[CustomOp] Fix ext_tensor.cast failed bug (#34884)

* fix ext_tensor.cast failed bug * remove useless deps * fix windows cmake failed * try to fix windows make failed * fix make error on windwos
PaddlePaddle · Aug 18, 2021 · 4d88cdb · 4d88cdb
1 parent dd533dd
commit 4d88cdb
Show file tree

Hide file tree

Showing 3 changed files with 19 additions and 3 deletions.
diff --git a/paddle/fluid/extension/src/ext_tensor.cu b/paddle/fluid/extension/src/ext_tensor.cu
@@ -0,0 +1 @@
+ext_tensor.cc
diff --git a/paddle/fluid/framework/CMakeLists.txt b/paddle/fluid/framework/CMakeLists.txt
@@ -17,7 +17,7 @@ function(windows_symbolic TARGET)
     add_custom_command(OUTPUT ${final_path}/.${src}.cu
             COMMAND ${CMAKE_COMMAND} -E copy_if_different "${final_path}/${src}.cc" "${final_path}/.${src}.cu"
             COMMENT "create hidden file of ${src}.cu")
-    add_custom_target(${TARGET} ALL DEPENDS .${src}.cu)
+    add_custom_target(${TARGET} ALL DEPENDS ${final_path}/.${src}.cu)
   endforeach()
 endfunction()
 
@@ -413,8 +413,16 @@ include_directories(${PADDLE_SOURCE_DIR}/paddle/fluid/platform)
 include_directories(${PADDLE_SOURCE_DIR}/paddle/fluid/extension/include)
 include_directories(${PADDLE_SOURCE_DIR}/paddle/utils)
 
-if(WITH_ROCM)
-  hip_library(custom_tensor SRCS ../extension/src/ext_tensor.cc DEPS lod_tensor memory enforce)
+if (WITH_GPU)
+  if (WIN32)
+    windows_symbolic(ext_tensor_cu SRCS ext_tensor.cu PATH ../extension/src)
+    nv_library(custom_tensor SRCS ../extension/src/.ext_tensor.cu DEPS lod_tensor memory enforce)
+    add_dependencies(custom_tensor ext_tensor_cu)
+  else()
+    nv_library(custom_tensor SRCS ../extension/src/ext_tensor.cu DEPS lod_tensor memory enforce)
+  endif(WIN32)
+elseif (WITH_ROCM)
+  hip_library(custom_tensor SRCS ../extension/src/ext_tensor.cu DEPS lod_tensor memory enforce)
 else()
   cc_library(custom_tensor SRCS ../extension/src/ext_tensor.cc DEPS lod_tensor memory enforce)
 endif()

diff --git a/paddle/fluid/framework/custom_tensor_test.cc b/paddle/fluid/framework/custom_tensor_test.cc
@@ -144,6 +144,13 @@ void TestCast(paddle::DataType data_type) {
   t1.template mutable_data<T>();
   auto t2 = t1.cast(data_type);
   CHECK(t2.type() == data_type);
+#ifdef PADDLE_WITH_CUDA
+  auto tg1 = paddle::Tensor(paddle::PlaceType::kGPU);
+  tg1.reshape(tensor_shape);
+  tg1.template mutable_data<T>();
+  auto tg2 = tg1.cast(data_type);
+  CHECK(tg2.type() == data_type);
+#endif
 }
 
 void GroupTestCopy() {