Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into stablize_depthwise_conv

Author: jerrywgz

.pre-commit-config.yaml

@@ -49,4 +49,7 @@ repos:
         entry: python ./tools/codestyle/copyright.hook
         language: system
         files: \.(c|cc|cxx|cpp|cu|h|hpp|hxx|proto|py|sh)$
-        exclude: (?!.*third_party)^.*$ | (?!.*book)^.*$
+        exclude: |
+            (?x)^(
+                paddle/utils/.*
+            )$

CMakeLists.txt

@@ -130,7 +130,7 @@ if(WIN32)
         # NOTE(zhouwei25): GPU compile have too high memory utilization when parallel compiling,
         # For Visual Studio generators, /MP should be added. 
         # For other generators like Ninja, it is not need to add /MP.
-        if("${CMAKE_GENERATOR}" STREQUAL "Visual Studio" AND NOT WITH_GPU)
+        if(CMAKE_GENERATOR MATCHES "Visual Studio" AND NOT WITH_GPU)
             math(EXPR PROCESS_MAX "${CPU_CORES} * 2 / 3")
             set(${flag_var} "${${flag_var}} /MP${PROCESS_MAX}")
         endif()

cmake/cupti.cmake

@@ -9,6 +9,7 @@ find_path(CUPTI_INCLUDE_DIR cupti.h
         $ENV{CUPTI_ROOT} $ENV{CUPTI_ROOT}/include
         ${CUDA_TOOLKIT_ROOT_DIR}/extras/CUPTI/include
         ${CUDA_TOOLKIT_ROOT_DIR}/targets/x86_64-linux/include
+        ${CUDA_TOOLKIT_ROOT_DIR}/targets/aarch64-linux/include
         NO_DEFAULT_PATH
         )
 

cmake/external/gflags.cmake

@@ -41,6 +41,7 @@ ExternalProject_Add(
     ${SHALLOW_CLONE}
     "${GFLAGS_DOWNLOAD_CMD}"
     PREFIX          ${GFLAGS_PREFIX_DIR}
+    UPDATE_COMMAND  ""
     SOURCE_DIR      ${GFLAGS_SOURCE_DIR}
     BUILD_COMMAND   ${BUILD_COMMAND}
     INSTALL_COMMAND ${INSTALL_COMMAND}

cmake/external/glog.cmake

@@ -45,6 +45,7 @@ ExternalProject_Add(
     DEPENDS         gflags
     PREFIX          ${GLOG_PREFIX_DIR}
     SOURCE_DIR      ${GLOG_SOURCE_DIR}
+    UPDATE_COMMAND  ""
     CMAKE_ARGS      -DCMAKE_CXX_COMPILER=${CMAKE_CXX_COMPILER}
                     -DCMAKE_C_COMPILER=${CMAKE_C_COMPILER}
                     -DCMAKE_CXX_FLAGS=${GLOG_CMAKE_CXX_FLAGS}

cmake/external/mkldnn.cmake

@@ -20,7 +20,7 @@ SET(MKLDNN_SOURCE_DIR     ${THIRD_PARTY_PATH}/mkldnn/src/extern_mkldnn)
 SET(MKLDNN_INSTALL_DIR    ${THIRD_PARTY_PATH}/install/mkldnn)
 SET(MKLDNN_INC_DIR        "${MKLDNN_INSTALL_DIR}/include" CACHE PATH "mkldnn include directory." FORCE)
 SET(MKLDNN_REPOSITORY     ${GIT_URL}/oneapi-src/oneDNN.git)
-SET(MKLDNN_TAG            593e0de6267d2575f3e4c9e9818f0f11253d093a)
+SET(MKLDNN_TAG            e2d45252ae9c3e91671339579e3c0f0061f81d49)
 
 
 # Introduce variables:
@@ -79,49 +79,44 @@ ExternalProject_Add(
                         -DCMAKE_CXX_FLAGS=${MKLDNN_CXXFLAG}
                         -DDNNL_BUILD_TESTS=OFF -DDNNL_BUILD_EXAMPLES=OFF
     CMAKE_CACHE_ARGS    -DCMAKE_INSTALL_PREFIX:PATH=${MKLDNN_INSTALL_DIR}
-    BUILD_BYPRODUCTS    ${MKLDNN_LIB}
 )
 
