Merge branch 'master' into ompd

Author: jprotze

README.rst

@@ -280,10 +280,10 @@ Options for ``NVPTX device RTL``
   compatible with NVCC, this option can be use to pass to NVCC a valid compiler
   to avoid the error.
 
- **LIBOMPTARGET_NVPTX_COMPUTE_CAPABILITY** = ``35``
-  CUDA compute capability that should be supported by the NVPTX device RTL. E.g.
-  for compute capability 6.0, the option "60" should be used. Compute capability
-  3.5 is the minimum required.
+ **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"
+  should be used. Compute capability 3.5 is the minimum required.
 
  **LIBOMPTARGET_NVPTX_DEBUG** = ``OFF|ON``
   Enable printing of debug messages from the NVPTX device RTL.

cmake/DetectTestCompiler/CMakeLists.txt

@@ -1,11 +1,14 @@
 cmake_minimum_required(VERSION 2.8)
 project(DetectTestCompiler C CXX)
 
+include(CheckCCompilerFlag)
+include(CheckCXXCompilerFlag)
+
 function(write_compiler_information lang)
   set(information "${CMAKE_${lang}_COMPILER}")
   set(information "${information}\\;${CMAKE_${lang}_COMPILER_ID}")
   set(information "${information}\\;${CMAKE_${lang}_COMPILER_VERSION}")
-  set(information "${information}\\;${OpenMP_${lang}_FLAGS}")
+  set(information "${information}\\;${${lang}_FLAGS}")
   file(WRITE ${CMAKE_CURRENT_BINARY_DIR}/${lang}CompilerInformation.txt ${information})
 endfunction(write_compiler_information)
 
@@ -15,5 +18,22 @@ if (NOT OpenMP_Found)
   set(OpenMP_CXX_FLAGS "-fopenmp")
 endif()
 
+set(C_FLAGS ${flags} ${OpenMP_C_FLAGS})
+set(CXX_FLAGS ${flags} ${OpenMP_CXX_FLAGS})
+
+# TODO: Implement blockaddress in GlobalISel and remove this flag!
+if (CMAKE_C_COMPILER_ID STREQUAL "Clang")
+  check_c_compiler_flag("-fno-experimental-isel" C_HAS_EXPERIMENTAL_ISEL_FLAG)
+  check_cxx_compiler_flag("-fno-experimental-isel" CXX_HAS_EXPERIMENTAL_ISEL_FLAG)
+  macro(add_experimental_isel_flag lang)
+    if (${lang}_HAS_EXPERIMENTAL_ISEL_FLAG)
+      set(${lang}_FLAGS "-fno-experimental-isel ${${lang}_FLAGS}")
+    endif()
+  endmacro(add_experimental_isel_flag)
+
+  add_experimental_isel_flag(C)
+  add_experimental_isel_flag(CXX)
+endif()
+
 write_compiler_information(C)
 write_compiler_information(CXX)

cmake/OpenMPTesting.cmake

@@ -117,7 +117,8 @@ else()
   # Cannot use CLANG_VERSION because we are not guaranteed that this is already set.
   set(OPENMP_TEST_COMPILER_VERSION "${LLVM_VERSION}")
   set(OPENMP_TEST_COMPILER_VERSION_MAJOR "${LLVM_MAJOR_VERSION}")
-  set(OPENMP_TEST_COMPILER_OPENMP_FLAGS "-fopenmp")
+  # TODO: Implement blockaddress in GlobalISel and remove this flag!
+  set(OPENMP_TEST_COMPILER_OPENMP_FLAGS "-fopenmp -fno-experimental-isel")
 endif()
 
 # Function to set compiler features for use in lit.

libomptarget/cmake/Modules/LibomptargetGetDependencies.cmake

@@ -134,7 +134,16 @@ find_library (
 
 # There is a libcuda.so in lib64/stubs that can be used for linking.
 if (NOT LIBOMPTARGET_DEP_CUDA_DRIVER_LIBRARIES AND CUDA_FOUND)
-  get_filename_component(CUDA_LIBDIR ${CUDA_LIBRARIES} DIRECTORY)
+  # Since CMake 3.3 FindCUDA.cmake defaults to using static libraries. In this
+  # case CUDA_LIBRARIES contains additional linker arguments which breaks
+  # get_filename_component below. Fortunately, since that change the module
+  # exports CUDA_cudart_static_LIBRARY which points to a single file in the
+  # right directory.
+  set(cuda_library ${CUDA_LIBRARIES})
+  if (DEFINED CUDA_cudart_static_LIBRARY)
+    set(cuda_library ${CUDA_cudart_static_LIBRARY})
+  endif()
+  get_filename_component(CUDA_LIBDIR ${cuda_library} DIRECTORY)
   find_library (
       LIBOMPTARGET_DEP_CUDA_DRIVER_LIBRARIES
     NAMES

libomptarget/deviceRTLs/nvptx/CMakeLists.txt

@@ -60,9 +60,18 @@ if(LIBOMPTARGET_DEP_CUDA_FOUND)
 
