phabricator via cfe-commits]

skc7 updated this revision to Diff 406351.
skc7 added a comment.

Rebase


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D114533/new/

https://reviews.llvm.org/D114533

Files:
  clang/lib/CodeGen/CGAtomic.cpp
  llvm/docs/LangRef.rst
  llvm/include/llvm/Analysis/InstSimplifyFolder.h
  llvm/include/llvm/Analysis/TargetFolder.h
  llvm/include/llvm/IR/ConstantFolder.h
  llvm/include/llvm/IR/Constants.h
  llvm/include/llvm/IR/IRBuilder.h
  llvm/include/llvm/IR/IRBuilderFolder.h
  llvm/include/llvm/IR/InstrTypes.h
  llvm/include/llvm/IR/Instructions.h
  llvm/include/llvm/IR/NoFolder.h
  llvm/lib/Analysis/ConstantFolding.cpp
  llvm/lib/Analysis/LoopUnrollAnalyzer.cpp
  llvm/lib/AsmParser/LLParser.cpp
  llvm/lib/IR/AutoUpgrade.cpp
  llvm/lib/IR/Constants.cpp
  llvm/lib/IR/Instructions.cpp
  llvm/lib/IR/Verifier.cpp
  llvm/lib/Transforms/Coroutines/Coroutines.cpp
  llvm/lib/Transforms/Utils/VNCoercion.cpp
  llvm/test/Transforms/GVN/gvn-eliminate-inttoptr-ptrtoint-for-load.ll
  llvm/test/Transforms/GVN/gvn-eliminate-inttoptr-ptrtoint-for-vector-load.ll
  
llvm/test/Transforms/GVN/gvn-eliminate-inttoptr-ptrtoint-for-vector-ptr-load.ll
  llvm/test/Verifier/bitcast-vector-pointer-as-neg.ll
  llvm/test/Verifier/bitcast-vector-pointer-different-addrspace-illegal.ll
  llvm/test/Verifier/bitcast-vector-pointer-neg.ll
  llvm/test/Verifier/bitcast-vector-pointer-pos.ll
  llvm/test/Verifier/bitcast-vector-pointer-same-addrspace.ll
  llvm/unittests/IR/InstructionsTest.cpp

Index: llvm/unittests/IR/InstructionsTest.cpp
===
--- llvm/unittests/IR/InstructionsTest.cpp
+++ llvm/unittests/IR/InstructionsTest.cpp
@@ -189,6 +189,10 @@
 TEST(InstructionsTest, CastInst) {
   LLVMContext C;
 
+  DataLayout DL("e-p:64:64-p1:64:64-p2:32:32-p3:32:32-p4:64:64-p5:32:32-"
+"p6:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-"
+"v256:256-v512:512-v1024:1024-v2048:2048-n32:64-S32-A5-ni:7");
+
   Type *Int8Ty = Type::getInt8Ty(C);
   Type *Int16Ty = Type::getInt16Ty(C);
   Type *Int32Ty = Type::getInt32Ty(C);
@@ -217,7 +221,11 @@
   Type *Int32PtrAS1Ty = PointerType::get(Int32Ty, 1);
   Type *Int64PtrAS1Ty = PointerType::get(Int64Ty, 1);
 
+  Type *Int32PtrAS2Ty = PointerType::get(Int32Ty, 2);
+  Type *Int32PtrAS3Ty = PointerType::get(Int32Ty, 3);
+
   Type *V2Int32PtrAS1Ty = FixedVectorType::get(Int32PtrAS1Ty, 2);
+  Type *V2Int32PtrAS2Ty = FixedVectorType::get(Int32PtrAS2Ty, 2);
   Type *V2Int64PtrAS1Ty = FixedVectorType::get(Int64PtrAS1Ty, 2);
   Type *V4Int32PtrAS1Ty = FixedVectorType::get(Int32PtrAS1Ty, 4);
   Type *VScaleV4Int32PtrAS1Ty = ScalableVectorType::get(Int32PtrAS1Ty, 4);
@@ -238,50 +246,52 @@
   EXPECT_EQ(CastInst::Trunc, CastInst::getCastOpcode(c64, true, V8x8Ty, true));
   EXPECT_EQ(CastInst::SExt, CastInst::getCastOpcode(c8, true, V8x64Ty, true));
 
-  EXPECT_FALSE(CastInst::isBitCastable(V8x8Ty, X86MMXTy));
-  EXPECT_FALSE(CastInst::isBitCastable(X86MMXTy, V8x8Ty));
-  EXPECT_FALSE(CastInst::isBitCastable(Int64Ty, X86MMXTy));
-  EXPECT_FALSE(CastInst::isBitCastable(V8x64Ty, V8x8Ty));
-  EXPECT_FALSE(CastInst::isBitCastable(V8x8Ty, V8x64Ty));
-
-  // Check address space casts are rejected since we don't know the sizes here
-  EXPECT_FALSE(CastInst::isBitCastable(Int32PtrTy, Int32PtrAS1Ty));
-  EXPECT_FALSE(CastInst::isBitCastable(Int32PtrAS1Ty, Int32PtrTy));
-  EXPECT_FALSE(CastInst::isBitCastable(V2Int32PtrTy, V2Int32PtrAS1Ty));
-  EXPECT_FALSE(CastInst::isBitCastable(V2Int32PtrAS1Ty, V2Int32PtrTy));
-  EXPECT_TRUE(CastInst::isBitCastable(V2Int32PtrAS1Ty, V2Int64PtrAS1Ty));
+  EXPECT_FALSE(CastInst::isBitCastable(V8x8Ty, X86MMXTy, DL));
+  EXPECT_FALSE(CastInst::isBitCastable(X86MMXTy, V8x8Ty, DL));
+  EXPECT_FALSE(CastInst::isBitCastable(Int64Ty, X86MMXTy, DL));
+  EXPECT_FALSE(CastInst::isBitCastable(V8x64Ty, V8x8Ty, DL));
+  EXPECT_FALSE(CastInst::isBitCastable(V8x8Ty, V8x64Ty, DL));
+
+  // Check validity of casts here
+  EXPECT_TRUE(CastInst::isBitCastable(Int32PtrAS2Ty, Int32PtrAS3Ty, DL));
+  EXPECT_FALSE(CastInst::isBitCastable(Int32PtrAS1Ty, Int32PtrAS2Ty, DL));
+  EXPECT_TRUE(CastInst::isBitCastable(Int32PtrTy, Int32PtrAS1Ty, DL));
+  EXPECT_TRUE(CastInst::isBitCastable(Int32PtrAS1Ty, Int32PtrTy, DL));
+  EXPECT_TRUE(CastInst::isBitCastable(V2Int32PtrTy, V2Int32PtrAS1Ty, DL));
+  EXPECT_TRUE(CastInst::isBitCastable(V2Int32PtrAS1Ty, V2Int32PtrTy, DL));
+  EXPECT_TRUE(CastInst::isBitCastable(V2Int32PtrAS1Ty, V2Int64PtrAS1Ty, DL));
+  EXPECT_FALSE(CastInst::isBitCastable(V2Int32PtrAS1Ty, V2Int32PtrAS2Ty, DL));
   EXPECT_EQ(CastInst::AddrSpaceCast, CastInst::getCastOpcode(v2ptr32, true,
  V2Int32PtrAS1Ty,
  true));
 
   // Test mismatched number of elements for pointers
-  EXPECT_FALSE(CastInst::isBitCastable(V2Int32PtrAS1Ty, V4Int64PtrAS1Ty));
-  EXPECT_FALSE(CastInst::isBitCastable(V4Int64P

[PATCH] D124496: [Clang][Attr] clanf-format update

[krishna chaitanya sankisa via Phabricator via cfe-commits]

skc7 created this revision.
Herald added a project: All.
skc7 requested review of this revision.
Herald added a project: clang.
Herald added a subscriber: cfe-commits.

Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D124496

Files:
  clang/lib/CodeGen/CGCall.cpp


Index: clang/lib/CodeGen/CGCall.cpp
===
--- clang/lib/CodeGen/CGCall.cpp
+++ clang/lib/CodeGen/CGCall.cpp
@@ -2432,7 +2432,8 @@
 // Decide whether the argument we're handling could be partially undef
 if (CodeGenOpts.EnableNoundefAttrs &&
 DetermineNoUndef(ParamType, getTypes(), DL, AI)) {
-  if(!FuncAttrs.contains(llvm::Attribute::Convergent))
+  // Skip adding noundef attribute to arguments when function has 
convergent attribute.
+  if (!FuncAttrs.contains(llvm::Attribute::Convergent))
 Attrs.addAttribute(llvm::Attribute::NoUndef);
 }
 


Index: clang/lib/CodeGen/CGCall.cpp
===
--- clang/lib/CodeGen/CGCall.cpp
+++ clang/lib/CodeGen/CGCall.cpp
@@ -2432,7 +2432,8 @@
 // Decide whether the argument we're handling could be partially undef
 if (CodeGenOpts.EnableNoundefAttrs &&
 DetermineNoUndef(ParamType, getTypes(), DL, AI)) {
-  if(!FuncAttrs.contains(llvm::Attribute::Convergent))
+  // Skip adding noundef attribute to arguments when function has convergent attribute.
+  if (!FuncAttrs.contains(llvm::Attribute::Convergent))
 Attrs.addAttribute(llvm::Attribute::NoUndef);
 }
 
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D124158: [Clang][Attr] Skip adding noundef attribute to arguments when function has convergent attribute

[krishna chaitanya sankisa via Phabricator via cfe-commits]

skc7 updated this revision to Diff 425393.
skc7 added a comment.

clang-format to CGCall.cpp. Added comment for the change


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D124158/new/

https://reviews.llvm.org/D124158

Files:
  clang/lib/CodeGen/CGCall.cpp


Index: clang/lib/CodeGen/CGCall.cpp
===
--- clang/lib/CodeGen/CGCall.cpp
+++ clang/lib/CodeGen/CGCall.cpp
@@ -2432,7 +2432,8 @@
 // Decide whether the argument we're handling could be partially undef
 if (CodeGenOpts.EnableNoundefAttrs &&
 DetermineNoUndef(ParamType, getTypes(), DL, AI)) {
-  if(!FuncAttrs.contains(llvm::Attribute::Convergent))
+  // Skip adding noundef attribute to arguments when function has 
convergent attribute.
+  if (!FuncAttrs.contains(llvm::Attribute::Convergent))
 Attrs.addAttribute(llvm::Attribute::NoUndef);
 }
 


Index: clang/lib/CodeGen/CGCall.cpp
===
--- clang/lib/CodeGen/CGCall.cpp
+++ clang/lib/CodeGen/CGCall.cpp
@@ -2432,7 +2432,8 @@
 // Decide whether the argument we're handling could be partially undef
 if (CodeGenOpts.EnableNoundefAttrs &&
 DetermineNoUndef(ParamType, getTypes(), DL, AI)) {
-  if(!FuncAttrs.contains(llvm::Attribute::Convergent))
+  // Skip adding noundef attribute to arguments when function has convergent attribute.
+  if (!FuncAttrs.contains(llvm::Attribute::Convergent))
 Attrs.addAttribute(llvm::Attribute::NoUndef);
 }
 
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D124158: [Clang][Attr] Skip adding noundef attribute to arguments when function has convergent attribute

[krishna chaitanya sankisa via Phabricator via cfe-commits]

skc7 updated this revision to Diff 425394.
skc7 added a comment.

update


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D124158/new/

https://reviews.llvm.org/D124158

Files:
  clang/lib/CodeGen/CGCall.cpp
  clang/test/CodeGen/PowerPC/ppc64le-varargs-f128.c
  clang/test/CodeGenCUDA/address-spaces.cu
  clang/test/CodeGenCUDA/builtins-amdgcn.cu
  clang/test/CodeGenCUDA/cuda-builtin-vars.cu
  clang/test/CodeGenCUDA/kernel-args-alignment.cu
  clang/test/CodeGenCUDA/kernel-args.cu
  clang/test/CodeGenCUDA/redux-builtins.cu
  clang/test/CodeGenCUDA/usual-deallocators.cu
  clang/test/CodeGenCUDA/vtbl.cu
  clang/test/CodeGenCUDASPIRV/kernel-argument.cu
  clang/test/CodeGenOpenCL/addr-space-struct-arg.cl
  clang/test/CodeGenOpenCL/address-spaces.cl
  clang/test/CodeGenOpenCL/amdgcn-automatic-variable.cl
  clang/test/CodeGenOpenCL/amdgpu-abi-struct-coerce.cl
  clang/test/CodeGenOpenCL/amdgpu-call-kernel.cl
  clang/test/CodeGenOpenCL/amdgpu-printf.cl
  clang/test/CodeGenOpenCL/as_type.cl
  clang/test/CodeGenOpenCL/atomic-ops-libcall.cl
  clang/test/CodeGenOpenCL/blocks.cl
  clang/test/CodeGenOpenCL/byval.cl
  clang/test/CodeGenOpenCL/const-str-array-decay.cl
  clang/test/CodeGenOpenCL/constant-addr-space-globals.cl
  clang/test/CodeGenOpenCL/convergent.cl
  clang/test/CodeGenOpenCL/fpmath.cl
  clang/test/CodeGenOpenCL/half.cl
  clang/test/CodeGenOpenCL/kernel-param-alignment.cl
  clang/test/CodeGenOpenCL/kernels-have-spir-cc-by-default.cl
  clang/test/CodeGenOpenCL/no-half.cl
  clang/test/CodeGenOpenCL/overload.cl
  clang/test/CodeGenOpenCL/size_t.cl
  clang/test/CodeGenOpenCL/spir-calling-conv.cl
  clang/test/CodeGenOpenCLCXX/address-space-deduction.clcpp
  clang/test/CodeGenOpenCLCXX/addrspace-of-this.clcpp
  clang/test/CodeGenOpenCLCXX/addrspace-operators.clcpp
  clang/test/CodeGenOpenCLCXX/addrspace-references.clcpp
  clang/test/CodeGenOpenCLCXX/addrspace-with-class.clcpp
  clang/test/CodeGenSYCL/address-space-conversions.cpp
  clang/test/CodeGenSYCL/address-space-mangling.cpp
  clang/test/CodeGenSYCL/functionptr-addrspace.cpp
  clang/test/CodeGenSYCL/unique_stable_name.cpp
  clang/test/OpenMP/amdgcn-attributes.cpp
  clang/test/OpenMP/amdgcn_target_global_constructor.cpp
  clang/test/OpenMP/assumes_include_nvptx.cpp
  clang/test/OpenMP/declare_target_codegen.cpp
  clang/test/OpenMP/declare_target_codegen_globalization.cpp
  clang/test/OpenMP/declare_target_link_codegen.cpp
  clang/test/OpenMP/declare_variant_mixed_codegen.c
  clang/test/OpenMP/distribute_codegen.cpp
  clang/test/OpenMP/distribute_simd_codegen.cpp
  clang/test/OpenMP/nvptx_allocate_codegen.cpp
  clang/test/OpenMP/nvptx_data_sharing.cpp
  clang/test/OpenMP/nvptx_declare_target_var_ctor_dtor_codegen.cpp
  clang/test/OpenMP/nvptx_distribute_parallel_generic_mode_codegen.cpp
  clang/test/OpenMP/nvptx_multi_target_parallel_codegen.cpp
  clang/test/OpenMP/nvptx_nested_parallel_codegen.cpp
  clang/test/OpenMP/nvptx_parallel_codegen.cpp
  clang/test/OpenMP/nvptx_parallel_for_codegen.cpp
  clang/test/OpenMP/nvptx_target_firstprivate_codegen.cpp
  clang/test/OpenMP/nvptx_target_parallel_codegen.cpp
  clang/test/OpenMP/nvptx_target_parallel_num_threads_codegen.cpp
  clang/test/OpenMP/nvptx_target_parallel_reduction_codegen.cpp
  clang/test/OpenMP/nvptx_target_printf_codegen.c
  clang/test/OpenMP/nvptx_target_teams_codegen.cpp
  clang/test/OpenMP/nvptx_target_teams_distribute_codegen.cpp
  clang/test/OpenMP/nvptx_target_teams_distribute_parallel_for_codegen.cpp
  
clang/test/OpenMP/nvptx_target_teams_distribute_parallel_for_generic_mode_codegen.cpp
  clang/test/OpenMP/nvptx_target_teams_distribute_parallel_for_simd_codegen.cpp
  clang/test/OpenMP/nvptx_teams_codegen.cpp
  clang/test/OpenMP/nvptx_teams_reduction_codegen.cpp
  clang/test/OpenMP/nvptx_unsupported_type_codegen.cpp
  clang/test/OpenMP/openmp_offload_codegen.cpp
  clang/test/OpenMP/reduction_implicit_map.cpp
  clang/test/OpenMP/target_firstprivate_codegen.cpp
  clang/test/OpenMP/target_parallel_codegen.cpp
  clang/test/OpenMP/target_parallel_debug_codegen.cpp
  clang/test/OpenMP/target_parallel_for_codegen.cpp
  clang/test/OpenMP/target_parallel_for_debug_codegen.cpp
  clang/test/OpenMP/target_parallel_for_simd_codegen.cpp
  clang/test/OpenMP/target_parallel_if_codegen.cpp
  clang/test/OpenMP/target_parallel_num_threads_codegen.cpp
  clang/test/OpenMP/target_private_codegen.cpp
  clang/test/OpenMP/target_reduction_codegen.cpp
  clang/test/OpenMP/target_teams_codegen.cpp
  clang/test/OpenMP/target_teams_distribute_codegen.cpp
  clang/test/OpenMP/target_teams_distribute_parallel_for_codegen.cpp
  
clang/test/OpenMP/target_teams_distribute_parallel_for_firstprivate_codegen.cpp
  clang/test/OpenMP/target_teams_distribute_parallel_for_private_codegen.cpp
  clang/test/OpenMP/target_teams_distribute_parallel_for_simd_codegen.cpp
  
clang/test/OpenMP/target_teams_distribute_parallel_for_simd_firstprivate_codegen.cpp
  
clang/test/OpenMP/target_teams_distribute

[PATCH] D124158: [Clang][Attr] Skip adding noundef attribute to arguments when function has convergent attribute

[krishna chaitanya sankisa via Phabricator via cfe-commits]

skc7 added inline comments.



