cavis/libnd4j/blas/CMakeLists.txt

405 lines
20 KiB
CMake
Raw Normal View History

2019-06-06 14:21:15 +02:00
################################################################################
# Copyright (c) 2015-2018 Skymind, Inc.
#
# This program and the accompanying materials are made available under the
# terms of the Apache License, Version 2.0 which is available at
# https://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.
#
# SPDX-License-Identifier: Apache-2.0
################################################################################
set(CMAKE_VERBOSE_MAKEFILE OFF)
if(LINUX)
link_directories(/usr/local/lib)
link_directories(/usr/lib)
link_directories(/lib)
endif()
if(APPLE)
message("Using apple")
link_directories(/usr/local/lib)
link_directories(/usr/lib)
link_directories(/lib)
endif()
if (SD_APPLE_BUILD)
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -DSD_APPLE_BUILD=true -mmacosx-version-min=10.10")
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -DSD_APPLE_BUILD=true -mmacosx-version-min=10.10")
endif()
if (SD_ARM_BUILD)
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -DSD_ARM_BUILD=true")
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -DSD_ARM_BUILD=true")
endif()
if (SD_ANDROID_BUILD)
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -DSD_ANDROID_BUILD=true")
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -DSD_ANDROID_BUILD=true")
endif()
if (SD_IOS_BUILD)
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -DSD_IOS_BUILD=true")
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -DSD_IOS_BUILD=true")
endif()
if(WIN32 AND NOT ANDROID)
2019-06-06 14:21:15 +02:00
get_property(dirs DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR} PROPERTY INCLUDE_DIRECTORIES)
if ("${CMAKE_CXX_COMPILER_ID}" STREQUAL "GNU")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wa,-mbig-obj")
endif()
foreach(dir ${dirs})
message(STATUS "dir='${dir}'")
endforeach()
# workaround for long command lines
SET(CMAKE_C_USE_RESPONSE_FILE_FOR_OBJECTS 1)
SET(CMAKE_CXX_USE_RESPONSE_FILE_FOR_OBJECTS 1)
SET(CMAKE_C_RESPONSE_FILE_LINK_FLAG "@")
SET(CMAKE_CXX_RESPONSE_FILE_LINK_FLAG "@")
SET(CMAKE_NINJA_FORCE_RESPONSE_FILE 1 CACHE INTERNAL "")
endif()
if ("${SD_ALL_OPS}")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -DSD_ALL_OPS=true")
2019-06-06 14:21:15 +02:00
else()
message("_OPS: ${SD_OPS_LIST}")
foreach(OP "${SD_OPS_LIST}")
2019-06-06 14:21:15 +02:00
message(STATUS "${OP}")
endforeach()
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${SD_OPS_LIST}")
2019-06-06 14:21:15 +02:00
endif()
IF(${SD_ARCH} MATCHES "arm*")
set(ARCH_TUNE "-march=${SD_ARCH}")
ELSEIF(${SD_ARCH} MATCHES "power*")
set(ARCH_TUNE "-mcpu=${SD_ARCH} -mtune=${SD_ARCH} -D__POWER")
ELSEIF(${SD_EXTENSION} MATCHES "avx2")
Platform helpers (#8216) * platform helpers draft Signed-off-by: raver119 <raver119@gmail.com> * typo Signed-off-by: raver119 <raver119@gmail.com> * disable platform cmake Signed-off-by: raver119 <raver119@gmail.com> * another draft Signed-off-by: raver119 <raver119@gmail.com> * mkldnn convolution refactored Signed-off-by: raver119 <raver119@gmail.com> * minor tweaks Signed-off-by: raver119 <raver119@gmail.com> * one more safety check Signed-off-by: raver119 <raver119@gmail.com> * prototype works Signed-off-by: raver119 <raver119@gmail.com> * meh Signed-off-by: raver119 <raver119@gmail.com> * force static library mode for mkldnn Signed-off-by: raver119 <raver119@gmail.com> * - ismax fix - experimental arg fix - don't enforce openblas on Apple hardware Signed-off-by: raver119 <raver119@gmail.com> * bunch of small fixes Signed-off-by: raver119@gmail.com <raver119@gmail.com> * declare concurrent Signed-off-by: raver119@gmail.com <raver119@gmail.com> * - MKLDNN version upgrade to 1.0.2 - avgpool2d/maxpool2d APIs update Signed-off-by: raver119 <raver119@gmail.com> * - avgpool2d_bp/maxpool2d_bp APIs update Signed-off-by: raver119 <raver119@gmail.com> * - conv2d/batchnorm APIs update Signed-off-by: raver119 <raver119@gmail.com> * - lrn/conv2d_bp/conv3d/conv3d_bp APIs update Signed-off-by: raver119 <raver119@gmail.com> * all ops converted to MKLDNN 1.x Signed-off-by: raver119 <raver119@gmail.com> * bunch of tweaks Signed-off-by: raver119 <raver119@gmail.com> * namespace for platform helpers Signed-off-by: raver119 <raver119@gmail.com> * make sure platform helpers aren't opimized out Signed-off-by: raver119 <raver119@gmail.com> * build cpu_features on x86 systems Signed-off-by: raver119 <raver119@gmail.com> * build cpu_features on x86 systems Signed-off-by: raver119 <raver119@gmail.com> * more of cpu_features Signed-off-by: raver119 <raver119@gmail.com> * - mkldnn removed from java - cpu_features checks in CpuNDArrayFactory Signed-off-by: raver119 <raver119@gmail.com> * F16C definition renamed Signed-off-by: raver119 <raver119@gmail.com> * some mkldnn rearrangements Signed-off-by: raver119 <raver119@gmail.com> * check supported instructions before doing anything Signed-off-by: raver119 <raver119@gmail.com> * typo Signed-off-by: raver119 <raver119@gmail.com> * missied impl Signed-off-by: raver119 <raver119@gmail.com> * BUILD_PIC option Signed-off-by: raver119 <raver119@gmail.com> * conv2d fix Signed-off-by: raver119 <raver119@gmail.com> * avgpool3d fix Signed-off-by: raver119 <raver119@gmail.com> * avgpool3d_bp fix Signed-off-by: raver119 <raver119@gmail.com> * avgpool2d_bp leak fix Signed-off-by: raver119 <raver119@gmail.com> * avgpool3d_bp leak fix Signed-off-by: raver119 <raver119@gmail.com> * maxpool bp leaks fixed Signed-off-by: raver119 <raver119@gmail.com> * printf removed Signed-off-by: raver119 <raver119@gmail.com> * batchnorm fix Signed-off-by: raver119 <raver119@gmail.com> * AVX warning/error polishing Signed-off-by: AlexDBlack <blacka101@gmail.com> * Fix Signed-off-by: AlexDBlack <blacka101@gmail.com> * More polish Signed-off-by: AlexDBlack <blacka101@gmail.com> * Polish Signed-off-by: AlexDBlack <blacka101@gmail.com> * remove previous MKL-DNN support layer Signed-off-by: raver119 <raver119@gmail.com> * avx2 tweak Signed-off-by: raver119 <raver119@gmail.com> * allow static for apple Signed-off-by: raver119@gmail.com <raver119@gmail.com> * exclude mkldnn in one more place Signed-off-by: raver119 <raver119@gmail.com> * exclude mkldnn in one more place Signed-off-by: raver119 <raver119@gmail.com> * restore OPENBLAS_PATH use Signed-off-by: raver119 <raver119@gmail.com> * add runtime check for avx/avx2 support Signed-off-by: raver119 <raver119@gmail.com> * convolution_auto Signed-off-by: raver119 <raver119@gmail.com> * Add logic for helper argument * minor test fix Signed-off-by: raver119 <raver119@gmail.com> * few tweaks Signed-off-by: raver119 <raver119@gmail.com> * few tweaks Signed-off-by: raver119 <raver119@gmail.com> * skip OpTracker props for non-x86 builds Signed-off-by: raver119 <raver119@gmail.com> * linux arm isn't x86 :) Signed-off-by: raver119 <raver119@gmail.com> * avx-512 Signed-off-by: raver119 <raver119@gmail.com> * CUDA presets fix Signed-off-by: raver119 <raver119@gmail.com> * BUILD_PIC Signed-off-by: raver119 <raver119@gmail.com> * prefetchw for avx2 Signed-off-by: raver119 <raver119@gmail.com> * BUILD_PIC again Signed-off-by: raver119 <raver119@gmail.com>
2019-09-11 20:50:28 +02:00
message("Building AVX2 binary...")
set(ARCH_TUNE "-mmmx -msse -msse2 -msse3 -msse4.1 -msse4.2 -mavx -mavx2 -mfma -mf16c -mprefetchwt1 -DSD_F16C=true -DF_AVX2=true")
2019-06-06 14:21:15 +02:00
ELSE()
if ("${SD_ARCH}" STREQUAL "x86-64")
Platform helpers (#8216) * platform helpers draft Signed-off-by: raver119 <raver119@gmail.com> * typo Signed-off-by: raver119 <raver119@gmail.com> * disable platform cmake Signed-off-by: raver119 <raver119@gmail.com> * another draft Signed-off-by: raver119 <raver119@gmail.com> * mkldnn convolution refactored Signed-off-by: raver119 <raver119@gmail.com> * minor tweaks Signed-off-by: raver119 <raver119@gmail.com> * one more safety check Signed-off-by: raver119 <raver119@gmail.com> * prototype works Signed-off-by: raver119 <raver119@gmail.com> * meh Signed-off-by: raver119 <raver119@gmail.com> * force static library mode for mkldnn Signed-off-by: raver119 <raver119@gmail.com> * - ismax fix - experimental arg fix - don't enforce openblas on Apple hardware Signed-off-by: raver119 <raver119@gmail.com> * bunch of small fixes Signed-off-by: raver119@gmail.com <raver119@gmail.com> * declare concurrent Signed-off-by: raver119@gmail.com <raver119@gmail.com> * - MKLDNN version upgrade to 1.0.2 - avgpool2d/maxpool2d APIs update Signed-off-by: raver119 <raver119@gmail.com> * - avgpool2d_bp/maxpool2d_bp APIs update Signed-off-by: raver119 <raver119@gmail.com> * - conv2d/batchnorm APIs update Signed-off-by: raver119 <raver119@gmail.com> * - lrn/conv2d_bp/conv3d/conv3d_bp APIs update Signed-off-by: raver119 <raver119@gmail.com> * all ops converted to MKLDNN 1.x Signed-off-by: raver119 <raver119@gmail.com> * bunch of tweaks Signed-off-by: raver119 <raver119@gmail.com> * namespace for platform helpers Signed-off-by: raver119 <raver119@gmail.com> * make sure platform helpers aren't opimized out Signed-off-by: raver119 <raver119@gmail.com> * build cpu_features on x86 systems Signed-off-by: raver119 <raver119@gmail.com> * build cpu_features on x86 systems Signed-off-by: raver119 <raver119@gmail.com> * more of cpu_features Signed-off-by: raver119 <raver119@gmail.com> * - mkldnn removed from java - cpu_features checks in CpuNDArrayFactory Signed-off-by: raver119 <raver119@gmail.com> * F16C definition renamed Signed-off-by: raver119 <raver119@gmail.com> * some mkldnn rearrangements Signed-off-by: raver119 <raver119@gmail.com> * check supported instructions before doing anything Signed-off-by: raver119 <raver119@gmail.com> * typo Signed-off-by: raver119 <raver119@gmail.com> * missied impl Signed-off-by: raver119 <raver119@gmail.com> * BUILD_PIC option Signed-off-by: raver119 <raver119@gmail.com> * conv2d fix Signed-off-by: raver119 <raver119@gmail.com> * avgpool3d fix Signed-off-by: raver119 <raver119@gmail.com> * avgpool3d_bp fix Signed-off-by: raver119 <raver119@gmail.com> * avgpool2d_bp leak fix Signed-off-by: raver119 <raver119@gmail.com> * avgpool3d_bp leak fix Signed-off-by: raver119 <raver119@gmail.com> * maxpool bp leaks fixed Signed-off-by: raver119 <raver119@gmail.com> * printf removed Signed-off-by: raver119 <raver119@gmail.com> * batchnorm fix Signed-off-by: raver119 <raver119@gmail.com> * AVX warning/error polishing Signed-off-by: AlexDBlack <blacka101@gmail.com> * Fix Signed-off-by: AlexDBlack <blacka101@gmail.com> * More polish Signed-off-by: AlexDBlack <blacka101@gmail.com> * Polish Signed-off-by: AlexDBlack <blacka101@gmail.com> * remove previous MKL-DNN support layer Signed-off-by: raver119 <raver119@gmail.com> * avx2 tweak Signed-off-by: raver119 <raver119@gmail.com> * allow static for apple Signed-off-by: raver119@gmail.com <raver119@gmail.com> * exclude mkldnn in one more place Signed-off-by: raver119 <raver119@gmail.com> * exclude mkldnn in one more place Signed-off-by: raver119 <raver119@gmail.com> * restore OPENBLAS_PATH use Signed-off-by: raver119 <raver119@gmail.com> * add runtime check for avx/avx2 support Signed-off-by: raver119 <raver119@gmail.com> * convolution_auto Signed-off-by: raver119 <raver119@gmail.com> * Add logic for helper argument * minor test fix Signed-off-by: raver119 <raver119@gmail.com> * few tweaks Signed-off-by: raver119 <raver119@gmail.com> * few tweaks Signed-off-by: raver119 <raver119@gmail.com> * skip OpTracker props for non-x86 builds Signed-off-by: raver119 <raver119@gmail.com> * linux arm isn't x86 :) Signed-off-by: raver119 <raver119@gmail.com> * avx-512 Signed-off-by: raver119 <raver119@gmail.com> * CUDA presets fix Signed-off-by: raver119 <raver119@gmail.com> * BUILD_PIC Signed-off-by: raver119 <raver119@gmail.com> * prefetchw for avx2 Signed-off-by: raver119 <raver119@gmail.com> * BUILD_PIC again Signed-off-by: raver119 <raver119@gmail.com>
2019-09-11 20:50:28 +02:00
message("Building x86_64 binary...")
