[PATCH] D117634: [OpenMP] Expand short verisions of OpenMP offloading triples

[Joseph Huber via Phabricator via cfe-commits]

jhuber6 updated this revision to Diff 401357.
jhuber6 edited the summary of this revision.
jhuber6 added a comment.
Herald added a project: clang.
Herald added a subscriber: cfe-commits.

Changing approach to simply expand the triple where we parse it for OpenMP.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D117634/new/

https://reviews.llvm.org/D117634

Files:
  clang/lib/Driver/Driver.cpp
  clang/test/Driver/fat_archive_nvptx.cpp
  openmp/libomptarget/DeviceRTL/CMakeLists.txt


Index: openmp/libomptarget/DeviceRTL/CMakeLists.txt
===================================================================
--- openmp/libomptarget/DeviceRTL/CMakeLists.txt
+++ openmp/libomptarget/DeviceRTL/CMakeLists.txt
@@ -227,7 +227,7 @@
 
 # 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})
Index: clang/test/Driver/fat_archive_nvptx.cpp
===================================================================
--- clang/test/Driver/fat_archive_nvptx.cpp
+++ 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 @@
     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
Index: clang/lib/Driver/Driver.cpp
===================================================================
--- clang/lib/Driver/Driver.cpp
+++ clang/lib/Driver/Driver.cpp
@@ -774,6 +774,18 @@
           llvm::Triple TT(Val);
           std::string NormalizedName = TT.normalize();
 
+          // We want to normalize the shortened versions of triples passed in to
+          // the values used for the bitcode libraries.
+          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()) {


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D117634.401357.patch
Type: text/x-patch
Size: 4246 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/cfe-commits/attachments/20220119/cdfb7d66/attachment.bin>