Update Mac OS X port

* follow comments to fix bugs

cmake/cblas.cmake

@@ -44,8 +44,8 @@ set(ATLAS_LIB_SEARCH_PATHS
         /usr/lib
         /usr/lib/blas/atlas
         /usr/lib/atlas
-        /usr/lib/atlas-base)   # special for ubuntu 14.04.
+        /usr/lib/atlas-base   # special for ubuntu 14.04.
-
+    )
 find_path(ATLAS_INC_DIR NAMES cblas.h 
   PATHS ${ATLAS_INCLUDE_SEARCH_PATHS})
 find_library(ATLAS_CBLAS_LIB NAMES cblas libcblas.so.3 

cmake/util.cmake

@@ -24,7 +24,9 @@ function(target_circle_link_libraries TARGET_NAME)
                 list(APPEND libsInArgn ${arg})
             endif()
         endforeach()
-
+        if("${CMAKE_CXX_COMPILER_ID}" STREQUAL "Clang")
+            list(APPEND LIBS "-undefined dynamic_lookup")
+        endif()
         list(REVERSE libsInArgn)
         target_link_libraries(${TARGET_NAME}
             ${LIBS}

paddle/api/Matrix.cpp

@@ -95,7 +95,7 @@ float Matrix::get(size_t x, size_t y) const throw(RangeError) {
 }
 
 void Matrix::set(size_t x, size_t y, float val) throw(RangeError,
-                                                     UnsupportError) {
+                                                      UnsupportError) {
   if (x > this->getWidth() || y > this->getHeight()) {
     RangeError e;
     throw e;
@@ -239,7 +239,7 @@ void Matrix::toNumpyMatInplace(float** view_data, int* dim1,
 }
 void Matrix::copyToNumpyMat(float** view_m_data, int* dim1,
                             int* dim2) throw(UnsupportError) {
-  static_assert(sizeof(float) == sizeof(float),
+  static_assert(sizeof(paddle::real) == sizeof(float),
                 "Currently PaddleAPI only support for single "
                 "precision version of paddle.");
   if (this->isSparse()) {
@@ -251,12 +251,12 @@ void Matrix::copyToNumpyMat(float** view_m_data, int* dim1,
     if (auto cpuMat = dynamic_cast<paddle::CpuMatrix*>(m->mat.get())) {
       auto src = cpuMat->getData();
       auto dest = *view_m_data;
-      std::memcpy(dest, src, sizeof(float) * (*dim1) * (*dim2));
+      std::memcpy(dest, src, sizeof(paddle::real) * (*dim1) * (*dim2));
     } else if (auto gpuMat = dynamic_cast<paddle::GpuMatrix*>(m->mat.get())) {
       auto src = gpuMat->getData();
       auto dest = *view_m_data;
       hl_memcpy_device2host(dest, src,
-                            sizeof(float) * (*dim1) * (*dim2));
+                            sizeof(paddle::real) * (*dim1) * (*dim2));
     } else {
       LOG(WARNING) << "Unexpected Situation";
       throw UnsupportError();

paddle/gserver/gradientmachines/NeuralNetwork.cpp

@@ -385,10 +385,17 @@ void NeuralNetwork::setOutputGrad(const std::vector<Argument>& args) {
   }
 }
 
+extern NeuralNetwork* newCustomNerualNetwork(
+  const std::string& name, NeuralNetwork* network) __attribute__((weak));
+
 NeuralNetwork* NeuralNetwork::newNeuralNetwork(
     const std::string& name,
     NeuralNetwork* rootNetwork) {
-    return new NeuralNetwork(name, rootNetwork);
+    if (newCustomNerualNetwork) {
+      return newCustomNerualNetwork(name, rootNetwork);
+    } else {
+      return new NeuralNetwork(name, rootNetwork);
+    }
 }
 
 }  // namespace paddle

paddle/trainer/tests/test_Trainer.cpp

@@ -94,7 +94,11 @@ TEST(checkGradient, multi) {
 TEST(checkGradient, hsigmoid) { checkGradientTest(configFile2, false, false); }
 
 TEST(checkGradient, chunk) {
+#if defined(__APPLE__) || defined (__OSX__)
   EXPECT_EQ(0, system("python trainer/tests/gen_proto_data.py"));
+#else
+  EXPECT_EQ(0, system("python2 trainer/tests/gen_proto_data.py"));
+#endif
   checkGradientTest(configFile3, false, false);
 #ifndef PADDLE_ONLY_CPU
   checkGradientTest(configFile3, true, true);

paddle/utils/PythonUtil.cpp

@@ -144,12 +144,12 @@ PyObjectPtr createPythonClass(
     const std::map<std::string, std::string>& kwargs) {
   PyGuard guard;
   PyObjectPtr pyModule(PyImport_ImportModule(moduleName.c_str()));
-  // LOG(INFO) << "createPythonClass moduleName.c_str:" << moduleName.c_str();
+  LOG(INFO) << "createPythonClass moduleName.c_str:" << moduleName.c_str();
   CHECK_PY(pyModule) << "Import module " << moduleName << " failed.";
   PyObjectPtr pyDict(PyModule_GetDict(pyModule.get()));
   CHECK_PY(pyDict) << "Get Dict failed.";
   PyObjectPtr pyClass(PyDict_GetItemString(pyDict.get(), className.c_str()));
-  // LOG(INFO) << "createPythonClass className.c_str():" << className.c_str();
+  LOG(INFO) << "createPythonClass className.c_str():" << className.c_str();
   CHECK_PY(pyClass) << "Import class " << className << " failed.";
   PyObjectPtr argsObjectList(PyTuple_New(args.size()));
   for (size_t i = 0; i < args.size(); ++i) {

paddle/utils/PythonUtil.h

@@ -35,13 +35,6 @@ limitations under the License. */
 #include <Python.h>
 #include <frameobject.h>
 
