[OPENMP]Fix PR46146: Do not consider globalized variables as NRVO candidates.

Summary:
If the variables must be globalized in OpenMP mode (local automatic
variable, GPU compilation mode, the variable may escape its declaration
context by the reference or by the pointer), it should not be considered
as the NRVO candidate. Otherwise, incorrect the return value of the
function might not be updated.

Reviewers: jdoerfert

Subscribers: yaxunl, guansong, sstefan1, cfe-commits, caomhin

Tags: #clang

Differential Revision: https://reviews.llvm.org/D80936

diff --git a/clang/lib/CodeGen/CGStmt.cpp b/clang/lib/CodeGen/CGStmt.cpp
index 3559e77..cccb15a 100644 (file)
--- a/clang/lib/CodeGen/CGStmt.cpp
+++ b/clang/lib/CodeGen/CGStmt.cpp
@@ -11,6 +11,7 @@
 //===----------------------------------------------------------------------===//
 
 #include "CGDebugInfo.h"
+#include "CGOpenMPRuntime.h"
 #include "CodeGenFunction.h"
 #include "CodeGenModule.h"
 #include "TargetInfo.h"
@@ -1106,8 +1107,13 @@ void CodeGenFunction::EmitReturnStmt(const ReturnStmt &S) {
 
   // FIXME: Clean this up by using an LValue for ReturnTemp,
   // EmitStoreThroughLValue, and EmitAnyExpr.
-  if (getLangOpts().ElideConstructors &&
-      S.getNRVOCandidate() && S.getNRVOCandidate()->isNRVOVariable()) {
+  // Check if the NRVO candidate was not globalized in OpenMP mode.
+  if (getLangOpts().ElideConstructors && S.getNRVOCandidate() &&
+      S.getNRVOCandidate()->isNRVOVariable() &&
+      (!getLangOpts().OpenMP ||
+       !CGM.getOpenMPRuntime()
+            .getAddressOfLocalVariable(*this, S.getNRVOCandidate())
+            .isValid())) {
     // Apply the named return value optimization for this return statement,
     // which means doing nothing: the appropriate result has already been
     // constructed into the NRVO variable.

diff --git a/clang/test/OpenMP/nvptx_NRVO_variable.cpp b/clang/test/OpenMP/nvptx_NRVO_variable.cpp
new file mode 100644 (file)
index 0000000..9bbe5d0
--- /dev/null
+++ b/clang/test/OpenMP/nvptx_NRVO_variable.cpp
@@ -0,0 +1,30 @@
+// Test target codegen - host bc file has to be created first.
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s
+// expected-no-diagnostics
+#ifndef HEADER
+#define HEADER
+
+struct S {
+  int a;
+  S() : a(1) {}
+};
+
+#pragma omp declare target
+void bar(S &);
+// CHECK-LABEL: foo
+S foo() {
+  // CHECK: [[RETVAL:%.+]] = alloca %struct.S,
+  S s;
+  // CHECK: call void @{{.+}}bar{{.+}}(%struct.S* {{.*}}[[S_REF:%.+]])
+  bar(s);
+  // CHECK: [[DEST:%.+]] = bitcast %struct.S* [[RETVAL]] to i8*
+  // CHECK: [[SOURCE:%.+]] = bitcast %struct.S* [[S_REF]] to i8*
+  // CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* {{.*}}[[DEST]], i8* {{.*}}[[SOURCE]], i64 4, i1 false)
+  // CHECK: [[VAL:%.+]] = load %struct.S, %struct.S* [[RETVAL]],
+  // CHECK: ret %struct.S [[VAL]]
+  return s;
+}
+#pragma omp end declare target
+
+#endif