Fix cmake cuda build for Windows & Enable cmake windows gpu build (#2754)

* Fix cmake cuda build for Windows

* add gpu test jobs

* Update .circleci/regenerate.py
Co-authored-by: Francisco Massa <fvsmassa@gmail.com>

.circleci/config.yml

@@ -1145,6 +1145,10 @@ workflows:
           cu_version: cpu
           name: cmake_windows_cpu
           python_version: '3.8'
+      - cmake_windows_gpu:
+          cu_version: cu101
+          name: cmake_windows_gpu
+          python_version: '3.8'
       - cmake_macos_cpu:
           cu_version: cpu
           name: cmake_macos_cpu

.circleci/regenerate.py

@@ -191,8 +191,8 @@ def cmake_workflows(indentation=6):
     jobs = []
     python_version = '3.8'
     for os_type in ['linux', 'windows', 'macos']:
-        # Right now CMake builds are failling on Windows (GPU)
-        device_types = ['cpu', 'gpu'] if os_type == 'linux' else ['cpu']
+        # Skip OSX CUDA
+        device_types = ['cpu', 'gpu'] if os_type != 'macos' else ['cpu']
         for device in device_types:
             job = {
                 'name': f'cmake_{os_type}_{device}',
@@ -200,7 +200,7 @@ def cmake_workflows(indentation=6):
             }
 
             job['cu_version'] = 'cu101' if device == 'gpu' else 'cpu'
-            if device == 'gpu':
+            if device == 'gpu' and os_type == 'linux':
                 job['wheel_docker_image'] = 'pytorch/manylinux-cuda101'
             jobs.append({f'cmake_{os_type}_{device}': job})
     return indent(indentation, jobs)

CMakeLists.txt

@@ -9,6 +9,7 @@ if(WITH_CUDA)
   enable_language(CUDA)
   add_definitions(-D__CUDA_NO_HALF_OPERATORS__)
   add_definitions(-DWITH_CUDA)
+  set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} --expt-relaxed-constexpr")
 endif()
 
 find_package(Python3 COMPONENTS Development)
@@ -17,6 +18,15 @@ find_package(Torch REQUIRED)
 find_package(PNG REQUIRED)
 find_package(JPEG REQUIRED)
 
+function(CUDA_CONVERT_FLAGS EXISTING_TARGET)
+    get_property(old_flags TARGET ${EXISTING_TARGET} PROPERTY INTERFACE_COMPILE_OPTIONS)
+    if(NOT "${old_flags}" STREQUAL "")
+        string(REPLACE ";" "," CUDA_flags "${old_flags}")
+        set_property(TARGET ${EXISTING_TARGET} PROPERTY INTERFACE_COMPILE_OPTIONS
+            "$<$<BUILD_INTERFACE:$<COMPILE_LANGUAGE:CXX>>:${old_flags}>$<$<BUILD_INTERFACE:$<COMPILE_LANGUAGE:CUDA>>:-Xcompiler=${CUDA_flags}>"
+            )
+    endif()
+endfunction()
 
 file(GLOB HEADERS torchvision/csrc/*.h)
 # Image extension
@@ -29,6 +39,26 @@ endif()
 file(GLOB MODELS_HEADERS torchvision/csrc/models/*.h)
 file(GLOB MODELS_SOURCES torchvision/csrc/models/*.h torchvision/csrc/models/*.cpp)
 
+if(MSVC)
+  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /wd4819")
+  if(WITH_CUDA)
+    set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} -Xcompiler=/wd4819")
+    foreach(diag cc_clobber_ignored integer_sign_change useless_using_declaration
+      set_but_not_used field_without_dll_interface
+      base_class_has_different_dll_interface
+      dll_interface_conflict_none_assumed
+      dll_interface_conflict_dllexport_assumed
+      implicit_return_from_non_void_function
+      unsigned_compare_with_zero
+      declared_but_not_referenced
+      bad_friend_decl)
+      string(APPEND CMAKE_CUDA_FLAGS " -Xcudafe --diag_suppress=${diag}")
+    endforeach()
+    CUDA_CONVERT_FLAGS(torch_cpu)
+    CUDA_CONVERT_FLAGS(torch_cuda)
+  endif()
+endif()
+
 add_library(${PROJECT_NAME} SHARED ${MODELS_SOURCES} ${OPERATOR_SOURCES} ${IMAGE_SOURCES})
 target_link_libraries(${PROJECT_NAME} PRIVATE ${TORCH_LIBRARIES} ${PNG_LIBRARY} ${JPEG_LIBRARIES} Python3::Python)
 set_target_properties(${PROJECT_NAME} PROPERTIES EXPORT_NAME TorchVision)