2019-06-06 14:21:15 +02:00
set(ARCH_TYPE "generic")
Platform helpers (#8216) * platform helpers draft Signed-off-by: raver119 <raver119@gmail.com> * typo Signed-off-by: raver119 <raver119@gmail.com> * disable platform cmake Signed-off-by: raver119 <raver119@gmail.com> * another draft Signed-off-by: raver119 <raver119@gmail.com> * mkldnn convolution refactored Signed-off-by: raver119 <raver119@gmail.com> * minor tweaks Signed-off-by: raver119 <raver119@gmail.com> * one more safety check Signed-off-by: raver119 <raver119@gmail.com> * prototype works Signed-off-by: raver119 <raver119@gmail.com> * meh Signed-off-by: raver119 <raver119@gmail.com> * force static library mode for mkldnn Signed-off-by: raver119 <raver119@gmail.com> * - ismax fix - experimental arg fix - don't enforce openblas on Apple hardware Signed-off-by: raver119 <raver119@gmail.com> * bunch of small fixes Signed-off-by: raver119@gmail.com <raver119@gmail.com> * declare concurrent Signed-off-by: raver119@gmail.com <raver119@gmail.com> * - MKLDNN version upgrade to 1.0.2 - avgpool2d/maxpool2d APIs update Signed-off-by: raver119 <raver119@gmail.com> * - avgpool2d_bp/maxpool2d_bp APIs update Signed-off-by: raver119 <raver119@gmail.com> * - conv2d/batchnorm APIs update Signed-off-by: raver119 <raver119@gmail.com> * - lrn/conv2d_bp/conv3d/conv3d_bp APIs update Signed-off-by: raver119 <raver119@gmail.com> * all ops converted to MKLDNN 1.x Signed-off-by: raver119 <raver119@gmail.com> * bunch of tweaks Signed-off-by: raver119 <raver119@gmail.com> * namespace for platform helpers Signed-off-by: raver119 <raver119@gmail.com> * make sure platform helpers aren't opimized out Signed-off-by: raver119 <raver119@gmail.com> * build cpu_features on x86 systems Signed-off-by: raver119 <raver119@gmail.com> * build cpu_features on x86 systems Signed-off-by: raver119 <raver119@gmail.com> * more of cpu_features Signed-off-by: raver119 <raver119@gmail.com> * - mkldnn removed from java - cpu_features checks in CpuNDArrayFactory Signed-off-by: raver119 <raver119@gmail.com> * F16C definition renamed Signed-off-by: raver119 <raver119@gmail.com> * some mkldnn rearrangements Signed-off-by: raver119 <raver119@gmail.com> * check supported instructions before doing anything Signed-off-by: raver119 <raver119@gmail.com> * typo Signed-off-by: raver119 <raver119@gmail.com> * missied impl Signed-off-by: raver119 <raver119@gmail.com> * BUILD_PIC option Signed-off-by: raver119 <raver119@gmail.com> * conv2d fix Signed-off-by: raver119 <raver119@gmail.com> * avgpool3d fix Signed-off-by: raver119 <raver119@gmail.com> * avgpool3d_bp fix Signed-off-by: raver119 <raver119@gmail.com> * avgpool2d_bp leak fix Signed-off-by: raver119 <raver119@gmail.com> * avgpool3d_bp leak fix Signed-off-by: raver119 <raver119@gmail.com> * maxpool bp leaks fixed Signed-off-by: raver119 <raver119@gmail.com> * printf removed Signed-off-by: raver119 <raver119@gmail.com> * batchnorm fix Signed-off-by: raver119 <raver119@gmail.com> * AVX warning/error polishing Signed-off-by: AlexDBlack <blacka101@gmail.com> * Fix Signed-off-by: AlexDBlack <blacka101@gmail.com> * More polish Signed-off-by: AlexDBlack <blacka101@gmail.com> * Polish Signed-off-by: AlexDBlack <blacka101@gmail.com> * remove previous MKL-DNN support layer Signed-off-by: raver119 <raver119@gmail.com> * avx2 tweak Signed-off-by: raver119 <raver119@gmail.com> * allow static for apple Signed-off-by: raver119@gmail.com <raver119@gmail.com> * exclude mkldnn in one more place Signed-off-by: raver119 <raver119@gmail.com> * exclude mkldnn in one more place Signed-off-by: raver119 <raver119@gmail.com> * restore OPENBLAS_PATH use Signed-off-by: raver119 <raver119@gmail.com> * add runtime check for avx/avx2 support Signed-off-by: raver119 <raver119@gmail.com> * convolution_auto Signed-off-by: raver119 <raver119@gmail.com> * Add logic for helper argument * minor test fix Signed-off-by: raver119 <raver119@gmail.com> * few tweaks Signed-off-by: raver119 <raver119@gmail.com> * few tweaks Signed-off-by: raver119 <raver119@gmail.com> * skip OpTracker props for non-x86 builds Signed-off-by: raver119 <raver119@gmail.com> * linux arm isn't x86 :) Signed-off-by: raver119 <raver119@gmail.com> * avx-512 Signed-off-by: raver119 <raver119@gmail.com> * CUDA presets fix Signed-off-by: raver119 <raver119@gmail.com> * BUILD_PIC Signed-off-by: raver119 <raver119@gmail.com> * prefetchw for avx2 Signed-off-by: raver119 <raver119@gmail.com> * BUILD_PIC again Signed-off-by: raver119 <raver119@gmail.com>
2019-09-11 20:50:28 +02:00
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -DF_X64=true")
2019-06-06 14:21:15 +02:00
else()
set(ARCH_TYPE "${SD_ARCH}")
2019-06-06 14:21:15 +02:00
endif()
IF(${SD_EXTENSION} MATCHES "avx512")
Platform helpers (#8216) * platform helpers draft Signed-off-by: raver119 <raver119@gmail.com> * typo Signed-off-by: raver119 <raver119@gmail.com> * disable platform cmake Signed-off-by: raver119 <raver119@gmail.com> * another draft Signed-off-by: raver119 <raver119@gmail.com> * mkldnn convolution refactored Signed-off-by: raver119 <raver119@gmail.com> * minor tweaks Signed-off-by: raver119 <raver119@gmail.com> * one more safety check Signed-off-by: raver119 <raver119@gmail.com> * prototype works Signed-off-by: raver119 <raver119@gmail.com> * meh Signed-off-by: raver119 <raver119@gmail.com> * force static library mode for mkldnn Signed-off-by: raver119 <raver119@gmail.com> * - ismax fix - experimental arg fix - don't enforce openblas on Apple hardware Signed-off-by: raver119 <raver119@gmail.com> * bunch of small fixes Signed-off-by: raver119@gmail.com <raver119@gmail.com> * declare concurrent Signed-off-by: raver119@gmail.com <raver119@gmail.com> * - MKLDNN version upgrade to 1.0.2 - avgpool2d/maxpool2d APIs update Signed-off-by: raver119 <raver119@gmail.com> * - avgpool2d_bp/maxpool2d_bp APIs update Signed-off-by: raver119 <raver119@gmail.com> * - conv2d/batchnorm APIs update Signed-off-by: raver119 <raver119@gmail.com> * - lrn/conv2d_bp/conv3d/conv3d_bp APIs update Signed-off-by: raver119 <raver119@gmail.com> * all ops converted to MKLDNN 1.x Signed-off-by: raver119 <raver119@gmail.com> * bunch of tweaks Signed-off-by: raver119 <raver119@gmail.com> * namespace for platform helpers Signed-off-by: raver119 <raver119@gmail.com> * make sure platform helpers aren't opimized out Signed-off-by: raver119 <raver119@gmail.com> * build cpu_features on x86 systems Signed-off-by: raver119 <raver119@gmail.com> * build cpu_features on x86 systems Signed-off-by: raver119 <raver119@gmail.com> * more of cpu_features Signed-off-by: raver119 <raver119@gmail.com> * - mkldnn removed from java - cpu_features checks in CpuNDArrayFactory Signed-off-by: raver119 <raver119@gmail.com> * F16C definition renamed Signed-off-by: raver119 <raver119@gmail.com> * some mkldnn rearrangements Signed-off-by: raver119 <raver119@gmail.com> * check supported instructions before doing anything Signed-off-by: raver119 <raver119@gmail.com> * typo Signed-off-by: raver119 <raver119@gmail.com> * missied impl Signed-off-by: raver119 <raver119@gmail.com> * BUILD_PIC option Signed-off-by: raver119 <raver119@gmail.com> * conv2d fix Signed-off-by: raver119 <raver119@gmail.com> * avgpool3d fix Signed-off-by: raver119 <raver119@gmail.com> * avgpool3d_bp fix Signed-off-by: raver119 <raver119@gmail.com> * avgpool2d_bp leak fix Signed-off-by: raver119 <raver119@gmail.com> * avgpool3d_bp leak fix Signed-off-by: raver119 <raver119@gmail.com> * maxpool bp leaks fixed Signed-off-by: raver119 <raver119@gmail.com> * printf removed Signed-off-by: raver119 <raver119@gmail.com> * batchnorm fix Signed-off-by: raver119 <raver119@gmail.com> * AVX warning/error polishing Signed-off-by: AlexDBlack <blacka101@gmail.com> * Fix Signed-off-by: AlexDBlack <blacka101@gmail.com> * More polish Signed-off-by: AlexDBlack <blacka101@gmail.com> * Polish Signed-off-by: AlexDBlack <blacka101@gmail.com> * remove previous MKL-DNN support layer Signed-off-by: raver119 <raver119@gmail.com> * avx2 tweak Signed-off-by: raver119 <raver119@gmail.com> * allow static for apple Signed-off-by: raver119@gmail.com <raver119@gmail.com> * exclude mkldnn in one more place Signed-off-by: raver119 <raver119@gmail.com> * exclude mkldnn in one more place Signed-off-by: raver119 <raver119@gmail.com> * restore OPENBLAS_PATH use Signed-off-by: raver119 <raver119@gmail.com> * add runtime check for avx/avx2 support Signed-off-by: raver119 <raver119@gmail.com> * convolution_auto Signed-off-by: raver119 <raver119@gmail.com> * Add logic for helper argument * minor test fix Signed-off-by: raver119 <raver119@gmail.com> * few tweaks Signed-off-by: raver119 <raver119@gmail.com> * few tweaks Signed-off-by: raver119 <raver119@gmail.com> * skip OpTracker props for non-x86 builds Signed-off-by: raver119 <raver119@gmail.com> * linux arm isn't x86 :) Signed-off-by: raver119 <raver119@gmail.com> * avx-512 Signed-off-by: raver119 <raver119@gmail.com> * CUDA presets fix Signed-off-by: raver119 <raver119@gmail.com> * BUILD_PIC Signed-off-by: raver119 <raver119@gmail.com> * prefetchw for avx2 Signed-off-by: raver119 <raver119@gmail.com> * BUILD_PIC again Signed-off-by: raver119 <raver119@gmail.com>
2019-09-11 20:50:28 +02:00
message("Building AVX512 binary...")
