follow comments

Author: gangliao

cmake/cblas.cmake

@@ -44,7 +44,6 @@ if(MKL_INC_DIR AND MKL_CORE_LIB AND MKL_SEQUENTIAL_LIB AND MKL_INTEL_LP64)
  message(STATUS "Found MKL (include: ${CBLAS_INC_DIR}, library: ${CBLAS_LIBRARIES})")
  set(CBLAS_FOUND ON)
  if(${MKL_LAPACK_INC_DIR})
- add_definitions(-DPADDLE_USE_LAPACK)
  message(STATUS "Found lapack in MKL (include: ${MKL_LAPACK_INC_DIR})")
  endif()
  return() # return file.
@@ -80,7 +79,6 @@ if(ATLAS_INC_DIR AND ATLAS_CBLAS_LIB AND ATLAS_LIB AND NOT CBLAS_FOUND)
  message(STATUS "Found ATLAS (include: ${CBLAS_INC_DIR}, library: ${CBLAS_LIBRARIES})")
  set(CBLAS_FOUND ON)
  if(ATLAS_CLAPACK_INC_DIR)
- add_definitions(-DPADDLE_USE_LAPACK)
  message(STATUS "Found lapack in ATLAS (include: ${ATLAS_CLAPACK_INC_DIR})")
  endif()
  return()
@@ -114,7 +112,6 @@ if(OPENBLAS_INC_DIR AND OPENBLAS_LIB)
  message(STATUS "Found OpenBLAS (include: ${CBLAS_INC_DIR}, library: ${CBLAS_LIBRARIES})")
  set(CBLAS_FOUND ON)
  if(OPENBLAS_LAPACKE_INC_DIR)
- add_definitions(-DPADDLE_USE_LAPACK)
  message(STATUS "Found lapack in OpenBLAS (include: ${OPENBLAS_LAPACKE_INC_DIR})")
  endif()
  return()

cmake/external/openblas.cmake

@@ -27,8 +27,6 @@ IF(NOT ${CBLAS_FOUND})
  SET(CBLAS_LIBRARIES "${CBLAS_INSTALL_DIR}/lib/libopenblas.a" CACHE FILEPATH "openblas library" FORCE)
  ENDIF(WIN32)
 
- ADD_DEFINITIONS(-DPADDLE_USE_LAPACK)
-
  ExternalProject_Add(
  openblas
  ${EXTERNAL_PROJECT_LOG_ARGS}

paddle/cuda/include/hl_activation_functions.h

@@ -40,18 +40,18 @@ class Active {
 namespace gpu {
 static __device__ Active<real>::forward forward[] = HPPL_ACTIVE_FUNCTION;
 static __device__ Active<real>::backward backward[] = HPPL_ACTIVE_FUNCTION;
-}
+} // namespace gpu
 #else
 namespace cpu {
 static Active<real>::forward forward[] = HPPL_ACTIVE_FUNCTION;
 static Active<real>::backward backward[] = HPPL_ACTIVE_FUNCTION;
-}
+} // namespace cpu
 
 #ifdef __AVX__
 namespace avx {
 static Active<__m256>::forward forward[] = HPPL_ACTIVE_FUNCTION;
 static Active<__m256>::backward backward[] = HPPL_ACTIVE_FUNCTION;
-}
+} // namespace avx
 #endif
 #endif
 

paddle/cuda/include/hl_cnn.h

@@ -273,23 +273,23 @@ extern void hl_bilinear_forward(const real* inData,
  const real ratioW);
 
