[clang] [Clang] Automatically enable `-fconvergent-functions` on GPU targets (PR #111076)
via cfe-commits
cfe-commits at lists.llvm.org
Thu Oct 3 16:31:10 PDT 2024
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-clang
Author: Joseph Huber (jhuber6)
<details>
<summary>Changes</summary>
Summary:
This patch causes us to respect the `-fconvergent-functions` and
`-fno-convergent-functions` options correctly. GPU targets should have
this set all the time, but we now offer `-fno-convergent-functions` to
opt-out if you want to test broken behavior. This munged about with a
lot of the old weird logic, but I don't think it makes any real changes.
---
Patch is 171.77 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/111076.diff
13 Files Affected:
- (modified) clang/include/clang/Driver/Options.td (+5-4)
- (modified) clang/lib/Driver/ToolChains/Clang.cpp (+2-2)
- (modified) clang/lib/Frontend/CompilerInvocation.cpp (+7-9)
- (modified) clang/test/CodeGen/nvptx_attributes.c (+1-1)
- (modified) clang/test/CodeGenCXX/dynamic-cast-address-space.cpp (+2-2)
- (modified) clang/test/OpenMP/target_parallel_for_codegen.cpp (+2-2)
- (modified) clang/test/OpenMP/target_parallel_for_simd_codegen.cpp (+4-4)
- (modified) clang/test/OpenMP/target_teams_distribute_parallel_for_firstprivate_codegen.cpp (+77-77)
- (modified) clang/test/OpenMP/target_teams_distribute_parallel_for_private_codegen.cpp (+41-41)
- (modified) clang/test/OpenMP/target_teams_distribute_parallel_for_simd_firstprivate_codegen.cpp (+77-77)
- (modified) clang/test/OpenMP/target_teams_distribute_parallel_for_simd_private_codegen.cpp (+41-41)
- (modified) clang/test/OpenMP/target_teams_generic_loop_private_codegen.cpp (+25-25)
- (modified) clang/test/OpenMP/target_teams_map_codegen.cpp (+4-4)
``````````diff
diff --git a/clang/include/clang/Driver/Options.td b/clang/include/clang/Driver/Options.td
index 9d183ff2d69b3c..445e681313eba7 100644
--- a/clang/include/clang/Driver/Options.td
+++ b/clang/include/clang/Driver/Options.td
@@ -1195,10 +1195,11 @@ def cxx_isystem : JoinedOrSeparate<["-"], "cxx-isystem">, Group<clang_i_Group>,
def c : Flag<["-"], "c">, Flags<[NoXarchOption]>,
Visibility<[ClangOption, FlangOption]>, Group<Action_Group>,
HelpText<"Only run preprocess, compile, and assemble steps">;
-defm convergent_functions : BoolFOption<"convergent-functions",
- LangOpts<"ConvergentFunctions">, DefaultFalse,
- NegFlag<SetFalse, [], [ClangOption], "Assume all functions may be convergent.">,
- PosFlag<SetTrue, [], [ClangOption, CC1Option]>>;
+def fconvergent_functions : Flag<["-"], "fconvergent-functions">,
+ Visibility<[ClangOption, CC1Option]>,
+ HelpText< "Assume all functions may be convergent.">;
+def fno_convergent_functions : Flag<["-"], "fno-convergent-functions">,
+ Visibility<[ClangOption, CC1Option]>;
// Common offloading options
let Group = offload_Group in {
diff --git a/clang/lib/Driver/ToolChains/Clang.cpp b/clang/lib/Driver/ToolChains/Clang.cpp
index b9987288d82d10..70643baba2df91 100644
--- a/clang/lib/Driver/ToolChains/Clang.cpp
+++ b/clang/lib/Driver/ToolChains/Clang.cpp
@@ -6258,8 +6258,6 @@ void Clang::ConstructJob(Compilation &C, const JobAction &JA,
options::OPT_fno_unique_internal_linkage_names);
Args.addOptInFlag(CmdArgs, options::OPT_funique_basic_block_section_names,
options::OPT_fno_unique_basic_block_section_names);
- Args.addOptInFlag(CmdArgs, options::OPT_fconvergent_functions,
- options::OPT_fno_convergent_functions);
