[OpenMP] Expand short verisions of OpenMP offloading triples

[jhuber6]

Summary

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.

[jdoerfert]

Can we have a test? Similar to a/the test introduced with the libdevice handling.

[jhuber6]

Adding tests.

[jdoerfert]

LG

[JonChesterfield]

Wrong fix. The user typing -fopenmp-targets=amdgcn is an error, we shouldn't swallow errors here and hope the backend does something sane with the result. We should rewrite that in clang to the right triple.

This may 'work', if the correct triple is the one which wins the conflict, provided nothing triple-dependent has already happened in the IR, and we never target another OS, but that's much less robust than setting the HSA triple directly.

[arsenm]

llvm/lib/Linker/IRMover.cpp

1482

I'm a bit disturbed the linker is special casing bitcode file names

[jhuber6]

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

[JonChesterfield]

LG, thanks!

clang/lib/Driver/Driver.cpp

778 ↗

(On Diff #401357)

Might be worth mentioning in the comment that this is essentially a user convenience feature. We're not so much normalising, as treating fopenmp-target=nvtpx64 as an abbreviation for nvptx64-nvidia-cuda

llvm/lib/Linker/IRMover.cpp

Error IRLinker::run() {
   // the layout that is different from the one used by LLVM/clang (it does not
   // include i128). Issuing a warning is not very helpful as there's not much
   // the user can do about it.
   bool EnableDLWarning = true;
   bool EnableTripleWarning = true;
   if (SrcTriple.isNVPTX() && DstTriple.isNVPTX()) {
     std::string ModuleId = SrcM->getModuleIdentifier();
     StringRef FileName = llvm::sys::path::filename(ModuleId);
-    bool SrcIsLibDevice =
-        FileName.startswith("libdevice") && FileName.endswith(".10.bc");
+    bool SrcIsDeviceLib =
+        (FileName.startswith("libdevice") && FileName.endswith(".10.bc")) ||
+        (FileName.startswith("libomptarget") && FileName.endswith(".bc"));
     bool SrcHasLibDeviceDL =
         (SrcM->getDataLayoutStr().empty() ||
          SrcM->getDataLayoutStr() == "e-i64:64-v16:16-v32:32-n16:32:64");
     // libdevice bitcode uses nvptx64-nvidia-gpulibs or just
     // 'nvptx-unknown-unknown' triple (before CUDA-10.x) and is compatible with
-    // all NVPTX variants.
+    // all NVPTX variants. libomptarget bitcode uses nvptx64-nvidia-cuda.
     bool SrcHasLibDeviceTriple = (SrcTriple.getVendor() == Triple::NVIDIA &&
                                   SrcTriple.getOSName() == "gpulibs") ||
                                  (SrcTriple.getVendorName() == "unknown" &&
-                                  SrcTriple.getOSName() == "unknown");
-    EnableTripleWarning = !(SrcIsLibDevice && SrcHasLibDeviceTriple);
-    EnableDLWarning = !(SrcIsLibDevice && SrcHasLibDeviceDL);
+                                  SrcTriple.getOSName() == "unknown") ||
+                                 (SrcTriple.getVendor() == Triple::NVIDIA &&
+                                  SrcTriple.getOS() == Triple::CUDA);
+    EnableTripleWarning = !(SrcIsDeviceLib && SrcHasLibDeviceTriple);
+    EnableDLWarning = !(SrcIsDeviceLib && SrcHasLibDeviceDL);
+  } else if (SrcTriple.isAMDGPU() && DstTriple.isAMDGPU()) {
+    std::string ModuleId = SrcM->getModuleIdentifier();
+    StringRef FileName = llvm::sys::path::filename(ModuleId);
+    bool SrcIsDeviceLib =
+        (FileName.startswith("libomptarget") && FileName.endswith(".bc"));
+    // libomptarget bitcode uses an amdgcn-amd-amdhsa triple.
+    bool SrcHasLibDeviceTriple = SrcTriple.getVendor() == Triple::AMD &&
+                                 SrcTriple.getOS() == Triple::AMDHSA;
+    EnableTripleWarning = !(SrcIsDeviceLib && SrcHasLibDeviceTriple);
   }
 