-ADD_LIBRARY(shared_mkldnn SHARED IMPORTED GLOBAL)
-SET_PROPERTY(TARGET shared_mkldnn PROPERTY IMPORTED_LOCATION ${MKLDNN_LIB})
-ADD_DEPENDENCIES(shared_mkldnn ${MKLDNN_PROJECT})
 MESSAGE(STATUS "MKLDNN library: ${MKLDNN_LIB}")
 add_definitions(-DPADDLE_WITH_MKLDNN)
-
-# generate a static dummy target to track mkldnn dependencies
-# for cc_library(xxx SRCS xxx.c DEPS mkldnn)
-generate_dummy_static_lib(LIB_NAME "mkldnn" GENERATOR "mkldnn.cmake")
-
-TARGET_LINK_LIBRARIES(mkldnn ${MKLDNN_LIB} ${MKLML_IOMP_LIB})
-ADD_DEPENDENCIES(mkldnn ${MKLDNN_PROJECT})
-
 # copy the real so.0 lib to install dir
 # it can be directly contained in wheel or capi
 if(WIN32)
     SET(MKLDNN_SHARED_LIB ${MKLDNN_INSTALL_DIR}/bin/mkldnn.dll)
 
     file(TO_NATIVE_PATH ${MKLDNN_INSTALL_DIR} NATIVE_MKLDNN_INSTALL_DIR)
     file(TO_NATIVE_PATH ${MKLDNN_SHARED_LIB} NATIVE_MKLDNN_SHARED_LIB)
-    ADD_CUSTOM_COMMAND(TARGET ${MKLDNN_PROJECT} POST_BUILD
-        COMMAND (copy ${NATIVE_MKLDNN_INSTALL_DIR}\\bin\\dnnl.dll ${NATIVE_MKLDNN_SHARED_LIB} /Y))
-    add_custom_command(TARGET ${MKLDNN_PROJECT} POST_BUILD VERBATIM
-        COMMAND dumpbin /exports ${MKLDNN_INSTALL_DIR}/bin/mkldnn.dll > ${MKLDNN_INSTALL_DIR}/bin/exports.txt)
-    add_custom_command(TARGET ${MKLDNN_PROJECT} POST_BUILD VERBATIM
-        COMMAND echo LIBRARY mkldnn > ${MKLDNN_INSTALL_DIR}/bin/mkldnn.def)
-    add_custom_command(TARGET ${MKLDNN_PROJECT} POST_BUILD VERBATIM
-        COMMAND echo EXPORTS >> ${MKLDNN_INSTALL_DIR}/bin/mkldnn.def)
-    add_custom_command(TARGET ${MKLDNN_PROJECT} POST_BUILD VERBATIM
-        COMMAND echo off && (for /f "skip=19 tokens=4" %A in (${MKLDNN_INSTALL_DIR}/bin/exports.txt) do echo %A >> ${MKLDNN_INSTALL_DIR}/bin/mkldnn.def) && echo on)
-    add_custom_command(TARGET ${MKLDNN_PROJECT} POST_BUILD VERBATIM
-        COMMAND lib /def:${MKLDNN_INSTALL_DIR}/bin/mkldnn.def /out:${MKLDNN_INSTALL_DIR}/bin/mkldnn.lib /machine:x64)
+
+    ADD_CUSTOM_COMMAND(OUTPUT ${MKLDNN_LIB}
+        COMMAND (copy ${NATIVE_MKLDNN_INSTALL_DIR}\\bin\\dnnl.dll ${NATIVE_MKLDNN_SHARED_LIB} /Y)
+        COMMAND dumpbin /exports ${MKLDNN_INSTALL_DIR}/bin/mkldnn.dll > ${MKLDNN_INSTALL_DIR}/bin/exports.txt
+        COMMAND echo LIBRARY mkldnn > ${MKLDNN_INSTALL_DIR}/bin/mkldnn.def
+        COMMAND echo EXPORTS >> ${MKLDNN_INSTALL_DIR}/bin/mkldnn.def
+        COMMAND echo off && (for /f "skip=19 tokens=4" %A in (${MKLDNN_INSTALL_DIR}/bin/exports.txt) do echo %A >> ${MKLDNN_INSTALL_DIR}/bin/mkldnn.def) && echo on
+        COMMAND lib /def:${MKLDNN_INSTALL_DIR}/bin/mkldnn.def /out:${MKLDNN_LIB} /machine:x64
+        COMMENT "Generate mkldnn.lib manually--->"
+        DEPENDS ${MKLDNN_PROJECT}
+        VERBATIM)
+    ADD_CUSTOM_TARGET(mkldnn_cmd ALL DEPENDS ${MKLDNN_LIB})
 else(WIN32)
     SET(MKLDNN_SHARED_LIB ${MKLDNN_INSTALL_DIR}/libmkldnn.so.0)
     SET(MKLDNN_SHARED_LIB_1 ${MKLDNN_INSTALL_DIR}/libdnnl.so.1)
     SET(MKLDNN_SHARED_LIB_2 ${MKLDNN_INSTALL_DIR}/libdnnl.so.2)
-    ADD_CUSTOM_COMMAND(TARGET ${MKLDNN_PROJECT} POST_BUILD
-            COMMAND ${CMAKE_COMMAND} -E copy ${MKLDNN_LIB} ${MKLDNN_SHARED_LIB})
-    ADD_CUSTOM_COMMAND(TARGET ${MKLDNN_PROJECT} POST_BUILD
-            COMMAND ${CMAKE_COMMAND} -E copy ${MKLDNN_LIB} ${MKLDNN_SHARED_LIB_1})
-    ADD_CUSTOM_COMMAND(TARGET ${MKLDNN_PROJECT} POST_BUILD
-            COMMAND ${CMAKE_COMMAND} -E copy ${MKLDNN_LIB} ${MKLDNN_SHARED_LIB_2})
+    ADD_CUSTOM_COMMAND(OUTPUT ${MKLDNN_SHARED_LIB_2}
+        COMMAND ${CMAKE_COMMAND} -E copy ${MKLDNN_LIB} ${MKLDNN_SHARED_LIB}
+        COMMAND ${CMAKE_COMMAND} -E copy ${MKLDNN_LIB} ${MKLDNN_SHARED_LIB_1}
+        COMMAND ${CMAKE_COMMAND} -E copy ${MKLDNN_LIB} ${MKLDNN_SHARED_LIB_2}
+        DEPENDS ${MKLDNN_PROJECT})
+    ADD_CUSTOM_TARGET(mkldnn_cmd ALL DEPENDS ${MKLDNN_SHARED_LIB_2})
 endif(WIN32)
+
+# generate a static dummy target to track mkldnn dependencies
+# for cc_library(xxx SRCS xxx.c DEPS mkldnn)
+generate_dummy_static_lib(LIB_NAME "mkldnn" GENERATOR "mkldnn.cmake")
+
+TARGET_LINK_LIBRARIES(mkldnn ${MKLDNN_LIB} ${MKLML_IOMP_LIB})
+ADD_DEPENDENCIES(mkldnn ${MKLDNN_PROJECT} mkldnn_cmd)

