[OpenMP][NVPTX] Drop dependence on CUDA to build NVPTX deviceRTLs

With D94745, we no longer use CUDA SDK to compile `deviceRTLs`. Therefore,
many CMake code in the project is useless. This patch cleans up unnecessary code
and also drops the requirement to build NVPTX `deviceRTLs`. CUDA detection is
still being used however to determine whether we need to involve the tests. Auto
detection of compute capability is enabled by default and can be disabled by
setting CMake variable `LIBOMPTARGET_NVPTX_AUTODETECT_COMPUTE_CAPABILITY=OFF`.
If auto detection is enabled, and CUDA is also valid, it will only build the
bitcode library for the detected version; otherwise, all variants supported will
be generated. One drawback of this patch is, we now generate 96 variants of
bitcode library, and totally 1485 files to be built with a clean build on a
non-CUDA system. `LIBOMPTARGET_NVPTX_COMPUTE_CAPABILITIES=""` can be used to
disable building NVPTX `deviceRTLs`.

Reviewed By: JonChesterfield

Differential Revision: https://reviews.llvm.org/D95466

Author: shiltian

openmp/README.rst

@@ -281,7 +281,7 @@ Options for ``NVPTX device RTL``
 
  **LIBOMPTARGET_NVPTX_COMPUTE_CAPABILITIES** = ``35``
   List of CUDA compute capabilities that should be supported by the NVPTX
-  device RTL. E.g. for compute capabilities 6.0 and 7.0, the option "60,70"
+  device RTL. E.g. for compute capabilities 6.0 and 7.0, the option "60;70"
   should be used. Compute capability 3.5 is the minimum required.
 
  **LIBOMPTARGET_NVPTX_DEBUG** = ``OFF|ON``

openmp/libomptarget/cmake/Modules/LibomptargetGetDependencies.cmake

@@ -12,7 +12,7 @@
 # components of libomptarget. These are the dependencies we have:
 #
 # libelf : required by some targets to handle the ELF files at runtime.
-# libffi : required to launch target kernels given function and argument 
+# libffi : required to launch target kernels given function and argument
 #          pointers.
 # CUDA : required to control offloading to NVIDIA GPUs.
 # VEOS : required to control offloading to NEC Aurora.
@@ -47,18 +47,18 @@ find_library (
     /sw/lib
     ENV LIBRARY_PATH
     ENV LD_LIBRARY_PATH)
-    
+
 set(LIBOMPTARGET_DEP_LIBELF_INCLUDE_DIRS ${LIBOMPTARGET_DEP_LIBELF_INCLUDE_DIR})
 find_package_handle_standard_args(
-  LIBOMPTARGET_DEP_LIBELF 
+  LIBOMPTARGET_DEP_LIBELF
   DEFAULT_MSG
   LIBOMPTARGET_DEP_LIBELF_LIBRARIES
   LIBOMPTARGET_DEP_LIBELF_INCLUDE_DIRS)
 
 mark_as_advanced(
-  LIBOMPTARGET_DEP_LIBELF_INCLUDE_DIRS 
+  LIBOMPTARGET_DEP_LIBELF_INCLUDE_DIRS
   LIBOMPTARGET_DEP_LIBELF_LIBRARIES)
-  
+
 ################################################################################
 # Looking for libffi...
 ################################################################################
@@ -100,15 +100,15 @@ endif()
 
 set(LIBOMPTARGET_DEP_LIBFFI_INCLUDE_DIRS ${LIBOMPTARGET_DEP_LIBFFI_INCLUDE_DIR})
 find_package_handle_standard_args(
-  LIBOMPTARGET_DEP_LIBFFI 
+  LIBOMPTARGET_DEP_LIBFFI
   DEFAULT_MSG
   LIBOMPTARGET_DEP_LIBFFI_LIBRARIES
   LIBOMPTARGET_DEP_LIBFFI_INCLUDE_DIRS)
 
 mark_as_advanced(
-  LIBOMPTARGET_DEP_LIBFFI_INCLUDE_DIRS 
+  LIBOMPTARGET_DEP_LIBFFI_INCLUDE_DIRS
   LIBOMPTARGET_DEP_LIBFFI_LIBRARIES)
-  
+
 ################################################################################
 # Looking for CUDA...
 ################################################################################
@@ -118,7 +118,9 @@ endif()
 find_package(CUDA QUIET)
 
 # Try to get the highest Nvidia GPU architecture the system supports
-if (CUDA_FOUND)
+set(LIBOMPTARGET_NVPTX_AUTODETECT_COMPUTE_CAPABILITY TRUE CACHE BOOL
+  "Auto detect CUDA Compute Capability if CUDA is detected.")
+if (CUDA_FOUND AND LIBOMPTARGET_NVPTX_AUTODETECT_COMPUTE_CAPABILITY)
   cuda_select_nvcc_arch_flags(CUDA_ARCH_FLAGS)
   string(REGEX MATCH "sm_([0-9]+)" CUDA_ARCH_MATCH_OUTPUT ${CUDA_ARCH_FLAGS})
   if (NOT DEFINED CUDA_ARCH_MATCH_OUTPUT OR "${CMAKE_MATCH_1}" LESS 35)
@@ -133,7 +135,7 @@ set(LIBOMPTARGET_DEP_CUDA_FOUND ${CUDA_FOUND})
 set(LIBOMPTARGET_DEP_CUDA_INCLUDE_DIRS ${CUDA_INCLUDE_DIRS})
 
 mark_as_advanced(
-  LIBOMPTARGET_DEP_CUDA_FOUND 
+  LIBOMPTARGET_DEP_CUDA_FOUND
   LIBOMPTARGET_DEP_CUDA_INCLUDE_DIRS)
 
 ################################################################################