   if (EnableDLWarning && (SrcM->getDataLayout() != DstM.getDataLayout())) {
     emitWarning("Linking two modules of different data layouts: '" +
                 SrcM->getModuleIdentifier() + "' is '" +
                 SrcM->getDataLayoutStr() + "' whereas '" +
                 DstM.getModuleIdentifier() + "' is '" +
                 DstM.getDataLayoutStr() + "'\n");

llvm/test/Linker/Inputs/libomptarget-amdgcn.ll

+target triple = "amdgcn-amd-amdhsa"

llvm/test/Linker/Inputs/libomptarget-nvptx.ll

+target triple = "nvptx64-nvidia-cuda"

llvm/test/Linker/libomptarget-amdgcn.ll

+; Prepare bitcode files.
+; RUN: rm -rf %t && mkdir -p %t
+; RUN: llvm-as %s -o %t/main.bc
+; RUN: llvm-as %p/Inputs/libomptarget-amdgcn.ll -o %t/libomptarget-amdgcn.bc
+; RUN: llvm-as %p/Inputs/not-a-libdevice.ll -o %t/libomptarget-wrong-info.bc
+
+; No warnings expected when we link with libomptarget variants.
+; RUN: llvm-link %t/main.bc %t/libomptarget-amdgcn.bc -S 2>&1 \
+; RUN:  | FileCheck --check-prefixes COMMON,NOWARN %s
+
+; But make sure we still issue warnings if we see unexpected filename.
+; RUN: llvm-link %t/main.bc %t/libomptarget-wrong-info.bc -S 2>&1 \
+; RUN:  | FileCheck --check-prefixes COMMON,WARN %s
+
+target triple = "amdgcn-unknown-unknown"
+
+; WARN-DAG: warning: Linking two modules of different target triples:
+; NOWARN-NOT: warning:
+; COMMON-DAG: target triple = "amdgcn-unknown-unknown"

llvm/test/Linker/libomptarget-nvptx.ll

+; Prepare bitcode files.
+; RUN: rm -rf %t && mkdir -p %t
+; RUN: llvm-as %s -o %t/main.bc
+; RUN: llvm-as %p/Inputs/libomptarget-nvptx.ll -o %t/libomptarget-nvptx.bc
+; RUN: llvm-as %p/Inputs/not-a-libdevice.ll -o %t/libomptarget-wrong-info.bc
+
+; No warnings expected when we link with libomptarget variants.
+; RUN: llvm-link %t/main.bc %t/libomptarget-nvptx.bc -S 2>&1 \
+; RUN:  | FileCheck --check-prefixes COMMON,NOWARN %s
+
+; But make sure we still issue warnings if we see unexpected filename.
+; RUN: llvm-link %t/main.bc %t/libomptarget-wrong-info.bc -S 2>&1 \
+; RUN:  | FileCheck --check-prefixes COMMON,WARN %s
+
+
+target triple = "nvptx64-unknown-unknown"
+
+; WARN-DAG: warning: Linking two modules of different target triples:
+; NOWARN-NOT: warning:
+; COMMON-DAG: target triple = "nvptx64-unknown-unknown"

openmp/libomptarget/DeviceRTL/CMakeLists.txt

add_custom_command(TARGET ${bclib_target_name} POST_BUILD
                     ${LIBOMPTARGET_LIBRARY_DIR})
 
   # Install bitcode library under the lib destination folder.
   install(FILES ${CMAKE_CURRENT_BINARY_DIR}/${bclib_name} DESTINATION "${OPENMP_INSTALL_LIBDIR}")
 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 ${amdgpu_mcpus})
   compileDeviceRTLLibrary(${mcpu} amdgpu -target amdgcn-amd-amdhsa -D__AMDGCN__ -fvisibility=default -nogpulib)
 endforeach()