   # Get the compute capability the user requested or use SM_35 by default.
   # SM_35 is what clang uses by default.
-  set(LIBOMPTARGET_NVPTX_COMPUTE_CAPABILITY 35 CACHE STRING
-    "CUDA Compute Capability to be used to compile the NVPTX device RTL.")
-  set(CUDA_ARCH -arch sm_${LIBOMPTARGET_NVPTX_COMPUTE_CAPABILITY})
+  set(default_capabilities 35)
+  if (DEFINED LIBOMPTARGET_NVPTX_COMPUTE_CAPABILITY)
+    set(default_capabilities ${LIBOMPTARGET_NVPTX_COMPUTE_CAPABILITY})
+    libomptarget_warning_say("LIBOMPTARGET_NVPTX_COMPUTE_CAPABILITY is deprecated, please use LIBOMPTARGET_NVPTX_COMPUTE_CAPABILITIES")
+  endif()
+  set(LIBOMPTARGET_NVPTX_COMPUTE_CAPABILITIES ${default_capabilities} CACHE STRING
+    "List of CUDA Compute Capabilities to be used to compile the NVPTX device RTL.")
+  string(REPLACE "," ";" nvptx_sm_list ${LIBOMPTARGET_NVPTX_COMPUTE_CAPABILITIES})
+
+  foreach(sm ${nvptx_sm_list})
+    set(CUDA_ARCH ${CUDA_ARCH} -gencode arch=compute_${sm},code=sm_${sm})
+  endforeach()
 
   # Activate RTL message dumps if requested by the user.
   set(LIBOMPTARGET_NVPTX_DEBUG FALSE CACHE BOOL
@@ -132,6 +141,11 @@ if(LIBOMPTARGET_DEP_CUDA_FOUND)
         set(CUDA_PTX_VERSION ptx42)
       endif()
 
+      set(BC_DEBUG -DOMPTARGET_NVPTX_DEBUG=0)
+      if(${LIBOMPTARGET_NVPTX_DEBUG})
+        set(BC_DEBUG -DOMPTARGET_NVPTX_DEBUG=-1)
+      endif()
+
       # Set flags for Clang cuda compilation.  Only Clang is supported because there is
       # no other compiler capable of generating bitcode from cuda sources.
       set(CUDA_FLAGS
@@ -140,7 +154,8 @@ if(LIBOMPTARGET_DEP_CUDA_FOUND)
           -Xclang -target-feature
           -Xclang +${CUDA_PTX_VERSION}
           --cuda-device-only
-          -DOMPTARGET_NVPTX_TEST=0 -DOMPTARGET_NVPTX_DEBUG=0
+          -DOMPTARGET_NVPTX_TEST=0
+          ${BC_DEBUG}
       )
 
       # CUDA 9 header files use the nv_weak attribute which clang is not yet prepared
@@ -152,46 +167,47 @@ if(LIBOMPTARGET_DEP_CUDA_FOUND)
 
