Merge remote-tracking branch 'ups/develop' into fea/jit/rnn

Author: tensor-tang

CMakeLists.txt

@@ -204,6 +204,7 @@ include(external/eigen)     # download eigen3
 include(external/pybind11)  # download pybind11
 include(external/cares)
 include(external/cub)
+include(external/rocprim)
 include(external/xxhash)    # download xxhash
 include(external/dlpack)
 include(external/snappy)    # download snappy

Dockerfile

@@ -22,6 +22,27 @@ ENV HOME /root
 # Add bash enhancements
 COPY ./paddle/scripts/docker/root/ /root/
 
+# Prepare packages for Python
+RUN apt-get update && \
+    apt-get install -y make build-essential libssl-dev zlib1g-dev libbz2-dev \
+    libreadline-dev libsqlite3-dev wget curl llvm libncurses5-dev libncursesw5-dev \
+    xz-utils tk-dev libffi-dev liblzma-dev
+
+# Install Python3.6
+RUN mkdir -p /root/python_build/ && wget -q https://www.sqlite.org/2018/sqlite-autoconf-3250300.tar.gz && \
+    tar -zxf sqlite-autoconf-3250300.tar.gz && cd sqlite-autoconf-3250300 && \
+    ./configure -prefix=/usr/local && make -j8 && make install && cd ../ && rm sqlite-autoconf-3250300.tar.gz && \
+    wget -q https://www.python.org/ftp/python/3.6.0/Python-3.6.0.tgz && \
+    tar -xzf Python-3.6.0.tgz && cd Python-3.6.0 && \
+    CFLAGS="-Wformat" ./configure --prefix=/usr/local/ --enable-shared > /dev/null && \
+    make -j8 > /dev/null && make altinstall > /dev/null
+
+# Install Python3.7
+RUN wget -q https://www.python.org/ftp/python/3.7.0/Python-3.7.0.tgz && \
+    tar -xzf Python-3.7.0.tgz && cd Python-3.7.0 && \
+    CFLAGS="-Wformat" ./configure --prefix=/usr/local/ --enable-shared > /dev/null && \
+    make -j8 > /dev/null && make altinstall > /dev/null
+
 RUN apt-get update && \
     apt-get install -y --allow-downgrades patchelf \
     python3 python3-dev python3-pip \
@@ -74,6 +95,12 @@ RUN localedef -i en_US -f UTF-8 en_US.UTF-8
 RUN pip3 install -U wheel && \
     pip3 install -U docopt PyYAML sphinx==1.5.6 && \
     pip3 install sphinx-rtd-theme==0.1.9 recommonmark && \
+    pip3.6 install -U wheel && \
+    pip3.6 install -U docopt PyYAML sphinx==1.5.6 && \
+    pip3.6 install sphinx-rtd-theme==0.1.9 recommonmark && \
+    pip3.7 install -U wheel && \
+    pip3.7 install -U docopt PyYAML sphinx==1.5.6 && \
+    pip3.7 install sphinx-rtd-theme==0.1.9 recommonmark && \
     easy_install -U pip && \
     pip install -U pip setuptools wheel && \
     pip install -U docopt PyYAML sphinx==1.5.6 && \
@@ -82,22 +109,34 @@ RUN pip3 install -U wheel && \
 RUN pip3 install 'pre-commit==1.10.4' 'ipython==5.3.0' && \
     pip3 install 'ipykernel==4.6.0' 'jupyter==1.0.0' && \
     pip3 install opencv-python && \
+    pip3.6 install 'pre-commit==1.10.4' 'ipython==5.3.0' && \
+    pip3.6 install 'ipykernel==4.6.0' 'jupyter==1.0.0' && \
+    pip3.6 install opencv-python && \
+    pip3.7 install 'pre-commit==1.10.4' 'ipython==5.3.0' && \
+    pip3.7 install 'ipykernel==4.6.0' 'jupyter==1.0.0' && \
+    pip3.7 install opencv-python && \
     pip install 'pre-commit==1.10.4' '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 pip3.6 install pylint pytest astroid isort
+RUN pip3.7 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 pip3.6 install -r /root/requirements.txt
+RUN pip3.7 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 pip3.6 install certifi urllib3[secure]
+RUN pip3.7 install certifi urllib3[secure]
 RUN pip install certifi urllib3[secure]
 