# we need to set flag here, that we can use hardware f16 conversion + tell that cpu features should be tracked
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -mmmx -msse -msse2 -msse3 -msse4.1 -msse4.2 -mavx -mavx2 -mfma -mf16c -mavx512f -mavx512vl -mavx512bw -mavx512dq -mavx512cd -mbmi -mbmi2 -mprefetchwt1 -mclflushopt -mxsavec -mxsaves -DSD_F16C=true -DF_AVX512=true")
endif()
if (NOT WIN32)
# we don't want this definition for msvc
set(ARCH_TUNE "-march=${SD_ARCH} -mtune=${ARCH_TYPE}")
endif()
2019-06-06 14:21:15 +02:00
ENDIF()
if ("${CMAKE_CXX_COMPILER_ID}" STREQUAL "AppleClang" AND SD_X86_BUILD)
# apple clang but not ios-arm
SET( CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${ARCH_TUNE}")
elseif ("${CMAKE_CXX_COMPILER_ID}" STREQUAL "Clang")
2019-06-06 14:21:15 +02:00
# using Clang
SET( CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${ARCH_TUNE}")
elseif ("${CMAKE_CXX_COMPILER_ID}" STREQUAL "Intel")
# using Intel C++
SET( CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${ARCH_TUNE} -O3 -fp-model fast")
elseif ("${CMAKE_CXX_COMPILER_ID}" STREQUAL "MSVC")
# using Visual Studio C++
set( CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${ARCH_TUNE}")
2019-06-06 14:21:15 +02:00
elseif ("${CMAKE_CXX_COMPILER_ID}" STREQUAL "GNU")
# using GCC
compression ops (#436) * Added declarations for decode/encode_bitmap ops. Signed-off-by: shugeo <sgazeos@gmail.com> * Added implementation for bitmap encoding/decoding ops. Signed-off-by: shugeo <sgazeos@gmail.com> * Added helpers for encode/decode bitmap ops. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored encodingBitmap helper. Signed-off-by: shugeo <sgazeos@gmail.com> * threshold encode/decode skeleton * helper skeleton * minor import fix * encoder shape fn & op impl * thresholdEncode cpu impl Signed-off-by: raver119@gmail.com <raver119@gmail.com> * thresholdDecode cpu impl Signed-off-by: raver119@gmail.com <raver119@gmail.com> * Only cosmetical changes. Signed-off-by: shugeo <sgazeos@gmail.com> * placeholder Signed-off-by: raver119@gmail.com <raver119@gmail.com> * Added cuda implementation for bitmap decode helper. Signed-off-by: shugeo <sgazeos@gmail.com> * cuda thresholdEstimate Signed-off-by: raver119@gmail.com <raver119@gmail.com> * cuda thresholdDecode Signed-off-by: raver119@gmail.com <raver119@gmail.com> * next step Signed-off-by: raver119@gmail.com <raver119@gmail.com> * - nano cmakelist update (get rid of Clion section) - fixed forgotten throw in AtomicTests Signed-off-by: raver119@gmail.com <raver119@gmail.com> * thesholdEncode cuda impl Signed-off-by: raver119@gmail.com <raver119@gmail.com> * Added tests for bitmap encoding/decoding ops. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed tests for encode/decode bitmaps. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored decode/encode helpers. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed crashes with bitmap decode/encode helpers. Signed-off-by: shugeo <sgazeos@gmail.com> * bitmap encode/decode CPU Signed-off-by: raver119@gmail.com <raver119@gmail.com> * bitmap encode/decode CUDA Signed-off-by: raver119@gmail.com <raver119@gmail.com> * C API removed for threshold/bitmap encode Signed-off-by: raver119@gmail.com <raver119@gmail.com> * EncodeBitmap/DecodeBitmap Java side Signed-off-by: raver119@gmail.com <raver119@gmail.com> * EncodeThreshold/DecodeThreshold Java side Signed-off-by: raver119@gmail.com <raver119@gmail.com> * EncodeThreshold/DecodeThreshold Java side Signed-off-by: raver119@gmail.com <raver119@gmail.com> * few more tests for threshold encoding Signed-off-by: raver119@gmail.com <raver119@gmail.com> * minor test tweak Signed-off-by: raver119@gmail.com <raver119@gmail.com> * two special tests Signed-off-by: raver119@gmail.com <raver119@gmail.com> * encodeBitmap CPU fix Signed-off-by: raver119@gmail.com <raver119@gmail.com> * parallel_long/parallel_double proper spans fix Signed-off-by: raver119@gmail.com <raver119@gmail.com> * encodeThreshold CUDA fix Signed-off-by: raver119@gmail.com <raver119@gmail.com> * nano fix Signed-off-by: raver119@gmail.com <raver119@gmail.com> * grid tweaks Signed-off-by: raver119@gmail.com <raver119@gmail.com> * RTX adaptation for thresholdEncode Signed-off-by: raver119 <raver119@gmail.com> * don't allow threshold encoding for length < 2 Signed-off-by: raver119@gmail.com <raver119@gmail.com> * get rid of NDArrayCompressor in EncodingHandler Signed-off-by: raver119@gmail.com <raver119@gmail.com> * one more minor update of EncodingHandler Signed-off-by: raver119@gmail.com <raver119@gmail.com> * one more minor tweak of EncodingHandler Signed-off-by: raver119@gmail.com <raver119@gmail.com> * - matmul allows integer data types use - EncodingHandler boundary default value - few tests for integer matmul Signed-off-by: raver119@gmail.com <raver119@gmail.com> * minor fix of CUDA bitmap encode Signed-off-by: raver119@gmail.com <raver119@gmail.com> * boundary changed to integer everywhere Signed-off-by: raver119@gmail.com <raver119@gmail.com> * boundary changed to integer everywhere Signed-off-by: raver119@gmail.com <raver119@gmail.com> * re-enable CUDA deallocator Signed-off-by: raver119@gmail.com <raver119@gmail.com> * threshold encoder fix for systems without omp Signed-off-by: raver119@gmail.com <raver119@gmail.com> * - encode_threshold now requires non-negative boundary - minor tweak in EncodingHandler Signed-off-by: raver119@gmail.com <raver119@gmail.com> * restore parallelism in decode_bitmap Signed-off-by: raver119@gmail.com <raver119@gmail.com> * fall back to omp for encode_bitmap cpu Signed-off-by: raver119@gmail.com <raver119@gmail.com> * single time casts Signed-off-by: raver119@gmail.com <raver119@gmail.com> * - additional test for encode_threshold - sync buffers to device before calling for shape function Signed-off-by: raver119@gmail.com <raver119@gmail.com> Co-authored-by: shugeo <sgazeos@gmail.com>
2020-05-08 19:59:39 +02:00
SET( CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${ARCH_TUNE} -fmax-errors=2 ")
2019-06-06 14:21:15 +02:00
set(CMAKE_SHARED_LINKER_FLAGS "${CMAKE_SHARED_LINKER_FLAGS} -Wl,-rpath,$ORIGIN/")
compression ops (#436) * Added declarations for decode/encode_bitmap ops. Signed-off-by: shugeo <sgazeos@gmail.com> * Added implementation for bitmap encoding/decoding ops. Signed-off-by: shugeo <sgazeos@gmail.com> * Added helpers for encode/decode bitmap ops. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored encodingBitmap helper. Signed-off-by: shugeo <sgazeos@gmail.com> * threshold encode/decode skeleton * helper skeleton * minor import fix * encoder shape fn & op impl * thresholdEncode cpu impl Signed-off-by: raver119@gmail.com <raver119@gmail.com> * thresholdDecode cpu impl Signed-off-by: raver119@gmail.com <raver119@gmail.com> * Only cosmetical changes. Signed-off-by: shugeo <sgazeos@gmail.com> * placeholder Signed-off-by: raver119@gmail.com <raver119@gmail.com> * Added cuda implementation for bitmap decode helper. Signed-off-by: shugeo <sgazeos@gmail.com> * cuda thresholdEstimate Signed-off-by: raver119@gmail.com <raver119@gmail.com> * cuda thresholdDecode Signed-off-by: raver119@gmail.com <raver119@gmail.com> * next step Signed-off-by: raver119@gmail.com <raver119@gmail.com> * - nano cmakelist update (get rid of Clion section) - fixed forgotten throw in AtomicTests Signed-off-by: raver119@gmail.com <raver119@gmail.com> * thesholdEncode cuda impl Signed-off-by: raver119@gmail.com <raver119@gmail.com> * Added tests for bitmap encoding/decoding ops. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed tests for encode/decode bitmaps. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored decode/encode helpers. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed crashes with bitmap decode/encode helpers. Signed-off-by: shugeo <sgazeos@gmail.com> * bitmap encode/decode CPU Signed-off-by: raver119@gmail.com <raver119@gmail.com> * bitmap encode/decode CUDA Signed-off-by: raver119@gmail.com <raver119@gmail.com> * C API removed for threshold/bitmap encode Signed-off-by: raver119@gmail.com <raver119@gmail.com> * EncodeBitmap/DecodeBitmap Java side Signed-off-by: raver119@gmail.com <raver119@gmail.com> * EncodeThreshold/DecodeThreshold Java side Signed-off-by: raver119@gmail.com <raver119@gmail.com> * EncodeThreshold/DecodeThreshold Java side Signed-off-by: raver119@gmail.com <raver119@gmail.com> * few more tests for threshold encoding Signed-off-by: raver119@gmail.com <raver119@gmail.com> * minor test tweak Signed-off-by: raver119@gmail.com <raver119@gmail.com> * two special tests Signed-off-by: raver119@gmail.com <raver119@gmail.com> * encodeBitmap CPU fix Signed-off-by: raver119@gmail.com <raver119@gmail.com> * parallel_long/parallel_double proper spans fix Signed-off-by: raver119@gmail.com <raver119@gmail.com> * encodeThreshold CUDA fix Signed-off-by: raver119@gmail.com <raver119@gmail.com> * nano fix Signed-off-by: raver119@gmail.com <raver119@gmail.com> * grid tweaks Signed-off-by: raver119@gmail.com <raver119@gmail.com> * RTX adaptation for thresholdEncode Signed-off-by: raver119 <raver119@gmail.com> * don't allow threshold encoding for length < 2 Signed-off-by: raver119@gmail.com <raver119@gmail.com> * get rid of NDArrayCompressor in EncodingHandler Signed-off-by: raver119@gmail.com <raver119@gmail.com> * one more minor update of EncodingHandler Signed-off-by: raver119@gmail.com <raver119@gmail.com> * one more minor tweak of EncodingHandler Signed-off-by: raver119@gmail.com <raver119@gmail.com> * - matmul allows integer data types use - EncodingHandler boundary default value - few tests for integer matmul Signed-off-by: raver119@gmail.com <raver119@gmail.com> * minor fix of CUDA bitmap encode Signed-off-by: raver119@gmail.com <raver119@gmail.com> * boundary changed to integer everywhere Signed-off-by: raver119@gmail.com <raver119@gmail.com> * boundary changed to integer everywhere Signed-off-by: raver119@gmail.com <raver119@gmail.com> * re-enable CUDA deallocator Signed-off-by: raver119@gmail.com <raver119@gmail.com> * threshold encoder fix for systems without omp Signed-off-by: raver119@gmail.com <raver119@gmail.com> * - encode_threshold now requires non-negative boundary - minor tweak in EncodingHandler Signed-off-by: raver119@gmail.com <raver119@gmail.com> * restore parallelism in decode_bitmap Signed-off-by: raver119@gmail.com <raver119@gmail.com> * fall back to omp for encode_bitmap cpu Signed-off-by: raver119@gmail.com <raver119@gmail.com> * single time casts Signed-off-by: raver119@gmail.com <raver119@gmail.com> * - additional test for encode_threshold - sync buffers to device before calling for shape function Signed-off-by: raver119@gmail.com <raver119@gmail.com> Co-authored-by: shugeo <sgazeos@gmail.com>
2020-05-08 19:59:39 +02:00
if (CMAKE_BUILD_TYPE STREQUAL "Debug" AND NOT(APPLE) AND NOT(WIN32))
SET(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -rdynamic -Wl,-export-dynamic")
SET(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -export-dynamic")
endif()
2019-06-06 14:21:15 +02:00
endif()
IF(${CMAKE_SYSTEM_NAME} MATCHES "Linux")
include_directories("/usr/include")
include_directories("/usr/local/include")
ENDIF(${CMAKE_SYSTEM_NAME} MATCHES "Linux")
if(!SD_CUDA)
if(!SD_CPU)
set(SD_CUDA FALSE)
set(SD_CPU TRUE)
2019-06-06 14:21:15 +02:00
endif()
endif()
