Merge remote-tracking branch 'upstream/develop' into fix_unittest

PaddlePaddle · Apr 20, 2021 · d30a017 · d30a017 · paddle-bot-old · Apr 21, 2021
2 parents d428d3e + 5e7e7c9
commit d30a017
Show file tree

Hide file tree

Showing 644 changed files with 33,768 additions and 21,615 deletions.
diff --git a/CMakeLists.txt b/CMakeLists.txt
@@ -33,13 +33,20 @@ option(WITH_TENSORRT    "Compile PaddlePaddle with NVIDIA TensorRT"     OFF)
 option(WITH_XPU         "Compile PaddlePaddle with BAIDU KUNLUN XPU"    OFF)
 option(WITH_WIN_DUMP_DBG "Compile with windows core dump debug mode"    OFF)
 option(WITH_ASCEND         "Compile PaddlePaddle with ASCEND"        OFF)
+option(WITH_ROCM        "Compile PaddlePaddle with ROCM platform"       OFF)
+# NOTE(zhiqiu): WITH_ASCEND_CL can be compile on x86_64, so we can set WITH_ASCEND=OFF and WITH_ASCEND_CL=ON 
+# to develop some acl related functionality on x86
+option(WITH_ASCEND_CL         "Compile PaddlePaddle with ASCEND CL"        ${WITH_ASCEND})
 option(WITH_ASCEND_CXX11         "Compile PaddlePaddle with ASCEND and CXX11 ABI"        OFF)
 if (WITH_GPU  AND WITH_XPU)
     message(FATAL_ERROR "Error when compile GPU and XPU at the same time")
 endif()
-if (WITH_GPU  AND WITH_ASCEND)
+if (WITH_GPU AND WITH_ASCEND)
     message(FATAL_ERROR "Error when compile GPU and ASCEND at the same time")
 endif()
+if (WITH_GPU AND WITH_ROCM)
+    message(FATAL_ERROR "Error when compile CUDA and ROCM at the same time")
+endif()
 
 if(WITH_GPU AND NOT APPLE)
     enable_language(CUDA)
@@ -165,8 +172,6 @@ option(WITH_DISTRIBUTE  "Compile with distributed support"              OFF)
 option(WITH_BRPC_RDMA     "Use brpc rdma as the rpc protocal"           OFF)
 option(ON_INFER         "Turn on inference optimization and inference-lib generation" OFF)
 ################################ Internal Configurations #######################################
-option(WITH_ROCM        "Compile PaddlePaddle with ROCM platform"         OFF)
-option(WITH_RCCL        "Compile PaddlePaddle with RCCL support"          OFF)
 option(WITH_NV_JETSON   "Compile PaddlePaddle with NV JETSON"             OFF)
 option(WITH_PROFILER    "Compile PaddlePaddle with GPU profiler and gperftools"        OFF)
 option(WITH_COVERAGE    "Compile PaddlePaddle with code coverage"       OFF)
@@ -179,12 +184,14 @@ option(WITH_XBYAK       "Compile with xbyak support"                    ON)
 option(WITH_CONTRIB     "Compile the third-party contributation"        OFF)
 option(WITH_GRPC     "Use grpc as the default rpc framework"            ${WITH_DISTRIBUTE})
 option(WITH_PSCORE     "Compile with parameter server support"         ${WITH_DISTRIBUTE})
+option(WITH_HETERPS     "Compile with heterps"                          OFF})
 option(WITH_INFERENCE_API_TEST   "Test fluid inference C++ high-level api interface"  OFF)
 option(PY_VERSION       "Compile PaddlePaddle with python3 support"     ${PY_VERSION})
 option(WITH_DGC   "Use DGC(Deep Gradient Compression) or not" ${WITH_DISTRIBUTE})
 option(SANITIZER_TYPE "Choose the type of sanitizer, options are: Address, Leak, Memory, Thread, Undefined" OFF)
 option(WITH_LITE   "Compile Paddle Fluid with Lite Engine" OFF)
 option(WITH_NCCL   "Compile PaddlePaddle with NCCL support"             ON)
+option(WITH_RCCL   "Compile PaddlePaddle with RCCL support"             ON)
 option(WITH_XPU_BKCL    "Compile PaddlePaddle with BAIDU KUNLUN XPU BKCL"   OFF)
 option(WITH_CRYPTO   "Compile PaddlePaddle with crypto support"         ON)
 option(WITH_ARM   "Compile PaddlePaddle with arm support"         OFF)
@@ -302,9 +309,9 @@ endif(WITH_ROCM)
 
 if (NOT WITH_ROCM AND WITH_RCCL)
     MESSAGE(WARNING
-        "Disable RCCL when compiling without GPU. Force WITH_RCCL=OFF.")
-    set(WITH_NCCL OFF CACHE STRING
-        "Disable RCCL when compiling without GPU" FORCE)
+        "Disable RCCL when compiling without ROCM. Force WITH_RCCL=OFF.")
+    set(WITH_RCCL OFF CACHE STRING
+        "Disable RCCL when compiling without ROCM" FORCE)
 endif()
 
 if(WITH_RCCL)

diff --git a/cmake/configure.cmake b/cmake/configure.cmake
@@ -82,6 +82,10 @@ if(WITH_ASCEND)
     add_definitions(-DPADDLE_WITH_ASCEND)
 endif()
 