if (Arg *A = Args.getLastArg(options::OPT_fsplit_machine_functions,
options::OPT_fno_split_machine_functions)) {
@@ -6276,6 +6274,8 @@ void Clang::ConstructJob(Compilation &C, const JobAction &JA,
Args.AddLastArg(CmdArgs, options::OPT_finstrument_functions,
options::OPT_finstrument_functions_after_inlining,
options::OPT_finstrument_function_entry_bare);
+ Args.AddLastArg(CmdArgs, options::OPT_fconvergent_functions,
+ options::OPT_fno_convergent_functions);
// NVPTX/AMDGCN doesn't support PGO or coverage. There's no runtime support
// for sampling, overhead of call arc collection is way too high and there's
diff --git a/clang/lib/Frontend/CompilerInvocation.cpp b/clang/lib/Frontend/CompilerInvocation.cpp
index a0291ccfea2458..2b5b6a8d2c5911 100644
--- a/clang/lib/Frontend/CompilerInvocation.cpp
+++ b/clang/lib/Frontend/CompilerInvocation.cpp
@@ -3687,10 +3687,10 @@ void CompilerInvocationBase::GenerateLangArgs(const LangOptions &Opts,
if (Opts.Blocks && !(Opts.OpenCL && Opts.OpenCLVersion == 200))
GenerateArg(Consumer, OPT_fblocks);
- if (Opts.ConvergentFunctions &&
- !(Opts.OpenCL || (Opts.CUDA && Opts.CUDAIsDevice) || Opts.SYCLIsDevice ||
- Opts.HLSL))
+ if (Opts.ConvergentFunctions)
GenerateArg(Consumer, OPT_fconvergent_functions);
+ else
+ GenerateArg(Consumer, OPT_fno_convergent_functions);
if (Opts.NoBuiltin && !Opts.Freestanding)
GenerateArg(Consumer, OPT_fno_builtin);
@@ -4106,9 +4106,10 @@ bool CompilerInvocation::ParseLangArgs(LangOptions &Opts, ArgList &Args,
Opts.Blocks = Args.hasArg(OPT_fblocks) || (Opts.OpenCL
&& Opts.OpenCLVersion == 200);
- Opts.ConvergentFunctions = Args.hasArg(OPT_fconvergent_functions) ||
- Opts.OpenCL || (Opts.CUDA && Opts.CUDAIsDevice) ||
- Opts.SYCLIsDevice || Opts.HLSL;
+ Opts.ConvergentFunctions = Args.hasFlag(
+ OPT_fconvergent_functions, OPT_fno_convergent_functions,
+ Opts.OpenMPIsTargetDevice || T.isAMDGPU() || T.isNVPTX() || Opts.OpenCL ||
+ Opts.CUDAIsDevice || Opts.SYCLIsDevice || Opts.HLSL);
Opts.NoBuiltin = Args.hasArg(OPT_fno_builtin) || Opts.Freestanding;
if (!Opts.NoBuiltin)
@@ -4164,9 +4165,6 @@ bool CompilerInvocation::ParseLangArgs(LangOptions &Opts, ArgList &Args,
bool IsTargetSpecified =
Opts.OpenMPIsTargetDevice || Args.hasArg(options::OPT_fopenmp_targets_EQ);
- Opts.ConvergentFunctions =
- Opts.ConvergentFunctions || Opts.OpenMPIsTargetDevice;
-
if (Opts.OpenMP || Opts.OpenMPSimd) {
if (int Version = getLastArgIntValue(
Args, OPT_fopenmp_version_EQ,
diff --git a/clang/test/CodeGen/nvptx_attributes.c b/clang/test/CodeGen/nvptx_attributes.c
index dcf79ad4e0e6a5..7dbd9f1321e280 100644
--- a/clang/test/CodeGen/nvptx_attributes.c
+++ b/clang/test/CodeGen/nvptx_attributes.c
@@ -1,7 +1,7 @@
// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --function-signature --check-attributes --check-globals
// RUN: %clang_cc1 -triple nvptx64-nvidia-cuda -target-cpu sm_61 -emit-llvm %s -o - | FileCheck %s
-// CHECK: Function Attrs: noinline nounwind optnone
+// CHECK: Function Attrs: convergent noinline nounwind optnone
// CHECK-LABEL: define {{[^@]+}}@foo
// CHECK-SAME: (ptr noundef [[RET:%.*]]) #[[ATTR0:[0-9]+]] {
// CHECK-NEXT: entry:
diff --git a/clang/test/CodeGenCXX/dynamic-cast-address-space.cpp b/clang/test/CodeGenCXX/dynamic-cast-address-space.cpp
index b967701ca1fa96..d0c87d9dfda5f7 100644
--- a/clang/test/CodeGenCXX/dynamic-cast-address-space.cpp
+++ b/clang/test/CodeGenCXX/dynamic-cast-address-space.cpp
@@ -106,9 +106,9 @@ const B& f(A *a) {
//.