cuDNN integration (#150) * initial commit Signed-off-by: raver119 <raver119@gmail.com> * one file Signed-off-by: raver119 <raver119@gmail.com> * few more includes Signed-off-by: raver119 <raver119@gmail.com> * m? Signed-off-by: raver119 <raver119@gmail.com> * const Signed-off-by: raver119 <raver119@gmail.com> * cudnn linkage in tests Signed-off-by: raver119 <raver119@gmail.com> * culibos Signed-off-by: raver119 <raver119@gmail.com> * static reminder Signed-off-by: raver119 <raver119@gmail.com> * platform engine tag Signed-off-by: raver119 <raver119@gmail.com> * HAVE_CUDNN moved to config.h.in Signed-off-by: raver119 <raver119@gmail.com> * include Signed-off-by: raver119 <raver119@gmail.com> * include Signed-off-by: raver119 <raver119@gmail.com> * skip cudnn handle creation if there's not cudnn Signed-off-by: raver119 <raver119@gmail.com> * meh Signed-off-by: raver119 <raver119@gmail.com> * target device in context Signed-off-by: raver119 <raver119@gmail.com> * platform engines Signed-off-by: raver119 <raver119@gmail.com> * platform engines Signed-off-by: raver119 <raver119@gmail.com> * allow multiple -h args Signed-off-by: raver119 <raver119@gmail.com> * allow multiple -h args Signed-off-by: raver119 <raver119@gmail.com> * move mkldnn out of CPU block Signed-off-by: raver119 <raver119@gmail.com> * link to mkldnn on cuda Signed-off-by: raver119 <raver119@gmail.com> * less prints Signed-off-by: raver119 <raver119@gmail.com> * minor tweaks Signed-off-by: raver119 <raver119@gmail.com> * next step Signed-off-by: raver119 <raver119@gmail.com> * conv2d NCHW draft Signed-off-by: raver119 <raver119@gmail.com> * conv2d biasAdd Signed-off-by: raver119 <raver119@gmail.com> * test for MKL/CUDNN combined use Signed-off-by: raver119 <raver119@gmail.com> * - provide additional code for conv2d ff based on cudnn api, not tested yet Signed-off-by: Yurii <iuriish@yahoo.com> * - further work on conv2d helper based on using cudnn api Signed-off-by: Yurii <iuriish@yahoo.com> * - fixing several cuda bugs which appeared after cudnn lib had been started to use Signed-off-by: Yurii <iuriish@yahoo.com> * - implementation of conv2d backprop op based on cudnn api Signed-off-by: Yurii <iuriish@yahoo.com> * - implementaion of conv3d and conv3d_bp ops based on cudnn api Signed-off-by: Yurii <iuriish@yahoo.com> * - bugs fixing in conv3d/conv3d_bp ops (cudnn in use) Signed-off-by: Yurii <iuriish@yahoo.com> * - implementation of depthwiseConv2d (ff/bp) op based on cudnn api Signed-off-by: Yurii <iuriish@yahoo.com> * - implementation of batchnorm ff op based on cudnn api Signed-off-by: Yurii <iuriish@yahoo.com> * - disable cudnn batchnorm temporary Signed-off-by: Yurii <iuriish@yahoo.com> * - add minor change in cmake Signed-off-by: Yurii <iuriish@yahoo.com> * engine for depthwise mkldnn Signed-off-by: raver119 <raver119@gmail.com> * couple of includes Signed-off-by: raver119 <raver119@gmail.com> * - provide permutation to cudnn batchnorm ff when format is NHWC Signed-off-by: Yurii <iuriish@yahoo.com> * lgamma fix Signed-off-by: raver119 <raver119@gmail.com> * - eliminate memory leak in two tests Signed-off-by: Yurii <iuriish@yahoo.com> Co-authored-by: Yurii Shyrma <iuriish@yahoo.com>
2020-01-20 19:32:46 +01:00
#if MKLDNN is enabled - we're building mkldnn-powered helpers
if (HAVE_MKLDNN)
file(GLOB_RECURSE CUSTOMOPS_MKLDNN_SOURCES false ../include/ops/declarable/platform/mkldnn/*.cpp ../include/ops/declarable/platform/mkldnn/mkldnnUtils.h)
endif()
if(SD_CUDA)
2019-06-06 14:21:15 +02:00
message("Build cublas")
find_package(CUDA)
add_definitions(-D__CUDABLAS__=true)
if ("${CMAKE_CXX_COMPILER_ID}" STREQUAL "MSVC")
set (CMAKE_CXX_FLAGS "")
endif()
if (CUDA_FOUND)
message("CUDA include directory: ${CUDA_INCLUDE_DIRS}")
include_directories(${CUDA_INCLUDE_DIRS})
message("CUDA found!")
if ("${SD_EXPERIMENTAL}" STREQUAL "yes")
2019-06-06 14:21:15 +02:00
message("Experimental mode ENABLED")
set(CMAKE_CUDA_FLAGS " ${CMAKE_CUDA_FLAGS} -D__ND4J_EXPERIMENTAL__=true")
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -D__ND4J_EXPERIMENTAL__=true")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -D__ND4J_EXPERIMENTAL__=true")
set(EXPM " -D__ND4J_EXPERIMENTAL__=true")
2019-06-06 14:21:15 +02:00
endif()
# the only difference for debug mode here is host/device debug symbols
set(CMAKE_CUDA_FLAGS_DEBUG " -G -g")
# we need -fPIC on Linux/GCC
if ("${CMAKE_CXX_COMPILER_ID}" STREQUAL "GNU")
message("Enabling fPIC...")
set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} -Xcompiler=-fPIC")
endif()
if(CUDA_VERSION VERSION_GREATER "9.2") # cuda 10
if ("${COMPUTE}" STREQUAL "all")
if (APPLE)
set(CMAKE_CUDA_FLAGS " ${CMAKE_CUDA_FLAGS} -DCUDA_10 ${EXPM} -w --cudart=static --expt-extended-lambda -Xfatbin -compress-all -gencode arch=compute_30,code=sm_30 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_60,code=sm_60")
2019-06-06 14:21:15 +02:00
else()
set(CMAKE_CUDA_FLAGS " ${CMAKE_CUDA_FLAGS} -DCUDA_10 ${EXPM} -w --cudart=static --expt-extended-lambda -Xfatbin -compress-all -gencode arch=compute_30,code=sm_30 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=sm_70")
2019-06-06 14:21:15 +02:00
endif()
else()
set(CMAKE_CUDA_FLAGS " ${CMAKE_CUDA_FLAGS} -DCUDA_10 ${EXPM} -w --cudart=static --expt-extended-lambda -arch=compute_${COMPUTE} -code=sm_${COMPUTE}")
endif()
elseif(CUDA_VERSION VERSION_GREATER "8.0") # cuda 9
if ("${COMPUTE}" STREQUAL "all")
if (APPLE)
set(CMAKE_CUDA_FLAGS " ${CMAKE_CUDA_FLAGS} -DCUDA_9 ${EXPM} -w --cudart=static --expt-extended-lambda -Xfatbin -compress-all -gencode arch=compute_30,code=sm_30 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_60,code=sm_60")
2019-06-06 14:21:15 +02:00
else()
set(CMAKE_CUDA_FLAGS " ${CMAKE_CUDA_FLAGS} -DCUDA_9 ${EXPM} -w --cudart=static --expt-extended-lambda -Xfatbin -compress-all -gencode arch=compute_30,code=sm_30 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=sm_70")
2019-06-06 14:21:15 +02:00
endif()
else()
set(CMAKE_CUDA_FLAGS " ${CMAKE_CUDA_FLAGS} -DCUDA_9 ${EXPM} -w --cudart=static --expt-extended-lambda -Xfatbin -compress-all -arch=compute_${COMPUTE} -code=sm_${COMPUTE}")
2019-06-06 14:21:15 +02:00
endif()
elseif (CUDA_VERSION VERSION_GREATER "7.5") # cuda 8.0
if ("${COMPUTE}" STREQUAL "all")
set(CMAKE_CUDA_FLAGS " ${CMAKE_CUDA_FLAGS} -DCUDA_8 ${EXPM} -w --cudart=static --expt-extended-lambda -Xfatbin -compress-all -gencode arch=compute_30,code=sm_30 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_60,code=sm_60")
else()
set(CMAKE_CUDA_FLAGS " ${CMAKE_CUDA_FLAGS} -DCUDA_8 ${EXPM} -w --cudart=static --expt-extended-lambda --Xfatbin -compress-all -arch=compute_${COMPUTE} -code=sm_${COMPUTE}")
2019-06-06 14:21:15 +02:00
endif()
else()
if ("${COMPUTE}" STREQUAL "all")
set(CMAKE_CUDA_FLAGS " ${CMAKE_CUDA_FLAGS} -DCUDA_75 ${EXPM} -w --cudart=static --expt-extended-lambda -Xfatbin -compress-all -gencode arch=compute_30,code=sm_30 -gencode arch=compute_52,code=sm_52")
2019-06-06 14:21:15 +02:00
else()
set(CMAKE_CUDA_FLAGS " ${CMAKE_CUDA_FLAGS} -DCUDA_75 ${EXPM} -w --cudart=static --expt-extended-lambda -Xfatbin -compress-all -arch=compute_${COMPUTE} -code=sm_${COMPUTE}")
2019-06-06 14:21:15 +02:00
endif()
endif()
file(GLOB_RECURSE PERF_SOURCES false ../include/performance/*.cpp ../include/performance/*.h)
Merge master to upstream (#7945) * Shugeo strided slice zeros (#14) * Modified strided_slice op to properly work with empty-like shapes. * Fixed test for reduce_mean with empty-like input. * [WIP] Last merge (#15) * correct logsoftmax looss (#2) * Small SameDiff listener fix (#4) * Various fixes (#6) * #7839 Fix for asXMatrix and tests * #7866 EmbeddingSequenceLayer dtype fix + test * #7856 SameDiff save/load stream methods * #7859 RegressionEvaluation rank 4 fix + tests + axis configuration * EvaluationBinary 3d/4d * More evaluation 3d/4d tests * #7847 Evaluation empty checks * Small test ifx * #7848 Fix median edge case * Improve DL4J samediff layer tests * [WIP] FastText wrapper implemented (#8) * FastText implemented * Some fixes * Fix shapes for wordsNearest * Validation of input vectors * Fixes * Fixed test * Thread tagged * Some tweaks * setContextClassLoader for DeallocatorServiceThread * Numpy format tests (#1) * Various fixes (#11) * #7852 SameDiff gather fix * #7892 SameDiff placeholder to constant conversion * #7890 validate input rank for MLN/CG init methods * Fix broken permute shape calculation * Permute and gather fixes * Tests * #7850 LogSumExp fix + test * Handful of test fixes * Empty arrays with non-scalar shapes (#10) * minor rearrangements for lambdas * empty tensors with non-scalar shapes * numpy empty tensors with non-scalar shapes * few more empty tweaks * Small fixes * conv3d signature update * micro fix in batchnorm mkldnn * Import fixes * Fix * MKL-DNN update * Small fill fix * fill with empty input + test * Fixes * Small error improvement * Fix * one special test * couple of fixes for lstm * Rewrite TFGraphMapper.getNDArrayFromTensor to be maintainable and less error prone * Fixes * FP16 * Unsigned * BFloat16 * Fill op - empty tweaks * - couple of fixes for empty arrays construction - stack updated * strided slice fix * one transform test * provide method for reducing shapeInfo in case of input array is empty * Fixed reduceAlongDimensions to use empty input properly. * couple of broadcast tests * couple of tests broadcast tests + tweak to make them pass * add check of non-empty to methods producing sub-arrays * Fixed reshapeC with zeros in shape. * complete empty check in reduce_... legacy ops * Concat and cumsum/prod * Tweak to empty shape inference on import * add empty check to the rest of reduce legacy ops * one more test * correct typo in evalReduceShapeInfoEmpty * Added tests for reduce_* ops to tests with zero shapes. * few more tests for empty reductions * Fixed strided_slice op with empty case and tests. * one more empty reduction test * Fixed strided_slice test. * add empty check to NDArray::reshapei * infOrMax * empty min/max with infinity tests * made unstack working correctly with empty arrays * few IndexReduce tests + tweaks for empty shapes * add test for empty concat * few tests fixed * Validation fix for reductions on empty shapes * Reverse fix * Reduction shape calc fixes * SameDiff.generateOutputVariable: don't use shape function to determine number of outputs * Range fix * - NDArray constructor updated for scalars/empty arrays - few tests fixed * More fixes * Empty creator fixes * concat fix * concat fix * TF import tests: allow 'both all NaN' and 'both all inf' to pass * Slice, zero fraction, and reshape fixes * transpose, gather * Zero fraction * scalar cast fix * Empty reduction axis support * few more tests fixed * Fixed input checks conforming with TF for concat op and tests. * few tests fixed * matmul scalar shape fix * Fixed checkout for data type and scalarity with concat to allow non-empty scalars with vector concats. * broadcast bool fix * few more tests * few more tests * correct evalReduceShapeInfoEmpty * argmax/argmin + tests * one more empty edge case + one more test * argmax/argmin/realdiv_bp tweaks * empty reshape test + fix * Helper fixes * Small fixes * Gather test fix * Gather test fix * Small fixes * reduce scalar zero values * scalar mean workaround * Remove debug code * along dim mean workaround * one more test * - equalsTo() tweak for empty arrays - one more test * broadcast tweaks * [WIP] Fixing outstanding issues for NLP (#9) * Avoid using not-inited objects * Test fixed. * Redundant method avoided for models like FastText * KMeans++ implementation * KMeans++ implementation * Disable parallel execution * KMeans++ * Tests * Dev branch merge (#16) * SameDiff: convertDataType and gradient check util improvements (#12) * GradCheck util improvements * StopGradient constructor + test * SameDiff: Add datatype conversion * Javadoc and add DataType.isNumerical() * Small