提交 ef28f66f 编写于 作者: T Tao Luo 提交者: GitHub

Merge pull request #2940 from tensor-tang/develop

enable Intel MKLDNN library and Intel MKL small package
上级 91d2a57a 19c465bb
develop 2.0.1-rocm-post Ligoml-patch-1 OliverLPH-patch-1 OliverLPH-patch-2 PaddlePM-patch-1 PaddlePM-patch-2 ZHUI-patch-1 add_default_att add_model_benchmark_ci add_some_yaml_config addfile all_new_design_exec ascendrc ascendrelease cherry_undefined_var compile_windows delete_2.0.1-rocm-post delete_add_default_att delete_all_new_design_exec delete_ascendrc delete_compile_windows delete_delete_addfile delete_disable_iterable_dataset_unittest delete_fix_dataloader_memory_leak delete_fix_imperative_dygraph_error delete_fix_retry_ci delete_fix_undefined_var delete_improve_sccache delete_incubate/lite delete_paddle_tiny_install delete_paralleltest delete_prv-disable-more-cache delete_revert-31068-fix_conv3d_windows delete_revert-31562-mean delete_revert-33630-bug-fix delete_revert-34159-add_npu_bce_logical_dev delete_revert-34910-spinlocks_for_allocator delete_revert-35069-revert-34910-spinlocks_for_allocator delete_revert-36057-dev/read_flags_in_ut dingjiaweiww-patch-1 disable_iterable_dataset_unittest dy2static enable_eager_model_test final_state_gen_python_c final_state_intermediate fix-numpy-issue fix_concat_slice fix_dataloader_memory_leak fix_imperative_dygraph_error fix_npu_ci fix_op_flops fix_retry_ci fix_rnn_docs fix_tensor_type fix_undefined_var fixiscan fixiscan1 fixiscan2 fixiscan3 github/fork/123malin/netifaces github/fork/123malin/tdm_abacus github/fork/AshburnLee/dev_unique github/fork/ForFishes/fix_memory_matmul github/fork/ForFishes/rm_fluid github/fork/LielinJiang/move-2.0-api github/fork/LielinJiang/visual-dl-cb github/fork/LiuChiachi/add-transformer-generate-square-subsequent-mask-api github/fork/LiuChiachi/fix-example-code-for-hapi-Model github/fork/LiuChiachi/remove-input-requirment-in-dygraph-Model github/fork/MrChengmo/fix_ps_profiler github/fork/MrChengmo/update_ps_heter github/fork/PWhiddy/patch-1 github/fork/Shixiaowei02/dev/save_load_upgrade github/fork/TCChenlong/fix_hapi github/fork/TCChenlong/fix_inden github/fork/Thunderbrook/xpu_slice github/fork/XieYunshen/disable_ut_test_parallel_executor_fetch_isolated_var github/fork/XieYunshen/disable_ut_test_parallel_executor_fetch_isolated_var_2 github/fork/XieYunshen/disable_ut_test_parallel_executor_fetch_isolated_var_3 github/fork/XieYunshen/timeout_20S_ut github/fork/ZeyuChen/remove-nltk github/fork/arlesniak/arlesniak/selective__mkldnn_flags github/fork/baiyfbupt/code_doc_mig github/fork/chalsliu/set_timeout github/fork/chen-zhiyu/develop github/fork/chenwhql/ci/try_to_find_test_buffer_shared_memory_reuse_pass_error github/fork/chenwhql/dygraph/remove_scale_loss_and_apply_collective_grads github/fork/chenwhql/saveload/add_get_inference_program github/fork/chenwhql/saveload/remove_save_load_config github/fork/cryoco/pass-compatibility-trt github/fork/danleifeng/isempty_api2.0 github/fork/frankwhzhang/api_transfer github/fork/hbwx24/error_msg/cuda_kernel_error_msg github/fork/heavengate/cherry_yolo_box github/fork/heavengate/update_yolo_box