[OpenMP][NVPTX] Refined CMake logic to choose compute capabilites

[tianshilei1992]

Summary

This patch refines the logic to choose compute capabilites via the
environment variable LIBOMPTARGET_NVPTX_COMPUTE_CAPABILITIES. It supports the
following values (all case insensitive):

• "all": Build deviceRTLs for all supported compute capabilites;
• "auto": Only build for the compute capability auto detected. Note that this requires CUDA. If CUDA is not found, a CMake fatal error will be raised.
• "xx,yy" or "xx;yy": Build for compute capabilities xx and yy.

If LIBOMPTARGET_NVPTX_COMPUTE_CAPABILITIES is not set, it is equivalent to set
it to all.

[jdoerfert]

openmp/libomptarget/deviceRTLs/nvptx/CMakeLists.txt

103

Ye said before we probably don't want this so new capabilities can be compiled for in the future. I guess a warning is better.

[tianshilei1992]

comments

[jdoerfert]

LG

openmp/libomptarget/cmake/Modules/LibomptargetGetDependencies.cmake

 # Looking for CUDA...
 ################################################################################
 if (CUDA_TOOLKIT_ROOT_DIR)
   set(LIBOMPTARGET_CUDA_TOOLKIT_ROOT_DIR_PRESET TRUE)
 endif()
 find_package(CUDA QUIET)
 
 # Try to get the highest Nvidia GPU architecture the system supports
-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)
+if (CUDA_FOUND)
   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)
     libomptarget_warning_say("Setting Nvidia GPU architecture support for OpenMP target runtime library to sm_35 by default")
     set(LIBOMPTARGET_DEP_CUDA_ARCH "35")
   else()
     set(LIBOMPTARGET_DEP_CUDA_ARCH "${CMAKE_MATCH_1}")
   endif()

openmp/libomptarget/deviceRTLs/nvptx/CMakeLists.txt

 ##===----------------------------------------------------------------------===##
 #
 # 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
 #
 ##===----------------------------------------------------------------------===##
 #
 # Build the NVPTX (CUDA) Device RTL if the CUDA tools are available
 #
 ##===----------------------------------------------------------------------===##
 
-# By default we will not build NVPTX deviceRTL on a non-CUDA
+# By default we will not build NVPTX deviceRTL on a CUDA free system
 set(LIBOMPTARGET_BUILD_NVPTX_BCLIB FALSE CACHE BOOL
-  "Whether build NVPTX deviceRTL on non-CUDA system.")
+  "Whether build NVPTX deviceRTL on CUDA free system.")
 
 if (NOT (LIBOMPTARGET_DEP_CUDA_FOUND OR LIBOMPTARGET_BUILD_NVPTX_BCLIB))
-  libomptarget_say("Not building NVPTX deviceRTL by default on non-CUDA system.")
+  libomptarget_say("Not building NVPTX deviceRTL by default on CUDA free system.")
   return()
 endif()
 
 # Check if we can create an LLVM bitcode implementation of the runtime library
 # that could be inlined in the user application. For that we need to find
 # a Clang compiler capable of compiling our CUDA files to LLVM bitcode and
 # an LLVM linker.
 set(LIBOMPTARGET_NVPTX_CUDA_COMPILER "" CACHE STRING

 get_filename_component(devicertl_base_directory
   ${CMAKE_CURRENT_SOURCE_DIR}
   DIRECTORY)
 set(devicertl_common_directory
   ${devicertl_base_directory}/common)
 set(devicertl_nvptx_directory
   ${devicertl_base_directory}/nvptx)
 
-if (DEFINED LIBOMPTARGET_DEP_CUDA_ARCH)
-  set(default_capabilities ${LIBOMPTARGET_DEP_CUDA_ARCH})
-else()
-  set(default_capabilities 35 37 50 52 53 60 61 62 70 72 75 80)
-endif()
+set(all_capabilities 35 37 50 52 53 60 61 62 70 72 75 80)
 
-set(LIBOMPTARGET_NVPTX_COMPUTE_CAPABILITIES ${default_capabilities} CACHE STRING
+set(LIBOMPTARGET_NVPTX_COMPUTE_CAPABILITIES ${all_capabilities} CACHE STRING
   "List of CUDA Compute Capabilities to be used to compile the NVPTX device RTL.")
+string(TOLOWER ${LIBOMPTARGET_NVPTX_COMPUTE_CAPABILITIES} LIBOMPTARGET_NVPTX_COMPUTE_CAPABILITIES)
 
-set(nvptx_sm_list ${LIBOMPTARGET_NVPTX_COMPUTE_CAPABILITIES})
+if (LIBOMPTARGET_NVPTX_COMPUTE_CAPABILITIES STREQUAL "all")
+  set(nvptx_sm_list ${all_capabilities})
+elseif(LIBOMPTARGET_NVPTX_COMPUTE_CAPABILITIES STREQUAL "auto")
+  if (NOT LIBOMPTARGET_DEP_CUDA_FOUND)
+    libomptarget_error_say("[NVPTX] Cannot auto detect compute capability as CUDA not found.")
+  endif()
+  set(nvptx_sm_list ${LIBOMPTARGET_DEP_CUDA_ARCH})
+else()
+  string(REPLACE "," ";" nvptx_sm_list "${LIBOMPTARGET_NVPTX_COMPUTE_CAPABILITIES}")
+endif()
 
 # If user set LIBOMPTARGET_NVPTX_COMPUTE_CAPABILITIES to empty, we disable the
 # build.
 if (NOT nvptx_sm_list)
   libomptarget_say("Not building CUDA offloading device RTL: empty compute capability list")
   return()
 endif()
 
 # Check all SM values
 foreach(sm ${nvptx_sm_list})
-  if (NOT ${sm} IN_LIST default_capabilities)
-    message(FATAL_ERROR "LIBOMPTARGET-NVPTX: compute capability ${sm} is not supported. Supported values: ${default_capabilities}")
+  if (NOT ${sm} IN_LIST all_capabilities)
+    libomptarget_warning_say("[NVPTX] Compute capability ${sm} is not supported. Make sure clang can work with it.")
   endif()
 endforeach()
 
 # Override default MAX_SM in src/target_impl.h if requested
 if (DEFINED LIBOMPTARGET_NVPTX_MAX_SM)
   set(MAX_SM_DEFINITION "-DMAX_SM=${LIBOMPTARGET_NVPTX_MAX_SM}")
 endif()