Comment at: clang/lib/CodeGen/CGCall.cpp:2435
 DetermineNoUndef(ParamType, getTypes(), DL, AI)) {
-  Attrs.addAttribute(llvm::Attribute::NoUndef);
+  if(!FuncAttrs.contains(llvm::Attribute::Convergent))
+Attrs.addAttribute(llvm::Attribute::NoUndef);

arsenm wrote:
> Missing space before (.
>  
> Needs comment explaining this
Updated



Comment at: 
llvm/test/Transforms/SimplifyCFG/tautological-conditional-branch-convergent-noundef.ll:26
+  %i3 = phi double [%i2, %bb2], [undef, %bb1] 
+  %i4 = call noundef double @two(double %i3, i1 %i1) 
+  ret void

arsenm wrote:
> Aren't the cases with defined handling of undef lanes still defined for the 
> result?
ret double %i4? 


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D124158/new/

https://reviews.llvm.org/D124158

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D124158: [Clang][Attr] Skip adding noundef attribute to arguments when function has convergent attribute

[krishna chaitanya sankisa via Phabricator via cfe-commits]

skc7 updated this revision to Diff 425442.
skc7 added a comment.

fix failing tests


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D124158/new/

https://reviews.llvm.org/D124158

Files:
  clang/lib/CodeGen/CGCall.cpp
  clang/test/CodeGen/PowerPC/ppc64le-varargs-f128.c
  clang/test/CodeGenCUDA/address-spaces.cu
  clang/test/CodeGenCUDA/builtins-amdgcn.cu
  clang/test/CodeGenCUDA/cuda-builtin-vars.cu
  clang/test/CodeGenCUDA/kernel-args-alignment.cu
  clang/test/CodeGenCUDA/kernel-args.cu
  clang/test/CodeGenCUDA/redux-builtins.cu
  clang/test/CodeGenCUDA/surface.cu
  clang/test/CodeGenCUDA/usual-deallocators.cu
  clang/test/CodeGenCUDA/vtbl.cu
  clang/test/CodeGenCUDASPIRV/kernel-argument.cu
  clang/test/CodeGenOpenCL/addr-space-struct-arg.cl
  clang/test/CodeGenOpenCL/address-spaces.cl
  clang/test/CodeGenOpenCL/amdgcn-automatic-variable.cl
  clang/test/CodeGenOpenCL/amdgpu-abi-struct-coerce.cl
  clang/test/CodeGenOpenCL/amdgpu-call-kernel.cl
  clang/test/CodeGenOpenCL/amdgpu-printf.cl
  clang/test/CodeGenOpenCL/as_type.cl
  clang/test/CodeGenOpenCL/atomic-ops-libcall.cl
  clang/test/CodeGenOpenCL/blocks.cl
  clang/test/CodeGenOpenCL/byval.cl
  clang/test/CodeGenOpenCL/const-str-array-decay.cl
  clang/test/CodeGenOpenCL/constant-addr-space-globals.cl
  clang/test/CodeGenOpenCL/convergent.cl
  clang/test/CodeGenOpenCL/fpmath.cl
  clang/test/CodeGenOpenCL/half.cl
  clang/test/CodeGenOpenCL/kernel-param-alignment.cl
  clang/test/CodeGenOpenCL/kernels-have-spir-cc-by-default.cl
  clang/test/CodeGenOpenCL/no-half.cl
  clang/test/CodeGenOpenCL/overload.cl
  clang/test/CodeGenOpenCL/size_t.cl
  clang/test/CodeGenOpenCL/spir-calling-conv.cl
  clang/test/CodeGenOpenCLCXX/address-space-deduction.clcpp
  clang/test/CodeGenOpenCLCXX/addrspace-of-this.clcpp
  clang/test/CodeGenOpenCLCXX/addrspace-operators.clcpp
  clang/test/CodeGenOpenCLCXX/addrspace-references.clcpp
  clang/test/CodeGenOpenCLCXX/addrspace-with-class.clcpp
  clang/test/CodeGenSYCL/address-space-conversions.cpp
  clang/test/CodeGenSYCL/address-space-mangling.cpp
  clang/test/CodeGenSYCL/functionptr-addrspace.cpp
  clang/test/CodeGenSYCL/unique_stable_name.cpp
  clang/test/OpenMP/amdgcn-attributes.cpp
  clang/test/OpenMP/amdgcn_target_global_constructor.cpp
  clang/test/OpenMP/assumes_include_nvptx.cpp
  clang/test/OpenMP/declare_target_codegen.cpp
  clang/test/OpenMP/declare_target_codegen_globalization.cpp
  clang/test/OpenMP/declare_target_link_codegen.cpp
  clang/test/OpenMP/declare_variant_mixed_codegen.c
  clang/test/OpenMP/distribute_codegen.cpp
  clang/test/OpenMP/distribute_simd_codegen.cpp
  clang/test/OpenMP/nvptx_allocate_codegen.cpp
  clang/test/OpenMP/nvptx_data_sharing.cpp
  clang/test/OpenMP/nvptx_declare_target_var_ctor_dtor_codegen.cpp
  clang/test/OpenMP/nvptx_distribute_parallel_generic_mode_codegen.cpp
  clang/test/OpenMP/nvptx_lambda_capturing.cpp
  clang/test/OpenMP/nvptx_multi_target_parallel_codegen.cpp
  clang/test/OpenMP/nvptx_nested_parallel_codegen.cpp
  clang/test/OpenMP/nvptx_parallel_codegen.cpp
  clang/test/OpenMP/nvptx_parallel_for_codegen.cpp
  clang/test/OpenMP/nvptx_target_firstprivate_codegen.cpp
  clang/test/OpenMP/nvptx_target_parallel_codegen.cpp
  clang/test/OpenMP/nvptx_target_parallel_num_threads_codegen.cpp
  clang/test/OpenMP/nvptx_target_parallel_reduction_codegen.cpp
  clang/test/OpenMP/nvptx_target_printf_codegen.c
  clang/test/OpenMP/nvptx_target_teams_codegen.cpp
  clang/test/OpenMP/nvptx_target_teams_distribute_codegen.cpp
  clang/test/OpenMP/nvptx_target_teams_distribute_parallel_for_codegen.cpp
  
clang/test/OpenMP/nvptx_target_teams_distribute_parallel_for_generic_mode_codegen.cpp
  clang/test/OpenMP/nvptx_target_teams_distribute_parallel_for_simd_codegen.cpp
  clang/test/OpenMP/nvptx_teams_codegen.cpp
  clang/test/OpenMP/nvptx_teams_reduction_codegen.cpp
  clang/test/OpenMP/nvptx_unsupported_type_codegen.cpp
  clang/test/OpenMP/openmp_offload_codegen.cpp
  clang/test/OpenMP/reduction_implicit_map.cpp
  clang/test/OpenMP/target_firstprivate_codegen.cpp
  clang/test/OpenMP/target_parallel_codegen.cpp
  clang/test/OpenMP/target_parallel_debug_codegen.cpp
  clang/test/OpenMP/target_parallel_for_codegen.cpp
  clang/test/OpenMP/target_parallel_for_debug_codegen.cpp
  clang/test/OpenMP/target_parallel_for_simd_codegen.cpp
  clang/test/OpenMP/target_parallel_if_codegen.cpp
  clang/test/OpenMP/target_parallel_num_threads_codegen.cpp
  clang/test/OpenMP/target_private_codegen.cpp
  clang/test/OpenMP/target_reduction_codegen.cpp
  clang/test/OpenMP/target_teams_codegen.cpp
  clang/test/OpenMP/target_teams_distribute_codegen.cpp
  clang/test/OpenMP/target_teams_distribute_parallel_for_codegen.cpp
  
clang/test/OpenMP/target_teams_distribute_parallel_for_firstprivate_codegen.cpp
  clang/test/OpenMP/target_teams_distribute_parallel_for_private_codegen.cpp
  clang/test/OpenMP/target_teams_distribute_parallel_for_simd_codegen.cpp
  
clang/test/OpenMP/target_teams_dist

[PATCH] D124158: [Clang][Attr] Skip adding noundef attribute to arguments when function has convergent attribute

[krishna chaitanya sankisa via Phabricator via cfe-commits]

skc7 updated this revision to Diff 425458.
skc7 added a comment.

skip adding noundef to return type


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D124158/new/

https://reviews.llvm.org/D124158

Files:
  clang/lib/CodeGen/CGCall.cpp
  clang/test/CodeGen/PowerPC/ppc64le-varargs-f128.c
  clang/test/CodeGenCUDA/address-spaces.cu
  clang/test/CodeGenCUDA/builtins-amdgcn.cu
  clang/test/CodeGenCUDA/cuda-builtin-vars.cu
  clang/test/CodeGenCUDA/kernel-args-alignment.cu
  clang/test/CodeGenCUDA/kernel-args.cu
  clang/test/CodeGenCUDA/lambda.cu
  clang/test/CodeGenCUDA/redux-builtins.cu
  clang/test/CodeGenCUDA/surface.cu
  clang/test/CodeGenCUDA/unnamed-types.cu
  clang/test/CodeGenCUDA/usual-deallocators.cu
  clang/test/CodeGenCUDA/vtbl.cu
  clang/test/CodeGenCUDASPIRV/kernel-argument.cu
  clang/test/CodeGenHIP/hipspv-addr-spaces.cpp
  clang/test/CodeGenOpenCL/addr-space-struct-arg.cl
  clang/test/CodeGenOpenCL/address-spaces.cl
  clang/test/CodeGenOpenCL/amdgcn-automatic-variable.cl
  clang/test/CodeGenOpenCL/amdgpu-abi-struct-coerce.cl
  clang/test/CodeGenOpenCL/amdgpu-call-kernel.cl
  clang/test/CodeGenOpenCL/amdgpu-printf.cl
  clang/test/CodeGenOpenCL/as_type.cl
  clang/test/CodeGenOpenCL/atomic-ops-libcall.cl
  clang/test/CodeGenOpenCL/blocks.cl
  clang/test/CodeGenOpenCL/byval.cl
  clang/test/CodeGenOpenCL/const-str-array-decay.cl
  clang/test/CodeGenOpenCL/constant-addr-space-globals.cl
  clang/test/CodeGenOpenCL/convergent.cl
  clang/test/CodeGenOpenCL/fpmath.cl
  clang/test/CodeGenOpenCL/half.cl
  clang/test/CodeGenOpenCL/kernel-param-alignment.cl
  clang/test/CodeGenOpenCL/kernels-have-spir-cc-by-default.cl
  clang/test/CodeGenOpenCL/no-half.cl
  clang/test/CodeGenOpenCL/overload.cl
  clang/test/CodeGenOpenCL/size_t.cl
  clang/test/CodeGenOpenCL/spir-calling-conv.cl
  clang/test/CodeGenOpenCLCXX/address-space-deduction.clcpp
  clang/test/CodeGenOpenCLCXX/addrspace-derived-base.clcpp
  clang/test/CodeGenOpenCLCXX/addrspace-new-delete.clcpp
  clang/test/CodeGenOpenCLCXX/addrspace-of-this.clcpp
  clang/test/CodeGenOpenCLCXX/addrspace-operators.clcpp
  clang/test/CodeGenOpenCLCXX/addrspace-references.clcpp
  clang/test/CodeGenOpenCLCXX/addrspace-with-class.clcpp
  clang/test/CodeGenOpenCLCXX/template-address-spaces.clcpp
  clang/test/CodeGenSYCL/address-space-conversions.cpp
  clang/test/CodeGenSYCL/address-space-mangling.cpp
  clang/test/CodeGenSYCL/functionptr-addrspace.cpp
  clang/test/CodeGenSYCL/unique_stable_name.cpp
  clang/test/OpenMP/amdgcn-attributes.cpp
  clang/test/OpenMP/amdgcn_target_global_constructor.cpp
  clang/test/OpenMP/assumes_include_nvptx.cpp
  clang/test/OpenMP/declare_target_codegen.cpp
  clang/test/OpenMP/declare_target_codegen_globalization.cpp
  clang/test/OpenMP/declare_target_link_codegen.cpp
  clang/test/OpenMP/declare_variant_mixed_codegen.c
  clang/test/OpenMP/distribute_codegen.cpp
  clang/test/OpenMP/distribute_simd_codegen.cpp
  clang/test/OpenMP/nvptx_allocate_codegen.cpp
  clang/test/OpenMP/nvptx_data_sharing.cpp
  clang/test/OpenMP/nvptx_declare_target_var_ctor_dtor_codegen.cpp
  clang/test/OpenMP/nvptx_declare_variant_name_mangling.cpp
  clang/test/OpenMP/nvptx_distribute_parallel_generic_mode_codegen.cpp
  clang/test/OpenMP/nvptx_lambda_capturing.cpp
  clang/test/OpenMP/nvptx_multi_target_parallel_codegen.cpp
  clang/test/OpenMP/nvptx_nested_parallel_codegen.cpp
  clang/test/OpenMP/nvptx_parallel_codegen.cpp
  clang/test/OpenMP/nvptx_parallel_for_codegen.cpp
  clang/test/OpenMP/nvptx_target_firstprivate_codegen.cpp
  clang/test/OpenMP/nvptx_target_parallel_codegen.cpp
  clang/test/OpenMP/nvptx_target_parallel_num_threads_codegen.cpp
  clang/test/OpenMP/nvptx_target_parallel_reduction_codegen.cpp
  clang/test/OpenMP/nvptx_target_printf_codegen.c
  clang/test/OpenMP/nvptx_target_teams_codegen.cpp
  clang/test/OpenMP/nvptx_target_teams_distribute_codegen.cpp
  clang/test/OpenMP/nvptx_target_teams_distribute_parallel_for_codegen.cpp
  
clang/test/OpenMP/nvptx_target_teams_distribute_parallel_for_generic_mode_codegen.cpp
  clang/test/OpenMP/nvptx_target_teams_distribute_parallel_for_simd_codegen.cpp
  clang/test/OpenMP/nvptx_teams_codegen.cpp
  clang/test/OpenMP/nvptx_teams_reduction_codegen.cpp
  clang/test/OpenMP/nvptx_unsupported_type_codegen.cpp
  clang/test/OpenMP/openmp_offload_codegen.cpp
  clang/test/OpenMP/reduction_implicit_map.cpp
  clang/test/OpenMP/target_firstprivate_codegen.cpp
  clang/test/OpenMP/target_parallel_codegen.cpp
  clang/test/OpenMP/target_parallel_debug_codegen.cpp
  clang/test/OpenMP/target_parallel_for_codegen.cpp
  clang/test/OpenMP/target_parallel_for_debug_codegen.cpp
  clang/test/OpenMP/target_parallel_for_simd_codegen.cpp
  clang/test/OpenMP/target_parallel_if_codegen.cpp
  clang/test/OpenMP/target_parallel_num_threads_codegen.cpp
  clang/test/OpenMP/target_private_codegen.cpp
  clang/test/OpenMP/target_reduction_codegen.cpp
  clang/test/OpenMP/target_teams_codegen.cpp
  clang/test/OpenMP/