github/fork/iclementine/rnn_fix github/fork/iducn/testestse github/fork/jczaja/prv-25537-fix github/fork/jeff41404/release/1.8 github/fork/jiweibo/api_2.0 github/fork/jiweibo/fix_lite_resnet50_test github/fork/juncaipeng/fix_doc_1 github/fork/lfchener/sample_code github/fork/littletomatodonkey/fix_reg_doc github/fork/liym27/dy2stat_update_assign_to_rc20 github/fork/luotao1/profiler_ut github/fork/mapingshuo/add_wait github/fork/mapingshuo/doc_2.0 github/fork/mapingshuo/zero-0.5 github/fork/miraiwk/dev github/fork/pangyoki/add-Categorical-class-branch github/fork/pangyoki/add-multinomial-op-branch github/fork/pangyoki/fix-test_distritbution-CI github/fork/qjing666/doublegrad github/fork/qjing666/fix_hdfs_download github/fork/sandyhouse/add_gather_etc github/fork/sandyhouse/add_send_recv_alltoall_etc github/fork/sandyhouse/pipeline_exe_run github/fork/seiriosPlus/feature/large_scale_kv_save_delta github/fork/seiriosPlus/fix/paddle_errors_fix github/fork/seiriosPlus/fix/paddle_op_errors github/fork/shangzhizhou/fix_test_activation_op_random_bug github/fork/smallv0221/yxp0924 github/fork/smallv0221/yxp0925 github/fork/swtkiwi/del-matplotlib github/fork/tianshuo78520a/kunlun_test github/fork/tianshuo78520a/update_dockerfile github/fork/wanghaoshuang/bert_fuse github/fork/wanghaoshuang/label_smooth github/fork/wanghuancoder/develop_CUDASynchronize github/fork/wanghuancoder/develop_Layer_doc github/fork/wanghuancoder/develop_ParameterList_doc github/fork/wanghuancoder/develop_Sequential_doc github/fork/wanghuancoder/develop_bilinear_tensor_product github/fork/wanghuancoder/develop_coverage_build_sh github/fork/wanghuancoder/develop_in_dynamic_mode_doc github/fork/wanghuancoder/develop_unique_name_doc github/fork/wangxicoding/fleet_meta_combine github/fork/wawltor/error_message_fix_5 github/fork/willthefrog/remove_l2_norm github/fork/windstamp/momentum_op github/fork/windstamp/mv_op_5 github/fork/windstamp/normal_api github/fork/wojtuss/wojtuss/fusion_gru_quantization github/fork/wojtuss/wojtuss/quantization-with-shift github/fork/wzzju/fix_err_info github/fork/wzzju/pure_fp16 github/fork/xiemoyuan/op_error_message github/fork/xiemoyuan/optimize_error_message github/fork/yaoxuefeng6/fix_doc github/fork/yaoxuefeng6/mod_dataset_v2 github/fork/yongqiangma/lod github/fork/ysh329/fix-clip-by-norm-error github/fork/ysh329/fix-error-clip-by-value github/fork/yukavio/error_info github/fork/zhangting2020/conv_filter_grad github/fork/zhangting2020/is_compile_with_cuda github/fork/zhangting2020/place_doc github/fork/zhangting2020/program github/fork/zhhsplendid/fix_any github/fork/zhhsplendid/refine_api2 github/fork/zhhsplendid/refine_api2_test github/fork/zhhsplendid/refine_api_test_ptb_lm github/fork/zhhsplendid/refine_api_test_resnet github/fork/zhhsplendid/refine_api_test_simnet github/fork/zhiqiu/dev/refine_initializer github/fork/zhiqiu/dev/remove_inplace_argument github/fork/zlsh80826/nvinfer_plugin_var_len_cuda11 improve_sccache incubate/infrt incubate/lite inplace_addto make_flag_adding_easier master move_embedding_to_phi move_histogram_to_pten move_sgd_to_phi move_slice_to_pten