 /**
-* @brief Bilinear interpolation backward.
-*
-* @param[out] inGrad input gradient.
-* @param[in] inImgH input image height.
-* @param[in] inImgW input image width.
-* @param[in] inputH input batchSize.
-* @param[in] inputW input image data dim.
-* @param[in] outGrad output gradient.
-* @param[in] outImgH output image height.
-* @param[in] outImgW output image width.
-* @param[in] outputH output batchSize.
-* @param[in] outputW output image data dim.
-* @param[in] numChannels number of channels.
-* @param[in] ratioH inImgH / outImgH.
-* @param[in] ratioW inImgW / outImgW.
-*
-*/
+ * @brief Bilinear interpolation backward.
+ *
+ * @param[out] inGrad input gradient.
+ * @param[in] inImgH input image height.
+ * @param[in] inImgW input image width.
+ * @param[in] inputH input batchSize.
+ * @param[in] inputW input image data dim.
+ * @param[in] outGrad output gradient.
+ * @param[in] outImgH output image height.
+ * @param[in] outImgW output image width.
+ * @param[in] outputH output batchSize.
+ * @param[in] outputW output image data dim.
+ * @param[in] numChannels number of channels.
+ * @param[in] ratioH inImgH / outImgH.
+ * @param[in] ratioW inImgW / outImgW.
+ *
+ */
 extern void hl_bilinear_backward(real* inGrad,
  const size_t inImgH,
  const size_t inImgW,

paddle/cuda/src/hl_cuda_cublas.cc

@@ -16,7 +16,7 @@ limitations under the License. */
 #include <sys/time.h>
 #include "hl_cuda.h"
 #include "hl_thread.ph"
-#include "paddle/utils/DynamicLoad.h"
+#include "paddle/utils/DynamicLoader.h"
 #include "paddle/utils/Logging.h"
 
 namespace dynload {

paddle/cuda/src/hl_cuda_cudnn.cc

@@ -17,7 +17,7 @@ limitations under the License. */
 #include <gflags/gflags.h>
 #include "hl_cuda_cudnn.ph"
 #include "hl_thread.ph"
-#include "paddle/utils/DynamicLoad.h"
+#include "paddle/utils/DynamicLoader.h"
 #include "paddle/utils/Logging.h"
 
 DEFINE_int32(cudnn_conv_workspace_limit_in_mb,

paddle/cuda/src/hl_cuda_device.cc

@@ -24,7 +24,7 @@ limitations under the License. */
 #include "hl_cuda.ph"
 #include "hl_thread.ph"
 #include "paddle/utils/Logging.h"
-#include "paddle/utils/DynamicLoad.h"
+#include "paddle/utils/DynamicLoader.h"
 // clang-format on
 
 namespace dynload {

paddle/cuda/src/hl_warpctc_wrap.cc

@@ -14,7 +14,7 @@ limitations under the License. */
 
 #include "hl_warpctc_wrap.h"
 #include <mutex>
-#include "paddle/utils/DynamicLoad.h"
+#include "paddle/utils/DynamicLoader.h"
 #include "paddle/utils/Logging.h"
 
 namespace dynload {

paddle/function/BufferArgTest.cpp

@@ -12,8 +12,8 @@ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 See the License for the specific language governing permissions and
 limitations under the License. */
 
-#include "BufferArg.h"
 #include <gtest/gtest.h>
+#include "BufferArg.h"
 #include "paddle/math/MemoryHandle.h"
 
 namespace paddle {

paddle/function/CosSimOp.cpp

@@ -165,12 +165,12 @@ void CosSimBackward<DEVICE_TYPE_CPU>(const CpuMatrix& out_grad,
  real reciprocal_square_sum_x = 1.0f / square_sum_x;
  real reciprocal_square_sum_y = 1.0f / square_sum_y;
  for (size_t j = 0; j < dim; ++j) {
- prev_grad_x[j] +=
- out[i] * grad[i] * (prev_out_y[j] * reciprocal_xy -
-  prev_out_x[j] * reciprocal_square_sum_x);
- prev_grad_y[j] +=
- out[i] * grad[i] * (prev_out_x[j] * reciprocal_xy -
-  prev_out_y[j] * reciprocal_square_sum_y);
+ prev_grad_x[j] += out[i] * grad[i] *
+   (prev_out_y[j] * reciprocal_xy -
+ prev_out_x[j] * reciprocal_square_sum_x);
+ prev_grad_y[j] += out[i] * grad[i] *
+   (prev_out_x[j] * reciprocal_xy -
+ prev_out_y[j] * reciprocal_square_sum_y);
  }
  }
  }