 

cmake/external/eigen.cmake

@@ -17,7 +17,7 @@ if(WITH_AMD_GPU)
         extern_eigen3
         ${EXTERNAL_PROJECT_LOG_ARGS}
         GIT_REPOSITORY  "https://github.com/sabreshao/hipeigen.git"
-        GIT_TAG         0cba03ff9f8f9f70bbd92ac5857b031aa8fed6f9
+        GIT_TAG         7cb2b6e5a4b4a1efe658abb215cd866c6fb2275e
         PREFIX          ${EIGEN_SOURCE_DIR}
         UPDATE_COMMAND  ""
         CONFIGURE_COMMAND ""

cmake/external/mkldnn.cmake

@@ -53,7 +53,7 @@ ExternalProject_Add(
     ${EXTERNAL_PROJECT_LOG_ARGS}
     DEPENDS             ${MKLDNN_DEPENDS}
     GIT_REPOSITORY      "https://github.com/01org/mkl-dnn.git"
-    GIT_TAG             "21fb5f2af1dd14e132af4f1b79160977ee487818"
+    GIT_TAG             "830a10059a018cd2634d94195140cf2d8790a75a"
     PREFIX              ${MKLDNN_SOURCES_DIR}
     UPDATE_COMMAND      ""
     CMAKE_ARGS          -DCMAKE_CXX_COMPILER=${CMAKE_CXX_COMPILER}

cmake/external/rocprim.cmake

@@ -0,0 +1,44 @@
+if (NOT WITH_AMD_GPU)
+    return()
+endif()
+
+# rocprim is "ROCm Parallel Primitives" for short.
+# It is a header-only library providing HIP and HC parallel primitives
+# for developing performant GPU-accelerated code on AMD ROCm platform.
+
+if("x${HCC_HOME}" STREQUAL "x")
+  set(HCC_HOME "/opt/rocm/hcc")
+endif()
+
+INCLUDE(ExternalProject)
+
+SET(ROCPRIM_SOURCE_DIR ${THIRD_PARTY_PATH}/rocprim)
+SET(ROCPRIM_INSTALL_DIR  ${THIRD_PARTY_PATH}/install/rocprim)
+SET(ROCPRIM_INCLUDE_DIR ${ROCPRIM_INSTALL_DIR}/include)
+
+ExternalProject_Add(
+    extern_rocprim
+    GIT_REPOSITORY "https://github.com/ROCmSoftwarePlatform/rocPRIM.git"
+    GIT_TAG        5bd41b96ab8d8343330fb2c3e1b96775bde3b3fc 
+    PREFIX         ${ROCPRIM_SOURCE_DIR}
+    UPDATE_COMMAND  ""
+    CMAKE_ARGS     -DCMAKE_CXX_COMPILER=${HCC_HOME}/bin/hcc
+    CMAKE_ARGS     -DONLY_INSTALL=ON
+    CMAKE_ARGS     -DBUILD_TEST=OFF
+    CMAKE_ARGS     -DCMAKE_INSTALL_PREFIX=${ROCPRIM_INSTALL_DIR}
+
+    INSTALL_DIR    ${ROCPRIM_INSTALL_DIR}
+    ${EXTERNAL_PROJECT_LOG_ARGS}
+)
+
+INCLUDE_DIRECTORIES(${ROCPRIM_INCLUDE_DIR})
+
+if (${CMAKE_VERSION} VERSION_LESS "3.3.0")
+    set(dummyfile ${CMAKE_CURRENT_BINARY_DIR}/rocprim_dummy.c)
+    file(WRITE ${dummyfile} "const char *dummy_rocprim = \"${dummyfile}\";")
+    add_library(rocprim STATIC ${dummyfile})
+else()
+    add_library(rocprim INTERFACE)
+endif()
+
+add_dependencies(rocprim extern_rocprim)