move_temporal_shift_to_phi move_yolo_box_to_phi npu_fix_alloc numel paddle_tiny_install paralleltest preln_ernie prv-disable-more-cache prv-md-even-more prv-onednn-2.5 pten_tensor_refactor release/0.11.0 release/0.12.0 release/0.13.0 release/0.14.0 release/0.15.0 release/1.0.0 release/1.1 release/1.2 release/1.3 release/1.4 release/1.5 release/1.6 release/1.7 release/1.8 release/2.0 release/2.0-alpha release/2.0-beta release/2.0-rc release/2.0-rc1 release/2.1 release/2.2 release/2.3 release/2.3-fc-ernie-fix release/2.4 release/lite-0.1 revert-24981-add_device_attr_for_regulization revert-26856-strategy_example2 revert-27520-disable_pr revert-31068-fix_conv3d_windows revert-31562-mean revert-32290-develop-hardlabel revert-33037-forci revert-33475-fix_cifar_label_dimension revert-33630-bug-fix revert-34159-add_npu_bce_logical_dev revert-34406-add_copy_from_tensor revert-34910-spinlocks_for_allocator revert-35069-revert-34910-spinlocks_for_allocator revert-36057-dev/read_flags_in_ut revert-36201-refine_fast_threaded_ssa_graph_executor revert-36985-add_license revert-37318-refactor_dygraph_to_eager revert-37926-eager_coreops_500 revert-37956-revert-37727-pylayer_support_tuple revert-38100-mingdong revert-38301-allocation_rearrange_pr revert-38703-numpy_bf16_package_reupload revert-38732-remove_useless_header_in_elementwise_mul_grad revert-38959-Reduce_Grad revert-39143-adjust_empty revert-39227-move_trace_op_to_pten revert-39268-dev/remove_concat_fluid_kernel revert-40170-support_partial_grad revert-41056-revert-40727-move_some_activaion_to_phi revert-41065-revert-40993-mv_ele_floordiv_pow revert-41068-revert-40790-phi_new revert-41944-smaller_inference_api_test revert-42149-do-not-reset-default-stream-for-stream-safe-cuda-allocator revert-43155-fix_ut_tempfile revert-43882-revert-41944-smaller_inference_api_test revert-45808-phi/simplify_size_op revert-46827-deform_comment rocm_dev_0217 support_weight_transpose test_benchmark_ci test_feature_precision_test_c test_model_benchmark test_model_benchmark_ci zhiqiu-patch-1 v2.4.0-rc0 v2.3.2 v2.3.1 v2.3.0 v2.3.0-rc0 v2.2.2 v2.2.1 v2.2.0 v2.2.0-rc0 v2.2.0-bak0 v2.1.3 v2.1.2 v2.1.1 v2.1.0 v2.1.0-rc0 v2.0.2 v2.0.1 v2.0.0 v2.0.0-rc1 v2.0.0-rc0 v2.0.0-beta0 v2.0.0-alpha0 v1.8.5 v1.8.4 v1.8.3 v1.8.2 v1.8.1 v1.8.0 v1.7.2 v1.7.1 v1.7.0 v1.6.3 v1.6.2 v1.6.1 v1.6.0 v1.6.0-rc0 v1.5.2 v1.5.1 v1.5.0 v1.4.1 v1.4.0 v1.3.2 v1.3.1 v1.3.0 v1.2.1 v1.2.0 v1.1.0 v1.0.2 v1.0.1 v1.0.0 v1.0.0-rc0 v0.15.0 v0.15.0-rc0 v0.14.0 v0.13.0 v0.12.0 v0.11.1a2 v0.11.1a1 v0.11.0 lite-v0.1
无相关合并请求
......@@ -36,6 +36,8 @@ include(simd)
################################ Configurations #######################################
option(WITH_GPU "Compile PaddlePaddle with NVIDIA GPU" ${CUDA_FOUND})
option(WITH_AVX "Compile PaddlePaddle with AVX intrinsics" ${AVX_FOUND})
option(WITH_MKLDNN "Compile PaddlePaddle with mkl-dnn support." OFF)
option(WITH_MKLML "Compile PaddlePaddle with mklml package." OFF)
option(WITH_DSO "Compile PaddlePaddle with dynamic linked CUDA" ON)
option(WITH_TESTING "Compile PaddlePaddle with unit testing" ON)
option(WITH_SWIG_PY "Compile PaddlePaddle with inference api" ON)
