Merge remote-tracking branch 'ups/develop' into fea/jitkernel

test=develop

Author: tensor-tang

Dockerfile

@@ -24,6 +24,7 @@ COPY ./paddle/scripts/docker/root/ /root/
 
 RUN apt-get update && \
     apt-get install -y --allow-downgrades patchelf \
+    python3 python3-dev python3-pip \
     git python-pip python-dev python-opencv openssh-server bison \
     libnccl2=2.1.2-1+cuda8.0 libnccl-dev=2.1.2-1+cuda8.0 \
     wget unzip unrar tar xz-utils bzip2 gzip coreutils ntp \
@@ -70,24 +71,33 @@ RUN localedef -i en_US -f UTF-8 en_US.UTF-8
 # specify sphinx version as 1.5.6 and remove -U option for [pip install -U
 # sphinx-rtd-theme] since -U option will cause sphinx being updated to newest
 # version(1.7.1 for now), which causes building documentation failed.
-RUN easy_install -U pip && \
+RUN pip3 install -U wheel && \
+    pip3 install -U docopt PyYAML sphinx==1.5.6 && \
+    pip3 install sphinx-rtd-theme==0.1.9 recommonmark && \
+    easy_install -U pip && \
     pip install -U wheel && \
     pip install -U docopt PyYAML sphinx==1.5.6 && \
     pip install sphinx-rtd-theme==0.1.9 recommonmark
 
-RUN pip install pre-commit 'ipython==5.3.0' && \
+RUN pip3 install pre-commit 'ipython==5.3.0' && \
+    pip3 install 'ipykernel==4.6.0' 'jupyter==1.0.0' && \
+    pip3 install opencv-python && \
+    pip install pre-commit 'ipython==5.3.0' && \
     pip install 'ipykernel==4.6.0' 'jupyter==1.0.0' && \
     pip install opencv-python
 
 #For docstring checker
+RUN pip3 install pylint pytest astroid isort
 RUN pip install pylint pytest astroid isort LinkChecker
 
 COPY ./python/requirements.txt /root/
+RUN pip3 install -r /root/requirements.txt
 RUN pip install -r /root/requirements.txt
 
 # To fix https://github.com/PaddlePaddle/Paddle/issues/1954, we use
 # the solution in https://urllib3.readthedocs.io/en/latest/user-guide.html#ssl-py2
 RUN apt-get install -y libssl-dev libffi-dev
+RUN pip3 install certifi urllib3[secure]
 RUN pip install certifi urllib3[secure]
 
 

cmake/cblas.cmake

@@ -40,7 +40,7 @@ set(OPENBLAS_LIB_SEARCH_PATHS
         /usr/local/opt/openblas/lib)
 
 find_path(OPENBLAS_INC_DIR NAMES cblas.h
-  PATHS ${OPENBLAS_INCLUDE_SEARCH_PATHS})
+  PATHS ${OPENBLAS_INCLUDE_SEARCH_PATHS} NO_DEFAULT_PATH)
 find_path(OPENBLAS_LAPACKE_INC_DIR NAMES lapacke.h
   PATHS ${OPENBLAS_INCLUDE_SEARCH_PATHS})
 find_library(OPENBLAS_LIB NAMES openblas

cmake/external/openblas.cmake

@@ -27,7 +27,7 @@ IF(NOT ${CBLAS_FOUND})
 
     SET(CBLAS_SOURCES_DIR ${THIRD_PARTY_PATH}/openblas)
     SET(CBLAS_INSTALL_DIR ${THIRD_PARTY_PATH}/install/openblas)
-    SET(CBLAS_INCLUDE_DIR "${CBLAS_INSTALL_DIR}/include" CACHE PATH "openblas include directory." FORCE)
+    SET(CBLAS_INC_DIR "${CBLAS_INSTALL_DIR}/include" CACHE PATH "openblas include directory." FORCE)
 
     SET(CBLAS_LIBRARIES
         "${CBLAS_INSTALL_DIR}/lib/${CMAKE_STATIC_LIBRARY_PREFIX}openblas${CMAKE_STATIC_LIBRARY_SUFFIX}"
@@ -96,7 +96,7 @@ IF(NOT ${CBLAS_FOUND})
     ENDIF(NOT WIN32)
     SET(CBLAS_PROVIDER openblas)
     IF(WITH_C_API)
-        INSTALL(DIRECTORY ${CBLAS_INCLUDE_DIR} DESTINATION third_party/openblas)
+        INSTALL(DIRECTORY ${CBLAS_INC_DIR} DESTINATION third_party/openblas)
         # Because libopenblas.a is a symbolic link of another library, thus need to
         # install the whole directory.
         IF(ANDROID)
@@ -117,8 +117,8 @@ IF(NOT ${CBLAS_FOUND})
 ENDIF(NOT ${CBLAS_FOUND})
 
