clang/openmp: Fix alignment for ThreadID Address variables

[tstellar]

Summary

There are places in the runtime, like __kmp_init_indirect_csptr, which
assume these pointers are aligned to sizeof(void*), so make sure we emit
them with the correct alignment.

Fixes #62668

[arsenm]

Needs test

[tstellar]

Add test case.

[jlpeyton]

LGTM

clang/lib/CodeGen/CGOpenMPRuntime.cpp

CGF.EmitStoreOfScalar(ThreadID,
                         CGF.MakeAddrLValue(ThreadIDTemp, Int32Ty));
 
   return ThreadIDTemp;
 }
 
 llvm::Value *CGOpenMPRuntime::getCriticalRegionLock(StringRef CriticalName) {
   std::string Prefix = Twine("gomp_critical_user_", CriticalName).str();
   std::string Name = getName({Prefix, "var"});
-  return OMPBuilder.getOrCreateInternalVariable(KmpCriticalNameTy, Name);
+  llvm::GlobalVariable *G = OMPBuilder.getOrCreateInternalVariable(KmpCriticalNameTy, Name);
+  llvm::Align PtrAlign = OMPBuilder.M.getDataLayout().getPointerABIAlignment(G->getAddressSpace());
+  if (PtrAlign > llvm::Align(G->getAlignment()))
+    G->setAlignment(PtrAlign);
+  return G;
 }
 
 namespace {
 /// Common pre(post)-action for different OpenMP constructs.
 class CommonActionTy final : public PrePostActionTy {
   llvm::FunctionCallee EnterCallee;
   ArrayRef<llvm::Value *> EnterArgs;
   llvm::FunctionCallee ExitCallee;

clang/test/OpenMP/for_reduction_codegen.cpp

-// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --function-signature --include-generated-funcs --replace-value-regex "__omp_offloading_[0-9a-z]+_[0-9a-z]+" "reduction_size[.].+[.]" "pl_cond[.].+[.|,]" --prefix-filecheck-ir-name _
+// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --function-signature --check-globals --include-generated-funcs --replace-value-regex "__omp_offloading_[0-9a-z]+_[0-9a-z]+" "reduction_size[.].+[.]" "pl_cond[.].+[.|,]" --prefix-filecheck-ir-name _ --global-value-regex ".gomp_critical_user[a-zA-Z_.]+"
 // RUN: %clang_cc1 -verify -fopenmp -x c++ -triple x86_64-apple-darwin10 -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix=CHECK1
 // RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple x86_64-apple-darwin10 -emit-pch -o %t %s
 // RUN: %clang_cc1 -fopenmp -x c++ -triple x86_64-apple-darwin10 -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix=CHECK1
 // RUN: %clang_cc1 -verify -fopenmp -x c++ -std=c++11 -DLAMBDA -triple x86_64-apple-darwin10 -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix=CHECK3
 // RUN: %clang_cc1 -verify -fopenmp -x c++ -fblocks -DBLOCKS -triple x86_64-apple-darwin10 -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix=CHECK4
 
 // RUN: %clang_cc1 -verify -fopenmp-simd -x c++ -triple x86_64-apple-darwin10 -emit-llvm %s -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
 // RUN: %clang_cc1 -fopenmp-simd -x c++ -std=c++11 -triple x86_64-apple-darwin10 -emit-pch -o %t %s

 
 
 // Reduction list for runtime.
 
 
 
 
 #endif
+//.
+// CHECK1: @.gomp_critical_user_.reduction.var = common global [8 x i32] zeroinitializer, align 8
+// CHECK1: @.gomp_critical_user_.atomic_reduction.var = common global [8 x i32] zeroinitializer, align 8
+//.
+// CHECK3: @.gomp_critical_user_.reduction.var = common global [8 x i32] zeroinitializer, align 8
+//.
+// CHECK4: @.gomp_critical_user_.reduction.var = common global [8 x i32] zeroinitializer, align 8
+//.
 // CHECK1-LABEL: define {{[^@]+}}@main
 // CHECK1-SAME: () #[[ATTR0:[0-9]+]] {
 // CHECK1-NEXT:  entry:
 // CHECK1-NEXT:    [[RETVAL:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[TEST:%.*]] = alloca [[STRUCT_S:%.*]], align 4
 // CHECK1-NEXT:    [[T_VAR:%.*]] = alloca float, align 4
 // CHECK1-NEXT:    [[T_VAR1:%.*]] = alloca float, align 4
 // CHECK1-NEXT:    [[VEC:%.*]] = alloca [2 x i32], align 4