cmake/flags.cmake

@@ -129,6 +129,9 @@ set(COMMON_FLAGS
     -Wno-error=parentheses-equality # Warnings in pybind11
     -Wno-error=ignored-attributes  # Warnings in Eigen, gcc 6.3
     -Wno-error=terminate  # Warning in PADDLE_ENFORCE
+    -Wno-error=int-in-bool-context # Warning in Eigen gcc 7.2
+    -Wimplicit-fallthrough=0 # Warning in tinyformat.h
+    -Wno-error=maybe-uninitialized # Warning in boost gcc 7.2
 )
 
 set(GPU_COMMON_FLAGS

cmake/generic.cmake

@@ -454,25 +454,29 @@ function(hip_library TARGET_NAME)
       else()
         add_library(${TARGET_NAME} STATIC ${_cmake_options} ${_generated_files} ${_sources})
         set_target_properties(${TARGET_NAME} PROPERTIES LINKER_LANGUAGE CXX)
-        target_link_libraries(${TARGET_NAME} /opt/rocm/hip/lib/libhip_hcc.so /opt/rocm/hip/lib/libhip_device.a)
-	find_fluid_modules(${TARGET_NAME})
+        target_link_libraries(${TARGET_NAME} /opt/rocm/hip/lib/libhip_hcc.so /opt/rocm/hip/lib/libhip_device.a /opt/rocm/rccl/lib/librccl.so /opt/rocm/hiprand/lib/libhiprand.so)
+        find_fluid_modules(${TARGET_NAME})
       endif()
-      if (hip_library_DEPS)
-	add_dependencies(${TARGET_NAME} ${hip_library_DEPS})
-	target_link_libraries(${TARGET_NAME} ${hip_library_DEPS})
+      if("${hip_library_DEPS}" MATCHES "ARCHIVE_START")
+        # Support linking flags: --whole-archive (Linux) / -force_load (MacOS).
+        # WARNING: Please don't use ARCHIVE_START&ARCHIVE_END if TARGET_NAME will be linked by other libraries.
+        target_circle_link_libraries(${TARGET_NAME} ${hip_library_DEPS})
+        list(REMOVE_ITEM hip_library_DEPS ARCHIVE_START ARCHIVE_END)
+      else()
+        target_link_libraries(${TARGET_NAME} ${hip_library_DEPS})
       endif()
       # cpplint code style
       foreach(source_file ${hip_library_SRCS})
-	string(REGEX REPLACE "\\.[^.]*$" "" source ${source_file})
-	if(EXISTS ${CMAKE_CURRENT_SOURCE_DIR}/${source}.h)
-	  list(APPEND hip_library_HEADERS ${CMAKE_CURRENT_SOURCE_DIR}/${source}.h)
-	endif()
+        string(REGEX REPLACE "\\.[^.]*$" "" source ${source_file})
+        if(EXISTS ${CMAKE_CURRENT_SOURCE_DIR}/${source}.h)
+          list(APPEND hip_library_HEADERS ${CMAKE_CURRENT_SOURCE_DIR}/${source}.h)
+        endif()
       endforeach()
     else(hip_library_SRCS)
       if (hip_library_DEPS)
-	merge_static_libs(${TARGET_NAME} ${hip_library_DEPS})
+        merge_static_libs(${TARGET_NAME} ${hip_library_DEPS})
       else()
-	message(FATAL "Please specify source file or library in nv_library.")
+        message(FATAL "Please specify source file or library in nv_library.")
       endif()
     endif(hip_library_SRCS)
   endif()

cmake/hip.cmake

@@ -3,6 +3,8 @@ if(NOT WITH_AMD_GPU)
 endif()
 
 include_directories("/opt/rocm/include")
+include_directories("/opt/rocm/hip/include")
+include_directories("/opt/rocm/miopen/include")
 include_directories("/opt/rocm/hipblas/include")
 include_directories("/opt/rocm/hiprand/include")
 include_directories("/opt/rocm/rocrand/include")
@@ -11,20 +13,40 @@ include_directories("/opt/rocm/thrust")
 
 list(APPEND EXTERNAL_LIBS "-L/opt/rocm/lib/ -lhip_hcc")
 