+if(WITH_ASCEND_CL)
+    add_definitions(-DPADDLE_WITH_ASCEND_CL)
+endif()
+
 if(WITH_XPU)
     message(STATUS "Compile with XPU!")
     add_definitions(-DPADDLE_WITH_XPU)
@@ -169,6 +173,9 @@ if(WITH_PSCORE)
     add_definitions(-DPADDLE_WITH_PSCORE)
 endif()
 
+if(WITH_HETERPS)
+    add_definitions(-DPADDLE_WITH_HETERPS)
+endif()
 
 if(WITH_GRPC)
     add_definitions(-DPADDLE_WITH_GRPC)

diff --git a/cmake/external/ascend.cmake b/cmake/external/ascend.cmake
@@ -21,38 +21,65 @@ else()
     set(ASCEND_DIR /usr/local/Ascend)
 endif()
 
-set(ASCEND_DRIVER_DIR ${ASCEND_DIR}/driver/lib64)
-set(ASCEND_DRIVER_COMMON_DIR ${ASCEND_DIR}/driver/lib64/common)
-set(ASCEND_DRIVER_SHARE_DIR ${ASCEND_DIR}/driver/lib64/share)
-set(ASCEND_RUNTIME_DIR ${ASCEND_DIR}/fwkacllib/lib64)
-set(ASCEND_ATC_DIR ${ASCEND_DIR}/atc/lib64)
-set(ASCEND_ACL_DIR ${ASCEND_DIR}/acllib/lib64)
-set(STATIC_ACL_LIB ${ASCEND_ACL_DIR})
-
-set(ASCEND_MS_RUNTIME_PATH ${ASCEND_RUNTIME_DIR} ${ASCEND_ACL_DIR} ${ASCEND_ATC_DIR})
-set(ASCEND_MS_DRIVER_PATH ${ASCEND_DRIVER_DIR} ${ASCEND_DRIVER_COMMON_DIR})
-set(ATLAS_RUNTIME_DIR ${ASCEND_DIR}/ascend-toolkit/latest/fwkacllib/lib64)
-set(ATLAS_RUNTIME_INC_DIR ${ASCEND_DIR}/ascend-toolkit/latest/fwkacllib/include)
-set(ATLAS_ACL_DIR ${ASCEND_DIR}/ascend-toolkit/latest/acllib/lib64)
-set(ATLAS_ATC_DIR ${ASCEND_DIR}/ascend-toolkit/latest/atc/lib64)
-set(ATLAS_MS_RUNTIME_PATH ${ATLAS_RUNTIME_DIR} ${ATLAS_ACL_DIR} ${ATLAS_ATC_DIR})
-
-set(atlas_graph_lib ${ATLAS_RUNTIME_DIR}/libgraph.so)
-set(atlas_ge_runner_lib ${ATLAS_RUNTIME_DIR}/libge_runner.so)
-set(atlas_acl_lib ${ATLAS_RUNTIME_DIR}/libascendcl.so)
-INCLUDE_DIRECTORIES(${ATLAS_RUNTIME_INC_DIR})
-
-if(EXISTS ${ATLAS_RUNTIME_INC_DIR}/graph/ascend_string.h)
+if(EXISTS ${ASCEND_DIR}/ascend-toolkit/latest/fwkacllib/include/graph/ascend_string.h)
+  # It means CANN 20.2 +
   add_definitions(-DPADDLE_WITH_ASCEND_STRING)
 endif()
 
-ADD_LIBRARY(ascend_ge SHARED IMPORTED GLOBAL)
-SET_PROPERTY(TARGET ascend_ge PROPERTY IMPORTED_LOCATION ${atlas_ge_runner_lib})
+if(WITH_ASCEND)
+  set(ASCEND_DRIVER_DIR ${ASCEND_DIR}/driver/lib64)
+  set(ASCEND_DRIVER_COMMON_DIR ${ASCEND_DIR}/driver/lib64/common)
+  set(ASCEND_DRIVER_SHARE_DIR ${ASCEND_DIR}/driver/lib64/share)
+  set(ASCEND_RUNTIME_DIR ${ASCEND_DIR}/fwkacllib/lib64)
+  set(ASCEND_ATC_DIR ${ASCEND_DIR}/atc/lib64)
+  set(ASCEND_ACL_DIR ${ASCEND_DIR}/acllib/lib64)
+  set(STATIC_ACL_LIB ${ASCEND_ACL_DIR})
 
