[OpenMP] NVPTX: Set default/minimum compute capability to sm_35

The current implementation of the nvptx runtime (to be upstreamed shortly) uses the atomicMax operation on 64-bit integers.
This is only supported in compute capabilities 3.5 and later. I've changed the clang default to sm_35.

Differential Revision: https://reviews.llvm.org/D40977

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@320082 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/CMakeLists.txt b/CMakeLists.txt
index 884879851544dbf94b296fd7013f22ffd3d77067..2eee8e6148f77b70da4cf9f5e2287ce9d6336179 100644 (file)
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -241,14 +241,15 @@ set(CLANG_DEFAULT_OBJCOPY "objcopy" CACHE STRING
 set(CLANG_DEFAULT_OPENMP_RUNTIME "libomp" CACHE STRING
   "Default OpenMP runtime used by -fopenmp.")
 
-# OpenMP offloading requires at least sm_30 because we use shuffle instructions
-# to generate efficient code for reductions.
-set(CLANG_OPENMP_NVPTX_DEFAULT_ARCH "sm_30" CACHE STRING
+# OpenMP offloading requires at least sm_35 because we use shuffle instructions
+# to generate efficient code for reductions and the atomicMax instruction on
+# 64-bit integers in the implementation of conditional lastprivate.
+set(CLANG_OPENMP_NVPTX_DEFAULT_ARCH "sm_35" CACHE STRING
   "Default architecture for OpenMP offloading to Nvidia GPUs.")
 string(REGEX MATCH "^sm_([0-9]+)$" MATCHED_ARCH "${CLANG_OPENMP_NVPTX_DEFAULT_ARCH}")
-if (NOT DEFINED MATCHED_ARCH OR "${CMAKE_MATCH_1}" LESS 30)
-  message(WARNING "Resetting default architecture for OpenMP offloading to Nvidia GPUs to sm_30")
-  set(CLANG_OPENMP_NVPTX_DEFAULT_ARCH "sm_30" CACHE STRING
+if (NOT DEFINED MATCHED_ARCH OR "${CMAKE_MATCH_1}" LESS 35)
+  message(WARNING "Resetting default architecture for OpenMP offloading to Nvidia GPUs to sm_35")
+  set(CLANG_OPENMP_NVPTX_DEFAULT_ARCH "sm_35" CACHE STRING
     "Default architecture for OpenMP offloading to Nvidia GPUs." FORCE)
 endif()