-// #ifndef _POSIX_C_SOURCE
-// #warning "no _POSIX_C_SOURCE defined in Python.h"
-// #endif
-// #ifndef _XOPEN_SOURCE
-// #warning "no _XOPEN_SOURCE defined in Python.h"
-// #endif
-
 #endif
 
 #include "paddle/utils/Util.h"

paddle/utils/Stat.cpp

@@ -13,28 +13,12 @@ See the License for the specific language governing permissions and
 limitations under the License. */
 
 #include "Stat.h"
-
+#include "Util.h"
-#include <sys/syscall.h>  // for syscall()
-#include <sys/types.h>
 #include <iomanip>
 #include <algorithm>
 
 namespace paddle {
 
-// return the thread id used by glog
-pid_t getTID() {
-  #if defined(__APPLE__) || defined(__OSX__)
-      pid_t tid = syscall(SYS_thread_selfid);
-  #else
-      #ifndef __NR_gettid
-      #define __NR_gettid 224
-      #endif
-      pid_t tid = syscall(__NR_gettid);
-  #endif
-  CHECK_NE(tid, -1);
-  return tid;
-}
-
 StatSet globalStat("GlobalStatInfo");
 
 void Stat::addSample(uint64_t value) {

paddle/utils/Thread.h

@@ -13,24 +13,10 @@ See the License for the specific language governing permissions and
 limitations under the License. */
 
 #pragma once
+#include "Util.h"
 #include "Logging.h"
 #include <thread>
 
-#include <sys/syscall.h>
-#include <unistd.h>
-inline pid_t gettid() {
-#if defined(__APPLE__) || defined(__OSX__)
-  pid_t tid = syscall(SYS_thread_selfid);
-#else
-  #ifndef __NR_gettid
-  #define __NR_gettid 224
-  #endif
-  pid_t tid = syscall(__NR_gettid);
-#endif
-  CHECK_NE(tid, -1);
-  return tid;
-}
-
 #include "Queue.h"
 #include "ThreadLocal.h"
 
@@ -186,7 +172,7 @@ public:
         jobFinishBarrier_(numWorkers + 1),
         jobFunc_(nullptr),
         checkOwner_(checkOwner) {
-    ownerThreadId_ = ::gettid();
+    ownerThreadId_ = getTID();
     workers_.resize(numWorkers);
     start();
   }
@@ -210,7 +196,7 @@ public:
    */
   void exec(JobFunc jobFunc, JobFunc ownerFunc = nullptr) {
     if (checkOwner_) {
-      CHECK_EQ(ownerThreadId_, ::gettid())
+      CHECK_EQ(ownerThreadId_, getTID())
           << "this sync thread pool should be used in one thread";
     }
 

paddle/utils/ThreadLocal.cpp

@@ -12,10 +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 "Util.h"
 #include "ThreadLocal.h"
-
-#include "Thread.h"
-
 #include "CommandLineParser.h"
 
 P_DEFINE_bool(thread_local_rand_use_global_seed, false,
@@ -31,11 +29,11 @@ unsigned int* ThreadLocalRand::getSeed() {
   if (!p) {  // init seed
     if (FLAGS_thread_local_rand_use_global_seed) {
       p = new unsigned int(defaultSeed_);
-    } else if (getpid() == gettid()) {  // main thread
+    } else if (getpid() == getTID()) {  // main thread
       // deterministic, but differs from global srand()
       p = new unsigned int(defaultSeed_ - 1);
     } else {
-      p = new unsigned int(defaultSeed_ + gettid());
+      p = new unsigned int(defaultSeed_ + getTID());
       LOG(INFO) << "thread use undeterministic rand seed:" << *p;
     }
     seed_.set(p);
@@ -51,7 +49,7 @@ std::default_random_engine& ThreadLocalRandomEngine::get() {
     int defaultSeed = ThreadLocalRand::getDefaultSeed();
     engine->seed(FLAGS_thread_local_rand_use_global_seed
                      ? defaultSeed
-                     : defaultSeed + gettid());
+                     : defaultSeed + getTID());
     engine_.set(engine);
   }
   return *engine;

paddle/utils/Util.cpp

@@ -93,6 +93,19 @@ static void installProfilerSwitch() {}
 
 namespace paddle {
 
+pid_t getTID() {
+  #if defined(__APPLE__) || defined(__OSX__)
+      pid_t tid = syscall(SYS_thread_selfid);
+  #else
+      #ifndef __NR_gettid
+      #define __NR_gettid 224
+      #endif
+      pid_t tid = syscall(__NR_gettid);
+  #endif
+  CHECK_NE(tid, -1);
+  return tid;
+}
+
 static bool g_initialized = false;
 typedef std::pair<int, std::function<void()>> PriorityFuncPair;
 typedef std::vector<PriorityFuncPair> InitFuncList;

paddle/utils/Util.h

@@ -24,6 +24,8 @@ limitations under the License. */
 #include <unordered_map>
 #include <mutex>
 #include <functional>
+#include <sys/syscall.h>  // for syscall()
+#include <sys/types.h>
 
 #include "CommandLineParser.h"
 #include "Logging.h"
@@ -63,6 +65,9 @@ limitations under the License. */
 
 namespace paddle {
 
+// return the thread id used by glog
+pid_t getTID();
+
 /**
  * return the 1-based index of the highest bit set
  *