......@@ -74,6 +76,10 @@ if(ANDROID)
"Disable PYTHON when cross-compiling for Android" FORCE)
set(WITH_RDMA OFF CACHE STRING
"Disable RDMA when cross-compiling for Android" FORCE)
set(WITH_MKLDNN OFF CACHE STRING
"Disable MKLDNN when cross-compiling for Android" FORCE)
set(WITH_MKLML OFF CACHE STRING
"Disable MKLML package when cross-compiling for Android" FORCE)
endif(ANDROID)
set(THIRD_PARTY_PATH "${CMAKE_BINARY_DIR}/third_party" CACHE STRING
......@@ -87,6 +93,7 @@ endif()
########################################################################################
include(external/mklml) # download mklml package
include(external/zlib) # download, build, install zlib
include(external/gflags) # download, build, install gflags
include(external/glog) # download, build, install glog
......@@ -94,6 +101,7 @@ include(external/gtest) # download, build, install gtest
include(external/protobuf) # download, build, install protobuf
include(external/python) # download, build, install python
include(external/openblas) # download, build, install openblas
include(external/mkldnn) # download, build, install mkldnn
include(external/swig) # download, build, install swig
include(external/warpctc) # download, build, install warpctc
include(external/any) # download libn::any
......@@ -135,6 +143,10 @@ if(WITH_GPU)
endif(NOT WITH_DSO)
endif(WITH_GPU)
if(WITH_MKLDNN)
list(APPEND EXTERNAL_LIBS ${MKLDNN_LIBRARY} ${MKLDNN_IOMP_LIB})
endif()
if(USE_NNPACK)
include(external/nnpack)
list(APPEND EXTERNAL_LIBS ${NNPACK_LIBS})
......
......@@ -15,23 +15,44 @@
set(CBLAS_FOUND OFF)
## Find MKL First.
set(INTEL_ROOT "/opt/intel" CACHE PATH "Folder contains intel libs")
set(MKL_ROOT ${INTEL_ROOT}/mkl CACHE PATH "Folder contains MKL")
## Find MKLML First.
if(WITH_MKLML AND MKLML_INC_DIR AND MKLML_LIB)
set(CBLAS_FOUND ON)
set(CBLAS_PROVIDER MKLML)
set(CBLAS_INC_DIR ${MKLML_INC_DIR})
set(CBLAS_LIBRARIES ${MKLML_LIB})
add_definitions(-DPADDLE_USE_MKLML)
add_definitions(-DLAPACK_FOUND)
message(STATUS "Found cblas and lapack in MKLML "
"(include: ${CBLAS_INC_DIR}, library: ${CBLAS_LIBRARIES})")
return()
endif()
## Then find MKL.
set(INTEL_MKL_ROOT "/opt/intel/mkl" CACHE PATH "Folder contains intel mkl libs")
set(MKL_ROOT $ENV{MKL_ROOT} CACHE PATH "Folder contains env MKL")
set(MKL_INCLUDE_SEARCH_PATHS
${MKL_ROOT}/include
${INTEL_MKL_ROOT}/include)
set(MKL_LIB_SEARCH_PATHS
${MKL_ROOT}/lib
${MKL_ROOT}/lib/intel64
${INTEL_MKL_ROOT}/lib
${INTEL_MKL_ROOT}/lib/intel64)
find_path(MKL_INC_DIR mkl.h PATHS
${MKL_ROOT}/include)
${MKL_INCLUDE_SEARCH_PATHS})
find_path(MKL_LAPACK_INC_DIR mkl_lapacke.h PATHS
${MKL_ROOT}/include)
${MKL_INCLUDE_SEARCH_PATHS})
find_library(MKL_CORE_LIB NAMES mkl_core PATHS
${MKL_ROOT}/lib
${MKL_ROOT}/lib/intel64)
${MKL_LIB_SEARCH_PATHS})
find_library(MKL_SEQUENTIAL_LIB NAMES mkl_sequential PATHS
${MKL_ROOT}/lib
${MKL_ROOT}/lib/intel64)
${MKL_LIB_SEARCH_PATHS})
find_library(MKL_INTEL_LP64 NAMES mkl_intel_lp64 PATHS
${MKL_ROOT}/lib
${MKL_ROOT}/lib/intel64)
${MKL_LIB_SEARCH_PATHS})
if(MKL_LAPACK_INC_DIR AND MKL_INC_DIR AND MKL_CORE_LIB AND MKL_SEQUENTIAL_LIB AND MKL_INTEL_LP64)
set(CBLAS_FOUND ON)
......