[PATCH] D124158: [Clang][Attr] Skip adding noundef attribute to arguments when function has convergent attribute

[krishna chaitanya sankisa via Phabricator via cfe-commits]

skc7 updated this revision to Diff 425463.
skc7 added a comment.

update test


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D124158/new/

https://reviews.llvm.org/D124158

Files:
  clang/lib/CodeGen/CGCall.cpp
  clang/test/CodeGen/PowerPC/ppc64le-varargs-f128.c
  clang/test/CodeGenCUDA/address-spaces.cu
  clang/test/CodeGenCUDA/builtins-amdgcn.cu
  clang/test/CodeGenCUDA/cuda-builtin-vars.cu
  clang/test/CodeGenCUDA/kernel-args-alignment.cu
  clang/test/CodeGenCUDA/kernel-args.cu
  clang/test/CodeGenCUDA/lambda.cu
  clang/test/CodeGenCUDA/redux-builtins.cu
  clang/test/CodeGenCUDA/surface.cu
  clang/test/CodeGenCUDA/unnamed-types.cu
  clang/test/CodeGenCUDA/usual-deallocators.cu
  clang/test/CodeGenCUDA/vtbl.cu
  clang/test/CodeGenCUDASPIRV/kernel-argument.cu
  clang/test/CodeGenHIP/hipspv-addr-spaces.cpp
  clang/test/CodeGenOpenCL/addr-space-struct-arg.cl
  clang/test/CodeGenOpenCL/address-spaces.cl
  clang/test/CodeGenOpenCL/amdgcn-automatic-variable.cl
  clang/test/CodeGenOpenCL/amdgpu-abi-struct-coerce.cl
  clang/test/CodeGenOpenCL/amdgpu-call-kernel.cl
  clang/test/CodeGenOpenCL/amdgpu-printf.cl
  clang/test/CodeGenOpenCL/as_type.cl
  clang/test/CodeGenOpenCL/atomic-ops-libcall.cl
  clang/test/CodeGenOpenCL/blocks.cl
  clang/test/CodeGenOpenCL/byval.cl
  clang/test/CodeGenOpenCL/const-str-array-decay.cl
  clang/test/CodeGenOpenCL/constant-addr-space-globals.cl
  clang/test/CodeGenOpenCL/convergent.cl
  clang/test/CodeGenOpenCL/fpmath.cl
  clang/test/CodeGenOpenCL/half.cl
  clang/test/CodeGenOpenCL/kernel-param-alignment.cl
  clang/test/CodeGenOpenCL/kernels-have-spir-cc-by-default.cl
  clang/test/CodeGenOpenCL/no-half.cl
  clang/test/CodeGenOpenCL/overload.cl
  clang/test/CodeGenOpenCL/size_t.cl
  clang/test/CodeGenOpenCL/spir-calling-conv.cl
  clang/test/CodeGenOpenCLCXX/address-space-deduction.clcpp
  clang/test/CodeGenOpenCLCXX/addrspace-derived-base.clcpp
  clang/test/CodeGenOpenCLCXX/addrspace-new-delete.clcpp
  clang/test/CodeGenOpenCLCXX/addrspace-of-this.clcpp
  clang/test/CodeGenOpenCLCXX/addrspace-operators.clcpp
  clang/test/CodeGenOpenCLCXX/addrspace-references.clcpp
  clang/test/CodeGenOpenCLCXX/addrspace-with-class.clcpp
  clang/test/CodeGenOpenCLCXX/template-address-spaces.clcpp
  clang/test/CodeGenSYCL/address-space-conversions.cpp
  clang/test/CodeGenSYCL/address-space-mangling.cpp
  clang/test/CodeGenSYCL/functionptr-addrspace.cpp
  clang/test/CodeGenSYCL/unique_stable_name.cpp
  clang/test/OpenMP/amdgcn-attributes.cpp
  clang/test/OpenMP/amdgcn_target_global_constructor.cpp
  clang/test/OpenMP/assumes_include_nvptx.cpp
  clang/test/OpenMP/declare_target_codegen.cpp
  clang/test/OpenMP/declare_target_codegen_globalization.cpp
  clang/test/OpenMP/declare_target_link_codegen.cpp
  clang/test/OpenMP/declare_variant_mixed_codegen.c
  clang/test/OpenMP/distribute_codegen.cpp
  clang/test/OpenMP/distribute_simd_codegen.cpp
  clang/test/OpenMP/nvptx_allocate_codegen.cpp
  clang/test/OpenMP/nvptx_data_sharing.cpp
  clang/test/OpenMP/nvptx_declare_target_var_ctor_dtor_codegen.cpp
  clang/test/OpenMP/nvptx_declare_variant_name_mangling.cpp
  clang/test/OpenMP/nvptx_distribute_parallel_generic_mode_codegen.cpp
  clang/test/OpenMP/nvptx_lambda_capturing.cpp
  clang/test/OpenMP/nvptx_multi_target_parallel_codegen.cpp
  clang/test/OpenMP/nvptx_nested_parallel_codegen.cpp
  clang/test/OpenMP/nvptx_parallel_codegen.cpp
  clang/test/OpenMP/nvptx_parallel_for_codegen.cpp
  clang/test/OpenMP/nvptx_target_firstprivate_codegen.cpp
  clang/test/OpenMP/nvptx_target_parallel_codegen.cpp
  clang/test/OpenMP/nvptx_target_parallel_num_threads_codegen.cpp
  clang/test/OpenMP/nvptx_target_parallel_reduction_codegen.cpp
  clang/test/OpenMP/nvptx_target_printf_codegen.c
  clang/test/OpenMP/nvptx_target_teams_codegen.cpp
  clang/test/OpenMP/nvptx_target_teams_distribute_codegen.cpp
  clang/test/OpenMP/nvptx_target_teams_distribute_parallel_for_codegen.cpp
  
clang/test/OpenMP/nvptx_target_teams_distribute_parallel_for_generic_mode_codegen.cpp
  clang/test/OpenMP/nvptx_target_teams_distribute_parallel_for_simd_codegen.cpp
  clang/test/OpenMP/nvptx_teams_codegen.cpp
  clang/test/OpenMP/nvptx_teams_reduction_codegen.cpp
  clang/test/OpenMP/nvptx_unsupported_type_codegen.cpp
  clang/test/OpenMP/openmp_offload_codegen.cpp
  clang/test/OpenMP/reduction_implicit_map.cpp
  clang/test/OpenMP/target_firstprivate_codegen.cpp
  clang/test/OpenMP/target_parallel_codegen.cpp
  clang/test/OpenMP/target_parallel_debug_codegen.cpp
  clang/test/OpenMP/target_parallel_for_codegen.cpp
  clang/test/OpenMP/target_parallel_for_debug_codegen.cpp
  clang/test/OpenMP/target_parallel_for_simd_codegen.cpp
  clang/test/OpenMP/target_parallel_if_codegen.cpp
  clang/test/OpenMP/target_parallel_num_threads_codegen.cpp
  clang/test/OpenMP/target_private_codegen.cpp
  clang/test/OpenMP/target_reduction_codegen.cpp
  clang/test/OpenMP/target_teams_codegen.cpp
  clang/test/OpenMP/target_teams_distribute

[PATCH] D124158: [Clang][Attr] Skip adding noundef attribute to arguments when function has convergent attribute

[krishna chaitanya sankisa via Phabricator via cfe-commits]

skc7 added inline comments.



Comment at: 
llvm/test/Transforms/SimplifyCFG/tautological-conditional-branch-convergent-noundef.ll:26
+  %i3 = phi double [%i2, %bb2], [undef, %bb1] 
+  %i4 = call noundef double @two(double %i3, i1 %i1) 
+  ret void

skc7 wrote:
> arsenm wrote:
> > Aren't the cases with defined handling of undef lanes still defined for the 
> > result?
> ret double %i4? 
Updated patch to skip adding noundef attribute to return types aswell


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D124158/new/

https://reviews.llvm.org/D124158

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D124158: [Clang][Attr] Skip adding noundef attribute to arguments when function has convergent attribute

[krishna chaitanya sankisa via Phabricator via cfe-commits]

skc7 added a comment.

In D124158#3477281 , @jdoerfert wrote:

>> For Ex: SimplifyCFG pass removes the branch leading to a BB which has an 
>> incoming value that will always trigger undefined behavior. This basically 
>> modifies the CFG and combines the basic blocks. This works for CPU 
>> execution. But on a GPU, there are intrinsics like "__shfl_sync(unsigned 
>> mask, T var, int srcLane, int width=warpSize)", Where the exchange of 
>> variable occurs simultaneously for all active threads within the warp. So, 
>> here in the cuda/hip kernel, variable var in shuffl_sync may not be 
>> initialised, and LLVM IR treats it as undef. Currently all the arguments are 
>> tagged with noundef attribute and the above mentioned optimization by 
>> SimplifyCFG gets applied and the kernel execution becomes ambiguous. So, the 
>> proposed change is to skip adding noundef attribute to arguments when a 
>> function has been tagged with convergent attribute.
>
> Can we please have an example for this. I don't know what would be broken w/ 
> noundef + convergent and I somewhat doubt noundef is the problem.

For the below source kernel from hypre, the optimisation by simplifyCFG pass 
caused issue with kernel execution on GPU.
We figured out that enabling noudef analysis by default is triggering this 
optimization.

**source kernel:**
Note: variable t is uninitialised intially and gets initialiazed when lane is 0.
void kernel{

  double t, measure_row;
  int lane = hypre_cuda_get_lane_id<1>();

...

  if (lane == 0) {t = read_only_load(measure_diag + row);}
  measure_row = __shfl_sync(HYPRE_WARP_FULL_MASK, t, 0);

...
}

**Example LLVM IR for a similar scenario:**
define void @func(i32 noundef %arg17) {
bb1:

  %i1 = icmp eq i32 %arg17, 0
  br i1 %i1, label %bb2, label %bb3

bb2:  ; preds = %bb1

  %i2 = call noundef double @read_only_load()
  br label %bb3

bb3:  ; preds = %bb2, %bb1

  %i3 = phi double [ %i2, %bb2 ], [ undef, %bb1 ]
  %i4 = call noundef double @__shfl_sync(double noundef %i3)
  ret void

}

declare double @read_only_load()
declare double @__shfl_sync(double noundef) convergent

**IR Dump After SimplifyCFGPass on func:**
define void @func(i32 noundef %arg17) {
bb1:

  %i1 = icmp eq i32 %arg17, 0
  call void @llvm.assume(i1 %i1)
  %i2 = call noundef double @read_only_load()
  %i4 = call noundef double @__shfl_sync(double noundef %i2)
  ret void

}


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D124158/new/

https://reviews.llvm.org/D124158

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D128907: [Clang] Disable noundef attribute for languages which allow uninitialized function arguments

[krishna chaitanya sankisa via Phabricator via cfe-commits]

skc7 updated this revision to Diff 444657.
skc7 added a comment.

Rebase and fix for review comments.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D128907/new/

https://reviews.llvm.org/D128907

Files:
  clang/include/clang/Basic/LangOptions.h
  clang/lib/CodeGen/CGCall.cpp
  clang/test/CodeGen/PowerPC/ppc64le-varargs-f128.c
  clang/test/CodeGenCUDA/address-spaces.cu
  clang/test/CodeGenCUDA/builtins-amdgcn.cu
  clang/test/CodeGenCUDA/cuda-builtin-vars.cu
  clang/test/CodeGenCUDA/kernel-args-alignment.cu
  clang/test/CodeGenCUDA/kernel-args.cu
  clang/test/CodeGenCUDA/lambda.cu
  clang/test/CodeGenCUDA/redux-builtins.cu
  clang/test/CodeGenCUDA/surface.cu
  clang/test/CodeGenCUDA/unnamed-types.cu
  clang/test/CodeGenCUDA/usual-deallocators.cu
  clang/test/CodeGenCUDA/vtbl.cu
  clang/test/CodeGenCUDASPIRV/kernel-argument.cu
  clang/test/CodeGenHIP/hipspv-addr-spaces.cpp
  clang/test/CodeGenHIP/noundef-attribute-hip-device-verify.hip
  clang/test/CodeGenOpenCL/addr-space-struct-arg.cl
  clang/test/CodeGenOpenCL/address-spaces.cl
  clang/test/CodeGenOpenCL/amdgcn-automatic-variable.cl
  clang/test/CodeGenOpenCL/amdgpu-abi-struct-coerce.cl
  clang/test/CodeGenOpenCL/amdgpu-call-kernel.cl
  clang/test/CodeGenOpenCL/amdgpu-printf.cl
  clang/test/CodeGenOpenCL/as_type.cl
  clang/test/CodeGenOpenCL/atomic-ops-libcall.cl
  clang/test/CodeGenOpenCL/blocks.cl
  clang/test/CodeGenOpenCL/byval.cl
  clang/test/CodeGenOpenCL/const-str-array-decay.cl
  clang/test/CodeGenOpenCL/constant-addr-space-globals.cl
  clang/test/CodeGenOpenCL/convergent.cl
  clang/test/CodeGenOpenCL/fpmath.cl
  clang/test/CodeGenOpenCL/half.cl
  clang/test/CodeGenOpenCL/kernel-param-alignment.cl
  clang/test/CodeGenOpenCL/kernels-have-spir-cc-by-default.cl
  clang/test/CodeGenOpenCL/no-half.cl
  clang/test/CodeGenOpenCL/overload.cl
  clang/test/CodeGenOpenCL/size_t.cl
  clang/test/CodeGenOpenCL/spir-calling-conv.cl
  clang/test/CodeGenOpenCLCXX/address-space-deduction.clcpp
  clang/test/CodeGenOpenCLCXX/addrspace-derived-base.clcpp
  clang/test/CodeGenOpenCLCXX/addrspace-new-delete.clcpp
  clang/test/CodeGenOpenCLCXX/addrspace-of-this.clcpp
  clang/test/CodeGenOpenCLCXX/addrspace-operators.clcpp
  clang/test/CodeGenOpenCLCXX/addrspace-references.clcpp
  clang/test/CodeGenOpenCLCXX/addrspace-with-class.clcpp
  clang/test/CodeGenOpenCLCXX/template-address-spaces.clcpp
  clang/test/CodeGenSYCL/address-space-conversions.cpp
  clang/test/CodeGenSYCL/address-space-mangling.cpp
  clang/test/CodeGenSYCL/functionptr-addrspace.cpp
  clang/test/CodeGenSYCL/unique_stable_name.cpp
  clang/test/OpenMP/amdgcn-attributes.cpp
  clang/test/OpenMP/amdgcn_target_global_constructor.cpp
  clang/test/OpenMP/assumes_include_nvptx.cpp
  clang/test/OpenMP/declare_target_codegen.cpp
  clang/test/OpenMP/declare_target_codegen_globalization.cpp
  clang/test/OpenMP/declare_target_link_codegen.cpp
  clang/test/OpenMP/declare_variant_mixed_codegen.c
  clang/test/OpenMP/distribute_codegen.cpp
  clang/test/OpenMP/distribute_simd_codegen.cpp
  clang/test/OpenMP/nvptx_allocate_codegen.cpp
  clang/test/OpenMP/nvptx_data_sharing.cpp
  clang/test/OpenMP/nvptx_declare_target_var_ctor_dtor_codegen.cpp
  clang/test/OpenMP/nvptx_declare_variant_name_mangling.cpp
  clang/test/OpenMP/nvptx_distribute_parallel_generic_mode_codegen.cpp
  clang/test/OpenMP/nvptx_lambda_capturing.cpp
  clang/test/OpenMP/nvptx_multi_target_parallel_codegen.cpp
  clang/test/OpenMP/nvptx_nested_parallel_codegen.cpp
  clang/test/OpenMP/nvptx_parallel_codegen.cpp
  clang/test/OpenMP/nvptx_parallel_for_codegen.cpp
  clang/test/OpenMP/nvptx_target_firstprivate_codegen.cpp
  clang/test/OpenMP/nvptx_target_parallel_codegen.cpp
  clang/test/OpenMP/nvptx_target_parallel_num_threads_codegen.cpp
  clang/test/OpenMP/nvptx_target_parallel_reduction_codegen.cpp
  clang/test/OpenMP/nvptx_target_printf_codegen.c
  clang/test/OpenMP/nvptx_target_teams_codegen.cpp
  clang/test/OpenMP/nvptx_target_teams_distribute_codegen.cpp
  clang/test/OpenMP/nvptx_target_teams_distribute_parallel_for_codegen.cpp
  