-ADD_LIBRARY(ascend_graph SHARED IMPORTED GLOBAL)
-SET_PROPERTY(TARGET ascend_graph PROPERTY IMPORTED_LOCATION ${atlas_graph_lib})
+  set(ASCEND_MS_RUNTIME_PATH ${ASCEND_RUNTIME_DIR} ${ASCEND_ACL_DIR} ${ASCEND_ATC_DIR})
+  set(ASCEND_MS_DRIVER_PATH ${ASCEND_DRIVER_DIR} ${ASCEND_DRIVER_COMMON_DIR})
+  set(ATLAS_RUNTIME_DIR ${ASCEND_DIR}/ascend-toolkit/latest/fwkacllib/lib64)
+  set(ATLAS_RUNTIME_INC_DIR ${ASCEND_DIR}/ascend-toolkit/latest/fwkacllib/include)
+  set(ATLAS_ACL_DIR ${ASCEND_DIR}/ascend-toolkit/latest/acllib/lib64)
+  set(ATLAS_ATC_DIR ${ASCEND_DIR}/ascend-toolkit/latest/atc/lib64)
+  set(ATLAS_MS_RUNTIME_PATH ${ATLAS_RUNTIME_DIR} ${ATLAS_ACL_DIR} ${ATLAS_ATC_DIR})
 
-ADD_LIBRARY(atlas_acl SHARED IMPORTED GLOBAL)
-SET_PROPERTY(TARGET atlas_acl PROPERTY IMPORTED_LOCATION ${atlas_acl_lib})
+  set(atlas_graph_lib ${ATLAS_RUNTIME_DIR}/libgraph.so)
+  set(atlas_ge_runner_lib ${ATLAS_RUNTIME_DIR}/libge_runner.so)
+  set(atlas_acl_lib ${ATLAS_RUNTIME_DIR}/libascendcl.so)
+  INCLUDE_DIRECTORIES(${ATLAS_RUNTIME_INC_DIR})
 
-add_custom_target(extern_ascend DEPENDS ascend_ge ascend_graph atlas_acl)
+
+
+  ADD_LIBRARY(ascend_ge SHARED IMPORTED GLOBAL)
+  SET_PROPERTY(TARGET ascend_ge PROPERTY IMPORTED_LOCATION ${atlas_ge_runner_lib})
+
+  ADD_LIBRARY(ascend_graph SHARED IMPORTED GLOBAL)
+  SET_PROPERTY(TARGET ascend_graph PROPERTY IMPORTED_LOCATION ${atlas_graph_lib})
+
+  ADD_LIBRARY(atlas_acl SHARED IMPORTED GLOBAL)
+  SET_PROPERTY(TARGET atlas_acl PROPERTY IMPORTED_LOCATION ${atlas_acl_lib})
+
+  add_custom_target(extern_ascend DEPENDS ascend_ge ascend_graph atlas_acl)
+endif()
+
+if(WITH_ASCEND_CL)
+  set(ASCEND_CL_DIR ${ASCEND_DIR}/ascend-toolkit/latest/fwkacllib/lib64)
+
+  set(ascendcl_lib ${ASCEND_CL_DIR}/libascendcl.so)
+  set(acl_op_compiler_lib ${ASCEND_CL_DIR}/libacl_op_compiler.so)
+  set(FWKACLLIB_INC_DIR ${ASCEND_DIR}/ascend-toolkit/latest/fwkacllib/include)
+  set(ACLLIB_INC_DIR ${ASCEND_DIR}/ascend-toolkit/latest/acllib/include)
+
+  message(STATUS "FWKACLLIB_INC_DIR ${FWKACLLIB_INC_DIR}")
+  message(STATUS "ASCEND_CL_DIR ${ASCEND_CL_DIR}")
+  INCLUDE_DIRECTORIES(${FWKACLLIB_INC_DIR})
+  INCLUDE_DIRECTORIES(${ACLLIB_INC_DIR})
+
+  ADD_LIBRARY(ascendcl SHARED IMPORTED GLOBAL)
+  SET_PROPERTY(TARGET ascendcl PROPERTY IMPORTED_LOCATION ${ascendcl_lib})
+
+  ADD_LIBRARY(acl_op_compiler SHARED IMPORTED GLOBAL)
+  SET_PROPERTY(TARGET acl_op_compiler PROPERTY IMPORTED_LOCATION ${acl_op_compiler_lib})
+  add_custom_target(extern_ascend_cl DEPENDS ascendcl acl_op_compiler)
+
+endif()
diff --git a/cmake/external/brpc.cmake b/cmake/external/brpc.cmake
@@ -39,7 +39,7 @@ set(prefix_path "${THIRD_PARTY_PATH}/install/gflags|${THIRD_PARTY_PATH}/install/
 ExternalProject_Add(
         extern_brpc
         ${EXTERNAL_PROJECT_LOG_ARGS}
-        # TODO(gongwb): change to de newst repo when they changed.
+        # TODO(gongwb): change to de newst repo when they changed
         GIT_REPOSITORY  "https://github.com/wangjiawei04/brpc"
         GIT_TAG         "e203afb794caf027da0f1e0776443e7d20c0c28e"
         PREFIX          ${BRPC_SOURCES_DIR}