fix * Fix SameDiff TF import test cases intermediate naming (workaround for bad default) * TFGraphTestAllHelper: check intermediates in execution order * Add missing debug listener * [WIP] lstmBlock fix + other changes (#13) - fixes lstmBlock issue - changes NDArray method reshape(), permute(), transpose() by making them return instance instead of pointer - CheckNumerics op - fixes for ReduceBool IsInfOrNan & IsFinite * Small test fix * CheckNumerics op wrapper * Fix some issues on master (#17) * Fix DataVec test issue * Fix issue with dl4j SameDiff output layer * Dtype fix for lambda layers * #7912 BertIterator dtype fix (use float32 not global default) * [WIP] Next set of CUDA stuff (#7) New CUDA implementations and improvements * bad file * Dev branch master merge (#23) * SameDiff: convertDataType and gradient check util improvements (#12) * GradCheck util improvements * StopGradient constructor + test * SameDiff: Add datatype conversion * Javadoc and add DataType.isNumerical() * Small fix * Fix SameDiff TF import test cases intermediate naming (workaround for bad default) * TFGraphTestAllHelper: check intermediates in execution order * Add missing debug listener * [WIP] lstmBlock fix + other changes (#13) - fixes lstmBlock issue - changes NDArray method reshape(), permute(), transpose() by making them return instance instead of pointer - CheckNumerics op - fixes for ReduceBool IsInfOrNan & IsFinite * Small test fix * CheckNumerics op wrapper * Compatibility of deserialization (#18) Signed-off-by: Alexander Stoyakin <alexander.stoyakin@gmail.com> * SameDiff: add activation gradient checking support for debugging (#19) * SameDiff gradient checker: first pass on activation gradient checks * Fixes + tests for activation gradient checking * Javadoc * [WIP] Some nd4j data type corrections (#20) * Adjust data type * Set correct Data type. * Size of proper data type. * fix averaged cpu load (#22) * SameDiff ops, TF import and fixes (#24) * CheckNumerics tests + fixes + misc fixes Signed-off-by: AlexDBlack <blacka101@gmail.com> * Fake quant Signed-off-by: AlexDBlack <blacka101@gmail.com> * Fixes Signed-off-by: AlexDBlack <blacka101@gmail.com> * FakeQuantWithMinMaxArgs Signed-off-by: AlexDBlack <blacka101@gmail.com> * CheckNumerics fix Signed-off-by: AlexDBlack <blacka101@gmail.com> * Fix libnd4j ALL_INTS and ALL_FLOATS declaration (uint and bfloat types) Signed-off-by: AlexDBlack <blacka101@gmail.com> * Small fix Signed-off-by: AlexDBlack <blacka101@gmail.com> * Javadoc Signed-off-by: AlexDBlack <blacka101@gmail.com> * Exception tweak Signed-off-by: AlexDBlack <blacka101@gmail.com> * fix Signed-off-by: AlexDBlack <blacka101@gmail.com> * Fix for out of scope stack allocated var use Signed-off-by: AlexDBlack <blacka101@gmail.com> * Ignores Signed-off-by: AlexDBlack <blacka101@gmail.com> * Ignore for known failing test (already logged issue) Signed-off-by: AlexDBlack <blacka101@gmail.com> * Merge upstream to fork (#25) * Add thousand-separator commas to TotalParams (#7915) * Add thousand-separator commas to TotalParams The number of parameters can be quite large, and it would help the reading of the summary printout to have the TotalParams column & values at the bottom have thousand-separator-commas in them. * Add thousand-separator commas to MultiLayerNetwork Corresponding change to MultiLayerNetwork Signed-off-by: Jxtps Jxtps <jxtps435@gmail.com> * Update contributing and issue/PR templates (#7934) Signed-off-by: AlexDBlack <blacka101@gmail.com> * Fix link to AdaDelta paper (#7942) Fix link to AdaDelta paper hosted on matthewzeiler.com Signed-off-by: Jxtps * Fixes, and ignores for known/logged failing issues (#7943) Signed-off-by: AlexDBlack <blacka101@gmail.com> * SameDiff + DL4J/SameDiff: Multiple fixes (#28) * #7919 HDF5 attribute buffer length fix Signed-off-by: AlexDBlack <blacka101@gmail.com> * #7909 Arbiter constructor exception ux improvements Signed-off-by: AlexDBlack <blacka101@gmail.com> * #7925 RNN output layer length checks Signed-off-by: AlexDBlack <blacka101@gmail.com> * #7939 Add listener for validating inputs are not incorrectly modified Signed-off-by: AlexDBlack <blacka101@gmail.com> * #7939 Integrate NonInplaceValidationListener into tests * #7844 DL4J SameDiff fixes for variable minibatch size * DL4J SameDiff fixes - ensure gradient for input placeholder is available Signed-off-by: AlexDBlack <blacka101@gmail.com> * Tweaks to ExternalErrorsFunction - use placeholders, make more robust * Another fix * More fixes * More SameDiff/DL4J fixes * Scope out scalar array creation in BaseScalarOp * Remove debug code Signed-off-by: AlexDBlack <blacka101@gmail.com> * [WIP] Final dev branch merge (#29) * SameDiff: convertDataType and gradient check util improvements (#12) * GradCheck util improvements * StopGradient constructor + test * SameDiff: Add datatype conversion * Javadoc and add DataType.isNumerical() * Small fix * Fix SameDiff TF import test cases intermediate naming (workaround for bad default) * TFGraphTestAllHelper: check intermediates in execution order * Add missing debug listener * [WIP] lstmBlock fix + other changes (#13) - fixes lstmBlock issue - changes NDArray method reshape(), permute(), transpose() by making them return instance instead of pointer - CheckNumerics op - fixes for ReduceBool IsInfOrNan & IsFinite * Small test fix * CheckNumerics op wrapper * Compatibility of deserialization (#18) Signed-off-by: Alexander Stoyakin <alexander.stoyakin@gmail.com> * SameDiff: add activation gradient checking support for debugging (#19) * SameDiff gradient checker: first pass on activation gradient checks * Fixes + tests for activation gradient checking * Javadoc * [WIP] Some nd4j data type corrections (#20) * Adjust data type * Set correct Data type. * Size of proper data type. * fix averaged cpu load (#22) * [WIP] Multiple dataset iterators (#27) * Splitting dataset into arbitrary number * Fixes * Multiple split of iterator * Test * Test * Some fixes * signature change * one more tweak Signed-off-by: raver119 <raver119@gmail.com> * one more test for sequential use of DataSetIteratorSplitter Signed-off-by: raver119 <raver119@gmail.com> * Fixes * Fixes * one more test for Alexander Signed-off-by: raver119 <raver119@gmail.com> * Some fixes * Some fixes * one more test for Alexander Signed-off-by: raver119 <raver119@gmail.com> * minor test fix Signed-off-by: raver119 <raver119@gmail.com> * Some fixes * Some fixes * couple of assertions tweaked Signed-off-by: raver119 <raver119@gmail.com> * MDS splitter test :/ Signed-off-by: raver119 <raver119@gmail.com> * Minor refactoring * Multi dataset * Some fixes * More tests * Small number of test fixes/improvements (failures on CI) (#31) Signed-off-by: AlexDBlack <blacka101@gmail.com> * [WIP] More CUDA stuff (#26) * initial commit Signed-off-by: raver119 <raver119@gmail.com> * LRN BP CUDA Signed-off-by: raver119 <raver119@gmail.com> * less memory Signed-off-by: raver119 <raver119@gmail.com> * Fixed bug with crop_and_resize op helper. * get rid of unnecessary index-calculation dunction Signed-off-by: Yurii <yurii@skymind.io> * Fixed sort with nth_element cuda-based helper. * Refactored nth_element. * Refactored nth_element op and tests. * Modified usage of dim array with sortTad routine. * Refactored main routine of helper for non_max_image_suppression op. * non_max_image_suppression op helper with cuda kernel implementation. Initial revision. * fix vol2col cuda kernel * meh Signed-off-by: raver119 <raver119@gmail.com> * topK concept Signed-off-by: raver119 <raver119@gmail.com> * unsorted topK with scanWitdh of 1 Signed-off-by: raver119 <raver119@gmail.com> * correct vol2col tests * sorted/unsorted topK Signed-off-by: raver119 <raver119@gmail.com> * implementation and fixing col2im/col2vol * Corrected usage flags with input/output with reverse op. * dup is const now Signed-off-by: raver119 <raver119@gmail.com> * percentile op Signed-off-by: raver119 <raver119@gmail.com> * group tests for mapool2d Signed-off-by: Yurii <yurii@skymind.io> * special test for george Signed-off-by: raver119 <raver119@gmail.com> * less threads for sortTad Signed-off-by: raver119 <raver119@gmail.com> * provide conv2d for cuda Signed-off-by: Yurii <yurii@skymind.io> * remove auther in sort tad kernel code Signed-off-by: Yurii <yurii@skymind.io> * provide depthwise_conv2d for cuda Signed-off-by: Yurii <yurii@skymind.io> * - max_pooling_with_argmax - null check for special use Signed-off-by: raver119 <raver119@gmail.com> * dts cuda Signed-off-by: raver119 <raver119@gmail.com> * provide sconv2d for cuda Signed-off-by: Yurii <yurii@skymind.io> * std cuda Signed-off-by: raver119 <raver119@gmail.com> * Refactored non_max_suppression op to conform TF implementation. * Improved suppression helper. * provide pooling3d for cuda Signed-off-by: Yurii <yurii@skymind.io> * minor lstm rearrangements Signed-off-by: raver119 <raver119@gmail.com> * more of minor lstm rearrangements Signed-off-by: raver119 <raver119@gmail.com> * (bi)dynamic_rnn Signed-off-by: raver119 <raver119@gmail.com> * templates init order Signed-off-by: raver119 <raver119@gmail.com> * Refactored non_max_suppression op. * Added cuda kernel for non_max_suppression. * CPU sort by key/value Signed-off-by: raver119 <raver119@gmail.com> * CPU sort TAD by key/value Signed-off-by: raver119 <raver119@gmail.com> * CPU sort TAD by key/value tests Signed-off-by: raver119 <raver119@gmail.com> * Eliminate compiler error with cuda implementation. * - repaired gradCheck in cuda - provide conv2d_bp for cuda Signed-off-by: Yurii <yurii@skymind.io> * missed signature Signed-off-by: raver119 <raver119@gmail.com> * provide depthwise_conv2d_bp for cuda Signed-off-by: Yurii <yurii@skymind.io> * Implementation of lup helper with cuda kernel. Initial commit. * further work on backprops for convolutions Signed-off-by: Yurii <yurii@skymind.io> * CUDA linear sort by key/val Signed-off-by: raver119 <raver119@gmail.com> * CUDA tad sort by key/val Signed-off-by: raver119 <raver119@gmail.com> * start providing of backprop for pooling2d/3d Signed-off-by: Yurii <yurii@skymind.io> * Added atomicAdd for bool datatype. * dynamic partition concept Signed-off-by: raver119 <raver119@gmail.com> * dynamic partition concept Signed-off-by: raver119 <raver119@gmail.com> * dynamic partition scalar CUDA Signed-off-by: raver119 <raver119@gmail.com> * important comment Signed-off-by: raver119 <raver119@gmail.com> * fix pooling2d/3d backprop helpers Signed-off-by: Yurii <yurii@skymind.io> * Added non-linear test with dynamic_partition. * Improved test for dynamic_partition. * dynamic_partition TAD concept Signed-off-by: raver119 <raver119@gmail.com> * - dynamic_partition TAD CUDA impl - dynamic_partition TAD CPU fix Signed-off-by: raver119 <raver119@gmail.com> * - rewrite cpu code for usampling2d/3d - write cuda code for usampling2d/3d Signed-off-by: Yurii <yurii@skymind.io> * dynamic_stitch CUDA vector case Signed-off-by: raver119 <raver119@gmail.com> * dynamic_stitch CUDA TAD case concept Signed-off-by: raver119 <raver119@gmail.com> * dynamic_stitch CUDA TAD case impl Signed-off-by: raver119 <raver119@gmail.com> * Added tests for dynamic_stitch 3D-4D cases. * minor tests tweaks Signed-off-by: raver119 <raver119@gmail.com> * Fixed type check for dynamic stitch. * min/max bp Signed-off-by: raver119 <raver119@gmail.com> * rewrite code for upsampling2d/3d cpu Signed-off-by: Yurii <yurii@skymind.io> * reduce min/max/norm_max bp Signed-off-by: raver119 <raver119@gmail.com> * lup implementation. Additional enhancements. * provide code for upsamling2d/3d backprop Signed-off-by: Yurii <yurii@skymind.io> * weightedCrossEntropyWithLogits Signed-off-by: raver119 <raver119@gmail.com> * Fixed template math atomicMul for 64bit ints. * Refactored dynamic_partition_bp op. * inverseBroadcast fix Signed-off-by: raver119 <raver119@gmail.com> * DynamicPartitionBP test datatype fixed. * - nd4j_atomicMul Windows fix - cpu/NDArrayLambda.hpp excluded from CUDA Signed-off-by: raver119 <raver119@gmail.com>
