[OPENMP][NVPTX]Correct codegen for 128 bit long double.

If the host uses 128 bit long doubles, the compiler should generate correct code for NVPTX devices. If the return type has 128 bit long doubles, in LLVM IR this type must be coerced to int array instead.

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@363720 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/CodeGen/TargetInfo.cpp b/lib/CodeGen/TargetInfo.cpp
index 707425ea813057d566912a9653893c99166194e3..b1ff46049facd78c08dd55e331211c4e89e49bf2 100644 (file)
--- a/lib/CodeGen/TargetInfo.cpp
+++ b/lib/CodeGen/TargetInfo.cpp
@@ -6330,7 +6330,9 @@ private:
 static bool isUnsupportedType(ASTContext &Context, QualType T) {
   if (!Context.getTargetInfo().hasFloat16Type() && T->isFloat16Type())
     return true;
-  if (!Context.getTargetInfo().hasFloat128Type() && T->isFloat128Type())
+  if (!Context.getTargetInfo().hasFloat128Type() &&
+      (T->isFloat128Type() ||
+       (T->isRealFloatingType() && Context.getTypeSize(T) == 128)))
     return true;
   if (!Context.getTargetInfo().hasInt128Type() && T->isIntegerType() &&
       Context.getTypeSize(T) > 64)

diff --git a/test/OpenMP/nvptx_unsupported_type_codegen.cpp b/test/OpenMP/nvptx_unsupported_type_codegen.cpp
index 167496cb84fcb7fabd7c658f278e52bd8d140536..2573daaa4184200f3009886fbd46ec1bfcd2a7a5 100644 (file)
--- a/test/OpenMP/nvptx_unsupported_type_codegen.cpp
+++ b/test/OpenMP/nvptx_unsupported_type_codegen.cpp
@@ -1,6 +1,8 @@
 // Test target codegen - host bc file has to be created first.
 // RUN: %clang_cc1 -verify -fopenmp -x c++ -triple x86_64-unknown-linux -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-host.bc
-// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -aux-triple x86_64-unknown-linux -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-host.bc -o - | FileCheck %s
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx64-unknown-unknown -aux-triple x86_64-unknown-linux -fopenmp-targets=nvptx64-nvidia-cuda -aux-triple x86_64-unknown-linux -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-host.bc -o - | FileCheck %s
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple powerpc64le-unknown-linux-gnu -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-host.bc
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx64-unknown-unknown -aux-triple powerpc64le-unknown-linux-gnu -fopenmp-targets=nvptx64-nvidia-cuda -aux-triple x86_64-unknown-linux -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-host.bc -o - | FileCheck %s
 // expected-no-diagnostics
 
 // CHECK-DAG: [[T:%.+]] = type {{.+}}, fp128,
@@ -8,7 +10,11 @@
 
 struct T {
   char a;
+#ifndef _ARCH_PPC
   __float128 f;
+#else
+  long double f;
+#endif
   char c;
   T() : a(12), f(15) {}
   T &operator+(T &b) { f += b.a; return *this;}