clang/test/OpenMP/nvptx_target_teams_distribute_parallel_for_generic_mode_codegen.cpp
  clang/test/OpenMP/nvptx_target_teams_distribute_parallel_for_simd_codegen.cpp
  clang/test/OpenMP/nvptx_teams_codegen.cpp
  clang/test/OpenMP/nvptx_teams_reduction_codegen.cpp
  clang/test/OpenMP/nvptx_unsupported_type_codegen.cpp
  clang/test/OpenMP/openmp_offload_codegen.cpp
  clang/test/OpenMP/reduction_implicit_map.cpp
  clang/test/OpenMP/target_firstprivate_codegen.cpp
  clang/test/OpenMP/target_parallel_codegen.cpp
  clang/test/OpenMP/target_parallel_debug_codegen.cpp
  clang/test/OpenMP/target_parallel_for_codegen.cpp
  clang/test/OpenMP/target_parallel_for_debug_codegen.cpp
  clang/test/OpenMP/target_parallel_for_simd_codegen.cpp
  clang/test/OpenMP/target_parallel_if_codegen.cpp
  clang/test/OpenMP/target_parallel_num_threads_codegen.cpp
  clang/test/OpenMP/target_private_codegen.cpp
  clang

[PATCH] D130224: [Clang][Attribute] Introduce maybe_undef attribute for function arguments which accepts undef values

[krishna chaitanya sankisa via Phabricator via cfe-commits]

skc7 created this revision.
Herald added a reviewer: aaron.ballman.
Herald added a subscriber: jdoerfert.
Herald added a project: All.
skc7 requested review of this revision.
Herald added a project: clang.
Herald added a subscriber: cfe-commits.

Add the ability to put __attribute__((maybe_undef)) on function arguments. 
Clang will now remove noundef attribute and introduces a freeze instruction on 
the argument.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D130224

Files:
  clang/include/clang/Basic/Attr.td
  clang/include/clang/Basic/AttrDocs.td
  clang/lib/CodeGen/CGCall.cpp
  clang/lib/Sema/SemaDeclAttr.cpp
  clang/test/CodeGen/attr-maybeundef.c
  clang/test/CodeGenHIP/maybe_undef-attr-verify.hip
  clang/test/Misc/pragma-attribute-supported-attributes-list.test

Index: clang/test/Misc/pragma-attribute-supported-attributes-list.test
===
--- clang/test/Misc/pragma-attribute-supported-attributes-list.test
+++ clang/test/Misc/pragma-attribute-supported-attributes-list.test
@@ -83,6 +83,7 @@
 // CHECK-NEXT: Lockable (SubjectMatchRule_record)
 // CHECK-NEXT: MIGServerRoutine (SubjectMatchRule_function, SubjectMatchRule_objc_method, SubjectMatchRule_block)
 // CHECK-NEXT: MSStruct (SubjectMatchRule_record)
+// CHECK-NEXT: MayBeUndef (SubjectMatchRule_variable_is_parameter)
 // CHECK-NEXT: MicroMips (SubjectMatchRule_function)
 // CHECK-NEXT: MinSize (SubjectMatchRule_function, SubjectMatchRule_objc_method)
 // CHECK-NEXT: MinVectorWidth (SubjectMatchRule_function)
Index: clang/test/CodeGenHIP/maybe_undef-attr-verify.hip
===
--- /dev/null
+++ clang/test/CodeGenHIP/maybe_undef-attr-verify.hip
@@ -0,0 +1,33 @@
+// RUN: %clang_cc1 -no-opaque-pointers -triple amdgcn-amd-amdhsa -target-cpu gfx906 -x hip -fcuda-is-device -emit-llvm  %s \
+// RUN:   -o - | FileCheck %s
+
+#define __global__ __attribute__((global))
+#define __device__ __attribute__((device))
+#define __maybe_undef __attribute__((maybe_undef))
+#define WARP_SIZE 64
+
+static constexpr int warpSize = __AMDGCN_WAVEFRONT_SIZE;
+
+__device__ static inline unsigned int __lane_id() {
+return  __builtin_amdgcn_mbcnt_hi(
+-1, __builtin_amdgcn_mbcnt_lo(-1, 0));
+}
+
+__device__
+inline
+int __shfl_sync(int __maybe_undef var, int src_lane, int width = warpSize) {
+int self = __lane_id();
+int index = src_lane + (self & ~(width-1));
+return __builtin_amdgcn_ds_bpermute(index<<2, var);
+}
+
+// CHECK: define dso_local amdgpu_kernel void @_Z13shufflekernelv()
+// CHECK: [[TMP1:%.*]] = freeze i32 [[TMP2:%.*]]
+// CHECK: define linkonce_odr noundef i32 @_Z11__shfl_synciii(i32 %var, i32 noundef %src_lane, i32 noundef %width)
+__global__ void
+shufflekernel()
+{
+int t;
+int res;
+res = __shfl_sync(t, WARP_SIZE, 0);
+}
Index: clang/test/CodeGen/attr-maybeundef.c
===
--- /dev/null
+++ clang/test/CodeGen/attr-maybeundef.c
@@ -0,0 +1,14 @@
+// RUN: %clang_cc1 -no-opaque-pointers -emit-llvm %s -o - | FileCheck %s
+
+#define __maybe_undef __attribute__((maybe_undef))
+
+// CHECK: define dso_local void @t1(i32 noundef %param1, i32 %param2, float noundef %param3) #[[attr1:[0-9]+]]
+void t1(int param1, int __maybe_undef param2, float param3) {}
+
+// CHECK: define dso_local void @t2(i32 noundef %param1, i32 noundef %param2, float noundef %param3)
+// CHECK: [[TMP1:%.*]] = freeze i32 [[TMP2:%.*]]
+// CHECK: call void @t1(i32 noundef %0, i32 [[TMP1:%.*]], float noundef %2)
+// expected-error {{'maybe_undef' attribute only applies to parameters [-Wignored-attributes]}}
+void __maybe_undef t2(int param1, int param2, float param3) {
+t1(param1, param2, param3);
+}
Index: clang/lib/Sema/SemaDeclAttr.cpp
===
--- clang/lib/Sema/SemaDeclAttr.cpp
+++ clang/lib/Sema/SemaDeclAttr.cpp
@@ -8634,6 +8634,9 @@
   case ParsedAttr::AT_NoEscape:
 handleNoEscapeAttr(S, D, AL);
 break;
+  case ParsedAttr::AT_MayBeUndef:
+handleSimpleAttribute(S, D, AL);
+break;
   case ParsedAttr::AT_AssumeAligned:
 handleAssumeAlignedAttr(S, D, AL);
 break;
Index: clang/lib/CodeGen/CGCall.cpp
===
--- clang/lib/CodeGen/CGCall.cpp
+++ clang/lib/CodeGen/CGCall.cpp
@@ -2046,6 +2046,22 @@
   return false;
 }
 
+/// Check if the argument of a function has maybe_undef attribute.
+static bool IsArgumentMayBeUndef(const Decl *TargetDecl, unsigned ArgNo) {
+  bool ArgHasMayBeUndefAttr = false;
+  if (TargetDecl) {
+if (const FunctionDecl *FD = dyn_cast(TargetDecl)) {
+  if (FD && (ArgNo < FD->getNumParams())) {
+const ParmVarDecl *Param = FD->getParamDecl(ArgNo);
+if (Param && Param->hasAttr()) {
+  ArgHasMayBeUndefAttr = true;
+}
+  }
+}
+  }
+  return ArgHasMayBeUndefAttr;
+}
+

[PATCH] D130224: [Clang][Attribute] Introduce maybe_undef attribute for function arguments which accepts undef values

[krishna chaitanya sankisa via Phabricator via cfe-commits]

skc7 updated this revision to Diff 446727.
skc7 edited the summary of this revision.
skc7 added a comment.

Rebase. Remove skipping noundef attribute based on maybe_undef.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D130224/new/

https://reviews.llvm.org/D130224

Files:
  clang/include/clang/Basic/Attr.td
  clang/include/clang/Basic/AttrDocs.td
  clang/lib/CodeGen/CGCall.cpp
  clang/lib/Sema/SemaDeclAttr.cpp
  clang/test/CodeGen/attr-maybeundef.c
  clang/test/CodeGenHIP/maybe_undef-attr-verify.hip
  clang/test/Misc/pragma-attribute-supported-attributes-list.test

Index: clang/test/Misc/pragma-attribute-supported-attributes-list.test
===
--- clang/test/Misc/pragma-attribute-supported-attributes-list.test
+++ clang/test/Misc/pragma-attribute-supported-attributes-list.test
@@ -83,6 +83,7 @@
 // CHECK-NEXT: Lockable (SubjectMatchRule_record)
 // CHECK-NEXT: MIGServerRoutine (SubjectMatchRule_function, SubjectMatchRule_objc_method, SubjectMatchRule_block)
 // CHECK-NEXT: MSStruct (SubjectMatchRule_record)
+// CHECK-NEXT: MayBeUndef (SubjectMatchRule_variable_is_parameter)
 // CHECK-NEXT: MicroMips (SubjectMatchRule_function)
 // CHECK-NEXT: MinSize (SubjectMatchRule_function, SubjectMatchRule_objc_method)
 // CHECK-NEXT: MinVectorWidth (SubjectMatchRule_function)
Index: clang/test/CodeGenHIP/maybe_undef-attr-verify.hip
===
--- /dev/null
+++ clang/test/CodeGenHIP/maybe_undef-attr-verify.hip
@@ -0,0 +1,33 @@
+// RUN: %clang_cc1 -no-opaque-pointers -triple amdgcn-amd-amdhsa -target-cpu gfx906 -x hip -fcuda-is-device -emit-llvm  %s \
+// RUN:   -o - | FileCheck %s
+
+#define __global__ __attribute__((global))
+#define __device__ __attribute__((device))
+#define __maybe_undef __attribute__((maybe_undef))
+#define WARP_SIZE 64
+
+static constexpr int warpSize = __AMDGCN_WAVEFRONT_SIZE;
+
+__device__ static inline unsigned int __lane_id() {
+return  __builtin_amdgcn_mbcnt_hi(
+-1, __builtin_amdgcn_mbcnt_lo(-1, 0));
+}
+
+__device__
+inline
+int __shfl_sync(int __maybe_undef var, int src_lane, int width = warpSize) {
+int self = __lane_id();
+int index = src_lane + (self & ~(width-1));
+return __builtin_amdgcn_ds_bpermute(index<<2, var);
+}
+
+// CHECK: define dso_local amdgpu_kernel void @_Z13shufflekernelv()
+// CHECK: [[TMP1:%.*]] = freeze i32 [[TMP2:%.*]]
+// CHECK: define linkonce_odr noundef i32 @_Z11__shfl_synciii(i32 noundef %var, i32 noundef %src_lane, i32 noundef %width)
+__global__ void
+shufflekernel()
+{
+int t;
+int res;
+res = __shfl_sync(t, WARP_SIZE, 0);
+}
Index: clang/test/CodeGen/attr-maybeundef.c
===
--- /dev/null
+++ clang/test/CodeGen/attr-maybeundef.c
@@ -0,0 +1,14 @@
+// RUN: %clang_cc1 -no-opaque-pointers -emit-llvm %s -o - | FileCheck %s
+
+#define __maybe_undef __attribute__((maybe_undef))
+
+// CHECK: define dso_local void @t1(i32 noundef %param1, i32 noundef %param2, float noundef %param3) #[[attr1:[0-9]+]]
+void t1(int param1, int __maybe_undef param2, float param3) {}
+
+// CHECK: define dso_local void @t2(i32 noundef %param1, i32 noundef %param2, float noundef %param3)
+// CHECK: [[TMP1:%.*]] = freeze i32 [[TMP2:%.*]]
+// CHECK: call void @t1(i32 noundef %0, i32 noundef [[TMP1:%.*]], float noundef %2)
+// expected-error {{'maybe_undef' attribute only applies to parameters [-Wignored-attributes]}}
+void __maybe_undef t2(int param1, int param2, float param3) {
+t1(param1, param2, param3);
+}
Index: clang/lib/Sema/SemaDeclAttr.cpp
===
--- clang/lib/Sema/SemaDeclAttr.cpp
+++ clang/lib/Sema/SemaDeclAttr.cpp
@@ -8634,6 +8634,9 @@
   case ParsedAttr::AT_NoEscape:
 handleNoEscapeAttr(S, D, AL);
 break;
+  case ParsedAttr::AT_MayBeUndef:
+handleSimpleAttribute(S, D, AL);
+break;
   case ParsedAttr::AT_AssumeAligned:
 handleAssumeAlignedAttr(S, D, AL);
 break;
Index: clang/lib/CodeGen/CGCall.cpp
===
--- clang/lib/CodeGen/CGCall.cpp
+++ clang/lib/CodeGen/CGCall.cpp
@@ -2046,6 +2046,22 @@
   return false;
 }
 
+/// Check if the argument of a function has maybe_undef attribute.
+static bool IsArgumentMayBeUndef(const Decl *TargetDecl, unsigned ArgNo) {
+  bool ArgHasMayBeUndefAttr = false;
+  if (TargetDecl) {
+if (const FunctionDecl *FD = dyn_cast(TargetDecl)) {
+  if (FD && (ArgNo < FD->getNumParams())) {
+const ParmVarDecl *Param = FD->getParamDecl(ArgNo);
+if (Param && Param->hasAttr()) {
+  ArgHasMayBeUndefAttr = true;
+}
+  }
+}
+  }
+  return ArgHasMayBeUndefAttr;
+}
+
 /// Construct the IR attribute list of a function or call.
 ///
 /// When adding an attribute, please consider where it should be handled:
@@ -4816,6 +4832,8 @@
 unsigned FirstIRArg, NumI

[PATCH] D130224: [Clang][Attribute] Introduce maybe_undef attribute for function arguments which accepts undef values

[krishna chaitanya sankisa via Phabricator via cfe-commits]

skc7 updated this revision to Diff 446919.
skc7 added a comment.