-// CHECK: attributes #[[ATTR0]] = { mustprogress noinline optnone "no-trapping-math"="true" "stack-protector-buffer-size"="8" }
+// CHECK: attributes #[[ATTR0]] = { convergent mustprogress noinline optnone "no-trapping-math"="true" "stack-protector-buffer-size"="8" }
// CHECK: attributes #[[ATTR1:[0-9]+]] = { nounwind willreturn memory(read) }
-// CHECK: attributes #[[ATTR2:[0-9]+]] = { "no-trapping-math"="true" "stack-protector-buffer-size"="8" }
+// CHECK: attributes #[[ATTR2:[0-9]+]] = { convergent "no-trapping-math"="true" "stack-protector-buffer-size"="8" }
// CHECK: attributes #[[ATTR3]] = { nounwind }
// CHECK: attributes #[[ATTR4]] = { noreturn }
//.
diff --git a/clang/test/OpenMP/target_parallel_for_codegen.cpp b/clang/test/OpenMP/target_parallel_for_codegen.cpp
index 8a8c8a02aaef06..5378ff18b34c9d 100644
--- a/clang/test/OpenMP/target_parallel_for_codegen.cpp
+++ b/clang/test/OpenMP/target_parallel_for_codegen.cpp
@@ -3782,7 +3782,7 @@ int bar(int n){
// CHECK9-NEXT: store i32 [[TMP0]], ptr [[DOTLINEAR_START]], align 4
// CHECK9-NEXT: [[TMP1:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK9-NEXT: store i32 [[TMP1]], ptr [[DOTLINEAR_START1]], align 4
-// CHECK9-NEXT: [[CALL:%.*]] = call noundef i64 @_Z7get_valv() #[[ATTR4:[0-9]+]]
+// CHECK9-NEXT: [[CALL:%.*]] = call noundef i64 @_Z7get_valv()
// CHECK9-NEXT: store i64 [[CALL]], ptr [[DOTLINEAR_STEP]], align 8
// CHECK9-NEXT: store i64 0, ptr [[DOTOMP_LB]], align 8
// CHECK9-NEXT: store i64 3, ptr [[DOTOMP_UB]], align 8
@@ -4561,7 +4561,7 @@ int bar(int n){
// CHECK11-NEXT: store i32 [[TMP0]], ptr [[DOTLINEAR_START]], align 4
// CHECK11-NEXT: [[TMP1:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK11-NEXT: store i32 [[TMP1]], ptr [[DOTLINEAR_START1]], align 4
-// CHECK11-NEXT: [[CALL:%.*]] = call noundef i64 @_Z7get_valv() #[[ATTR4:[0-9]+]]
+// CHECK11-NEXT: [[CALL:%.*]] = call noundef i64 @_Z7get_valv()
// CHECK11-NEXT: store i64 [[CALL]], ptr [[DOTLINEAR_STEP]], align 8
// CHECK11-NEXT: store i64 0, ptr [[DOTOMP_LB]], align 8
// CHECK11-NEXT: store i64 3, ptr [[DOTOMP_UB]], align 8
diff --git a/clang/test/OpenMP/target_parallel_for_simd_codegen.cpp b/clang/test/OpenMP/target_parallel_for_simd_codegen.cpp
index 4bde6a4cfda3fb..e4570dbb1efcd7 100644
--- a/clang/test/OpenMP/target_parallel_for_simd_codegen.cpp
+++ b/clang/test/OpenMP/target_parallel_for_simd_codegen.cpp
@@ -9131,7 +9131,7 @@ int bar(int n){
// CHECK17-NEXT: store i32 [[TMP0]], ptr [[DOTLINEAR_START]], align 4
// CHECK17-NEXT: [[TMP1:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK17-NEXT: store i32 [[TMP1]], ptr [[DOTLINEAR_START1]], align 4
-// CHECK17-NEXT: [[CALL:%.*]] = call noundef i64 @_Z7get_valv() #[[ATTR4:[0-9]+]]
+// CHECK17-NEXT: [[CALL:%.*]] = call noundef i64 @_Z7get_valv()
// CHECK17-NEXT: store i64 [[CALL]], ptr [[DOTLINEAR_STEP]], align 8
// CHECK17-NEXT: store i64 0, ptr [[DOTOMP_LB]], align 8