-set(HIP_HCC_FLAGS "${HIP_HCC_FLAGS} -fPIC -DPADDLE_WITH_HIP -std=c++14" )
+set(HIP_HCC_FLAGS "${HIP_HCC_FLAGS} -fPIC -DPADDLE_WITH_HIP -std=c++11" )
 
 if(WITH_DSO)
   set(HIP_HCC_FLAGS "${HIP_HCC_FLAGS} -DPADDLE_USE_DSO")
 endif(WITH_DSO)
 
-if(WITH_DOUBLE)
-  set(HIP_HCC_FLAGS "${HIP_HCC_FLAGS} -DPADDLE_TYPE_DOUBLE")
-endif(WITH_DOUBLE)
-
 if(WITH_TESTING)
   set(HIP_HCC_FLAGS "${HIP_HCC_FLAGS} -DPADDLE_WITH_TESTING")
 endif(WITH_TESTING)
 
+if(WITH_DISTRIBUTE)
+  set(HIP_HCC_FLAGS "${HIP_HCC_FLAGS} -DPADDLE_WITH_DISTRIBUTE")
+endif(WITH_DISTRIBUTE)
+
+if(WITH_GRPC)
+  set(HIP_HCC_FLAGS "${HIP_HCC_FLAGS} -DPADDLE_WITH_GRPC")
+endif(WITH_GRPC)
+
+if(NOT WITH_GOLANG)
+  set(HIP_HCC_FLAGS "${HIP_HCC_FLAGS} -DPADDLE_WITHOUT_GOLANG")
+endif(NOT WITH_GOLANG)
+
+if(WITH_MKLDNN)
+  set(HIP_HCC_FLAGS "${HIP_HCC_FLAGS} -DPADDLE_WITH_MKLDNN")
+endif(WITH_MKLDNN)
+
+set(HIP_HCC_FLAGS "${HIP_HCC_FLAGS} -DANY_IMPL_ANY_CAST_MOVEABLE")
+
+if(NOT WITH_RDMA)
+  set(HIP_HCC_FLAGS "${HIP_HCC_FLAGS} -DPADDLE_DISABLE_RDMA")
+endif(NOT WITH_RDMA)
+
+
+
 if(CMAKE_BUILD_TYPE  STREQUAL "Debug")
     list(APPEND HIP_HCC_FLAGS  ${CMAKE_CXX_FLAGS_DEBUG})
 elseif(CMAKE_BUILD_TYPE  STREQUAL "RelWithDebInfo")

cmake/operators.cmake

@@ -109,7 +109,8 @@ function(op_library TARGET)
 
     # Define operators that don't need pybind here.
     foreach(manual_pybind_op "compare_op" "logical_op" "nccl_op"
-"tensor_array_read_write_op" "tensorrt_engine_op" "conv_fusion_op")
+"tensor_array_read_write_op" "tensorrt_engine_op" "conv_fusion_op"
+"fusion_transpose_flatten_concat_op")
         if ("${TARGET}" STREQUAL "${manual_pybind_op}")
             set(pybind_flag 1)
         endif()

