[clang] eaee608 - [OpenMP] Use __OPENMP_NVPTX__ instead of _OPENMP in complex wrapper headers.

[Joachim Meyer via cfe-commits]

Author: Joachim Meyer
Date: 2020-10-29T23:24:49+01:00
New Revision: eaee608448c832e8f806faae30ae4100620c4688

URL: https://github.com/llvm/llvm-project/commit/eaee608448c832e8f806faae30ae4100620c4688
DIFF: https://github.com/llvm/llvm-project/commit/eaee608448c832e8f806faae30ae4100620c4688.diff

LOG: [OpenMP] Use __OPENMP_NVPTX__ instead of _OPENMP in complex wrapper headers.

This is very similar to 7f1e6fcff942, just fixing a left-over.
With this, it should be possible to use both, -x cuda and -fopenmp in the same invocation,
enabling to use both OpenMP, targeting CPU, and CUDA, targeting the GPU.

Reviewed By: jdoerfert

Differential Revision: https://reviews.llvm.org/D90415

Added: 
    

Modified: 
    clang/lib/Headers/__clang_cuda_complex_builtins.h
    clang/lib/Headers/openmp_wrappers/complex
    clang/lib/Headers/openmp_wrappers/complex.h

Removed: 
    


################################################################################
diff  --git a/clang/lib/Headers/__clang_cuda_complex_builtins.h b/clang/lib/Headers/__clang_cuda_complex_builtins.h
index 9b254f700b9d..2b701fef0ea2 100644
--- a/clang/lib/Headers/__clang_cuda_complex_builtins.h
+++ b/clang/lib/Headers/__clang_cuda_complex_builtins.h
@@ -16,7 +16,7 @@
 // to work with CUDA and OpenMP target offloading [in C and C++ mode].)
 
 #pragma push_macro("__DEVICE__")
-#ifdef _OPENMP
+#ifdef __OPENMP_NVPTX__
 #pragma omp declare target
 #define __DEVICE__ __attribute__((noinline, nothrow, cold, weak))
 #else
@@ -26,7 +26,7 @@
 // To make the algorithms available for C and C++ in CUDA and OpenMP we select
 // 
diff erent but equivalent function versions. TODO: For OpenMP we currently
 // select the native builtins as the overload support for templates is lacking.
-#if !defined(_OPENMP)
+#if !defined(__OPENMP_NVPTX__)
 #define _ISNANd std::isnan
 #define _ISNANf std::isnan
 #define _ISINFd std::isinf
@@ -276,7 +276,7 @@ __DEVICE__ float _Complex __divsc3(float __a, float __b, float __c, float __d) {
 #undef _fmaxd
 #undef _fmaxf
 
-#ifdef _OPENMP
+#ifdef __OPENMP_NVPTX__
 #pragma omp end declare target
 #endif
 

diff  --git a/clang/lib/Headers/openmp_wrappers/complex b/clang/lib/Headers/openmp_wrappers/complex
index 306ffe208053..142e526b81b3 100644
--- a/clang/lib/Headers/openmp_wrappers/complex
+++ b/clang/lib/Headers/openmp_wrappers/complex
@@ -18,7 +18,9 @@
 #include <cmath>
 
 #define __CUDA__
+#define __OPENMP_NVPTX__
 #include <__clang_cuda_complex_builtins.h>
+#undef __OPENMP_NVPTX__
 #endif
 
 // Grab the host header too.

diff  --git a/clang/lib/Headers/openmp_wrappers/complex.h b/clang/lib/Headers/openmp_wrappers/complex.h
index 829c7a785725..00d278548f82 100644
--- a/clang/lib/Headers/openmp_wrappers/complex.h
+++ b/clang/lib/Headers/openmp_wrappers/complex.h
@@ -18,7 +18,9 @@
 #include <math.h>
 
 #define __CUDA__
+#define __OPENMP_NVPTX__
 #include <__clang_cuda_complex_builtins.h>
+#undef __OPENMP_NVPTX__
 #endif
 
 // Grab the host header too.