// CHECK17-NEXT: store i64 3, ptr [[DOTOMP_UB]], align 8
@@ -9935,7 +9935,7 @@ int bar(int n){
// CHECK19-NEXT: store i32 [[TMP0]], ptr [[DOTLINEAR_START]], align 4
// CHECK19-NEXT: [[TMP1:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK19-NEXT: store i32 [[TMP1]], ptr [[DOTLINEAR_START1]], align 4
-// CHECK19-NEXT: [[CALL:%.*]] = call noundef i64 @_Z7get_valv() #[[ATTR4:[0-9]+]]
+// CHECK19-NEXT: [[CALL:%.*]] = call noundef i64 @_Z7get_valv()
// CHECK19-NEXT: store i64 [[CALL]], ptr [[DOTLINEAR_STEP]], align 8
// CHECK19-NEXT: store i64 0, ptr [[DOTOMP_LB]], align 8
// CHECK19-NEXT: store i64 3, ptr [[DOTOMP_UB]], align 8
@@ -10739,7 +10739,7 @@ int bar(int n){
// CHECK21-NEXT: store i32 [[TMP0]], ptr [[DOTLINEAR_START]], align 4
// CHECK21-NEXT: [[TMP1:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK21-NEXT: store i32 [[TMP1]], ptr [[DOTLINEAR_START1]], align 4
-// CHECK21-NEXT: [[CALL:%.*]] = call noundef i64 @_Z7get_valv() #[[ATTR4:[0-9]+]]
+// CHECK21-NEXT: [[CALL:%.*]] = call noundef i64 @_Z7get_valv()
// CHECK21-NEXT: store i64 [[CALL]], ptr [[DOTLINEAR_STEP]], align 8
// CHECK21-NEXT: store i64 0, ptr [[DOTOMP_LB]], align 8
// CHECK21-NEXT: store i64 3, ptr [[DOTOMP_UB]], align 8
@@ -11629,7 +11629,7 @@ int bar(int n){
// CHECK23-NEXT: store i32 [[TMP0]], ptr [[DOTLINEAR_START]], align 4
// CHECK23-NEXT: [[TMP1:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK23-NEXT: store i32 [[TMP1]], ptr [[DOTLINEAR_START1]], align 4
-// CHECK23-NEXT: [[CALL:%.*]] = call noundef i64 @_Z7get_valv() #[[ATTR4:[0-9]+]]
+// CHECK23-NEXT: [[CALL:%.*]] = call noundef i64 @_Z7get_valv()
// CHECK23-NEXT: store i64 [[CALL]], ptr [[DOTLINEAR_STEP]], align 8
// CHECK23-NEXT: store i64 0, ptr [[DOTOMP_LB]], align 8
// CHECK23-NEXT: store i64 3, ptr [[DOTOMP_UB]], align 8
diff --git a/clang/test/OpenMP/target_teams_distribute_parallel_for_firstprivate_codegen.cpp b/clang/test/OpenMP/target_teams_distribute_parallel_for_firstprivate_codegen.cpp
index 00a900d441b030..78e40e54671ac3 100644
--- a/clang/test/OpenMP/target_teams_distribute_parallel_for_firstprivate_codegen.cpp
+++ b/clang/test/OpenMP/target_teams_distribute_parallel_for_firstprivate_codegen.cpp
@@ -2718,17 +2718,17 @@ int main() {
// CHECK13: omp.arraycpy.body:
// CHECK13-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi ptr [ [[TMP1]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
// CHECK13-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi ptr [ [[ARRAY_BEGIN]], [[ENTRY]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
-// CHECK13-NEXT: call void @_ZN2StC1Ev(ptr noundef nonnull align 4 dereferenceable(8) [[AGG_TMP]]) #[[ATTR4:[0-9]+]]
-// CHECK13-NEXT: call void @_ZN1SIfEC1ERKS0_2St(ptr noundef nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST]], ptr noundef nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST]], ptr noundef [[AGG_TMP]]) #[[ATTR4]]