Fixes as per review comments.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D130224/new/

https://reviews.llvm.org/D130224

Files:
  clang/include/clang/Basic/Attr.td
  clang/include/clang/Basic/AttrDocs.td
  clang/lib/CodeGen/CGCall.cpp
  clang/lib/Sema/SemaDeclAttr.cpp
  clang/test/CodeGen/attr-maybeundef.c
  clang/test/CodeGenHIP/maybe_undef-attr-verify.hip
  clang/test/Misc/pragma-attribute-supported-attributes-list.test

Index: clang/test/Misc/pragma-attribute-supported-attributes-list.test
===
--- clang/test/Misc/pragma-attribute-supported-attributes-list.test
+++ clang/test/Misc/pragma-attribute-supported-attributes-list.test
@@ -83,6 +83,7 @@
 // CHECK-NEXT: Lockable (SubjectMatchRule_record)
 // CHECK-NEXT: MIGServerRoutine (SubjectMatchRule_function, SubjectMatchRule_objc_method, SubjectMatchRule_block)
 // CHECK-NEXT: MSStruct (SubjectMatchRule_record)
+// CHECK-NEXT: MayBeUndef (SubjectMatchRule_variable_is_parameter)
 // CHECK-NEXT: MicroMips (SubjectMatchRule_function)
 // CHECK-NEXT: MinSize (SubjectMatchRule_function, SubjectMatchRule_objc_method)
 // CHECK-NEXT: MinVectorWidth (SubjectMatchRule_function)
Index: clang/test/CodeGenHIP/maybe_undef-attr-verify.hip
===
--- /dev/null
+++ clang/test/CodeGenHIP/maybe_undef-attr-verify.hip
@@ -0,0 +1,44 @@
+// RUN: %clang_cc1 -no-opaque-pointers -triple amdgcn-amd-amdhsa -target-cpu gfx906 -x hip -fcuda-is-device -emit-llvm  %s \
+// RUN:   -o - | FileCheck %s
+
+#define __global__ __attribute__((global))
+#define __device__ __attribute__((device))
+#define __maybe_undef __attribute__((maybe_undef))
+#define WARP_SIZE 64
+
+static constexpr int warpSize = __AMDGCN_WAVEFRONT_SIZE;
+
+__device__ static inline unsigned int __lane_id() {
+return  __builtin_amdgcn_mbcnt_hi(
+-1, __builtin_amdgcn_mbcnt_lo(-1, 0));
+}
+
+__device__
+inline
+int __shfl_sync(int __maybe_undef var, int src_lane, int width = warpSize) {
+int self = __lane_id();
+int index = src_lane + (self & ~(width-1));
+return __builtin_amdgcn_ds_bpermute(index<<2, var);
+}
+
+__global__ void
+shufflekernel()
+{
+int t;
+int res;
+res = __shfl_sync(t, WARP_SIZE, 0);
+}
+
+// CHECK: define dso_local amdgpu_kernel void @_Z13shufflekernelv()
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:[[TMP1:%.*]] = alloca i32, align 4, addrspace(5)
+// CHECK-NEXT:[[TMP2:%.*]] = alloca i32, align 4, addrspace(5)
+// CHECK-NEXT:[[TMP3:%.*]] = addrspacecast i32 addrspace(5)* [[TMP1:%.*]] to i32*
+// CHECK-NEXT:[[TMP4:%.*]] = addrspacecast i32 addrspace(5)* [[TMP2:%.*]] to i32*
+// CHECK-NEXT:[[TMP5:%.*]] = load i32, i32* [[TMP3:%.*]], align 4
+// CHECK-NEXT:[[TMP6:%.*]] = freeze i32 [[TMP5:%.*]]
+// CHECK-NEXT:%call = call noundef i32 @_Z11__shfl_synciii(i32 noundef [[TMP6:%.*]], i32 noundef 64, i32 noundef 0) #4
+// CHECK-NEXT:store i32 %call, i32* [[TMP4:%.*]], align 4
+// CHECK-NEXT:  ret void
+
+// CHECK: define linkonce_odr noundef i32 @_Z11__shfl_synciii(i32 noundef %var, i32 noundef %src_lane, i32 noundef %width)
Index: clang/test/CodeGen/attr-maybeundef.c
===
--- /dev/null
+++ clang/test/CodeGen/attr-maybeundef.c
@@ -0,0 +1,14 @@
+// RUN: %clang_cc1 -no-opaque-pointers -emit-llvm %s -o - | FileCheck %s
+
+#define __maybe_undef __attribute__((maybe_undef))
+
+// CHECK: define dso_local void @t1(i32 noundef %param1, i32 noundef %param2, float noundef %param3) #[[attr1:[0-9]+]]
+void t1(int param1, int __maybe_undef param2, float param3) {}
+
+// CHECK: define dso_local void @t2(i32 noundef %param1, i32 noundef %param2, float noundef %param3)
+// CHECK: [[TMP1:%.*]] = freeze i32 [[TMP2:%.*]]
+// CHECK: call void @t1(i32 noundef %0, i32 noundef [[TMP1:%.*]], float noundef %2)
+// expected-error {{'maybe_undef' attribute only applies to parameters [-Wignored-attributes]}}
+void __maybe_undef t2(int param1, int param2, float param3) {
+t1(param1, param2, param3);
+}
Index: clang/lib/Sema/SemaDeclAttr.cpp
===
--- clang/lib/Sema/SemaDeclAttr.cpp
+++ clang/lib/Sema/SemaDeclAttr.cpp
@@ -8634,6 +8634,9 @@
   case ParsedAttr::AT_NoEscape:
 handleNoEscapeAttr(S, D, AL);
 break;
+  case ParsedAttr::AT_MayBeUndef:
+handleSimpleAttribute(S, D, AL);
+break;
   case ParsedAttr::AT_AssumeAligned:
 handleAssumeAlignedAttr(S, D, AL);
 break;
Index: clang/lib/CodeGen/CGCall.cpp
===
--- clang/lib/CodeGen/CGCall.cpp
+++ clang/lib/CodeGen/CGCall.cpp
@@ -2046,6 +2046,25 @@
   return false;
 }
 
+/// Check if the argument of a function has maybe_undef attribute.
+static bool IsArgumentMayBeUndef(const Decl *TargetDecl, unsigned ArgNo) {
+  if (!TargetDe

[PATCH] D130224: [Clang][Attribute] Introduce maybe_undef attribute for function arguments which accepts undef values

[krishna chaitanya sankisa via Phabricator via cfe-commits]

skc7 updated this revision to Diff 447383.
skc7 edited the summary of this revision.
skc7 added a comment.

Rebase. Ping.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D130224/new/

https://reviews.llvm.org/D130224

Files:
  clang/include/clang/Basic/Attr.td
  clang/include/clang/Basic/AttrDocs.td
  clang/lib/CodeGen/CGCall.cpp
  clang/lib/Sema/SemaDeclAttr.cpp
  clang/test/CodeGen/attr-maybeundef.c
  clang/test/CodeGenHIP/maybe_undef-attr-verify.hip
  clang/test/Misc/pragma-attribute-supported-attributes-list.test

Index: clang/test/Misc/pragma-attribute-supported-attributes-list.test
===
--- clang/test/Misc/pragma-attribute-supported-attributes-list.test
+++ clang/test/Misc/pragma-attribute-supported-attributes-list.test
@@ -83,6 +83,7 @@
 // CHECK-NEXT: Lockable (SubjectMatchRule_record)
 // CHECK-NEXT: MIGServerRoutine (SubjectMatchRule_function, SubjectMatchRule_objc_method, SubjectMatchRule_block)
 // CHECK-NEXT: MSStruct (SubjectMatchRule_record)
+// CHECK-NEXT: MayBeUndef (SubjectMatchRule_variable_is_parameter)
 // CHECK-NEXT: MicroMips (SubjectMatchRule_function)
 // CHECK-NEXT: MinSize (SubjectMatchRule_function, SubjectMatchRule_objc_method)
 // CHECK-NEXT: MinVectorWidth (SubjectMatchRule_function)
Index: clang/test/CodeGenHIP/maybe_undef-attr-verify.hip
===
--- /dev/null
+++ clang/test/CodeGenHIP/maybe_undef-attr-verify.hip
@@ -0,0 +1,44 @@
+// RUN: %clang_cc1 -no-opaque-pointers -triple amdgcn-amd-amdhsa -target-cpu gfx906 -x hip -fcuda-is-device -emit-llvm  %s \
+// RUN:   -o - | FileCheck %s
+
+#define __global__ __attribute__((global))
+#define __device__ __attribute__((device))
+#define __maybe_undef __attribute__((maybe_undef))
+#define WARP_SIZE 64
+
+static constexpr int warpSize = __AMDGCN_WAVEFRONT_SIZE;
+
+__device__ static inline unsigned int __lane_id() {
+return  __builtin_amdgcn_mbcnt_hi(
+-1, __builtin_amdgcn_mbcnt_lo(-1, 0));
+}
+
+__device__
+inline
+int __shfl_sync(int __maybe_undef var, int src_lane, int width = warpSize) {
+int self = __lane_id();
+int index = src_lane + (self & ~(width-1));
+return __builtin_amdgcn_ds_bpermute(index<<2, var);
+}
+
+__global__ void
+shufflekernel()
+{
+int t;
+int res;
+res = __shfl_sync(t, WARP_SIZE, 0);
+}
+
+// CHECK: define dso_local amdgpu_kernel void @_Z13shufflekernelv()
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:[[TMP1:%.*]] = alloca i32, align 4, addrspace(5)
+// CHECK-NEXT:[[TMP2:%.*]] = alloca i32, align 4, addrspace(5)
+// CHECK-NEXT:[[TMP3:%.*]] = addrspacecast i32 addrspace(5)* [[TMP1:%.*]] to i32*
+// CHECK-NEXT:[[TMP4:%.*]] = addrspacecast i32 addrspace(5)* [[TMP2:%.*]] to i32*
+// CHECK-NEXT:[[TMP5:%.*]] = load i32, i32* [[TMP3:%.*]], align 4
+// CHECK-NEXT:[[TMP6:%.*]] = freeze i32 [[TMP5:%.*]]
+// CHECK-NEXT:%call = call noundef i32 @_Z11__shfl_synciii(i32 noundef [[TMP6:%.*]], i32 noundef 64, i32 noundef 0) #4
+// CHECK-NEXT:store i32 %call, i32* [[TMP4:%.*]], align 4
+// CHECK-NEXT:  ret void
+
+// CHECK: define linkonce_odr noundef i32 @_Z11__shfl_synciii(i32 noundef %var, i32 noundef %src_lane, i32 noundef %width)
Index: clang/test/CodeGen/attr-maybeundef.c
===
--- /dev/null
+++ clang/test/CodeGen/attr-maybeundef.c
@@ -0,0 +1,14 @@
+// RUN: %clang_cc1 -no-opaque-pointers -emit-llvm %s -o - | FileCheck %s
+
+#define __maybe_undef __attribute__((maybe_undef))
+
+// CHECK: define dso_local void @t1(i32 noundef %param1, i32 noundef %param2, float noundef %param3) #[[attr1:[0-9]+]]
+void t1(int param1, int __maybe_undef param2, float param3) {}
+
+// CHECK: define dso_local void @t2(i32 noundef %param1, i32 noundef %param2, float noundef %param3)
+// CHECK: [[TMP1:%.*]] = freeze i32 [[TMP2:%.*]]
+// CHECK: call void @t1(i32 noundef %0, i32 noundef [[TMP1:%.*]], float noundef %2)
+// expected-error {{'maybe_undef' attribute only applies to parameters [-Wignored-attributes]}}
+void __maybe_undef t2(int param1, int param2, float param3) {
+t1(param1, param2, param3);
+}
Index: clang/lib/Sema/SemaDeclAttr.cpp
===
--- clang/lib/Sema/SemaDeclAttr.cpp
+++ clang/lib/Sema/SemaDeclAttr.cpp
@@ -8634,6 +8634,9 @@
   case ParsedAttr::AT_NoEscape:
 handleNoEscapeAttr(S, D, AL);
 break;
+  case ParsedAttr::AT_MayBeUndef:
+handleSimpleAttribute(S, D, AL);
+break;
   case ParsedAttr::AT_AssumeAligned:
 handleAssumeAlignedAttr(S, D, AL);
 break;
Index: clang/lib/CodeGen/CGCall.cpp
===
--- clang/lib/CodeGen/CGCall.cpp
+++ clang/lib/CodeGen/CGCall.cpp
@@ -2046,6 +2046,25 @@
   return false;
 }
 
+/// Check if the argument of a function has maybe_undef attribute.
+static bool IsArgumentMayBeUndef(const Decl *TargetDecl, unsigned

[PATCH] D125378: [Attribute] Introduce shuffle attribute to be used for __shfl_sync like cross-lane APIs

[krishna chaitanya sankisa via Phabricator via cfe-commits]

skc7 created this revision.
Herald added subscribers: jdoerfert, hiraditya.
Herald added a reviewer: aaron.ballman.
Herald added a project: All.
skc7 requested review of this revision.
Herald added projects: clang, LLVM.
Herald added subscribers: llvm-commits, cfe-commits.

This change introduces shuffle as function attribute in clang and llvm IR. It 
is used to identify __shfl_sync like cross-lane APIs [allows exchange of 
variable across all active threads]. At clang codegen, noundef attribute is 
skipped to arguments and return types for functions with shuffle attribute.

Shuffle attribute has been added as per suggestions/comments from review: 
D124158 


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D125378

Files:
  clang/include/clang/Basic/Attr.td
  clang/include/clang/Basic/AttrDocs.td
  clang/lib/CodeGen/CGCall.cpp
  clang/lib/Headers/__clang_cuda_intrinsics.h
  clang/lib/Sema/SemaDeclAttr.cpp
  clang/test/CodeGenHIP/shuffle-attr-verify.hip
  clang/test/CodeGenHIP/shuffle-noundef-attr.hip
  clang/test/Misc/pragma-attribute-supported-attributes-list.test
  llvm/include/llvm/Bitcode/LLVMBitCodes.h
  llvm/include/llvm/IR/Attributes.td
  llvm/include/llvm/IR/Function.h
  llvm/lib/Bitcode/Reader/BitcodeReader.cpp
  llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
  llvm/lib/IR/Attributes.cpp
  llvm/lib/Transforms/Utils/CodeExtractor.cpp

Index: llvm/lib/Transforms/Utils/CodeExtractor.cpp
===
--- llvm/lib/Transforms/Utils/CodeExtractor.cpp
+++ llvm/lib/Transforms/Utils/CodeExtractor.cpp
@@ -960,6 +960,7 @@
   case Attribute::NoCfCheck:
   case Attribute::MustProgress:
   case Attribute::NoProfile:
+  case Attribute::Shuffle:
 break;
   // These attributes cannot be applied to functions.
   case Attribute::Alignment:
Index: llvm/lib/IR/Attributes.cpp
===
--- llvm/lib/IR/Attributes.cpp
+++ llvm/lib/IR/Attributes.cpp
@@ -1804,7 +1804,8 @@
   .addAttribute(Attribute::StructRet)
   .addAttribute(Attribute::ByRef)
   .addAttribute(Attribute::ElementType)
-  .addAttribute(Attribute::AllocatedPointer);
+  .addAttribute(Attribute::AllocatedPointer)
+  .addAttribute(Attribute::Shuffle);
   }
 
 // Attributes that only apply to pointers or vectors of pointers.
Index: llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
===
--- llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
+++ llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
@@ -778,6 +778,8 @@
   case Attribute::EmptyKey:
   case Attribute::TombstoneKey:
 llvm_unreachable("Trying to encode EmptyKey/TombstoneKey");
+  case Attribute::Shuffle:
+return bitc::ATTR_KIND_SHUFFLE;
   }
 
   llvm_unreachable("Trying to encode unknown attribute");
Index: llvm/lib/Bitcode/Reader/BitcodeReader.cpp
===
--- llvm/lib/Bitcode/Reader/BitcodeReader.cpp
+++ llvm/lib/Bitcode/Reader/BitcodeReader.cpp
@@ -1632,6 +1632,8 @@
 return Attribute::MustProgress;
   case bitc::ATTR_KIND_HOT:
 return Attribute::Hot;
+  case bitc::ATTR_KIND_SHUFFLE:
+return Attribute::Shuffle;
   }
 }
 
Index: llvm/include/llvm/IR/Function.h
===
--- llvm/include/llvm/IR/Function.h
+++ llvm/include/llvm/IR/Function.h
@@ -626,6 +626,12 @@
 return AttributeSets.getUWTableKind();
   }
 