 MESSAGE(STATUS "BLAS library: ${CBLAS_LIBRARIES}")
-MESSAGE(STATUS "BLAS Include: ${CBLAS_INCLUDE_DIR}")
-INCLUDE_DIRECTORIES(${CBLAS_INCLUDE_DIR})
+MESSAGE(STATUS "BLAS Include: ${CBLAS_INC_DIR}")
+INCLUDE_DIRECTORIES(${CBLAS_INC_DIR})
 
 # FIXME(gangliao): generate cblas target to track all high performance
 # linear algebra libraries for cc_library(xxx SRCS xxx.c DEPS cblas)

paddle/fluid/API.spec

@@ -1,3 +1,4 @@
+
 # windows treat symbolic file as a real file, which is different with unix
 # We create a hidden file and compile it instead of origin source file.
 function(windows_symbolic TARGET)
@@ -9,11 +10,23 @@ function(windows_symbolic TARGET)
   if (NOT EXISTS ${CMAKE_CURRENT_SOURCE_DIR}/${src}.cc OR NOT EXISTS ${CMAKE_CURRENT_SOURCE_DIR}/${src}.cu)
       message(FATAL " ${src}.cc and ${src}.cu must exsits, and ${src}.cu must be symbolic file.")
   endif()
-  add_custom_command(OUTPUT .${src}.cu 
+
+  # only copy the xx.cu to .xx.cu when the content are modified
+  set(copy_flag 1)
+  if (EXISTS ${CMAKE_CURRENT_SOURCE_DIR}/.${src}.cu)
+  file(READ ${CMAKE_CURRENT_SOURCE_DIR}/${src}.cc SOURCE_STR)
+  file(READ ${CMAKE_CURRENT_SOURCE_DIR}/.${src}.cu TARGET_STR)
+  if (SOURCE_STR STREQUAL TARGET_STR)
+    set(copy_flag 0)
+  endif()
+  endif()
+  if (copy_flag)
+  add_custom_command(OUTPUT .${src}.cu
           COMMAND ${CMAKE_COMMAND} -E remove ${CMAKE_CURRENT_SOURCE_DIR}/.${src}.cu
           COMMAND ${CMAKE_COMMAND} -E copy "${CMAKE_CURRENT_SOURCE_DIR}/${src}.cc" "${CMAKE_CURRENT_SOURCE_DIR}/.${src}.cu"
           COMMENT "create hidden file of ${src}.cu")
-  add_custom_target(${TARGET} ALL DEPENDS .${src}.cu)  
+  endif(copy_flag)
+  add_custom_target(${TARGET} ALL DEPENDS .${src}.cu)
   endforeach()
 endfunction()
 
@@ -81,6 +94,8 @@ nv_test(data_device_transform_test SRCS data_device_transform_test.cu
 
 if(WITH_GPU)
   if (WIN32)
+    # windows treat symbolic file as a real file, which is different with unix
+    # We create a hidden file and compile it instead of origin source file.
       windows_symbolic(hidden_file SRCS data_type_transform.cu)
       nv_library(data_type_transform SRCS .data_type_transform.cu DEPS tensor)
       add_dependencies(data_type_transform hidden_file)
@@ -149,7 +164,7 @@ if(WITH_DISTRIBUTE)
   set_source_files_properties(executor.cc PROPERTIES COMPILE_FLAGS ${DISTRIBUTE_COMPILE_FLAGS})
 else()
   cc_library(executor SRCS executor.cc DEPS op_registry device_context scope framework_proto glog lod_rank_table feed_fetch_method graph_to_program_pass)
-  cc_test(test_naive_executor SRCS naive_executor_test.cc DEPS naive_executor op_registry device_context scope framework_proto glog lod_rank_table feed_fetch_method graph_to_program_pass elementwise_add_op)
+  cc_test(test_naive_executor SRCS naive_executor_test.cc DEPS naive_executor elementwise_add_op)
 endif()
 
 if (NOT WIN32)
@@ -169,15 +184,8 @@ cc_test(selected_rows_test SRCS selected_rows_test.cc DEPS selected_rows)
 cc_test(op_kernel_type_test SRCS op_kernel_type_test.cc DEPS place device_context framework_proto)
 cc_test(cow_ptr_tests SRCS details/cow_ptr_test.cc)
 
-# cc_test(channel_test SRCS channel_test.cc)
 cc_test(tuple_test SRCS tuple_test.cc )
 
 if (NOT WIN32)
 cc_test(rw_lock_test SRCS rw_lock_test.cc)
 endif (NOT WIN32)
-
-# disable test temporarily.
-# TODO https://github.com/PaddlePaddle/Paddle/issues/11971
-# cc_test(concurrency_test SRCS concurrency_test.cc DEPS go_op channel_close_op channel_create_op
-#         channel_send_op channel_recv_op sum_op select_op elementwise_add_op compare_op
-#         conditional_block_op while_op assign_op print_op executor proto_desc)