-// CHECK13-NEXT: call void @_ZN2StD1Ev(ptr noundef nonnull align 4 dereferenceable(8) [[AGG_TMP]]) #[[ATTR5:[0-9]+]]
+// CHECK13-NEXT: call void @_ZN2StC1Ev(ptr noundef nonnull align 4 dereferenceable(8) [[AGG_TMP]])
+// CHECK13-NEXT: call void @_ZN1SIfEC1ERKS0_2St(ptr noundef nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST]], ptr noundef nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST]], ptr noundef [[AGG_TMP]])
+// CHECK13-NEXT: call void @_ZN2StD1Ev(ptr noundef nonnull align 4 dereferenceable(8) [[AGG_TMP]]) #[[ATTR3:[0-9]+]]
// CHECK13-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr [[STRUCT_S]], ptr [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
// CHECK13-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr [[STRUCT_S]], ptr [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
// CHECK13-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq ptr [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP3]]
// CHECK13-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYCPY_DONE3]], label [[OMP_ARRAYCPY_BODY]]
// CHECK13: omp.arraycpy.done3:
-// CHECK13-NEXT: call void @_ZN2StC1Ev(ptr noundef nonnull align 4 dereferenceable(8) [[AGG_TMP5]]) #[[ATTR4]]
-// CHECK13-NEXT: call void @_ZN1SIfEC1ERKS0_2St(ptr noundef nonnull align 4 dereferenceable(4) [[VAR4]], ptr noundef nonnull align 4 dereferenceable(4) [[TMP2]], ptr noundef [[AGG_TMP5]]) #[[ATTR4]]
-// CHECK13-NEXT: call void @_ZN2StD1Ev(ptr noundef nonnull align 4 dereferenceable(8) [[AGG_TMP5]]) #[[ATTR5]]
+// CHECK13-NEXT: call void @_ZN2StC1Ev(ptr noundef nonnull align 4 dereferenceable(8) [[AGG_TMP5]])
+// CHECK13-NEXT: call void @_ZN1SIfEC1ERKS0_2St(ptr noundef nonnull align 4 dereferenceable(4) [[VAR4]], ptr noundef nonnull align 4 dereferenceable(4) [[TMP2]], ptr noundef [[AGG_TMP5]])
+// CHECK13-NEXT: call void @_ZN2StD1Ev(ptr noundef nonnull align 4 dereferenceable(8) [[AGG_TMP5]]) #[[ATTR3]]
// CHECK13-NEXT: [[TMP4:%.*]] = load ptr, ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK13-NEXT: [[TMP5:%.*]] = load i32, ptr [[TMP4]], align 4
// CHECK13-NEXT: call void @__kmpc_for_static_init_4(ptr @[[GLOB1:[0-9]+]], i32 [[TMP5]], i32 92, ptr [[DOTOMP_IS_LAST]], ptr [[DOTOMP_COMB_LB]], ptr [[DOTOMP_COMB_UB]], ptr [[DOTOMP_STRIDE]], i32 1, i32 1)
@@ -2778,14 +2778,14 @@ int main() {
// CHECK13-NEXT: [[TMP21:%.*]] = load ptr, ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK13-NEXT: [[TMP22:%.*]] = load i32, ptr [[TMP21]], align 4
// CHECK13-NEXT: call void @__kmpc_for_static_fini(ptr @[[GLOB1]], i32 [[TMP22]])
-// CHECK13-NEXT: call void @_ZN1SIfED1Ev(ptr noundef nonnull align 4 dereferenceable(4) [[VAR4]]) #[[ATTR5]]
+// CHECK13-NEXT: call void @_ZN1SIfED1Ev(ptr noundef nonnull align 4 dereferenceable(4) [[VAR4]]) #[[ATTR3]]
// CHECK13-NEXT: [[ARRAY_BEGIN7:%.*]] = getelementptr inbounds [2 x %struct.S], ptr [[S_ARR2]], i32 0, i32 0
// CHECK13-NEXT: [[TMP23:%.*]] = getelementptr inbounds [[STRUCT_S]], ptr [[ARRAY_BEGIN7]], i64 2
