intel/llvm
1
0
Fork 0
mirror of https://github.com/intel/llvm.git synced 2026-02-03 10:39:35 +08:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source 
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.

llvm-svn: 363720
This commit is contained in:
Alexey Bataev
2019-06-18 19:04:27 +00:00
parent 10e6128c62
commit 7ae267dc0f
2 changed files with 10 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
clang/lib/CodeGen/TargetInfo.cpp
View File

@@ -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)

8
clang/test/OpenMP/nvptx_unsupported_type_codegen.cpp
View File

@@ -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;}