2019-06-27 17:37:04 +02:00
file(GLOB_RECURSE EXCEPTIONS_SOURCES false ../include/exceptions/*.cpp ../include/exceptions/*.h)
file(GLOB_RECURSE EXEC_SOURCES false ../include/execution/impl/*.cpp ../include/execution/*.cu ../include/execution/*.h)
file(GLOB_RECURSE TYPES_SOURCES false ../include/types/*.cpp ../include/types/*.h)
file(GLOB_RECURSE ARRAY_SOURCES false ../include/array/impl/*.cpp ../include/array/cuda/*.cu ../include/array/*.h)
file(GLOB_RECURSE MEMORY_SOURCES false ../include/memory/impl/*.cpp ../include/memory/cuda/*.cu ../include/memory/*.h)
file(GLOB_RECURSE GRAPH_SOURCES false ../include/graph/*.cpp ../include/graph/*.cu ../include/graph/*.h)
file(GLOB_RECURSE CUSTOMOPS_SOURCES false ../include/ops/declarable/generic/*.cpp)
file(GLOB_RECURSE CUSTOMOPS_HELPERS_SOURCES false ../include/ops/declarable/helpers/cuda/*.cu ../include/ops/declarable/helpers/impl/*.cpp)
file(GLOB_RECURSE OPS_SOURCES false ../include/ops/impl/*.cpp ../include/ops/declarable/impl/*.cpp ../include/ops/*.h)
file(GLOB_RECURSE HELPERS_SOURCES false ../include/helpers/impl/*.cpp ../include/helpers/*.cu ../include/helpers/*.cupp ../include/helpers/*.h)
file(GLOB_RECURSE INDEXING_SOURCES false ../include/indexing/*.cpp ../include/indexing/*.h)
[WIP] multi-device support (#80) * fix pad javadoc and @see links. (#72) Signed-off-by: Robert Altena <Rob@Ra-ai.com> * [WIP] More fixes (#73) * special tests for ConstantTadHelper/ConstantShapeHelper Signed-off-by: raver119 <raver119@gmail.com> * release methods for data buffers Signed-off-by: raver119 <raver119@gmail.com> * delete temporary buffer Java side Signed-off-by: raver119 <raver119@gmail.com> * delete temporary buffer Java side Signed-off-by: raver119 <raver119@gmail.com> * delete temporary TadPack C++/Java side (#74) Signed-off-by: raver119 <raver119@gmail.com> * Zoo model TF import test updates (#75) * argLine fix, update compression_gru comment * updated comment for xception * undid but commented argLine change * updated xlnet comment * copyright headers * - new NDArray methods like()/ulike() (#77) - fix for depthwise_conv2d_bp + special test Signed-off-by: raver119 <raver119@gmail.com> * upsampling2d fix CUDA Signed-off-by: raver119 <raver119@gmail.com> * DL4J trace logging (#79) * MLN/CG trace logging for debugging Signed-off-by: AlexDBlack <blacka101@gmail.com> * Tiny tweak Signed-off-by: AlexDBlack <blacka101@gmail.com> * strided_slice_bp shape fn leak fix Signed-off-by: raver119 <raver119@gmail.com> * SameDiff fixes and naming (#78) * remove SDVariable inplace methods * import methods * npe fix in OpVal * removed SameDiff inplace ops from tests * Naming updates, moved to centralized methods in SameDiff, should use op_#:# for everything * quick fixes * javadoc * SDVariable eval with placeholders * use regex match * better matching * initial commit Signed-off-by: raver119 <raver119@gmail.com> * initial commit Signed-off-by: raver119 <raver119@gmail.com> * fix javadoc. (#76) * fix javadoc. Signed-off-by: Robert Altena <Rob@Ra-ai.com> * replace most @see with @link s. Signed-off-by: Robert Altena <Rob@Ra-ai.com> * 4 additional tests Signed-off-by: raver119 <raver119@gmail.com> * launch context reorganization Signed-off-by: raver119 <raver119@gmail.com> * LaunchContext reorganization Signed-off-by: raver119 <raver119@gmail.com> * per-device LaunchContext Signed-off-by: raver119 <raver119@gmail.com> * Various DL4J/ND4J fixes (#81) * #7954 Force refresh of UI when switching tabs on overview page Signed-off-by: AlexDBlack <blacka101@gmail.com> * #8017 Concurrent modification exception (synchronize) fix Signed-off-by: AlexDBlack <blacka101@gmail.com> * #8033 Don't initialize updater in middle of writing memory crash dump Signed-off-by: AlexDBlack <blacka101@gmail.com> * #8208 Fix shape checks for ND4J int[] creator methods Signed-off-by: AlexDBlack <blacka101@gmail.com> * #6385 #7992 Keras import naming fixes + cleanup Signed-off-by: AlexDBlack <blacka101@gmail.com> * #8016 Upsampling3D - add NDHWC format support Signed-off-by: AlexDBlack <blacka101@gmail.com> * ContextBuffers as separate entity Signed-off-by: raver119 <raver119@gmail.com> * Refactor NativeOps.h to export C functions * Actually export functions from NativeOps.h * Adapt the Java wrappers in ND4J generated with JavaCPP * Create C wrappers for some of the C++ classes currently used by ND4J * ContextBuffers as separate entity Signed-off-by: raver119 <raver119@gmail.com> * remove duplicate code in createBufferDetached. (#83) Signed-off-by: Robert Altena <Rob@Ra-ai.com> * Keras model import - updater lr fix (#84) * Keras model import - updater lr fix Signed-off-by: eraly <susan.eraly@gmail.com> * Keras model import - updater lr fix, cleanup Signed-off-by: eraly <susan.eraly@gmail.com> * ContextBuffers as separate entity Signed-off-by: raver119 <raver119@gmail.com> * ContextBuffers as separate entity Signed-off-by: raver119 <raver119@gmail.com> * Fix functions of OpaqueVariablesSet * thread-local buffers/affinity Signed-off-by: raver119 <raver119@gmail.com> * thread safety for LaunchContext Signed-off-by: raver119 <raver119@gmail.com> * more of thread safety Signed-off-by: raver119 <raver119@gmail.com> * one more multi threaded test Signed-off-by: raver119 <raver119@gmail.com> * SameDiff Convolution Config validation, better output methods (#82) * Conv Config validation & tests Signed-off-by: Ryan Nett <rnett@skymind.io> * stackOutputs utility method Signed-off-by: Ryan Nett <rnett@skymind.io> * use constructor for validation, support negative kernel sizes (infered from weights) Signed-off-by: Ryan Nett <rnett@skymind.io> * better output methods Signed-off-by: Ryan Nett <rnett@skymind.io> * move output to be with fit and evaluate Signed-off-by: Ryan Nett <rnett@skymind.io> * fixes Signed-off-by: Ryan Nett <rnett@skymind.io> * more fixes Signed-off-by: Ryan Nett <rnett@skymind.io> * refactor duplicate code from pad methods. (#86) * refactor duplicate code from pad methods. Signed-off-by: Robert Altena <Rob@Ra-ai.com> * replace switch with if. Signed-off-by: Robert Altena <Rob@Ra-ai.com> * Various ND4J/DL4J fixes and improvements (#87) * Reshape and reallocate - small fixes Signed-off-by: AlexDBlack <blacka101@gmail.com> * Reshape and reallocate - small fixes Signed-off-by: AlexDBlack <blacka101@gmail.com> * #6488 ElementWiseVertex broadcast support Signed-off-by: AlexDBlack <blacka101@gmail.com> * Constructors and broadcast supported it Transforms.max/min Signed-off-by: AlexDBlack <blacka101@gmail.com> * #8054 ElementWiseVertex now supports broadcast inputs Signed-off-by: AlexDBlack <blacka101@gmail.com> * #8057 Nd4j.create overload dtype fix Signed-off-by: AlexDBlack <blacka101@gmail.com> * #7551 ND4J Shape validation fix Signed-off-by: AlexDBlack <blacka101@gmail.com> * [WIP] Numpy boolean import (#91) * numpy bool type Signed-off-by: raver119 <raver119@gmail.com> * numpy bool java side Signed-off-by: raver119 <raver119@gmail.com> * remove create method with unused parameter. (#89) * remove create method with unused parameter. * removed more unused methods. Signed-off-by: Robert Altena <Rob@Ra-ai.com> * removing more unused code. Signed-off-by: Robert Altena <Rob@Ra-ai.com> * last removal of unused code. Signed-off-by: Robert Altena <Rob@Ra-ai.com> * remove createSparse methods. (#92) Signed-off-by: Robert Altena <Rob@Ra-ai.com> * Various ND4J/DL4J fixes (#90) * Deprecate Old*Op instances Signed-off-by: AlexDBlack <blacka101@gmail.com> * #8063 #8054 Broadcast exceptions + cleanup inplace ops Signed-off-by: AlexDBlack <blacka101@gmail.com> * Small fix Signed-off-by: AlexDBlack <blacka101@gmail.com> * Remove bad test condition Signed-off-by: AlexDBlack <blacka101@gmail.com> * #7993 Fix shape function issue in crop_and_resize op Signed-off-by: AlexDBlack <blacka101@gmail.com> * DL4J SameDiff lambda layer fix Signed-off-by: AlexDBlack <blacka101@gmail.com> * #8029 Fix for pnorm backprop math Signed-off-by: AlexDBlack <blacka101@gmail.com> * #8038 Fix Op profiler NaN/Inf triggering + add tests (#93) Signed-off-by: AlexDBlack <blacka101@gmail.com> * createUninitializedDetached refactoring. (#94) * wip * update interface, add null implementations. * Breaking one test in a weird way. Signed-off-by: Robert Altena <Rob@Ra-ai.com> * createUninitializedDetached refactored. Signed-off-by: Robert Altena <Rob@Ra-ai.com> * cuda build fix for issues introduced by recent refactoring Signed-off-by: raver119 <raver119@gmail.com> * [WIP] More of CUDA (#95) * initial commit Signed-off-by: raver119 <raver119@gmail.com> * Implementation of hashcode cuda helper. Working edition. * Fixed parallel test input arangements. * Fixed tests for hashcode op. * Fixed shape calculation for image:crop_and_resize op and test. * NativeOps tests. Initial test suite. * Added tests for indexReduce methods. * Added test on execBroadcast with NDArray as dimensions. * Added test on execBroadcastBool with NDArray as dimensions. * Added tests on execPairwiseTransform and execPairwiseTransofrmBool. * Added tests for execReduce with scalar results. * Added reduce tests for non-empty dims array. * Added tests for reduce3. * Added tests for execScalar. * Added tests for execSummaryStats. * - provide cpu/cuda code for batch_to_space - testing it Signed-off-by: Yurii <yurii@skymind.io> * - remove old test for batch_to_space (had wrong format and numbers were not checked) Signed-off-by: Yurii <yurii@skymind.io> * Fixed complilation errors with test. * Added test for execTransformFloat. * Added test for execTransformSame. * Added test for execTransformBool. * Added test for execTransformStrict. * Added tests for execScalar/execScalarBool with TADs. * Added test for flatten. * - provide cpu/cuda code for space_to_Batch operaion Signed-off-by: Yurii <yurii@skymind.io> * Added test for concat. * comment unnecessary stuff in s_t_b Signed-off-by: Yurii <yurii@skymind.io> * Added test for specialConcat. * Added tests for memcpy/set routines. * Fixed pullRow cuda test. * Added pullRow test. * Added average test. * - correct typo in NDArray::applyPairwiseTransform(nd4j::pairwise::BoolOps op...) Signed-off-by: Yurii <yurii@skymind.io> * - debugging and fixing cuda tests in JavaInteropTests file Signed-off-by: Yurii <yurii@skymind.io> * - correct some tests Signed-off-by: Yurii <yurii@skymind.io> * Added test for shuffle. * Fixed ops declarations. * Restored omp and added shuffle test. * Added convertTypes test. * Added tests for execRandom. Eliminated usage of RandomBuffer with NativeOps. * Added sort tests. * Added tests for execCustomOp. * - further debuging and fixing tests terminated with crash Signed-off-by: Yurii <yurii@skymind.io> * Added tests for calculateOutputShapes. * Addded Benchmarks test. * Commented benchmark tests. * change assertion Signed-off-by: raver119 <raver119@gmail.com> * Added tests for apply_sgd op. Added cpu helper for that op. * Implement cuda helper for aplly_sgd op. Fixed tests for NativeOps. * Added test for assign broadcastable. * Added tests for assign_bp op. * Added tests for axpy op. * - assign/execScalar/execTransformAny signature change - minor test fix Signed-off-by: raver119 <raver119@gmail.com> * Fixed axpy op. * meh Signed-off-by: raver119 <raver119@gmail.com> * - fix tests for nativeOps::concat Signed-off-by: Yurii <yurii@skymind.io> * sequential transform/scalar Signed-off-by: raver119 <raver119@gmail.com> * allow nested parallelism Signed-off-by: raver119 <raver119@gmail.com> * assign_bp leak fix Signed-off-by: raver119 <raver119@gmail.com> * block setRNG fix Signed-off-by: raver119 <raver119@gmail.com> * enable parallelism by default Signed-off-by: raver119 <raver119@gmail.com> * enable nested parallelism by default Signed-off-by: raver119 <raver119@gmail.com> * Added cuda implementation for row_count helper. * Added implementation for tnse gains op helper. * - take into account possible situations when input arrays are empty in reduce_ cuda stuff Signed-off-by: Yurii <yurii@skymind.io> * Implemented tsne/edge_forces op cuda-based helper. Parallelized cpu-based helper for edge_forces. * Added kernel for tsne/symmetrized op heleper. * Implementation of tsne/symmetrized op cuda helper. Working edition. * Eliminated waste printfs. * Added test for broadcastgradientargs op. * host-only fallback for empty reduce float Signed-off-by: raver119 <raver119@gmail.com> * - some tests fixes Signed-off-by: Yurii <yurii@skymind.io> * - correct the rest of reduce_ stuff Signed-off-by: Yurii <yurii@skymind.io> * - further correction of reduce_ stuff Signed-off-by: Yurii <yurii@skymind.io> * Added test for Cbow op. Also added cuda implementation for cbow helpers. * - improve code of stack operation for scalar case Signed-off-by: Yurii <yurii@skymind.io> * - provide cuda kernel for gatherND operation Signed-off-by: Yurii <yurii@skymind.io> * Implementation of cbow helpers with cuda kernels. * minor tests tweaks Signed-off-by: raver119 <raver119@gmail.com> * minor tests tweaks Signed-off-by: raver119 <raver119@gmail.com> * - further correction of cuda stuff Signed-off-by: Yurii <yurii@skymind.io> * Implementatation of cbow op helper with cuda kernels. Working edition. * Skip random testing for cudablas case. * lstmBlockCell context fix Signed-off-by: raver119 <raver119@gmail.com> * Added tests for ELU and ELU_BP ops. * Added tests for eq_scalar, gt_scalar, gte_scalar and lte_scalar ops. * Added tests for neq_scalar. * Added test for noop. * - further work on clipbynorm_bp Signed-off-by: Yurii <yurii@skymind.io> * - get rid of concat op call, use instead direct concat helper call Signed-off-by: Yurii <yurii@skymind.io> * lstmBlockCell context fix Signed-off-by: raver119 <raver119@gmail.com> * Added tests for lrelu and lrelu_bp. * Added tests for selu and selu_bp. * Fixed lrelu derivative helpers. * - some corrections in lstm Signed-off-by: Yurii <yurii@skymind.io> * operator * result shape fix Signed-off-by: raver119 <raver119@gmail.com> * - correct typo in lstmCell Signed-off-by: Yurii <yurii@skymind.io> * few tests fixed Signed-off-by: raver119 <raver119@gmail.com> * CUDA inverse broadcast bool fix Signed-off-by: raver119 <raver119@gmail.com> * disable MMAP test for CUDA Signed-off-by: raver119 <raver119@gmail.com> * BooleanOp syncToDevice Signed-off-by: raver119 <raver119@gmail.com> * meh Signed-off-by: raver119 <raver119@gmail.com> * additional data types for im2col/col2im Signed-off-by: raver119 <raver119@gmail.com> * Added test for firas_sparse op. * one more RandomBuffer test excluded Signed-off-by: raver119 <raver119@gmail.com> * Added tests for flatten op. * Added test for Floor op. * bunch of tests fixed Signed-off-by: raver119 <raver119@gmail.com> * mmulDot tests fixed Signed-off-by: raver119 <raver119@gmail.com> * more tests fixed Signed-off-by: raver119 <raver119@gmail.com> * Implemented floordiv_bp op and tests. * Fixed scalar case with cuda implementation for bds. * - work on cuda kernel for clip_by_norm backprop op is completed Signed-off-by: Yurii <yurii@skymind.io> * Eliminate cbow crach. * more tests fixed Signed-off-by: raver119 <raver119@gmail.com> * more tests fixed Signed-off-by: raver119 <raver119@gmail.com> * Eliminated abortion with batched nlp test. * more tests fixed Signed-off-by: raver119 <raver119@gmail.com> * Fixed shared flag initializing. * disabled bunch of cpu workspaces tests Signed-off-by: raver119 <raver119@gmail.com> * scalar operators fix: missing registerSpecialUse call Signed-off-by: raver119 <raver119@gmail.com> * Fixed logdet for cuda and tests. * - correct clipBynorm_bp Signed-off-by: Yurii <yurii@skymind.io> * Fixed crop_and_resize shape datatype. * - correct some mmul tests Signed-off-by: Yurii <yurii@skymind.io> * build fix Signed-off-by: raver119 <raver119@gmail.com> * exclude two methods for JNI Signed-off-by: raver119 <raver119@gmail.com> * exclude two methods for JNI Signed-off-by: raver119 <raver119@gmail.com> * exclude two methods for JNI (#97) Signed-off-by: raver119 <raver119@gmail.com> * temporary stack fix Signed-off-by: raver119 <raver119@gmail.com> * round robin affinity test Signed-off-by: raver119 <raver119@gmail.com> * get rid of legacy CudaContext methods Signed-off-by: raver119 <raver119@gmail.com> * get rid of legacy ContextPool classes/methods Signed-off-by: raver119 <raver119@gmail.com> * one legacy test removed Signed-off-by: raver119 <raver119@gmail.com> * few more fields rearranged Signed-off-by: raver119 <raver119@gmail.com> * OpaqueLaunchContext Signed-off-by: raver119 <raver119@gmail.com> * OpaqueLaunchContext++ Signed-off-by: raver119 <raver119@gmail.com> * more of OpaqueLaunchContext methods Signed-off-by: raver119 <raver119@gmail.com> * LaunchContext -> CudaContext Signed-off-by: raver119 <raver119@gmail.com> * AffinityManger changes Signed-off-by: raver119 <raver119@gmail.com> * AffinityManger changes Signed-off-by: raver119 <raver119@gmail.com> * cusolver handles Signed-off-by: raver119 <raver119@gmail.com> * typo Signed-off-by: raver119 <raver119@gmail.com> * cusolver method Signed-off-by: raver119 <raver119@gmail.com> * cusolver handle propagated Signed-off-by: raver119 <raver119@gmail.com> * blas/solver handles Signed-off-by: raver119 <raver119@gmail.com> * one more test Signed-off-by: raver119 <raver119@gmail.com> * legacy concat implementations replaced with new CustomOp Signed-off-by: raver119 <raver119@gmail.com> * one more test Signed-off-by: raver119 <raver119@gmail.com> * concat now uses way more blocks Signed-off-by: raver119 <raver119@gmail.com> * print Signed-off-by: raver119 <raver119@gmail.com> * no more triple template mmul Signed-off-by: raver119 <raver119@gmail.com> * bunch of kernels have dtypes reconsidered Signed-off-by: raver119 <raver119@gmail.com> * bunch of kernels have dtypes reconsidered Signed-off-by: raver119 <raver119@gmail.com> * bitonic sort reorganized Signed-off-by: raver119 <raver119@gmail.com> * bunch of cpu stuff removed from cuda scope Signed-off-by: raver119 <raver119@gmail.com> * bunch of cpu stuff removed from cuda scope Signed-off-by: raver119 <raver119@gmail.com> * type conversions moved to generic impl Signed-off-by: raver119 <raver119@gmail.com> * cpu data types pass Signed-off-by: raver119 <raver119@gmail.com> * non_max_suppression Signed-off-by: raver119 <raver119@gmail.com> * sortByValue fix Signed-off-by: raver119 <raver119@gmail.com> * ignore all mixed datatype tests for mmul Signed-off-by: raver119 <raver119@gmail.com> * special handling of OpProfiler exceptions Signed-off-by: raver119 <raver119@gmail.com> * - one failing concat test in cpp - Nd4j.tile now uses op internally Signed-off-by: raver119 <raver119@gmail.com> * get back dtype exception for legacy arrays deserialization Signed-off-by: raver119 <raver119@gmail.com>
2019-08-14 15:52:34 +02:00
file(GLOB_RECURSE LOOPS_SOURCES false ../include/loops/impl/*.cpp ../include/loops/*.h)
file(GLOB_RECURSE LEGACY_SOURCES false ../include/legacy/impl/*.cpp ../include/legacy/*.cu ../include/legacy/*.h)
Merge master to upstream (#7945) * Shugeo strided slice zeros (#14) * Modified strided_slice op to properly work with empty-like shapes. * Fixed test for reduce_mean with empty-like input. * [WIP] Last merge (#15) * correct logsoftmax looss (#2) * Small SameDiff listener fix (#4) * Various fixes (#6) * #7839 Fix for asXMatrix and tests * #7866 EmbeddingSequenceLayer dtype fix + test * #7856 SameDiff save/load stream methods * #7859 RegressionEvaluation rank 4 fix + tests + axis configuration * EvaluationBinary 3d/4d * More evaluation 3d/4d tests * #7847 Evaluation empty checks * Small test ifx * #7848 Fix median edge case * Improve DL4J samediff layer tests * [WIP] FastText wrapper implemented (#8) * FastText implemented * Some fixes * Fix shapes for wordsNearest * Validation of input vectors * Fixes * Fixed test * Thread tagged * Some tweaks * setContextClassLoader for DeallocatorServiceThread * Numpy format tests (#1) * Various fixes (#11) * #7852 SameDiff gather fix * #7892 SameDiff placeholder to constant conversion * #7890 validate input rank for MLN/CG init methods * Fix broken permute shape calculation * Permute and gather fixes * Tests * #7850 LogSumExp fix + test * Handful of test fixes * Empty arrays with non-scalar shapes (#10) * minor rearrangements for lambdas * empty tensors with non-scalar shapes * numpy empty tensors with non-scalar shapes * few more empty tweaks * Small fixes * conv3d signature update * micro fix in batchnorm mkldnn * Import fixes * Fix * MKL-DNN update * Small fill fix * fill with empty input + test * Fixes * Small error improvement * Fix * one special test * couple of fixes for lstm * Rewrite TFGraphMapper.getNDArrayFromTensor to be maintainable and less error prone * Fixes * FP16 * Unsigned * BFloat16 * Fill op - empty tweaks * - couple of fixes for empty arrays construction - stack updated * strided slice fix * one transform test * provide method for reducing shapeInfo in case of input array is empty * Fixed reduceAlongDimensions to use empty input properly. * couple of broadcast tests * couple of tests broadcast tests + tweak to make them pass * add check of non-empty to methods producing sub-arrays * Fixed reshapeC with zeros in shape. * complete empty check in reduce_... legacy ops * Concat and cumsum/prod * Tweak to empty shape inference on import * add empty check to the rest of reduce legacy ops * one more test * correct typo in evalReduceShapeInfoEmpty * Added tests for reduce_* ops to tests with zero shapes. * few more tests for empty reductions * Fixed strided_slice op with empty case and tests. * one more empty reduction test * Fixed strided_slice test. * add empty check to NDArray::reshapei * infOrMax * empty min/max with infinity tests * made unstack working correctly with empty arrays * few IndexReduce tests + tweaks for empty shapes * add test for empty concat * few tests fixed * Validation fix for reductions on empty shapes * Reverse fix * Reduction shape calc fixes * SameDiff.generateOutputVariable: don't use shape function to determine number of outputs * Range fix * - NDArray constructor updated for scalars/empty arrays - few tests fixed * More fixes * Empty creator fixes * concat fix * concat fix * TF import tests: allow 'both all NaN' and 'both all inf' to pass * Slice, zero fraction, and reshape fixes * transpose, gather * Zero fraction * scalar cast fix * Empty reduction axis support * few more tests fixed * Fixed input checks conforming with TF for concat op and tests. * few tests fixed * matmul scalar shape fix * Fixed checkout for data type and scalarity with concat to allow non-empty scalars with vector concats. * broadcast bool fix * few more tests * few more tests * correct evalReduceShapeInfoEmpty * argmax/argmin + tests * one