cmake/external/protobuf.cmake

@@ -198,16 +198,16 @@ FUNCTION(build_protobuf TARGET_NAME BUILD_FOR_HOST)
             "-Dprotobuf_MSVC_STATIC_RUNTIME=${MSVC_STATIC_CRT}")
     ENDIF()
 
-if(WITH_ASCEND AND NOT WITH_ASCEND_CXX11)
-    SET(PROTOBUF_REPOSITORY  https://gitee.com/tianjianhe/protobuf.git)
-    SET(PROTOBUF_TAG         v3.8.0)
-elseif(WITH_ASCEND_CL AND NOT WITH_ASCEND_CXX11)
-    SET(PROTOBUF_REPOSITORY  https://gitee.com/tianjianhe/protobuf.git)
-    SET(PROTOBUF_TAG         v3.8.0)
-else()
-    SET(PROTOBUF_REPOSITORY  ${GIT_URL}/protocolbuffers/protobuf.git)
-    SET(PROTOBUF_TAG         9f75c5aa851cd877fb0d93ccc31b8567a6706546)
-endif()
+    if(WITH_ASCEND AND NOT WITH_ASCEND_CXX11)
+        SET(PROTOBUF_REPOSITORY  https://gitee.com/tianjianhe/protobuf.git)
+        SET(PROTOBUF_TAG         v3.8.0)
+    elseif(WITH_ASCEND_CL AND NOT WITH_ASCEND_CXX11)
+        SET(PROTOBUF_REPOSITORY  https://gitee.com/tianjianhe/protobuf.git)
+        SET(PROTOBUF_TAG         v3.8.0)
+    else()
+        SET(PROTOBUF_REPOSITORY  ${GIT_URL}/protocolbuffers/protobuf.git)
+        SET(PROTOBUF_TAG         9f75c5aa851cd877fb0d93ccc31b8567a6706546)
+    endif()
 
     cache_third_party(${TARGET_NAME}
         REPOSITORY    ${PROTOBUF_REPOSITORY}

cmake/external/pybind11.cmake

@@ -39,6 +39,7 @@ ExternalProject_Add(
         # to be modified without triggering incremental compilation, and the
         # third-party library version changes cannot be incorporated.
         # reference: https://cmake.org/cmake/help/latest/module/ExternalProject.html
+        UPDATE_COMMAND    ""
         CONFIGURE_COMMAND ""
         BUILD_COMMAND     ""
         INSTALL_COMMAND   ""

cmake/external/xpu.cmake

@@ -35,7 +35,7 @@ ELSE ()
 ENDIF()
 