......@@ -67,6 +67,30 @@ else()
include_directories(${CUDA_TOOLKIT_INCLUDE})
endif(NOT WITH_GPU)
if(WITH_MKLDNN)
add_definitions(-DPADDLE_USE_MKLDNN)
if (WITH_MKLML AND MKLDNN_IOMP_DIR)
message(STATUS "Enable Intel OpenMP at ${MKLDNN_IOMP_DIR}")
set(OPENMP_FLAGS "-fopenmp")
set(CMAKE_C_CREATE_SHARED_LIBRARY_FORBIDDEN_FLAGS ${OPENMP_FLAGS})
set(CMAKE_CXX_CREATE_SHARED_LIBRARY_FORBIDDEN_FLAGS ${OPENMP_FLAGS})
set(CMAKE_SHARED_LINKER_FLAGS "${CMAKE_SHARED_LINKER_FLAGS} -L${MKLDNN_IOMP_DIR} -liomp5 -Wl,--as-needed")
set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -L${MKLDNN_IOMP_DIR} -liomp5 -Wl,--as-needed")
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} ${OPENMP_FLAGS}")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${OPENMP_FLAGS}")
else()
find_package(OpenMP)
if(OPENMP_FOUND)
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} ${OpenMP_C_FLAGS}")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${OpenMP_CXX_FLAGS}")
else()
message(WARNING "Can not find OpenMP."
"Some performance features in MKLDNN may not be available")
endif()
endif()
endif(WITH_MKLDNN)
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} ${SIMD_FLAG}")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${SIMD_FLAG}")
......
......@@ -34,9 +34,15 @@ IF(WITH_TESTING)
"${GTEST_INSTALL_DIR}/lib/libgtest_main.a" CACHE FILEPATH "gtest main libraries." FORCE)
ENDIF(WIN32)
IF(WITH_MKLML)
# wait for mklml downloading completed
SET(GTEST_DEPENDS ${MKLML_PROJECT})
ENDIF()
ExternalProject_Add(
extern_gtest
${EXTERNAL_PROJECT_LOG_ARGS}
DEPENDS ${GTEST_DEPENDS}
GIT_REPOSITORY "https://github.com/google/googletest.git"
GIT_TAG "release-1.8.0"
PREFIX ${GTEST_SOURCES_DIR}
......
# Copyright (c) 2017 PaddlePaddle Authors. All Rights Reserve.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# 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.
IF(NOT ${WITH_MKLDNN})
return()
ENDIF(NOT ${WITH_MKLDNN})
INCLUDE(ExternalProject)
SET(MKLDNN_PROJECT "extern_mkldnn")
SET(MKLDNN_SOURCES_DIR ${THIRD_PARTY_PATH}/mkldnn)
SET(MKLDNN_INSTALL_ROOT ${CMAKE_INSTALL_PREFIX})
IF(NOT "$ENV{HOME}" STREQUAL "/root")
SET(MKLDNN_INSTALL_ROOT "$ENV{HOME}")
ENDIF()
SET(MKLDNN_INSTALL_DIR "${MKLDNN_INSTALL_ROOT}/opt/paddle/third_party/mkldnn")
SET(MKLDNN_INCLUDE_DIR "${MKLDNN_INSTALL_DIR}/include" CACHE PATH "mkldnn include directory." FORCE)
IF(WIN32)
MESSAGE(WARNING "It is not supported compiling with mkldnn in windows Paddle yet."