paddle/fluid/API.spec

@@ -276,7 +276,7 @@ paddle.fluid.layers.hard_shrink ArgSpec(args=['x', 'threshold'], varargs=None, k
 paddle.fluid.layers.cumsum ArgSpec(args=['x', 'axis', 'exclusive', 'reverse'], varargs=None, keywords=None, defaults=(None, None, None))
 paddle.fluid.layers.thresholded_relu ArgSpec(args=['x', 'threshold'], varargs=None, keywords=None, defaults=(None,))
 paddle.fluid.layers.prior_box ArgSpec(args=['input', 'image', 'min_sizes', 'max_sizes', 'aspect_ratios', 'variance', 'flip', 'clip', 'steps', 'offset', 'name', 'min_max_aspect_ratios_order'], varargs=None, keywords=None, defaults=(None, [1.0], [0.1, 0.1, 0.2, 0.2], False, False, [0.0, 0.0], 0.5, None, False))
-paddle.fluid.layers.density_prior_box ArgSpec(args=['input', 'image', 'densities', 'fixed_sizes', 'fixed_ratios', 'variance', 'clip', 'steps', 'offset', 'name'], varargs=None, keywords=None, defaults=(None, None, None, [0.1, 0.1, 0.2, 0.2], False, [0.0, 0.0], 0.5, None))
+paddle.fluid.layers.density_prior_box ArgSpec(args=['input', 'image', 'densities', 'fixed_sizes', 'fixed_ratios', 'variance', 'clip', 'steps', 'offset', 'flatten_to_2d', 'name'], varargs=None, keywords=None, defaults=(None, None, None, [0.1, 0.1, 0.2, 0.2], False, [0.0, 0.0], 0.5, False, None))
 paddle.fluid.layers.multi_box_head ArgSpec(args=['inputs', 'image', 'base_size', 'num_classes', 'aspect_ratios', 'min_ratio', 'max_ratio', 'min_sizes', 'max_sizes', 'steps', 'step_w', 'step_h', 'offset', 'variance', 'flip', 'clip', 'kernel_size', 'pad', 'stride', 'name', 'min_max_aspect_ratios_order'], varargs=None, keywords=None, defaults=(None, None, None, None, None, None, None, 0.5, [0.1, 0.1, 0.2, 0.2], True, False, 1, 0, 1, None, False))
 paddle.fluid.layers.bipartite_match ArgSpec(args=['dist_matrix', 'match_type', 'dist_threshold', 'name'], varargs=None, keywords=None, defaults=(None, None, None))
 paddle.fluid.layers.target_assign ArgSpec(args=['input', 'matched_indices', 'negative_indices', 'mismatch_value', 'name'], varargs=None, keywords=None, defaults=(None, None, None))
@@ -342,7 +342,7 @@ paddle.fluid.transpiler.RoundRobin.dispatch ArgSpec(args=['self', 'varlist'], va
 paddle.fluid.transpiler.RoundRobin.reset ArgSpec(args=['self'], varargs=None, keywords=None, defaults=None)
 paddle.fluid.transpiler.DistributeTranspilerConfig.__init__ 
 paddle.fluid.nets.simple_img_conv_pool ArgSpec(args=['input', 'num_filters', 'filter_size', 'pool_size', 'pool_stride', 'pool_padding', 'pool_type', 'global_pooling', 'conv_stride', 'conv_padding', 'conv_dilation', 'conv_groups', 'param_attr', 'bias_attr', 'act', 'use_cudnn'], varargs=None, keywords=None, defaults=(0, 'max', False, 1, 0, 1, 1, None, None, None, True))
-paddle.fluid.nets.sequence_conv_pool ArgSpec(args=['input', 'num_filters', 'filter_size', 'param_attr', 'act', 'pool_type'], varargs=None, keywords=None, defaults=(None, 'sigmoid', 'max'))
+paddle.fluid.nets.sequence_conv_pool ArgSpec(args=['input', 'num_filters', 'filter_size', 'param_attr', 'act', 'pool_type', 'bias_attr'], varargs=None, keywords=None, defaults=(None, 'sigmoid', 'max', None))
 paddle.fluid.nets.glu ArgSpec(args=['input', 'dim'], varargs=None, keywords=None, defaults=(-1,))
 paddle.fluid.nets.scaled_dot_product_attention ArgSpec(args=['queries', 'keys', 'values', 'num_heads', 'dropout_rate'], varargs=None, keywords=None, defaults=(1, 0.0))
 paddle.fluid.nets.img_conv_group ArgSpec(args=['input', 'conv_num_filter', 'pool_size', 'conv_padding', 'conv_filter_size', 'conv_act', 'param_attr', 'conv_with_batchnorm', 'conv_batchnorm_drop_rate', 'pool_stride', 'pool_type', 'use_cudnn'], varargs=None, keywords=None, defaults=(1, 3, None, None, False, 0.0, 1, 'max', True))