+  /// Determine if the function is __shfl_sync like.
+  bool isShuffle() const {
+return hasFnAttribute(Attribute::Shuffle);
+  }
+  void setShuffle() { addFnAttr(Attribute::Shuffle); }
+
   /// True if the ABI mandates (or the user requested) that this
   /// function be in a unwind table.
   bool hasUWTable() const {
Index: llvm/include/llvm/IR/Attributes.td
===
--- llvm/include/llvm/IR/Attributes.td
+++ llvm/include/llvm/IR/Attributes.td
@@ -300,6 +300,9 @@
 /// Function is required to make Forward Progress.
 def MustProgress : EnumAttr<"mustprogress", [FnAttr]>;
 
+/// Function is a __shfl_sync like API.
+def Shuffle : EnumAttr<"shuffle", [FnAttr]>;
+
 /// Target-independent string attributes.
 def LessPreciseFPMAD : StrBoolAttr<"less-precise-fpmad">;
 def NoInfsFPMath : StrBoolAttr<"no-infs-fp-math">;
Index: llvm/include/llvm/Bitcode/LLVMBitCodes.h
===
--- llvm/include/llvm/Bitcode/LLVMBitCodes.h
+++ llvm/include/llvm/Bitcode/LLVMBitCodes.h
@@ -684,6 +684,7 @@
   ATTR_KIND_NO_SANITIZE_BOUNDS = 79,
   ATTR_KIND_ALLOC_ALIGN = 80,
   ATTR_KIND_ALLOCATED_POINTER = 81,
+  ATTR_KIND_SHUFFLE = 82,
 };
 
 enum ComdatSelectionKindCodes {
Index: clang/test/Misc/pragma-attribute-supported-attributes-list.test

[PATCH] D125378: [Attribute] Introduce shuffle attribute to be used for __shfl_sync like cross-lane APIs

[krishna chaitanya sankisa via Phabricator via cfe-commits]

skc7 updated this revision to Diff 428635.
skc7 added a comment.

clang-format


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D125378/new/

https://reviews.llvm.org/D125378

Files:
  clang/include/clang/Basic/Attr.td
  clang/include/clang/Basic/AttrDocs.td
  clang/lib/CodeGen/CGCall.cpp
  clang/lib/Headers/__clang_cuda_intrinsics.h
  clang/lib/Sema/SemaDeclAttr.cpp
  clang/test/CodeGenHIP/shuffle-attr-verify.hip
  clang/test/CodeGenHIP/shuffle-noundef-attr.hip
  clang/test/Misc/pragma-attribute-supported-attributes-list.test
  llvm/include/llvm/Bitcode/LLVMBitCodes.h
  llvm/include/llvm/IR/Attributes.td
  llvm/include/llvm/IR/Function.h
  llvm/lib/Bitcode/Reader/BitcodeReader.cpp
  llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
  llvm/lib/IR/Attributes.cpp
  llvm/lib/Transforms/Utils/CodeExtractor.cpp

Index: llvm/lib/Transforms/Utils/CodeExtractor.cpp
===
--- llvm/lib/Transforms/Utils/CodeExtractor.cpp
+++ llvm/lib/Transforms/Utils/CodeExtractor.cpp
@@ -960,6 +960,7 @@
   case Attribute::NoCfCheck:
   case Attribute::MustProgress:
   case Attribute::NoProfile:
+  case Attribute::Shuffle:
 break;
   // These attributes cannot be applied to functions.
   case Attribute::Alignment:
Index: llvm/lib/IR/Attributes.cpp
===
--- llvm/lib/IR/Attributes.cpp
+++ llvm/lib/IR/Attributes.cpp
@@ -1804,7 +1804,8 @@
   .addAttribute(Attribute::StructRet)
   .addAttribute(Attribute::ByRef)
   .addAttribute(Attribute::ElementType)
-  .addAttribute(Attribute::AllocatedPointer);
+  .addAttribute(Attribute::AllocatedPointer)
+  .addAttribute(Attribute::Shuffle);
   }
 
 // Attributes that only apply to pointers or vectors of pointers.
Index: llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
===
--- llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
+++ llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
@@ -778,6 +778,8 @@
   case Attribute::EmptyKey:
   case Attribute::TombstoneKey:
 llvm_unreachable("Trying to encode EmptyKey/TombstoneKey");
+  case Attribute::Shuffle:
+return bitc::ATTR_KIND_SHUFFLE;
   }
 
   llvm_unreachable("Trying to encode unknown attribute");
Index: llvm/lib/Bitcode/Reader/BitcodeReader.cpp
===
--- llvm/lib/Bitcode/Reader/BitcodeReader.cpp
+++ llvm/lib/Bitcode/Reader/BitcodeReader.cpp
@@ -1632,6 +1632,8 @@
 return Attribute::MustProgress;
   case bitc::ATTR_KIND_HOT:
 return Attribute::Hot;
+  case bitc::ATTR_KIND_SHUFFLE:
+return Attribute::Shuffle;
   }
 }
 
Index: llvm/include/llvm/IR/Function.h
===
--- llvm/include/llvm/IR/Function.h
+++ llvm/include/llvm/IR/Function.h
@@ -626,6 +626,10 @@
 return AttributeSets.getUWTableKind();
   }
 
+  /// Determine if the function is __shfl_sync like.
+  bool isShuffle() const { return hasFnAttribute(Attribute::Shuffle); }
+  void setShuffle() { addFnAttr(Attribute::Shuffle); }
+
   /// True if the ABI mandates (or the user requested) that this
   /// function be in a unwind table.
   bool hasUWTable() const {
Index: llvm/include/llvm/IR/Attributes.td
===
--- llvm/include/llvm/IR/Attributes.td
+++ llvm/include/llvm/IR/Attributes.td
@@ -300,6 +300,9 @@
 /// Function is required to make Forward Progress.
 def MustProgress : EnumAttr<"mustprogress", [FnAttr]>;
 
+/// Function is a __shfl_sync like API.
+def Shuffle : EnumAttr<"shuffle", [FnAttr]>;
+
 /// Target-independent string attributes.
 def LessPreciseFPMAD : StrBoolAttr<"less-precise-fpmad">;
 def NoInfsFPMath : StrBoolAttr<"no-infs-fp-math">;
Index: llvm/include/llvm/Bitcode/LLVMBitCodes.h
===
--- llvm/include/llvm/Bitcode/LLVMBitCodes.h
+++ llvm/include/llvm/Bitcode/LLVMBitCodes.h
@@ -684,6 +684,7 @@
   ATTR_KIND_NO_SANITIZE_BOUNDS = 79,
   ATTR_KIND_ALLOC_ALIGN = 80,
   ATTR_KIND_ALLOCATED_POINTER = 81,
+  ATTR_KIND_SHUFFLE = 82,
 };
 
 enum ComdatSelectionKindCodes {
Index: clang/test/Misc/pragma-attribute-supported-attributes-list.test
===
--- clang/test/Misc/pragma-attribute-supported-attributes-list.test
+++ clang/test/Misc/pragma-attribute-supported-attributes-list.test
@@ -161,6 +161,7 @@
 // CHECK-NEXT: ScopedLockable (SubjectMatchRule_record)
 // CHECK-NEXT: Section (SubjectMatchRule_function, SubjectMatchRule_variable_is_global, SubjectMatchRule_objc_method, SubjectMatchRule_objc_property)
 // CHECK-NEXT: SetTypestate (SubjectMatchRule_function_is_member)
+// CHECK-NEXT: Shuffle (SubjectMatchRule_function)
 // CHECK-NEXT: SpeculativeLoadHardening (SubjectMatchRule_function, SubjectMatchRule_objc_method)
 // CHE

[PATCH] D125378: [Attribute] Introduce shuffle attribute to be used for __shfl_sync like cross-lane APIs

[krishna chaitanya sankisa via Phabricator via cfe-commits]

skc7 updated this revision to Diff 428637.
skc7 added a comment.

rebase


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D125378/new/

https://reviews.llvm.org/D125378

Files:
  clang/include/clang/Basic/Attr.td
  clang/include/clang/Basic/AttrDocs.td
  clang/lib/CodeGen/CGCall.cpp
  clang/lib/Headers/__clang_cuda_intrinsics.h
  clang/lib/Sema/SemaDeclAttr.cpp
  clang/test/CodeGenHIP/shuffle-attr-verify.hip
  clang/test/CodeGenHIP/shuffle-noundef-attr.hip
  clang/test/Misc/pragma-attribute-supported-attributes-list.test
  llvm/include/llvm/Bitcode/LLVMBitCodes.h
  llvm/include/llvm/IR/Attributes.td
  llvm/include/llvm/IR/Function.h
  llvm/lib/Bitcode/Reader/BitcodeReader.cpp
  llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
  llvm/lib/IR/Attributes.cpp
  llvm/lib/Transforms/Utils/CodeExtractor.cpp

Index: llvm/lib/Transforms/Utils/CodeExtractor.cpp
===
--- llvm/lib/Transforms/Utils/CodeExtractor.cpp
+++ llvm/lib/Transforms/Utils/CodeExtractor.cpp
@@ -960,6 +960,7 @@
   case Attribute::NoCfCheck:
   case Attribute::MustProgress:
   case Attribute::NoProfile:
+  case Attribute::Shuffle:
 break;
   // These attributes cannot be applied to functions.
   case Attribute::Alignment:
Index: llvm/lib/IR/Attributes.cpp
===
--- llvm/lib/IR/Attributes.cpp
+++ llvm/lib/IR/Attributes.cpp
@@ -1804,7 +1804,8 @@
   .addAttribute(Attribute::StructRet)
   .addAttribute(Attribute::ByRef)
   .addAttribute(Attribute::ElementType)
-  .addAttribute(Attribute::AllocatedPointer);
+  .addAttribute(Attribute::AllocatedPointer)
+  .addAttribute(Attribute::Shuffle);
   }
 
 // Attributes that only apply to pointers or vectors of pointers.
Index: llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
===
--- llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
+++ llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
@@ -779,6 +779,8 @@
   case Attribute::EmptyKey:
   case Attribute::TombstoneKey:
 llvm_unreachable("Trying to encode EmptyKey/TombstoneKey");
+  case Attribute::Shuffle:
+return bitc::ATTR_KIND_SHUFFLE;
   }
 
   llvm_unreachable("Trying to encode unknown attribute");
Index: llvm/lib/Bitcode/Reader/BitcodeReader.cpp
===
--- llvm/lib/Bitcode/Reader/BitcodeReader.cpp
+++ llvm/lib/Bitcode/Reader/BitcodeReader.cpp
@@ -1632,6 +1632,8 @@
 return Attribute::MustProgress;
   case bitc::ATTR_KIND_HOT:
 return Attribute::Hot;
+  case bitc::ATTR_KIND_SHUFFLE:
+return Attribute::Shuffle;
   }
 }
 
Index: llvm/include/llvm/IR/Function.h
===
--- llvm/include/llvm/IR/Function.h
+++ llvm/include/llvm/IR/Function.h
@@ -626,6 +626,10 @@
 return AttributeSets.getUWTableKind();
   }
 
+  /// Determine if the function is __shfl_sync like.
+  bool isShuffle() const { return hasFnAttribute(Attribute::Shuffle); }
+  void setShuffle() { addFnAttr(Attribute::Shuffle); }
+
   /// True if the ABI mandates (or the user requested) that this
   /// function be in a unwind table.
   bool hasUWTable() const {
Index: llvm/include/llvm/IR/Attributes.td
===
--- llvm/include/llvm/IR/Attributes.td
+++ llvm/include/llvm/IR/Attributes.td
@@ -300,6 +300,9 @@
 /// Function is required to make Forward Progress.
 def MustProgress : EnumAttr<"mustprogress", [FnAttr]>;
 
+/// Function is a __shfl_sync like API.
+def Shuffle : EnumAttr<"shuffle", [FnAttr]>;
+
 /// Target-independent string attributes.
 def LessPreciseFPMAD : StrBoolAttr<"less-precise-fpmad">;
 def NoInfsFPMath : StrBoolAttr<"no-infs-fp-math">;
Index: llvm/include/llvm/Bitcode/LLVMBitCodes.h
===
--- llvm/include/llvm/Bitcode/LLVMBitCodes.h
+++ llvm/include/llvm/Bitcode/LLVMBitCodes.h
@@ -684,6 +684,7 @@
   ATTR_KIND_NO_SANITIZE_BOUNDS = 79,
   ATTR_KIND_ALLOC_ALIGN = 80,
   ATTR_KIND_ALLOCATED_POINTER = 81,
+  ATTR_KIND_SHUFFLE = 82,
 };
 
 enum ComdatSelectionKindCodes {
Index: clang/test/Misc/pragma-attribute-supported-attributes-list.test
===
--- clang/test/Misc/pragma-attribute-supported-attributes-list.test
+++ clang/test/Misc/pragma-attribute-supported-attributes-list.test
@@ -161,6 +161,7 @@
 // CHECK-NEXT: ScopedLockable (SubjectMatchRule_record)
 // CHECK-NEXT: Section (SubjectMatchRule_function, SubjectMatchRule_variable_is_global, SubjectMatchRule_objc_method, SubjectMatchRule_objc_property)
 // CHECK-NEXT: SetTypestate (SubjectMatchRule_function_is_member)
+// CHECK-NEXT: Shuffle (SubjectMatchRule_function)
 // CHECK-NEXT: SpeculativeLoadHardening (SubjectMatchRule_function, SubjectMatchRule_objc_method)
 // CHECK-NEX

[PATCH] D125378: [Attribute] Introduce shuffle attribute to be used for __shfl_sync like cross-lane APIs

[krishna chaitanya sankisa via Phabricator via cfe-commits]

skc7 added a comment.

In D125378#3506215 , @jdoerfert wrote:

> In D125378#3506001 , @nikic wrote:
>
>> Please specify the semantics of the new LLVM attribute in LangRef -- though 
>> I don't really understand why you need an LLVM-side attribute at all.
>
> +1. I doubt this patch is helpful.
>
>> Shuffle attribute has been added as per suggestions/comments from review: 
>> D124158 
>
> I failed to see where this was suggested.
>
> ---
>
> My suggestion was and still is summarized in: 
> https://reviews.llvm.org/D124158#3486110

@jdoerfert I meant to convey that, As a solution to review comments from 
D124158 , introduced this shuffle attribute 
to identify __shfl_sync like APIs.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D125378/new/

https://reviews.llvm.org/D125378

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D114533: LLVM IR should allow bitcast between address spaces with the same size.

[krishna chaitanya sankisa via Phabricator via cfe-commits]

skc7 created this revision.
skc7 added reviewers: sameerds, arsenm.
Herald added subscribers: dexonsmith, lxfind, jdoerfert, zzheng, hiraditya.
skc7 requested review of this revision.
Herald added subscribers: llvm-commits, cfe-commits, wdng.
Herald added projects: clang, LLVM.