 SET(XPU_BASE_URL_WITHOUT_DATE "https://baidu-kunlun-product.cdn.bcebos.com/KL-SDK/klsdk-dev")
-SET(XPU_BASE_URL "${XPU_BASE_URL_WITHOUT_DATE}/20210804")
+SET(XPU_BASE_URL "${XPU_BASE_URL_WITHOUT_DATE}/20210818")
 SET(XPU_XRE_URL  "${XPU_BASE_URL}/${XPU_XRE_DIR_NAME}.tar.gz" CACHE STRING "" FORCE)
 SET(XPU_XDNN_URL "${XPU_BASE_URL}/${XPU_XDNN_DIR_NAME}.tar.gz" CACHE STRING "" FORCE)
 SET(XPU_XCCL_URL "${XPU_BASE_URL_WITHOUT_DATE}/20210623/${XPU_XCCL_DIR_NAME}.tar.gz" CACHE STRING "" FORCE)

cmake/inference_lib.cmake

@@ -72,6 +72,12 @@ function(copy_part_of_thrid_party TARGET DST)
             copy(${TARGET}
                     SRCS ${MKLML_LIB} ${MKLML_IOMP_LIB} ${MKLML_INC_DIR}
                     DSTS ${dst_dir}/lib ${dst_dir}/lib ${dst_dir})
+            if(WITH_STRIP)
+                    add_custom_command(TARGET ${TARGET} POST_BUILD
+                            COMMAND strip -s ${dst_dir}/lib/libiomp5.so
+                            COMMAND strip -s ${dst_dir}/lib/libmklml_intel.so
+                            COMMENT "striping libiomp5.so\nstriping libmklml_intel.so")
+            endif()
         endif()
     elseif(${CBLAS_PROVIDER} STREQUAL EXTERN_OPENBLAS)
         set(dst_dir "${DST}/third_party/install/openblas")
@@ -94,8 +100,17 @@ function(copy_part_of_thrid_party TARGET DST)
                     DSTS ${dst_dir} ${dst_dir}/lib ${dst_dir}/lib)
         else()
             copy(${TARGET}
-                    SRCS ${MKLDNN_INC_DIR} ${MKLDNN_SHARED_LIB} ${MKLDNN_SHARED_LIB_1} ${MKLDNN_SHARED_LIB_2}
-                    DSTS ${dst_dir} ${dst_dir}/lib ${dst_dir}/lib ${dst_dir}/lib)
+                    SRCS ${MKLDNN_INC_DIR} ${MKLDNN_SHARED_LIB}
+                    DSTS ${dst_dir} ${dst_dir}/lib)
+            if(WITH_STRIP)
+                    add_custom_command(TARGET ${TARGET} POST_BUILD
+                            COMMAND strip -s ${dst_dir}/lib/libmkldnn.so.0
+                            COMMENT "striping libmkldnn.so.0")
+            endif()
+            add_custom_command(TARGET ${TARGET} POST_BUILD
+                    COMMAND ${CMAKE_COMMAND} -E create_symlink libmkldnn.so.0 ${dst_dir}/lib/libdnnl.so.1
+                    COMMAND ${CMAKE_COMMAND} -E create_symlink libmkldnn.so.0 ${dst_dir}/lib/libdnnl.so.2
+                    COMMENT "Make a symbol link of libmkldnn.so.0")
         endif()
     endif()
 
@@ -205,6 +220,9 @@ copy(inference_lib_dist
 copy(inference_lib_dist
         SRCS  ${PADDLE_SOURCE_DIR}/paddle/fluid/platform/float16.h
         DSTS  ${PADDLE_INFERENCE_INSTALL_DIR}/paddle/include/experimental/)
+copy(inference_lib_dist
+        SRCS  ${PADDLE_SOURCE_DIR}/paddle/utils/any.h
+        DSTS  ${PADDLE_INFERENCE_INSTALL_DIR}/paddle/include/experimental/)
 
 # CAPI inference library for only inference
 set(PADDLE_INFERENCE_C_INSTALL_DIR "${CMAKE_BINARY_DIR}/paddle_inference_c_install_dir" CACHE STRING
@@ -222,6 +240,13 @@ copy(inference_lib_dist
       SRCS  ${src_dir}/inference/capi_exp/pd_*.h  ${paddle_inference_c_lib}
       DSTS  ${PADDLE_INFERENCE_C_INSTALL_DIR}/paddle/include ${PADDLE_INFERENCE_C_INSTALL_DIR}/paddle/lib)
 
+if(WITH_STRIP AND NOT WIN32)
+        add_custom_command(TARGET inference_lib_dist POST_BUILD
+                COMMAND strip -s ${PADDLE_INFERENCE_C_INSTALL_DIR}/paddle/lib/libpaddle_inference_c.so
+                COMMAND strip -s ${PADDLE_INFERENCE_INSTALL_DIR}/paddle/lib/libpaddle_inference.so
+                COMMENT "striping libpaddle_inference_c.so\nstriping libpaddle_inference.so")
+endif()
+
 # fluid library for both train and inference
 set(fluid_lib_deps inference_lib_dist)
 add_custom_target(fluid_lib_dist ALL DEPENDS ${fluid_lib_deps})