Merge pull request #6459 from tensor-tang/develop

unify MKL macro definition

cmake/cblas.cmake

@@ -17,7 +17,7 @@ if(WITH_MKLML AND MKLML_INC_DIR AND MKLML_LIB)
   set(CBLAS_INC_DIR ${MKLML_INC_DIR})
   set(CBLAS_LIBRARIES ${MKLML_LIB})
 
-  add_definitions(-DPADDLE_USE_MKLML)
+  add_definitions(-DPADDLE_WITH_MKLML)
   add_definitions(-DLAPACK_FOUND)
 
   message(STATUS "Found cblas and lapack in MKLML "

cmake/external/mkldnn.cmake

@@ -67,5 +67,5 @@ ADD_LIBRARY(mkldnn SHARED IMPORTED GLOBAL)
 SET_PROPERTY(TARGET mkldnn PROPERTY IMPORTED_LOCATION ${MKLDNN_LIB})
 ADD_DEPENDENCIES(mkldnn ${MKLDNN_PROJECT})
 MESSAGE(STATUS "MKLDNN library: ${MKLDNN_LIB}")
-add_definitions(-DPADDLE_USE_MKLDNN)
+add_definitions(-DPADDLE_WITH_MKLDNN)
 LIST(APPEND external_project_dependencies mkldnn)

paddle/gserver/activations/ActivationFunction.cpp

@@ -24,7 +24,7 @@ limitations under the License. */
 #include "paddle/utils/ClassRegistrar.h"
 #include "paddle/utils/Logging.h"
 
-#ifdef PADDLE_USE_MKLDNN
+#ifdef PADDLE_WITH_MKLDNN
 #include "MKLDNNActivation.h"
 #endif
 
@@ -490,7 +490,7 @@ Error __must_check backward(Argument& act) {
 END_DEFINE_ACTIVATION(log)
 
 ActivationFunction* ActivationFunction::create(const std::string& type) {
-#ifdef PADDLE_USE_MKLDNN
+#ifdef PADDLE_WITH_MKLDNN
   if (!type.empty() && type.compare(0, 7, "mkldnn_") == 0) {
     return MKLDNNActivation::create(type);
   }

paddle/gserver/gradientmachines/NeuralNetwork.cpp

@@ -20,7 +20,7 @@ limitations under the License. */
 #include "paddle/utils/Logging.h"
 #include "paddle/utils/Stat.h"
 
-#ifdef PADDLE_USE_MKLDNN
+#ifdef PADDLE_WITH_MKLDNN
 #include "paddle/gserver/layers/MKLDNNLayer.h"
 #endif
 
@@ -307,7 +307,7 @@ void NeuralNetwork::backward(const UpdateCallback& callback) {
 }
 
 void NeuralNetwork::finish() {
-#ifdef PADDLE_USE_MKLDNN
+#ifdef PADDLE_WITH_MKLDNN
   FOR_EACH_R(layer, layers_) {
     MKLDNNLayerPtr dnnLayer = std::dynamic_pointer_cast<MKLDNNLayer>(*layer);
     if (dnnLayer) {

paddle/math/Allocator.h

@@ -48,7 +48,7 @@ public:
    */
   virtual void* alloc(size_t size) {
     void* ptr;
-#ifdef PADDLE_USE_MKLDNN
+#ifdef PADDLE_WITH_MKLDNN
     // refer to https://github.com/01org/mkl-dnn/blob/master/include/mkldnn.hpp
     // memory alignment
     CHECK_EQ(posix_memalign(&ptr, 4096ul, size), 0);

paddle/math/MathFunctions.cpp

@@ -206,7 +206,7 @@ double dotProduct<double>(const int n, const double* x, const double* y) {
 }
 #endif
 
-#if defined(PADDLE_USE_MKLML)
+#if defined(PADDLE_WITH_MKLML)
 
 template <>
 void vExp<float>(const int n, const float* a, float* r) {

paddle/math/MathFunctions.h

@@ -15,7 +15,7 @@ limitations under the License. */
 #ifndef MATHFUNCTIONS_H_
 #define MATHFUNCTIONS_H_
 
-#ifdef PADDLE_USE_MKLML
+#ifdef PADDLE_WITH_MKLML
 #include <mkl_cblas.h>
 #include <mkl_lapacke.h>
 #include <mkl_vml_functions.h>

paddle/memory/detail/system_allocator.cc

@@ -43,7 +43,7 @@ void* CPUAllocator::Alloc(size_t& index, size_t size) {
 
   void* p;
 
-#ifdef PADDLE_USE_MKLDNN
+#ifdef PADDLE_WITH_MKLDNN
   // refer to https://github.com/01org/mkl-dnn/blob/master/include/mkldnn.hpp
   // memory alignment
   PADDLE_ENFORCE_EQ(posix_memalign(&p, 4096ul, size), 0);

paddle/operators/math/math_function.cc

@@ -132,7 +132,7 @@ void matmul<platform::CPUPlace, double>(
       matrix_b.data<double>(), beta, matrix_out->data<double>());
 }
 
-#ifdef PADDLE_USE_MKLML
+#ifdef PADDLE_WITH_MKLML
 // Use cblas_{s,d}gemm_batched if available: Run with 1 group of size batchSize.
 template <>
 void batched_gemm<platform::CPUPlace, float>(

paddle/operators/math/math_function.h

@@ -13,7 +13,7 @@ See the License for the specific language governing permissions and
 limitations under the License. */
 
 #pragma once
-#ifdef PADDLE_USE_MKLML
+#ifdef PADDLE_WITH_MKLML
 #include <mkl_cblas.h>
 #include <mkl_lapacke.h>
 #include <mkl_vml_functions.h>

paddle/parameter/FirstOrderOptimizer.h

@@ -38,7 +38,7 @@ public:
     real torch_learningRate = optConfig_.learning_method() == "torch_momentum"
                                   ? 1.0 - paraConfig.momentum()
                                   : 1.0;
-#ifdef PADDLE_USE_MKLDNN
+#ifdef PADDLE_WITH_MKLDNN
     sgdUpdate(learningRate_ * paraConfig.learning_rate() *
                   (firstTime_ ? 1.0 : torch_learningRate),
               paraConfig.momentum(),

paddle/parameter/ParameterUpdateFunctions.cpp

@@ -30,7 +30,7 @@ void sgdUpdateCpu(real learningRate,
                   const real* grad,
                   real* momentumVec) {
   decayRate *= learningRate;
-#ifdef PADDLE_USE_MKLML
+#ifdef PADDLE_WITH_MKLML
 #pragma omp parallel for
 #endif
   for (size_t i = 0; i < size; ++i) {

paddle/utils/Flags.cpp

@@ -20,7 +20,7 @@ DEFINE_bool(use_gpu, false, "Only support CPU training");
 DEFINE_bool(use_gpu, true, "Whether to use GPU for training");
 #endif
 
-#ifdef PADDLE_USE_MKLDNN
+#ifdef PADDLE_WITH_MKLDNN
 // TODO(TJ): change to true when MKLDNN layers support multi-inputs
 DEFINE_bool(use_mkldnn, false, "Default still keep use CPU training");
 #else