"Force WITH_MKLDNN=OFF")
SET(WITH_MKLDNN OFF)
return()
ELSE(WIN32)
SET(MKLDNN_LIBRARY "${MKLDNN_INSTALL_DIR}/lib/libmkldnn.so" CACHE FILEPATH "mkldnn library." FORCE)
MESSAGE(STATUS "Set ${MKLDNN_INSTALL_DIR}/lib to runtime path")
SET(CMAKE_INSTALL_RPATH_USE_LINK_PATH TRUE)
#SET(CMAKE_MACOSX_RPATH 1) # hold for MacOS
SET(CMAKE_INSTALL_RPATH "${CMAKE_INSTALL_RPATH}" "${MKLDNN_INSTALL_DIR}/lib")
ENDIF(WIN32)
INCLUDE_DIRECTORIES(${MKLDNN_INCLUDE_DIR})
IF(${CBLAS_PROVIDER} STREQUAL "MKLML")
SET(MKLDNN_DEPENDS ${MKLML_PROJECT})
SET(MKLDNN_MKLROOT ${MKLML_ROOT})
SET(MKLDNN_IOMP_LIB ${MKLML_IOMP_LIB})
SET(MKLDNN_IOMP_DIR ${MKLML_LIB_DIR})
ENDIF()
ExternalProject_Add(
${MKLDNN_PROJECT}
${EXTERNAL_PROJECT_LOG_ARGS}
DEPENDS ${MKLDNN_DEPENDS}
GIT_REPOSITORY "https://github.com/01org/mkl-dnn.git"
GIT_TAG "v0.9"
PREFIX ${MKLDNN_SOURCES_DIR}
CONFIGURE_COMMAND mkdir -p <SOURCE_DIR>/build
BUILD_COMMAND cd <SOURCE_DIR>/build
&& cmake .. -DCMAKE_INSTALL_PREFIX=${MKLDNN_INSTALL_DIR} -DMKLROOT=${MKLDNN_MKLROOT}
&& $(MAKE)
INSTALL_COMMAND cd <SOURCE_DIR>/build && $(MAKE) install
UPDATE_COMMAND ""
)
ADD_LIBRARY(mkldnn SHARED IMPORTED GLOBAL)
SET_PROPERTY(TARGET mkldnn PROPERTY IMPORTED_LOCATION ${MKLDNN_LIBRARY})
ADD_DEPENDENCIES(mkldnn ${MKLDNN_PROJECT})
MESSAGE(STATUS "Mkldnn library: ${MKLDNN_LIBRARY}")
LIST(APPEND external_project_dependencies mkldnn)
# Copyright (c) 2017 PaddlePaddle Authors. All Rights Reserve.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# 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.
IF(NOT ${WITH_MKLML})
return()
ENDIF(NOT ${WITH_MKLML})
INCLUDE(ExternalProject)
SET(MKLML_PROJECT "extern_mklml")
SET(MKLML_VER "mklml_lnx_2018.0.20170425")
SET(MKLML_URL "https://github.com/01org/mkl-dnn/releases/download/v0.9/${MKLML_VER}.tgz")
SET(MKLML_SOURCE_DIR "${THIRD_PARTY_PATH}/mklml")
SET(MKLML_DOWNLOAD_DIR "${MKLML_SOURCE_DIR}/src/${MKLML_PROJECT}")
SET(MKLML_DST_DIR "opt/paddle/third_party/mklml")
SET(MKLML_INSTALL_ROOT "${CMAKE_INSTALL_PREFIX}")
IF(NOT "$ENV{HOME}" STREQUAL "/root")
SET(MKLML_INSTALL_ROOT "$ENV{HOME}")
ENDIF()
SET(MKLML_INSTALL_DIR ${MKLML_INSTALL_ROOT}/${MKLML_DST_DIR})
SET(MKLML_ROOT ${MKLML_INSTALL_DIR}/${MKLML_VER})
SET(MKLML_INC_DIR ${MKLML_ROOT}/include)
SET(MKLML_LIB_DIR ${MKLML_ROOT}/lib)
SET(MKLML_LIB ${MKLML_LIB_DIR}/libmklml_intel.so)
SET(MKLML_IOMP_LIB ${MKLML_LIB_DIR}/libiomp5.so)
SET(CMAKE_INSTALL_RPATH "${CMAKE_INSTALL_RPATH}" "${MKLML_ROOT}/lib")
INCLUDE_DIRECTORIES(${MKLML_INC_DIR})
SET(mklml_cmakefile ${MKLML_DOWNLOAD_DIR}/CMakeLists.txt)
FILE(WRITE ${mklml_cmakefile} "PROJECT(MKLML)\n"
"cmake_minimum_required(VERSION 3.0)\n"
"install(DIRECTORY ${MKLML_VER}\n"