When the addrspacecast instruction was added, the ability to bitcast between 
pointers from different address spaces was removed.
There are cases, where after analysis, cast between pointers from different 
address spaces can be concluded to be a no-op cast.
If bitcast can be allowed in these scenarios, it would help further optimise 
the IR in Transform passes since its a no-op cast.
This enhancement to bitcast will require that pointers to the two address 
spaces have the same bit widths(can be queried from DataLayout).
Frontend should never misuse the bitcast wherever addrspace cast would have 
been more appropriate.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D114533

Files:
  clang/lib/CodeGen/CGAtomic.cpp
  llvm/docs/LangRef.rst
  llvm/include/llvm/Analysis/TargetFolder.h
  llvm/include/llvm/IR/ConstantFolder.h
  llvm/include/llvm/IR/Constants.h
  llvm/include/llvm/IR/IRBuilder.h
  llvm/include/llvm/IR/IRBuilderFolder.h
  llvm/include/llvm/IR/InstrTypes.h
  llvm/include/llvm/IR/Instructions.h
  llvm/include/llvm/IR/NoFolder.h
  llvm/lib/Analysis/ConstantFolding.cpp
  llvm/lib/Analysis/LoopUnrollAnalyzer.cpp
  llvm/lib/AsmParser/LLParser.cpp
  llvm/lib/IR/AutoUpgrade.cpp
  llvm/lib/IR/Constants.cpp
  llvm/lib/IR/Instructions.cpp
  llvm/lib/IR/Verifier.cpp
  llvm/lib/Transforms/Coroutines/Coroutines.cpp
  llvm/lib/Transforms/Utils/VNCoercion.cpp
  llvm/test/Transforms/GVN/gvn-eliminate-inttoptr-ptrtoint-for-load.ll
  llvm/test/Transforms/GVN/gvn-eliminate-inttoptr-ptrtoint-for-vector-load.ll
  
llvm/test/Transforms/GVN/gvn-eliminate-inttoptr-ptrtoint-for-vector-ptr-load.ll
  llvm/test/Verifier/bitcast-vector-pointer-as-neg.ll
  llvm/test/Verifier/bitcast-vector-pointer-different-addrspace-illegal.ll
  llvm/test/Verifier/bitcast-vector-pointer-neg.ll
  llvm/test/Verifier/bitcast-vector-pointer-pos.ll
  llvm/test/Verifier/bitcast-vector-pointer-same-addrspace.ll
  llvm/unittests/IR/InstructionsTest.cpp

Index: llvm/unittests/IR/InstructionsTest.cpp
===
--- llvm/unittests/IR/InstructionsTest.cpp
+++ llvm/unittests/IR/InstructionsTest.cpp
@@ -189,6 +189,10 @@
 TEST(InstructionsTest, CastInst) {
   LLVMContext C;
 
+  DataLayout DL("e-p:64:64-p1:64:64-p2:32:32-p3:32:32-p4:64:64-p5:32:32-"
+"p6:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-"
+"v256:256-v512:512-v1024:1024-v2048:2048-n32:64-S32-A5-ni:7");
+
   Type *Int8Ty = Type::getInt8Ty(C);
   Type *Int16Ty = Type::getInt16Ty(C);
   Type *Int32Ty = Type::getInt32Ty(C);
@@ -217,7 +221,11 @@
   Type *Int32PtrAS1Ty = PointerType::get(Int32Ty, 1);
   Type *Int64PtrAS1Ty = PointerType::get(Int64Ty, 1);
 
+  Type *Int32PtrAS2Ty = PointerType::get(Int32Ty, 2);
+  Type *Int32PtrAS3Ty = PointerType::get(Int32Ty, 3);
+
   Type *V2Int32PtrAS1Ty = FixedVectorType::get(Int32PtrAS1Ty, 2);
+  Type *V2Int32PtrAS2Ty = FixedVectorType::get(Int32PtrAS2Ty, 2);
   Type *V2Int64PtrAS1Ty = FixedVectorType::get(Int64PtrAS1Ty, 2);
   Type *V4Int32PtrAS1Ty = FixedVectorType::get(Int32PtrAS1Ty, 4);
   Type *VScaleV4Int32PtrAS1Ty = ScalableVectorType::get(Int32PtrAS1Ty, 4);
@@ -238,50 +246,52 @@
   EXPECT_EQ(CastInst::Trunc, CastInst::getCastOpcode(c64, true, V8x8Ty, true));
   EXPECT_EQ(CastInst::SExt, CastInst::getCastOpcode(c8, true, V8x64Ty, true));
 
-  EXPECT_FALSE(CastInst::isBitCastable(V8x8Ty, X86MMXTy));
-  EXPECT_FALSE(CastInst::isBitCastable(X86MMXTy, V8x8Ty));
-  EXPECT_FALSE(CastInst::isBitCastable(Int64Ty, X86MMXTy));
-  EXPECT_FALSE(CastInst::isBitCastable(V8x64Ty, V8x8Ty));
-  EXPECT_FALSE(CastInst::isBitCastable(V8x8Ty, V8x64Ty));
-
-  // Check address space casts are rejected since we don't know the sizes here
-  EXPECT_FALSE(CastInst::isBitCastable(Int32PtrTy, Int32PtrAS1Ty));
-  EXPECT_FALSE(CastInst::isBitCastable(Int32PtrAS1Ty, Int32PtrTy));
-  EXPECT_FALSE(CastInst::isBitCastable(V2Int32PtrTy, V2Int32PtrAS1Ty));
-  EXPECT_FALSE(CastInst::isBitCastable(V2Int32PtrAS1Ty, V2Int32PtrTy));
-  EXPECT_TRUE(CastInst::isBitCastable(V2Int32PtrAS1Ty, V2Int64PtrAS1Ty));
+  EXPECT_FALSE(CastInst::isBitCastable(V8x8Ty, X86MMXTy, DL));
+  EXPECT_FALSE(CastInst::isBitCastable(X86MMXTy, V8x8Ty, DL));
+  EXPECT_FALSE(CastInst::isBitCastable(Int64Ty, X86MMXTy, DL));
+  EXPECT_FALSE(CastInst::isBitCastable(V8x64Ty, V8x8Ty, DL));
+  EXPECT_FALSE(CastInst::isBitCastable(V8x8Ty, V8x64Ty, DL));
+
+  // Check validity of casts here
+  EXPECT_TRUE(CastInst::isBitCastable(Int32PtrAS2Ty, Int32PtrAS3Ty, DL));
+  EXPECT_FALSE(CastInst::isBitCastable(Int32PtrAS1Ty, Int32PtrAS2Ty, DL));
+  EXPECT_TRUE(CastInst::isBitCastable(Int32PtrTy, Int32PtrAS1Ty, DL));
+  EXPECT_TRUE(CastInst::isBitCa

[PATCH] D114533: LLVM IR should allow bitcast between address spaces with the same size.

[krishna chaitanya sankisa via Phabricator via cfe-commits]

skc7 updated this revision to Diff 389983.
skc7 added a comment.

Updated diff with changes suggested by jrtc27


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D114533/new/

https://reviews.llvm.org/D114533

Files:
  clang/lib/CodeGen/CGAtomic.cpp
  llvm/docs/LangRef.rst
  llvm/include/llvm/Analysis/TargetFolder.h
  llvm/include/llvm/IR/ConstantFolder.h
  llvm/include/llvm/IR/Constants.h
  llvm/include/llvm/IR/IRBuilder.h
  llvm/include/llvm/IR/IRBuilderFolder.h
  llvm/include/llvm/IR/InstrTypes.h
  llvm/include/llvm/IR/Instructions.h
  llvm/include/llvm/IR/NoFolder.h
  llvm/lib/Analysis/ConstantFolding.cpp
  llvm/lib/Analysis/LoopUnrollAnalyzer.cpp
  llvm/lib/AsmParser/LLParser.cpp
  llvm/lib/IR/AutoUpgrade.cpp
  llvm/lib/IR/Constants.cpp
  llvm/lib/IR/Instructions.cpp
  llvm/lib/IR/Verifier.cpp
  llvm/lib/Transforms/Coroutines/Coroutines.cpp
  llvm/lib/Transforms/Utils/VNCoercion.cpp
  llvm/test/Transforms/GVN/gvn-eliminate-inttoptr-ptrtoint-for-load.ll
  llvm/test/Transforms/GVN/gvn-eliminate-inttoptr-ptrtoint-for-vector-load.ll
  
llvm/test/Transforms/GVN/gvn-eliminate-inttoptr-ptrtoint-for-vector-ptr-load.ll
  llvm/test/Verifier/bitcast-vector-pointer-as-neg.ll
  llvm/test/Verifier/bitcast-vector-pointer-different-addrspace-illegal.ll
  llvm/test/Verifier/bitcast-vector-pointer-neg.ll
  llvm/test/Verifier/bitcast-vector-pointer-pos.ll
  llvm/test/Verifier/bitcast-vector-pointer-same-addrspace.ll
  llvm/unittests/IR/InstructionsTest.cpp

Index: llvm/unittests/IR/InstructionsTest.cpp
===
--- llvm/unittests/IR/InstructionsTest.cpp
+++ llvm/unittests/IR/InstructionsTest.cpp
@@ -189,6 +189,10 @@
 TEST(InstructionsTest, CastInst) {
   LLVMContext C;
 
+  DataLayout DL("e-p:64:64-p1:64:64-p2:32:32-p3:32:32-p4:64:64-p5:32:32-"
+"p6:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-"
+"v256:256-v512:512-v1024:1024-v2048:2048-n32:64-S32-A5-ni:7");
+
   Type *Int8Ty = Type::getInt8Ty(C);
   Type *Int16Ty = Type::getInt16Ty(C);
   Type *Int32Ty = Type::getInt32Ty(C);
@@ -217,7 +221,11 @@
   Type *Int32PtrAS1Ty = PointerType::get(Int32Ty, 1);
   Type *Int64PtrAS1Ty = PointerType::get(Int64Ty, 1);
 
+  Type *Int32PtrAS2Ty = PointerType::get(Int32Ty, 2);
+  Type *Int32PtrAS3Ty = PointerType::get(Int32Ty, 3);
+
   Type *V2Int32PtrAS1Ty = FixedVectorType::get(Int32PtrAS1Ty, 2);
+  Type *V2Int32PtrAS2Ty = FixedVectorType::get(Int32PtrAS2Ty, 2);
   Type *V2Int64PtrAS1Ty = FixedVectorType::get(Int64PtrAS1Ty, 2);
   Type *V4Int32PtrAS1Ty = FixedVectorType::get(Int32PtrAS1Ty, 4);
   Type *VScaleV4Int32PtrAS1Ty = ScalableVectorType::get(Int32PtrAS1Ty, 4);
@@ -238,50 +246,52 @@
   EXPECT_EQ(CastInst::Trunc, CastInst::getCastOpcode(c64, true, V8x8Ty, true));
   EXPECT_EQ(CastInst::SExt, CastInst::getCastOpcode(c8, true, V8x64Ty, true));
 
-  EXPECT_FALSE(CastInst::isBitCastable(V8x8Ty, X86MMXTy));
-  EXPECT_FALSE(CastInst::isBitCastable(X86MMXTy, V8x8Ty));
-  EXPECT_FALSE(CastInst::isBitCastable(Int64Ty, X86MMXTy));
-  EXPECT_FALSE(CastInst::isBitCastable(V8x64Ty, V8x8Ty));
-  EXPECT_FALSE(CastInst::isBitCastable(V8x8Ty, V8x64Ty));
-
-  // Check address space casts are rejected since we don't know the sizes here
-  EXPECT_FALSE(CastInst::isBitCastable(Int32PtrTy, Int32PtrAS1Ty));
-  EXPECT_FALSE(CastInst::isBitCastable(Int32PtrAS1Ty, Int32PtrTy));
-  EXPECT_FALSE(CastInst::isBitCastable(V2Int32PtrTy, V2Int32PtrAS1Ty));
-  EXPECT_FALSE(CastInst::isBitCastable(V2Int32PtrAS1Ty, V2Int32PtrTy));
-  EXPECT_TRUE(CastInst::isBitCastable(V2Int32PtrAS1Ty, V2Int64PtrAS1Ty));
+  EXPECT_FALSE(CastInst::isBitCastable(V8x8Ty, X86MMXTy, DL));
+  EXPECT_FALSE(CastInst::isBitCastable(X86MMXTy, V8x8Ty, DL));
+  EXPECT_FALSE(CastInst::isBitCastable(Int64Ty, X86MMXTy, DL));
+  EXPECT_FALSE(CastInst::isBitCastable(V8x64Ty, V8x8Ty, DL));
+  EXPECT_FALSE(CastInst::isBitCastable(V8x8Ty, V8x64Ty, DL));
+
+  // Check validity of casts here
+  EXPECT_TRUE(CastInst::isBitCastable(Int32PtrAS2Ty, Int32PtrAS3Ty, DL));
+  EXPECT_FALSE(CastInst::isBitCastable(Int32PtrAS1Ty, Int32PtrAS2Ty, DL));
+  EXPECT_TRUE(CastInst::isBitCastable(Int32PtrTy, Int32PtrAS1Ty, DL));
+  EXPECT_TRUE(CastInst::isBitCastable(Int32PtrAS1Ty, Int32PtrTy, DL));
+  EXPECT_TRUE(CastInst::isBitCastable(V2Int32PtrTy, V2Int32PtrAS1Ty, DL));
+  EXPECT_TRUE(CastInst::isBitCastable(V2Int32PtrAS1Ty, V2Int32PtrTy, DL));
+  EXPECT_TRUE(CastInst::isBitCastable(V2Int32PtrAS1Ty, V2Int64PtrAS1Ty, DL));
+  EXPECT_FALSE(CastInst::isBitCastable(V2Int32PtrAS1Ty, V2Int32PtrAS2Ty, DL));
   EXPECT_EQ(CastInst::AddrSpaceCast, CastInst::getCastOpcode(v2ptr32, true,
  V2Int32PtrAS1Ty,
  true));
 
   // Test mismatched number of elements for pointers
-  EXPECT_FALSE(CastInst::isBitCastable(V2Int32PtrAS1Ty, V4Int64PtrAS1Ty));
-  EXPECT_FALSE(CastInst::isBitCastable(V4Int64PtrAS1Ty, V2

[PATCH] D114849: [AMDGPU][clang] Fix __builtin_nontemporal_store() failure on AMDGPU

[krishna chaitanya sankisa via Phabricator via cfe-commits]

skc7 created this revision.
skc7 added reviewers: sameerds, yaxunl.
Herald added subscribers: t-tye, tpr, dstuttard, jvesely, kzhuravl.
skc7 requested review of this revision.
Herald added subscribers: cfe-commits, wdng.
Herald added a project: clang.

__builtin_nontemporal_store() fails on AMDGPU. This is due to mismatch in 
address space while creating bitcast. This change matches addrspace of poiter 
type to src addrSpace in EmitNontemporalStore() in clang codegen.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D114849

Files:
  clang/lib/CodeGen/CGBuiltin.cpp
  clang/test/CodeGenOpenCL/amdgcn-non-temporal-store.cl


Index: clang/test/CodeGenOpenCL/amdgcn-non-temporal-store.cl
===
--- /dev/null
+++ clang/test/CodeGenOpenCL/amdgcn-non-temporal-store.cl
@@ -0,0 +1,8 @@
+// REQUIRES: amdgpu-registered-target
+// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -S -emit-llvm -o - %s | 
FileCheck %s
+// CHECK-LABEL: @test_non_temporal_store_kernel
+// CHECK: store i32 0, i32 addrspace(1)* %{{.*}}, align 4, !tbaa !{{.*}}, 
!nontemporal {{.*}}
+
+kernel void test_non_temporal_store_kernel(global unsigned int* io) {
+  __builtin_nontemporal_store(0, io);
+}
\ No newline at end of file
Index: clang/lib/CodeGen/CGBuiltin.cpp
===
--- clang/lib/CodeGen/CGBuiltin.cpp
+++ clang/lib/CodeGen/CGBuiltin.cpp
@@ -170,8 +170,9 @@
 
   // Convert the type of the pointer to a pointer to the stored type.
   Val = CGF.EmitToMemory(Val, E->getArg(0)->getType());
+  unsigned SrcAddrSpace = Address->getType()->getPointerAddressSpace();
   Value *BC = CGF.Builder.CreateBitCast(
-  Address, llvm::PointerType::getUnqual(Val->getType()), "cast");
+  Address, llvm::PointerType::get(Val->getType(), SrcAddrSpace), "cast");
   LValue LV = CGF.MakeNaturalAlignAddrLValue(BC, E->getArg(0)->getType());
   LV.setNontemporal(true);
   CGF.EmitStoreOfScalar(Val, LV, false);


Index: clang/test/CodeGenOpenCL/amdgcn-non-temporal-store.cl
===
--- /dev/null
+++ clang/test/CodeGenOpenCL/amdgcn-non-temporal-store.cl
@@ -0,0 +1,8 @@
+// REQUIRES: amdgpu-registered-target
+// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -S -emit-llvm -o - %s | FileCheck %s
+// CHECK-LABEL: @test_non_temporal_store_kernel
+// CHECK: store i32 0, i32 addrspace(1)* %{{.*}}, align 4, !tbaa !{{.*}}, !nontemporal {{.*}}
+
+kernel void test_non_temporal_store_kernel(global unsigned int* io) {
+  __builtin_nontemporal_store(0, io);
+}
\ No newline at end of file
Index: clang/lib/CodeGen/CGBuiltin.cpp
===
--- clang/lib/CodeGen/CGBuiltin.cpp
+++ clang/lib/CodeGen/CGBuiltin.cpp
@@ -170,8 +170,9 @@
 