// CHECK13-NEXT: br label [[ARRAYDESTROY_BODY:%.*]]
// CHECK13: arraydestroy.body:
// CHECK13-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi ptr [ [[TMP23]], [[OMP_LOOP_EXIT]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
// CHECK13-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S]], ptr [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
-// CHECK13-NEXT: call void @_ZN1SIfED1Ev(ptr noundef nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR5]]
+// CHECK13-NEXT: call void @_ZN1SIfED1Ev(ptr noundef nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR3]]
// CHECK13-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq ptr [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN7]]
// CHECK13-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE8:%.*]], label [[ARRAYDESTROY_BODY]]
// CHECK13: arraydestroy.done8:
@@ -2798,7 +2798,7 @@ int main() {
// CHECK13-NEXT: [[THIS_ADDR:%.*]] = alloca ptr, align 8
// CHECK13-NEXT: store ptr [[THIS]], ptr [[THIS_ADDR]], align 8
// CHECK13-NEXT: [[THIS1:%.*]] = load ptr, ptr [[THIS_ADDR]], align 8
-// CHECK13-NEXT: call void @_ZN2StC2Ev(ptr noundef nonnull align 4 dereferenceable(8) [[THIS1]]) #[[ATTR4]]
+// CHECK13-NEXT: call void @_ZN2StC2Ev(ptr noundef nonnull align 4 dereferenceable(8) [[THIS1]])
// CHECK13-NEXT: ret void
//
//
@@ -2813,7 +2813,7 @@ int main() {
// CHECK13-NEXT: store ptr [[T]], ptr [[T_INDIRECT_ADDR]], align 8
// CHECK13-NEXT: [[THIS1:%.*]] = load ptr, ptr [[THIS_ADDR]], align 8
// CHECK13-NEXT: [[TMP0:%.*]] = load ptr, ptr [[S_ADDR]], align 8
-// CHECK13-NEXT: call void @_ZN1SIfEC2ERKS0_2St(ptr noundef nonnull align 4 dereferenceable(4) [[THIS1]], ptr noundef nonnull align 4 dereferenceable(4) [[TMP0]], ptr noundef [[T]]) #[[ATTR4]]
+// CHECK13-NEXT: call void @_ZN1SIfEC2ERKS0_2St(ptr noundef nonnull align 4 dereferenceable(4) [[THIS1]], ptr noundef nonnull align 4 dereferenceable(4) [[TMP0]], ptr noundef [[T]])
// CHECK13-NEXT: ret void
//
//
@@ -2823,7 +2823,7 @@ int main() {
// CHECK13-NEXT: [[THIS_ADDR:%.*]] = alloca ptr, align 8
// CHECK13-NEXT: store ptr [[THIS]], ptr [[THIS_ADDR]], align 8
// CHECK13-NEXT: [[THIS1:%.*]] = load ptr, ptr [[THIS_ADDR]], align 8
-// CHECK13-NEXT: call void @_ZN2StD2Ev(ptr noundef nonnull align 4 dereferenceable(8) [[THIS1]]) #[[ATTR5]]
+// CHECK13-NEXT: call void @_ZN2StD2Ev(ptr noundef nonnull align 4 dereferenceable(8) [[THIS1]]) #[[ATTR3]]
// CHECK13-NEXT: ret void
//
//
@@ -2881,17 +2881,17 @@ int main() {
// CHECK13: omp.arraycpy.body:
// CHECK13-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi ptr [ [[TMP1]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
// CHECK13-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi ptr [ [[ARRAY_BEGIN]], [[ENTRY]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
-// CHECK13-NEXT: call void @_ZN2StC1Ev(ptr noundef nonnull align 4 dereferenceable(8) [[AGG_TMP]]) #[[ATTR4]]