" DESTINATION ${MKLML_DST_DIR})\n")
ExternalProject_Add(
${MKLML_PROJECT}
${EXTERNAL_PROJECT_LOG_ARGS}
PREFIX ${MKLML_SOURCE_DIR}
DOWNLOAD_DIR ${MKLML_DOWNLOAD_DIR}
DOWNLOAD_COMMAND wget --no-check-certificate -O ${MKLML_DOWNLOAD_DIR}/${MKLML_VER}.tgz ${MKLML_URL}
&& tar -xzf ${MKLML_DOWNLOAD_DIR}/${MKLML_VER}.tgz
DOWNLOAD_NO_PROGRESS 1
UPDATE_COMMAND ""
CMAKE_ARGS -DCMAKE_INSTALL_PREFIX=${MKLML_INSTALL_ROOT}
CMAKE_CACHE_ARGS -DCMAKE_INSTALL_PREFIX:PATH=${MKLML_INSTALL_ROOT}
)
ADD_LIBRARY(mklml SHARED IMPORTED GLOBAL)
SET_PROPERTY(TARGET mklml PROPERTY IMPORTED_LOCATION ${MKLML_LIB})
ADD_DEPENDENCIES(mklml ${MKLML_PROJECT})
LIST(APPEND external_project_dependencies mklml)
......@@ -202,7 +202,7 @@ double dotProduct<double>(const int n, const double* x, const double* y) {
return cblas_ddot(n, x, 1, y, 1);
}
#ifdef PADDLE_USE_MKL
#if defined(PADDLE_USE_MKL) || defined(PADDLE_USE_MKLML)
template <>
void vExp<float>(const int n, const float* a, float* r) {
......@@ -243,7 +243,55 @@ template <>
void vAdd<double>(const int n, const double* a, const double* b, double* r) {
vdAdd(n, a, b, r);
}
#else
DEFINE_MATRIX_BINARY_OP(vExp, b = std::exp(a));
template <class T>
void vExp(const int n, const T* a, T* r) {
hl_cpu_apply_binary_op<T, binary::vExp<T>, 0, 0>(
binary::vExp<T>(), const_cast<T*>(a), r, 1, n, n, n);
}
DEFINE_MATRIX_BINARY_OP(vLog, b = std::log(a));
template <class T>
void vLog(const int n, const T* a, T* r) {
hl_cpu_apply_binary_op<T, binary::vLog<T>, 0, 0>(
binary::vLog<T>(), const_cast<T*>(a), r, 1, n, n, n);
}
DEFINE_MATRIX_BINARY_PARAMETER_OP(vPow, ONE_PARAMETER, b = std::pow(a, p));
template <class T>
void vPow(const int n, const T* a, const T b, T* r) {
hl_cpu_apply_binary_op<T, binary::vPow<T>, 0, 0>(
binary::vPow<T>(b), const_cast<T*>(a), r, 1, n, n, n);
}
DEFINE_MATRIX_TERNARY_OP(vAdd, c = a + b);
template <class T>
void vAdd(const int n, const T* a, const T* b, T* r) {
hl_cpu_apply_ternary_op<T, ternary::vAdd<T>, 0, 0>(ternary::vAdd<T>(),
const_cast<T*>(a),
const_cast<T*>(b),
r,
1,
n,
n,
n,
n);
}
template void vExp(const int n, const float* a, float* r);
template void vExp(const int n, const double* a, double* r);
template void vLog(const int n, const float* a, float* r);
template void vLog(const int n, const double* a, double* r);
template void vPow(const int n, const float* a, const float b, float* r);
template void vPow(const int n, const double* a, const double b, double* r);
template void vAdd(const int n, const float* a, const float* b, float* r);
template void vAdd(const int n, const double* a, const double* b, double* r);
#endif
#ifdef PADDLE_USE_MKL
template <>