   // Convert the type of the pointer to a pointer to the stored type.
   Val = CGF.EmitToMemory(Val, E->getArg(0)->getType());
+  unsigned SrcAddrSpace = Address->getType()->getPointerAddressSpace();
   Value *BC = CGF.Builder.CreateBitCast(
-  Address, llvm::PointerType::getUnqual(Val->getType()), "cast");
+  Address, llvm::PointerType::get(Val->getType(), SrcAddrSpace), "cast");
   LValue LV = CGF.MakeNaturalAlignAddrLValue(BC, E->getArg(0)->getType());
   LV.setNontemporal(true);
   CGF.EmitStoreOfScalar(Val, LV, false);
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D114849: [AMDGPU][clang] Fix __builtin_nontemporal_store() failure on AMDGPU

[krishna chaitanya sankisa via Phabricator via cfe-commits]

skc7 updated this revision to Diff 391023.
skc7 added a comment.

added new life at eof amdgcn-non-temporal-store.cl


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D114849/new/

https://reviews.llvm.org/D114849

Files:
  clang/lib/CodeGen/CGBuiltin.cpp
  clang/test/CodeGenOpenCL/amdgcn-non-temporal-store.cl


Index: clang/test/CodeGenOpenCL/amdgcn-non-temporal-store.cl
===
--- /dev/null
+++ clang/test/CodeGenOpenCL/amdgcn-non-temporal-store.cl
@@ -0,0 +1,8 @@
+// REQUIRES: amdgpu-registered-target
+// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -S -emit-llvm -o - %s | 
FileCheck %s
+// CHECK-LABEL: @test_non_temporal_store_kernel
+// CHECK: store i32 0, i32 addrspace(1)* %{{.*}}, align 4, !tbaa !{{.*}}, 
!nontemporal {{.*}}
+
+kernel void test_non_temporal_store_kernel(global unsigned int* io) {
+  __builtin_nontemporal_store(0, io);
+}
Index: clang/lib/CodeGen/CGBuiltin.cpp
===
--- clang/lib/CodeGen/CGBuiltin.cpp
+++ clang/lib/CodeGen/CGBuiltin.cpp
@@ -170,8 +170,9 @@
 
   // Convert the type of the pointer to a pointer to the stored type.
   Val = CGF.EmitToMemory(Val, E->getArg(0)->getType());
+  unsigned SrcAddrSpace = Address->getType()->getPointerAddressSpace();
   Value *BC = CGF.Builder.CreateBitCast(
-  Address, llvm::PointerType::getUnqual(Val->getType()), "cast");
+  Address, llvm::PointerType::get(Val->getType(), SrcAddrSpace), "cast");
   LValue LV = CGF.MakeNaturalAlignAddrLValue(BC, E->getArg(0)->getType());
   LV.setNontemporal(true);
   CGF.EmitStoreOfScalar(Val, LV, false);


Index: clang/test/CodeGenOpenCL/amdgcn-non-temporal-store.cl
===
--- /dev/null
+++ clang/test/CodeGenOpenCL/amdgcn-non-temporal-store.cl
@@ -0,0 +1,8 @@
+// REQUIRES: amdgpu-registered-target
+// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -S -emit-llvm -o - %s | FileCheck %s
+// CHECK-LABEL: @test_non_temporal_store_kernel
+// CHECK: store i32 0, i32 addrspace(1)* %{{.*}}, align 4, !tbaa !{{.*}}, !nontemporal {{.*}}
+
+kernel void test_non_temporal_store_kernel(global unsigned int* io) {
+  __builtin_nontemporal_store(0, io);
+}
Index: clang/lib/CodeGen/CGBuiltin.cpp
===
--- clang/lib/CodeGen/CGBuiltin.cpp
+++ clang/lib/CodeGen/CGBuiltin.cpp
@@ -170,8 +170,9 @@
 
   // Convert the type of the pointer to a pointer to the stored type.
   Val = CGF.EmitToMemory(Val, E->getArg(0)->getType());
+  unsigned SrcAddrSpace = Address->getType()->getPointerAddressSpace();
   Value *BC = CGF.Builder.CreateBitCast(
-  Address, llvm::PointerType::getUnqual(Val->getType()), "cast");
+  Address, llvm::PointerType::get(Val->getType(), SrcAddrSpace), "cast");
   LValue LV = CGF.MakeNaturalAlignAddrLValue(BC, E->getArg(0)->getType());
   LV.setNontemporal(true);
   CGF.EmitStoreOfScalar(Val, LV, false);
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D114849: [AMDGPU][clang] Fix __builtin_nontemporal_store() failure on AMDGPU

[krishna chaitanya sankisa via Phabricator via cfe-commits]

This revision was landed with ongoing or failed builds.
This revision was automatically updated to reflect the committed changes.
Closed by commit rG16b781e6d16d: [AMDGPU][clang] Fix  
__builtin_nontemporal_store() failure on AMDGPU (authored by skc7).

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D114849/new/

https://reviews.llvm.org/D114849

Files:
  clang/lib/CodeGen/CGBuiltin.cpp
  clang/test/CodeGenOpenCL/amdgcn-non-temporal-store.cl


Index: clang/test/CodeGenOpenCL/amdgcn-non-temporal-store.cl
===
--- /dev/null
+++ clang/test/CodeGenOpenCL/amdgcn-non-temporal-store.cl
@@ -0,0 +1,8 @@
+// REQUIRES: amdgpu-registered-target
+// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -S -emit-llvm -o - %s | 
FileCheck %s
+// CHECK-LABEL: @test_non_temporal_store_kernel
+// CHECK: store i32 0, i32 addrspace(1)* %{{.*}}, align 4, !tbaa !{{.*}}, 
!nontemporal {{.*}}
+
+kernel void test_non_temporal_store_kernel(global unsigned int* io) {
+  __builtin_nontemporal_store(0, io);
+}
Index: clang/lib/CodeGen/CGBuiltin.cpp
===
--- clang/lib/CodeGen/CGBuiltin.cpp
+++ clang/lib/CodeGen/CGBuiltin.cpp
@@ -170,8 +170,9 @@
 
   // Convert the type of the pointer to a pointer to the stored type.
   Val = CGF.EmitToMemory(Val, E->getArg(0)->getType());
+  unsigned SrcAddrSpace = Address->getType()->getPointerAddressSpace();
   Value *BC = CGF.Builder.CreateBitCast(
-  Address, llvm::PointerType::getUnqual(Val->getType()), "cast");
+  Address, llvm::PointerType::get(Val->getType(), SrcAddrSpace), "cast");
   LValue LV = CGF.MakeNaturalAlignAddrLValue(BC, E->getArg(0)->getType());
   LV.setNontemporal(true);
   CGF.EmitStoreOfScalar(Val, LV, false);


Index: clang/test/CodeGenOpenCL/amdgcn-non-temporal-store.cl
===
--- /dev/null
+++ clang/test/CodeGenOpenCL/amdgcn-non-temporal-store.cl
@@ -0,0 +1,8 @@
+// REQUIRES: amdgpu-registered-target
+// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -S -emit-llvm -o - %s | FileCheck %s
+// CHECK-LABEL: @test_non_temporal_store_kernel
+// CHECK: store i32 0, i32 addrspace(1)* %{{.*}}, align 4, !tbaa !{{.*}}, !nontemporal {{.*}}
+
+kernel void test_non_temporal_store_kernel(global unsigned int* io) {
+  __builtin_nontemporal_store(0, io);
+}
Index: clang/lib/CodeGen/CGBuiltin.cpp
===
--- clang/lib/CodeGen/CGBuiltin.cpp
+++ clang/lib/CodeGen/CGBuiltin.cpp
@@ -170,8 +170,9 @@
 
   // Convert the type of the pointer to a pointer to the stored type.
   Val = CGF.EmitToMemory(Val, E->getArg(0)->getType());
+  unsigned SrcAddrSpace = Address->getType()->getPointerAddressSpace();
   Value *BC = CGF.Builder.CreateBitCast(
-  Address, llvm::PointerType::getUnqual(Val->getType()), "cast");
+  Address, llvm::PointerType::get(Val->getType(), SrcAddrSpace), "cast");
   LValue LV = CGF.MakeNaturalAlignAddrLValue(BC, E->getArg(0)->getType());
   LV.setNontemporal(true);
   CGF.EmitStoreOfScalar(Val, LV, false);
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D114533: LLVM IR should allow bitcast between address spaces with the same size.

[krishna chaitanya sankisa via Phabricator via cfe-commits]

skc7 updated this revision to Diff 391836.
skc7 added a comment.

updated test IR files.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D114533/new/

https://reviews.llvm.org/D114533

Files:
  clang/lib/CodeGen/CGAtomic.cpp
  llvm/docs/LangRef.rst
  llvm/include/llvm/Analysis/TargetFolder.h
  llvm/include/llvm/IR/ConstantFolder.h
  llvm/include/llvm/IR/Constants.h
  llvm/include/llvm/IR/IRBuilder.h
  llvm/include/llvm/IR/IRBuilderFolder.h
  llvm/include/llvm/IR/InstrTypes.h
  llvm/include/llvm/IR/Instructions.h
  llvm/include/llvm/IR/NoFolder.h
  llvm/lib/Analysis/ConstantFolding.cpp
  llvm/lib/Analysis/LoopUnrollAnalyzer.cpp
  llvm/lib/AsmParser/LLParser.cpp
  llvm/lib/IR/AutoUpgrade.cpp
  llvm/lib/IR/Constants.cpp
  llvm/lib/IR/Instructions.cpp
  llvm/lib/IR/Verifier.cpp
  llvm/lib/Transforms/Coroutines/Coroutines.cpp
  llvm/lib/Transforms/Utils/VNCoercion.cpp
  llvm/test/Transforms/GVN/gvn-eliminate-inttoptr-ptrtoint-for-load.ll
  llvm/test/Transforms/GVN/gvn-eliminate-inttoptr-ptrtoint-for-vector-load.ll
  
llvm/test/Transforms/GVN/gvn-eliminate-inttoptr-ptrtoint-for-vector-ptr-load.ll
  llvm/test/Verifier/bitcast-vector-pointer-as-neg.ll
  llvm/test/Verifier/bitcast-vector-pointer-different-addrspace-illegal.ll
  llvm/test/Verifier/bitcast-vector-pointer-neg.ll
  llvm/test/Verifier/bitcast-vector-pointer-pos.ll
  llvm/test/Verifier/bitcast-vector-pointer-same-addrspace.ll
  llvm/unittests/IR/InstructionsTest.cpp

Index: llvm/unittests/IR/InstructionsTest.cpp
===
--- llvm/unittests/IR/InstructionsTest.cpp
+++ llvm/unittests/IR/InstructionsTest.cpp
@@ -189,6 +189,10 @@
 TEST(InstructionsTest, CastInst) {
   LLVMContext C;
 
+  DataLayout DL("e-p:64:64-p1:64:64-p2:32:32-p3:32:32-p4:64:64-p5:32:32-"
+"p6:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-"
+"v256:256-v512:512-v1024:1024-v2048:2048-n32:64-S32-A5-ni:7");
+
   Type *Int8Ty = Type::getInt8Ty(C);
   Type *Int16Ty = Type::getInt16Ty(C);
   Type *Int32Ty = Type::getInt32Ty(C);
@@ -217,7 +221,11 @@
   Type *Int32PtrAS1Ty = PointerType::get(Int32Ty, 1);
   Type *Int64PtrAS1Ty = PointerType::get(Int64Ty, 1);
 
+  Type *Int32PtrAS2Ty = PointerType::get(Int32Ty, 2);
+  Type *Int32PtrAS3Ty = PointerType::get(Int32Ty, 3);
+
   Type *V2Int32PtrAS1Ty = FixedVectorType::get(Int32PtrAS1Ty, 2);
+  Type *V2Int32PtrAS2Ty = FixedVectorType::get(Int32PtrAS2Ty, 2);
   Type *V2Int64PtrAS1Ty = FixedVectorType::get(Int64PtrAS1Ty, 2);
   Type *V4Int32PtrAS1Ty = FixedVectorType::get(Int32PtrAS1Ty, 4);
   Type *VScaleV4Int32PtrAS1Ty = ScalableVectorType::get(Int32PtrAS1Ty, 4);
@@ -238,50 +246,52 @@
   EXPECT_EQ(CastInst::Trunc, CastInst::getCastOpcode(c64, true, V8x8Ty, true));
   EXPECT_EQ(CastInst::SExt, CastInst::getCastOpcode(c8, true, V8x64Ty, true));
 
-  EXPECT_FALSE(CastInst::isBitCastable(V8x8Ty, X86MMXTy));
-  EXPECT_FALSE(CastInst::isBitCastable(X86MMXTy, V8x8Ty));
-  EXPECT_FALSE(CastInst::isBitCastable(Int64Ty, X86MMXTy));
-  EXPECT_FALSE(CastInst::isBitCastable(V8x64Ty, V8x8Ty));
-  EXPECT_FALSE(CastInst::isBitCastable(V8x8Ty, V8x64Ty));
-
-  // Check address space casts are rejected since we don't know the sizes here
-  EXPECT_FALSE(CastInst::isBitCastable(Int32PtrTy, Int32PtrAS1Ty));
-  EXPECT_FALSE(CastInst::isBitCastable(Int32PtrAS1Ty, Int32PtrTy));
-  EXPECT_FALSE(CastInst::isBitCastable(V2Int32PtrTy, V2Int32PtrAS1Ty));
-  EXPECT_FALSE(CastInst::isBitCastable(V2Int32PtrAS1Ty, V2Int32PtrTy));
-  EXPECT_TRUE(CastInst::isBitCastable(V2Int32PtrAS1Ty, V2Int64PtrAS1Ty));
+  EXPECT_FALSE(CastInst::isBitCastable(V8x8Ty, X86MMXTy, DL));
+  EXPECT_FALSE(CastInst::isBitCastable(X86MMXTy, V8x8Ty, DL));
+  EXPECT_FALSE(CastInst::isBitCastable(Int64Ty, X86MMXTy, DL));
+  EXPECT_FALSE(CastInst::isBitCastable(V8x64Ty, V8x8Ty, DL));
+  EXPECT_FALSE(CastInst::isBitCastable(V8x8Ty, V8x64Ty, DL));
+
+  // Check validity of casts here
+  EXPECT_TRUE(CastInst::isBitCastable(Int32PtrAS2Ty, Int32PtrAS3Ty, DL));
+  EXPECT_FALSE(CastInst::isBitCastable(Int32PtrAS1Ty, Int32PtrAS2Ty, DL));
+  EXPECT_TRUE(CastInst::isBitCastable(Int32PtrTy, Int32PtrAS1Ty, DL));
+  EXPECT_TRUE(CastInst::isBitCastable(Int32PtrAS1Ty, Int32PtrTy, DL));
+  EXPECT_TRUE(CastInst::isBitCastable(V2Int32PtrTy, V2Int32PtrAS1Ty, DL));
+  EXPECT_TRUE(CastInst::isBitCastable(V2Int32PtrAS1Ty, V2Int32PtrTy, DL));
+  EXPECT_TRUE(CastInst::isBitCastable(V2Int32PtrAS1Ty, V2Int64PtrAS1Ty, DL));
+  EXPECT_FALSE(CastInst::isBitCastable(V2Int32PtrAS1Ty, V2Int32PtrAS2Ty, DL));
   EXPECT_EQ(CastInst::AddrSpaceCast, CastInst::getCastOpcode(v2ptr32, true,
  V2Int32PtrAS1Ty,
  true));
 
   // Test mismatched number of elements for pointers
-  EXPECT_FALSE(CastInst::isBitCastable(V2Int32PtrAS1Ty, V4Int64PtrAS1Ty));
-  EXPECT_FALSE(CastInst::isBitCastable(V4Int64PtrAS1Ty, V2Int32PtrAS1Ty));
-  EXP