-// CHECK13-NEXT: call void @_ZN1SIfEC1ERKS0_2St(ptr noundef nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST]], ptr noundef nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST]], ptr noundef [[AGG_TMP]]) #[[ATTR4]]
-// CHECK13-NEXT: call void @_ZN2StD1Ev(ptr noundef nonnull align 4 dereferenceable(8) [[AGG_TMP]]) #[[ATTR5]]
+// CHECK13-NEXT: call void @_ZN2StC1Ev(ptr noundef nonnull align 4 dereferenceable(8) [[AGG_TMP]])
+// CHECK13-NEXT: call void @_ZN1SIfEC1ERKS0_2St(ptr noundef nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST]], ptr noundef nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST]], ptr noundef [[AGG_TMP]])
+// CHECK13-NEXT: call void @_ZN2StD1Ev(ptr noundef nonnull align 4 dereferenceable(8) [[AGG_TMP]]) #[[ATTR3]]
// CHECK13-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr [[STRUCT_S]], ptr [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
// CHECK13-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr [[STRUCT_S]], ptr [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
// CHECK13-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq ptr [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP5]]
// CHECK13-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYCPY_DONE4]], label [[OMP_ARRAYCPY_BODY]]
// CHECK13: omp.arraycpy.done4:
-// CHECK13-NEXT: call void @_ZN2StC1Ev(ptr noundef nonnull align 4 dereferenceable(8) [[AGG_TMP6]]) #[[ATTR4]]
-// CHECK13-NEXT: call void @_ZN1SIfEC1ERKS0_2St(ptr noundef nonnull align 4 dereferenceable(4) [[VAR5]], ptr noundef nonnull align 4 dereferenceable(4) [[TMP2]], ptr noundef [[AGG_TMP6]]) #[[ATTR4]]
-// CHECK13-NEXT: call void @_ZN2StD1Ev(ptr noundef nonnull align 4 dereferenceable(8) [[AGG_TMP6]]) #[[ATTR5]]
+// CHECK13-NEXT: call void @_ZN2StC1Ev(ptr noundef nonnull align 4 dereferenceable(8) [[AGG_TMP6]])
+// CHECK13-NEXT: call void @_ZN1SIfEC1ERKS0_2St(ptr noundef nonnull align 4 dereferenceable(4) [[VAR5]], ptr noundef nonnull align 4 dereferenceable(4) [[TMP2]], ptr noundef [[AGG_TMP6]])
+// CHECK13-NEXT: call void @_ZN2StD1Ev(ptr noundef nonnull align 4 dereferenceable(8) [[AGG_TMP6]]) #[[ATTR3]]
// CHECK13-NEXT: [[TMP6:%.*]] = load ptr, ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK13-NEXT: [[TMP7:%.*]] = load i32, ptr [[TMP6]], align 4
// CHECK13-NEXT: call void @__kmpc_for_static_init_4(ptr @[[GLOB2:[0-9]+]], i32 [[TMP7]], i32 34, ptr [[DOTOMP_IS_LAST]], ptr [[DOTOMP_LB]], ptr [[DOTOMP_UB]], ptr [[DOTOMP_STRIDE]], i32 1, i32 1)
@@ -2948,14 +2948,14 @@ int main() {
// CHECK13-NEXT: [[TMP20:%.*]] = load ptr, ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK13-NEXT: [[TMP21:%.*]] = load i32, ptr [[TMP20]], align 4
// CHECK13-NEXT: call void @__kmpc_for_static_fini(ptr @[[GLOB2]], i32 [[TMP21]])
-// CHECK13-NEXT: call void @_ZN1SIfED1Ev(ptr noundef nonnull align 4...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/111076
More information about the cfe-commits
mailing list