void vInvSqrt<float>(const int n, const float* a, float* r) {
vsInvSqrt(n, a, r);
......@@ -275,20 +323,6 @@ void vTanh<double>(const int n, const double* a, double* r) {
}
#else
DEFINE_MATRIX_BINARY_OP(vExp, b = std::exp(a));
template <class T>
void vExp(const int n, const T* a, T* r) {
hl_cpu_apply_binary_op<T, binary::vExp<T>, 0, 0>(
binary::vExp<T>(), const_cast<T*>(a), r, 1, n, n, n);
}
DEFINE_MATRIX_BINARY_OP(vLog, b = std::log(a));
template <class T>
void vLog(const int n, const T* a, T* r) {
hl_cpu_apply_binary_op<T, binary::vLog<T>, 0, 0>(
binary::vLog<T>(), const_cast<T*>(a), r, 1, n, n, n);
}
DEFINE_MATRIX_BINARY_OP(vInvSqrt, b = 1.0f / std::sqrt(a));
template <class T>
void vInvSqrt(const int n, const T* a, T* r) {
......@@ -312,41 +346,12 @@ void vTanh(const int n, const T* a, T* r) {
binary::vTanh<T>(), const_cast<T*>(a), r, 1, n, n, n);
}
DEFINE_MATRIX_BINARY_PARAMETER_OP(vPow, ONE_PARAMETER, b = std::pow(a, p));
template <class T>
void vPow(const int n, const T* a, const T b, T* r) {
hl_cpu_apply_binary_op<T, binary::vPow<T>, 0, 0>(
binary::vPow<T>(b), const_cast<T*>(a), r, 1, n, n, n);
}
DEFINE_MATRIX_TERNARY_OP(vAdd, c = a + b);
template <class T>
void vAdd(const int n, const T* a, const T* b, T* r) {
hl_cpu_apply_ternary_op<T, ternary::vAdd<T>, 0, 0>(ternary::vAdd<T>(),
const_cast<T*>(a),
const_cast<T*>(b),
r,
1,
n,
n,
n,
n);
}
template void vExp(const int n, const float* a, float* r);
template void vExp(const int n, const double* a, double* r);
template void vLog(const int n, const float* a, float* r);
template void vLog(const int n, const double* a, double* r);
template void vInvSqrt(const int n, const double* a, double* r);
template void vInvSqrt(const int n, const float* a, float* r);
template void vLog1p(const int n, const float* a, float* r);
template void vLog1p(const int n, const double* a, double* r);
template void vTanh(const int n, const float* a, float* r);
template void vTanh(const int n, const double* a, double* r);
template void vPow(const int n, const float* a, const float b, float* r);
template void vPow(const int n, const double* a, const double b, double* r);
template void vAdd(const int n, const float* a, const float* b, float* r);
template void vAdd(const int n, const double* a, const double* b, double* r);
#endif
......
......@@ -15,6 +15,12 @@ limitations under the License. */
#ifndef MATHFUNCTIONS_H_
#define MATHFUNCTIONS_H_
#ifdef PADDLE_USE_MKLML
#include <mkl_cblas.h>
#include <mkl_lapacke.h>
#include <mkl_vml_functions.h>
#endif
#ifdef PADDLE_USE_MKL
#include <mkl.h>
#include <mkl_lapacke.h>
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册
反馈
建议
客服 返回
顶部