[OpenMP] Expand short verisions of OpenMP offloading triples

The OpenMP offloading libraries are built with fixed triples and linked
in during compile time. This would cause un-helpful errors if the user
passed in the wrong expansion of the triple used for the bitcode
library. because we only support these triples for OpenMP offloading we
can normalize them to the full verion used in the bitcode library.

Reviewed By: jdoerfert, JonChesterfield

Differential Revision: https://reviews.llvm.org/D117634

diff --git a/clang/lib/Driver/Driver.cpp b/clang/lib/Driver/Driver.cpp
index 82d67a8..c7314e1 100644 (file)
--- a/clang/lib/Driver/Driver.cpp
+++ b/clang/lib/Driver/Driver.cpp
@@ -774,6 +774,18 @@ void Driver::CreateOffloadingDeviceToolChains(Compilation &C,
           llvm::Triple TT(Val);
           std::string NormalizedName = TT.normalize();
 
+          // We want to expand the shortened versions of the triples passed in to
+          // the values used for the bitcode libraries for convenience.
+          if (TT.getVendor() == llvm::Triple::UnknownVendor ||
+              TT.getOS() == llvm::Triple::UnknownOS) {
+            if (TT.getArch() == llvm::Triple::nvptx)
+              TT = llvm::Triple("nvptx-nvidia-cuda");
+            else if (TT.getArch() == llvm::Triple::nvptx64)
+              TT = llvm::Triple("nvptx64-nvidia-cuda");
+            else if (TT.getArch() == llvm::Triple::amdgcn)
+              TT = llvm::Triple("amdgcn-amd-amdhsa");
+          }
+
           // Make sure we don't have a duplicate triple.
           auto Duplicate = FoundNormalizedTriples.find(NormalizedName);
           if (Duplicate != FoundNormalizedTriples.end()) {

diff --git a/clang/test/Driver/fat_archive_nvptx.cpp b/clang/test/Driver/fat_archive_nvptx.cpp
index 4c93752..a46c44f 100644 (file)
--- a/clang/test/Driver/fat_archive_nvptx.cpp
+++ b/clang/test/Driver/fat_archive_nvptx.cpp
@@ -6,9 +6,9 @@
 
 // Given a FatArchive, clang-offload-bundler should be called to create a
 // device specific archive, which should be passed to clang-nvlink-wrapper.
-// RUN: %clang -O2 -### -fopenmp -fopenmp-targets=nvptx64 %s -L%S/Inputs/openmp_static_device_link -lFatArchive 2>&1 | FileCheck %s
-// CHECK: clang{{.*}}"-cc1"{{.*}}"-triple" "nvptx64"{{.*}}"-target-cpu" "[[GPU:sm_[0-9]+]]"{{.*}}"-o" "[[HOSTBC:.*.s]]" "-x" "c++"{{.*}}.cpp
-// CHECK: clang-offload-bundler" "-unbundle" "-type=a" "-inputs={{.*}}/Inputs/openmp_static_device_link/libFatArchive.a" "-targets=openmp-nvptx64-[[GPU]]" "-outputs=[[DEVICESPECIFICARCHIVE:.*.a]]" "-allow-missing-bundles"
+// RUN: %clang -O2 -### -fopenmp -fopenmp-targets=nvptx64-nvidia-cuda %s -L%S/Inputs/openmp_static_device_link -lFatArchive 2>&1 | FileCheck %s
+// CHECK: clang{{.*}}"-cc1"{{.*}}"-triple" "nvptx64-nvidia-cuda"{{.*}}"-target-cpu" "[[GPU:sm_[0-9]+]]"{{.*}}"-o" "[[HOSTBC:.*.s]]" "-x" "c++"{{.*}}.cpp
+// CHECK: clang-offload-bundler" "-unbundle" "-type=a" "-inputs={{.*}}/Inputs/openmp_static_device_link/libFatArchive.a" "-targets=openmp-nvptx64-nvidia-cuda-[[GPU]]" "-outputs=[[DEVICESPECIFICARCHIVE:.*.a]]" "-allow-missing-bundles"
 // CHECK: clang-nvlink-wrapper{{.*}}"-o" "{{.*}}.out" "-arch" "[[GPU]]" "{{.*}}[[DEVICESPECIFICARCHIVE]]"
 // expected-no-diagnostics
 
@@ -72,8 +72,8 @@ void func_present(float* in, float* out, unsigned n){
     clang -O2 -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx908 -c func_1.c -o func_1_gfx908.o
     clang -O2 -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx906 -c func_2.c -o func_2_gfx906.o
     clang -O2 -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx908 -c func_2.c -o func_2_gfx908.o
-    clang -O2 -fopenmp -fopenmp-targets=nvptx64 -c func_1.c -o func_1_nvptx.o
-    clang -O2 -fopenmp -fopenmp-targets=nvptx64 -c func_2.c -o func_2_nvptx.o
+    clang -O2 -fopenmp -fopenmp-targets=nvptx64-nvidia-cuda -c func_1.c -o func_1_nvptx.o
+    clang -O2 -fopenmp -fopenmp-targets=nvptx64-nvidia-cuda -c func_2.c -o func_2_nvptx.o
 
 2. Create a fat archive by combining all the object file(s)
     llvm-ar cr libFatArchive.a func_1_gfx906.o func_1_gfx908.o func_2_gfx906.o func_2_gfx908.o func_1_nvptx.o func_2_nvptx.o

diff --git a/openmp/libomptarget/DeviceRTL/CMakeLists.txt b/openmp/libomptarget/DeviceRTL/CMakeLists.txt
index a3c6536..8185727 100644 (file)
--- a/openmp/libomptarget/DeviceRTL/CMakeLists.txt
+++ b/openmp/libomptarget/DeviceRTL/CMakeLists.txt
@@ -227,7 +227,7 @@ endfunction()
 
 # Generate a Bitcode library for all the compute capabilities the user requested
 foreach(sm ${nvptx_sm_list})
-  compileDeviceRTLLibrary(sm_${sm} nvptx -target nvptx64 -Xclang -target-feature -Xclang +ptx61 "-D__CUDA_ARCH__=${sm}0")
+  compileDeviceRTLLibrary(sm_${sm} nvptx -target nvptx64-nvidia-cuda -Xclang -target-feature -Xclang +ptx61 "-D__CUDA_ARCH__=${sm}0")
 endforeach()
 
 foreach(mcpu ${amdgpu_mcpus})