[libomptarget][nfc] Use unity build for nvcc to approximate LTO

[JonChesterfield]

Summary

[libomptarget][nfc] Use unity build for nvcc to approximate LTO

Nvcc doesn't support link time optimization. Including all the source
into one file is common in games dev where it is called a unity build.
The advantage is that moving functions from header to source no longer
carries a performance penalty.

A secondary advantage is we'll be able to rename the C++ files to .cpp
without confusing nvcc, provided unity.cu retains the current suffix.

This is a NFC if there are no bugs in nvcc. As there may be, I'm hoping
a reviewer will run a larger out of tree test suite against this patch.
The in tree ones pass.

openmp/libomptarget/deviceRTLs/nvptx/CMakeLists.txt

 
 if(LIBOMPTARGET_DEP_CUDA_FOUND)
   libomptarget_say("Building CUDA offloading device RTL.")
 
   # We really don't have any host code, so we don't need to care about
   # propagating host flags.
   set(CUDA_PROPAGATE_HOST_FLAGS OFF)
 
+  # Note: These files are also listed in unity.cu
   set(cuda_src_files
       ${devicertl_common_directory}/src/cancel.cu
       ${devicertl_common_directory}/src/critical.cu
       ${devicertl_common_directory}/src/data_sharing.cu
       ${devicertl_common_directory}/src/libcall.cu
       ${devicertl_common_directory}/src/loop.cu
       ${devicertl_common_directory}/src/omptarget.cu
       ${devicertl_common_directory}/src/parallel.cu
if(LIBOMPTARGET_DEP_CUDA_FOUND)
   endif()
 
   # NVPTX runtime library has to be statically linked. Dynamic linking is not
   # yet supported by the CUDA toolchain on the device.
   set(BUILD_SHARED_LIBS OFF)
   set(CUDA_SEPARABLE_COMPILATION ON)
   list(APPEND CUDA_NVCC_FLAGS -I${devicertl_base_directory}
                               -I${devicertl_nvptx_directory}/src)
-  cuda_add_library(omptarget-nvptx STATIC ${cuda_src_files} ${omp_data_objects}
+  cuda_add_library(omptarget-nvptx STATIC unity.cu
       OPTIONS ${CUDA_ARCH} ${CUDA_DEBUG})
 
   # Install device RTL under the lib destination folder.
   install(TARGETS omptarget-nvptx ARCHIVE DESTINATION "${OPENMP_INSTALL_LIBDIR}")
 
   target_link_libraries(omptarget-nvptx ${CUDA_LIBRARIES})
 
 

openmp/libomptarget/deviceRTLs/nvptx/unity.cu

+//===------ unity.cu - Unity build of NVPTX deviceRTL ------------ CUDA -*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+// Support compilers, specifically NVCC, which have not implemented link time
+// optimisation. This removes the runtime cost of moving inline functions into
+// source files in exchange for negligible build overhead.
+//
+//===----------------------------------------------------------------------===//
+
+#include "common/src/cancel.cu"
+#include "common/src/critical.cu"
+#include "common/src/data_sharing.cu"
+#include "common/src/libcall.cu"
+#include "common/src/loop.cu"
+#include "common/src/omp_data.cu"
+#include "common/src/omptarget.cu"
+#include "common/src/parallel.cu"
+#include "common/src/reduction.cu"
+#include "common/src/support.cu"
+#include "common/src/sync.cu"
+#include "common/src/task.cu"
+#include "src/target_impl.cu"