       # Get the compute capability the user requested or use SM_35 by default.
       set(CUDA_ARCH "")
-      set(CUDA_ARCH --cuda-gpu-arch=sm_${LIBOMPTARGET_NVPTX_COMPUTE_CAPABILITY})
-
-      # Compile cuda files to bitcode.
-      set(bc_files "")
-      foreach(src ${cuda_src_files})
-        get_filename_component(infile ${src} ABSOLUTE)
-        get_filename_component(outfile ${src} NAME)
-
-        add_custom_command(OUTPUT ${outfile}.bc
-          COMMAND ${LIBOMPTARGET_NVPTX_SELECTED_CUDA_COMPILER} ${CUDA_FLAGS} ${CUDA_ARCH} ${CUDA_INCLUDES}
-            -c ${infile} -o ${outfile}.bc
-          DEPENDS ${infile}
-          IMPLICIT_DEPENDS CXX ${infile}
-          COMMENT "Building LLVM bitcode ${outfile}.bc"
-          VERBATIM
+      foreach(sm ${nvptx_sm_list})
+        set(CUDA_ARCH --cuda-gpu-arch=sm_${sm})
+
+        # Compile cuda files to bitcode.
+        set(bc_files "")
+        foreach(src ${cuda_src_files})
+          get_filename_component(infile ${src} ABSOLUTE)
+          get_filename_component(outfile ${src} NAME)
+
+          add_custom_command(OUTPUT ${outfile}-sm_${sm}.bc
+            COMMAND ${LIBOMPTARGET_NVPTX_SELECTED_CUDA_COMPILER} ${CUDA_FLAGS} ${CUDA_ARCH} ${CUDA_INCLUDES}
+              -c ${infile} -o ${outfile}-sm_${sm}.bc
+            DEPENDS ${infile}
+            IMPLICIT_DEPENDS CXX ${infile}
+            COMMENT "Building LLVM bitcode ${outfile}-sm_${sm}.bc"
+            VERBATIM
+          )
+          set_property(DIRECTORY APPEND PROPERTY ADDITIONAL_MAKE_CLEAN_FILES ${outfile}-sm_${sm}.bc)
+
+          list(APPEND bc_files ${outfile}-sm_${sm}.bc)
+        endforeach()
+
+        # Link to a bitcode library.
+        add_custom_command(OUTPUT ${CMAKE_CURRENT_BINARY_DIR}/libomptarget-nvptx-sm_${sm}.bc
+            COMMAND ${LIBOMPTARGET_NVPTX_SELECTED_BC_LINKER}
+              -o ${CMAKE_CURRENT_BINARY_DIR}/libomptarget-nvptx-sm_${sm}.bc ${bc_files}
+            DEPENDS ${bc_files}
+            COMMENT "Linking LLVM bitcode libomptarget-nvptx-sm_${sm}.bc"
         )
-        set_property(DIRECTORY APPEND PROPERTY ADDITIONAL_MAKE_CLEAN_FILES ${outfile}.bc)
-
-        list(APPEND bc_files ${outfile}.bc)
-      endforeach()
-
-      # Link to a bitcode library.
-      add_custom_command(OUTPUT ${CMAKE_CURRENT_BINARY_DIR}/libomptarget-nvptx.bc
-          COMMAND ${LIBOMPTARGET_NVPTX_SELECTED_BC_LINKER}
-            -o ${CMAKE_CURRENT_BINARY_DIR}/libomptarget-nvptx.bc ${bc_files}
-          DEPENDS ${bc_files}
-          COMMENT "Linking LLVM bitcode libomptarget-nvptx.bc"
-      )
-      set_property(DIRECTORY APPEND PROPERTY ADDITIONAL_MAKE_CLEAN_FILES libomptarget-nvptx.bc)
+        set_property(DIRECTORY APPEND PROPERTY ADDITIONAL_MAKE_CLEAN_FILES libomptarget-nvptx-sm_${sm}.bc)
 
-      add_custom_target(omptarget-nvptx-bc ALL DEPENDS ${CMAKE_CURRENT_BINARY_DIR}/libomptarget-nvptx.bc)
+        add_custom_target(omptarget-nvptx-${sm}-bc ALL DEPENDS ${CMAKE_CURRENT_BINARY_DIR}/libomptarget-nvptx-sm_${sm}.bc)
 
-      # Copy library to destination.
-      add_custom_command(TARGET omptarget-nvptx-bc POST_BUILD
-                         COMMAND ${CMAKE_COMMAND} -E copy ${CMAKE_CURRENT_BINARY_DIR}/libomptarget-nvptx.bc
-                         $<TARGET_FILE_DIR:omptarget-nvptx>)
-
-      # Install device RTL under the lib destination folder.
-      install(FILES ${CMAKE_CURRENT_BINARY_DIR}/libomptarget-nvptx.bc DESTINATION "lib")
+        # Copy library to destination.
+        add_custom_command(TARGET omptarget-nvptx-${sm}-bc POST_BUILD
+                           COMMAND ${CMAKE_COMMAND} -E copy ${CMAKE_CURRENT_BINARY_DIR}/libomptarget-nvptx-sm_${sm}.bc
+                           $<TARGET_FILE_DIR:omptarget-nvptx>)
 
+        # Install device RTL under the lib destination folder.
+        install(FILES ${CMAKE_CURRENT_BINARY_DIR}/libomptarget-nvptx-sm_${sm}.bc DESTINATION "lib")
+      endforeach()
     endif()
   endif()
 

libomptarget/deviceRTLs/nvptx/src/counter_groupi.h

@@ -45,7 +45,7 @@ INLINE Counter omptarget_nvptx_CounterGroup::Next() {
 
 // set priv to n, to be used in later waitOrRelease
 INLINE void omptarget_nvptx_CounterGroup::Complete(Counter &priv, Counter n) {
-  PRINT(LD_SYNCD, "complete priv counter 0x%llx with val %lld->%lld (+%d)\n",
+  PRINT(LD_SYNCD, "complete priv counter 0x%llx with val %llu->%llu (+%llu)\n",
         P64(&priv), P64(priv), P64(priv + n), n);
   priv += n;
 }