[libomptarget] Change nvcc compilation to use a unity build

Summary:
[libomptarget] Change nvcc compilation to use a unity build

This allows nvcc to inline functions between what would otherwise be distinct
translation units, which in turn removes any runtime cost from implementing
functions in source files (as opposed to inline in headers).

This will then allow the circular dependencies in deviceRTL to be readily
broken and individual components more easily shared between architectures.

Reviewers: ABataev, jdoerfert, grokos, RaviNarayanaswamy, hfinkel, ronlieb, gregrodgers

Reviewed By: jdoerfert

Subscribers: mgorny, openmp-commits

Tags: #openmp

Differential Revision: https://reviews.llvm.org/D69489

2 files changed, 26 insertions, 1 deletions

diff --git a/openmp/libomptarget/deviceRTLs/nvptx/CMakeLists.txt b/openmp/libomptarget/deviceRTLs/nvptx/CMakeLists.txt
index 1cd13c50395..caf02d62c59 100644
--- a/openmp/libomptarget/deviceRTLs/nvptx/CMakeLists.txt
+++ b/openmp/libomptarget/deviceRTLs/nvptx/CMakeLists.txt
@@ -88,7 +88,7 @@ if(LIBOMPTARGET_DEP_CUDA_FOUND)
   set(BUILD_SHARED_LIBS OFF)
   set(CUDA_SEPARABLE_COMPILATION ON)
   list(APPEND CUDA_NVCC_FLAGS -I${devicertl_base_directory})
-  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.
diff --git a/openmp/libomptarget/deviceRTLs/nvptx/unity.cu b/openmp/libomptarget/deviceRTLs/nvptx/unity.cu
new file mode 100644
index 00000000000..b6cfd0d8b9a
--- /dev/null
+++ b/openmp/libomptarget/deviceRTLs/nvptx/unity.cu
@@ -0,0 +1,25 @@
+//===------ 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 preventing efficient incremental builds.
+//
+//===----------------------------------------------------------------------===//
+
+#include "src/cancel.cu"
+#include "src/critical.cu"
+#include "src/data_sharing.cu"
+#include "src/libcall.cu"
+#include "src/loop.cu"
+#include "src/omp_data.cu"
+#include "src/omptarget-nvptx.cu"
+#include "src/parallel.cu"
+#include "src/reduction.cu"
+#include "src/sync.cu"
+#include "src/task.cu"