diff --git a/cmake/external/gloo.cmake b/cmake/external/gloo.cmake
@@ -32,7 +32,7 @@ cache_third_party(extern_gloo
     TAG           ${GLOO_TAG}
     DIR           GLOO_SOURCE_DIR)
 
-if(WITH_ASCEND)
+  if(WITH_ASCEND OR WITH_ASCEND_CL)
   ExternalProject_Add(
       extern_gloo
       ${EXTERNAL_PROJECT_LOG_ARGS}

diff --git a/cmake/external/grpc.cmake b/cmake/external/grpc.cmake
diff --git a/cmake/external/mkldnn.cmake b/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            72efa005effb49595933e033cc732f215ef0445a)
+SET(MKLDNN_TAG            f58682cd8bd0615f41d879f8afc8f1511ab42d24)
 
 # Introduce variables:
 # * CMAKE_INSTALL_LIBDIR

diff --git a/cmake/external/protobuf.cmake b/cmake/external/protobuf.cmake
@@ -201,6 +201,9 @@ FUNCTION(build_protobuf TARGET_NAME BUILD_FOR_HOST)
 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)
@@ -239,7 +242,7 @@ endif()
     )
 ENDFUNCTION()
 
-if(WITH_ASCEND)
+if(WITH_ASCEND OR WITH_ASCEND_CL)
     SET(PROTOBUF_VERSION 3.8.0)
 else()
     SET(PROTOBUF_VERSION 3.1.0)

diff --git a/cmake/external/threadpool.cmake b/cmake/external/threadpool.cmake
@@ -16,7 +16,7 @@ INCLUDE(ExternalProject)
 
 SET(THREADPOOL_PREFIX_DIR ${THIRD_PARTY_PATH}/threadpool)
 SET(THREADPOOL_SOURCE_DIR ${THIRD_PARTY_PATH}/threadpool/src/extern_threadpool)
-if(WITH_ASCEND)
+if(WITH_ASCEND OR WITH_ASCEND_CL)
     SET(THREADPOOL_REPOSITORY https://gitee.com/tianjianhe/ThreadPool.git)
 else()
     SET(THREADPOOL_REPOSITORY ${GIT_URL}/progschj/ThreadPool.git)

diff --git a/cmake/external/warpctc.cmake b/cmake/external/warpctc.cmake
@@ -43,7 +43,7 @@ cache_third_party(extern_warpctc
     TAG          ${WARPCTC_TAG}
     DIR          WARPCTC_SOURCE_DIR)
 
-if(WITH_ASCEND)
+if(WITH_ASCEND OR WITH_ASCEND_CL)
     ExternalProject_Add(
         extern_warpctc
         ${EXTERNAL_PROJECT_LOG_ARGS}

diff --git a/cmake/external/xpu.cmake b/cmake/external/xpu.cmake
@@ -13,7 +13,7 @@ if(NOT XPU_SDK_ROOT)
   elseif(WITH_SUNWAY)
       SET(XPU_URL    "https://baidu-kunlun-public.su.bcebos.com/paddle_depence/sunway/xpu_2021_01_13.tar.gz" CACHE STRING "" FORCE)
   else()
-      SET(XPU_URL    "https://baidu-kunlun-public.su.bcebos.com/paddle_depence/xpu_2021_03_30.tar.gz" CACHE STRING "" FORCE)
+      SET(XPU_URL    "https://baidu-kunlun-public.su.bcebos.com/paddle_depence/xpu_2021_04_09.tar.gz" CACHE STRING "" FORCE)
   endif()
 
   SET(XPU_SOURCE_DIR              "${THIRD_PARTY_PATH}/xpu")