more empty edge case + one more test * argmax/argmin/realdiv_bp tweaks * empty reshape test + fix * Helper fixes * Small fixes * Gather test fix * Gather test fix * Small fixes * reduce scalar zero values * scalar mean workaround * Remove debug code * along dim mean workaround * one more test * - equalsTo() tweak for empty arrays - one more test * broadcast tweaks * [WIP] Fixing outstanding issues for NLP (#9) * Avoid using not-inited objects * Test fixed. * Redundant method avoided for models like FastText * KMeans++ implementation * KMeans++ implementation * Disable parallel execution * KMeans++ * Tests * Dev branch merge (#16) * SameDiff: convertDataType and gradient check util improvements (#12) * GradCheck util improvements * StopGradient constructor + test * SameDiff: Add datatype conversion * Javadoc and add DataType.isNumerical() * Small fix * Fix SameDiff TF import test cases intermediate naming (workaround for bad default) * TFGraphTestAllHelper: check intermediates in execution order * Add missing debug listener * [WIP] lstmBlock fix + other changes (#13) - fixes lstmBlock issue - changes NDArray method reshape(), permute(), transpose() by making them return instance instead of pointer - CheckNumerics op - fixes for ReduceBool IsInfOrNan & IsFinite * Small test fix * CheckNumerics op wrapper * Fix some issues on master (#17) * Fix DataVec test issue * Fix issue with dl4j SameDiff output layer * Dtype fix for lambda layers * #7912 BertIterator dtype fix (use float32 not global default) * [WIP] Next set of CUDA stuff (#7) New CUDA implementations and improvements * bad file * Dev branch master merge (#23) * SameDiff: convertDataType and gradient check util improvements (#12) * GradCheck util improvements * StopGradient constructor + test * SameDiff: Add datatype conversion * Javadoc and add DataType.isNumerical() * Small fix * Fix SameDiff TF import test cases intermediate naming (workaround for bad default) * TFGraphTestAllHelper: check intermediates in execution order * Add missing debug listener * [WIP] lstmBlock fix + other changes (#13) - fixes lstmBlock issue - changes NDArray method reshape(), permute(), transpose() by making them return instance instead of pointer - CheckNumerics op - fixes for ReduceBool IsInfOrNan & IsFinite * Small test fix * CheckNumerics op wrapper * Compatibility of deserialization (#18) Signed-off-by: Alexander Stoyakin <alexander.stoyakin@gmail.com> * SameDiff: add activation gradient checking support for debugging (#19) * SameDiff gradient checker: first pass on activation gradient checks * Fixes + tests for activation gradient checking * Javadoc * [WIP] Some nd4j data type corrections (#20) * Adjust data type * Set correct Data type. * Size of proper data type. * fix averaged cpu load (#22) * SameDiff ops, TF import and fixes (#24) * CheckNumerics tests + fixes + misc fixes Signed-off-by: AlexDBlack <blacka101@gmail.com> * Fake quant Signed-off-by: AlexDBlack <blacka101@gmail.com> * Fixes Signed-off-by: AlexDBlack <blacka101@gmail.com> * FakeQuantWithMinMaxArgs Signed-off-by: AlexDBlack <blacka101@gmail.com> * CheckNumerics fix Signed-off-by: AlexDBlack <blacka101@gmail.com> * Fix libnd4j ALL_INTS and ALL_FLOATS declaration (uint and bfloat types) Signed-off-by: AlexDBlack <blacka101@gmail.com> * Small fix Signed-off-by: AlexDBlack <blacka101@gmail.com> * Javadoc Signed-off-by: AlexDBlack <blacka101@gmail.com> * Exception tweak Signed-off-by: AlexDBlack <blacka101@gmail.com> * fix Signed-off-by: AlexDBlack <blacka101@gmail.com> * Fix for out of scope stack allocated var use Signed-off-by: AlexDBlack <blacka101@gmail.com> * Ignores Signed-off-by: AlexDBlack <blacka101@gmail.com> * Ignore for known failing test (already logged issue) Signed-off-by: AlexDBlack <blacka101@gmail.com> * Merge upstream to fork (#25) * Add thousand-separator commas to TotalParams (#7915) * Add thousand-separator commas to TotalParams The number of parameters can be quite large, and it would help the reading of the summary printout to have the TotalParams column & values at the bottom have thousand-separator-commas in them. * Add thousand-separator commas to MultiLayerNetwork Corresponding change to MultiLayerNetwork Signed-off-by: Jxtps Jxtps <jxtps435@gmail.com> * Update contributing and issue/PR templates (#7934) Signed-off-by: AlexDBlack <blacka101@gmail.com> * Fix link to AdaDelta paper (#7942) Fix link to AdaDelta paper hosted on matthewzeiler.com Signed-off-by: Jxtps * Fixes, and ignores for known/logged failing issues (#7943) Signed-off-by: AlexDBlack <blacka101@gmail.com> * SameDiff + DL4J/SameDiff: Multiple fixes (#28) * #7919 HDF5 attribute buffer length fix Signed-off-by: AlexDBlack <blacka101@gmail.com> * #7909 Arbiter constructor exception ux improvements Signed-off-by: AlexDBlack <blacka101@gmail.com> * #7925 RNN output layer length checks Signed-off-by: AlexDBlack <blacka101@gmail.com> * #7939 Add listener for validating inputs are not incorrectly modified Signed-off-by: AlexDBlack <blacka101@gmail.com> * #7939 Integrate NonInplaceValidationListener into tests * #7844 DL4J SameDiff fixes for variable minibatch size * DL4J SameDiff fixes - ensure gradient for input placeholder is available Signed-off-by: AlexDBlack <blacka101@gmail.com> * Tweaks to ExternalErrorsFunction - use placeholders, make more robust * Another fix * More fixes * More SameDiff/DL4J fixes * Scope out scalar array creation in BaseScalarOp * Remove debug code Signed-off-by: AlexDBlack <blacka101@gmail.com> * [WIP] Final dev branch merge (#29) * SameDiff: convertDataType and gradient check util improvements (#12) * GradCheck util improvements * StopGradient constructor + test * SameDiff: Add datatype conversion * Javadoc and add DataType.isNumerical() * Small fix * Fix SameDiff TF import test cases intermediate naming (workaround for bad default) * TFGraphTestAllHelper: check intermediates in execution order * Add missing debug listener * [WIP] lstmBlock fix + other changes (#13) - fixes lstmBlock issue - changes NDArray method reshape(), permute(), transpose() by making them return instance instead of pointer - CheckNumerics op - fixes for ReduceBool IsInfOrNan & IsFinite * Small test fix * CheckNumerics op wrapper * Compatibility of deserialization (#18) Signed-off-by: Alexander Stoyakin <alexander.stoyakin@gmail.com> * SameDiff: add activation gradient checking support for debugging (#19) * SameDiff gradient checker: first pass on activation gradient checks * Fixes + tests for activation gradient checking * Javadoc * [WIP] Some nd4j data type corrections (#20) * Adjust data type * Set correct Data type. * Size of proper data type. * fix averaged cpu load (#22) * [WIP] Multiple dataset iterators (#27) * Splitting dataset into arbitrary number * Fixes * Multiple split of iterator * Test * Test * Some fixes * signature change * one more tweak Signed-off-by: raver119 <raver119@gmail.com> * one more test for sequential use of DataSetIteratorSplitter Signed-off-by: raver119 <raver119@gmail.com> * Fixes * Fixes * one more test for Alexander Signed-off-by: raver119 <raver119@gmail.com> * Some fixes * Some fixes * one more test for Alexander Signed-off-by: raver119 <raver119@gmail.com> * minor test fix Signed-off-by: raver119 <raver119@gmail.com> * Some fixes * Some fixes * couple of assertions tweaked Signed-off-by: raver119 <raver119@gmail.com> * MDS splitter test :/ Signed-off-by: raver119 <raver119@gmail.com> * Minor refactoring * Multi dataset * Some fixes * More tests * Small number of test fixes/improvements (failures on CI) (#31) Signed-off-by: AlexDBlack <blacka101@gmail.com> * [WIP] More CUDA stuff (#26) * initial commit Signed-off-by: raver119 <raver119@gmail.com> * LRN BP CUDA Signed-off-by: raver119 <raver119@gmail.com> * less memory Signed-off-by: raver119 <raver119@gmail.com> * Fixed bug with crop_and_resize op helper. * get rid of unnecessary index-calculation dunction Signed-off-by: Yurii <yurii@skymind.io> * Fixed sort with nth_element cuda-based helper. * Refactored nth_element. * Refactored nth_element op and tests. * Modified usage of dim array with sortTad routine. * Refactored main routine of helper for non_max_image_suppression op. * non_max_image_suppression op helper with cuda kernel implementation. Initial revision. * fix vol2col cuda kernel * meh Signed-off-by: raver119 <raver119@gmail.com> * topK concept Signed-off-by: raver119 <raver119@gmail.com> * unsorted topK with scanWitdh of 1 Signed-off-by: raver119 <raver119@gmail.com> * correct vol2col tests * sorted/unsorted topK Signed-off-by: raver119 <raver119@gmail.com> * implementation and fixing col2im/col2vol * Corrected usage flags with input/output with reverse op. * dup is const now Signed-off-by: raver119 <raver119@gmail.com> * percentile op Signed-off-by: raver119 <raver119@gmail.com> * group tests for mapool2d Signed-off-by: Yurii <yurii@skymind.io> * special test for george Signed-off-by: raver119 <raver119@gmail.com> * less threads for sortTad Signed-off-by: raver119 <raver119@gmail.com> * provide conv2d for cuda Signed-off-by: Yurii <yurii@skymind.io> * remove auther in sort tad kernel code Signed-off-by: Yurii <yurii@skymind.io> * provide depthwise_conv2d for cuda Signed-off-by: Yurii <yurii@skymind.io> * - max_pooling_with_argmax - null check for special use Signed-off-by: raver119 <raver119@gmail.com> * dts cuda Signed-off-by: raver119 <raver119@gmail.com> * provide sconv2d for cuda Signed-off-by: Yurii <yurii@skymind.io> * std cuda Signed-off-by: raver119 <raver119@gmail.com> * Refactored non_max_suppression op to conform TF implementation. * Improved suppression helper. * provide pooling3d for cuda Signed-off-by: Yurii <yurii@skymind.io> * minor lstm rearrangements Signed-off-by: raver119 <raver119@gmail.com> * more of minor lstm rearrangements Signed-off-by: raver119 <raver119@gmail.com> * (bi)dynamic_rnn Signed-off-by: raver119 <raver119@gmail.com> * templates init order Signed-off-by: raver119 <raver119@gmail.com> * Refactored non_max_suppression op. * Added cuda kernel for non_max_suppression. * CPU sort by key/value Signed-off-by: raver119 <raver119@gmail.com> * CPU sort TAD by key/value Signed-off-by: raver119 <raver119@gmail.com> * CPU sort TAD by key/value tests Signed-off-by: raver119 <raver119@gmail.com> * Eliminate compiler error with cuda implementation. * - repaired gradCheck in cuda - provide conv2d_bp for cuda Signed-off-by: Yurii <yurii@skymind.io> * missed signature Signed-off-by: raver119 <raver119@gmail.com> * provide depthwise_conv2d_bp for cuda Signed-off-by: Yurii <yurii@skymind.io> * Implementation of lup helper with cuda kernel. Initial commit. * further work on backprops for convolutions Signed-off-by: Yurii <yurii@skymind.io> * CUDA linear sort by key/val Signed-off-by: raver119 <raver119@gmail.com> * CUDA tad sort by key/val Signed-off-by: raver119 <raver119@gmail.com> * start providing of backprop for pooling2d/3d Signed-off-by: Yurii <yurii@skymind.io> * Added atomicAdd for bool datatype. * dynamic partition concept Signed-off-by: raver119 <raver119@gmail.com> * dynamic partition concept Signed-off-by: raver119 <raver119@gmail.com> * dynamic partition scalar CUDA Signed-off-by: raver119 <raver119@gmail.com> * important comment Signed-off-by: raver119 <raver119@gmail.com> * fix pooling2d/3d backprop helpers Signed-off-by: Yurii <yurii@skymind.io> * Added non-linear test with dynamic_partition. * Improved test for dynamic_partition. * dynamic_partition TAD concept Signed-off-by: raver119 <raver119@gmail.com> * - dynamic_partition TAD CUDA impl - dynamic_partition TAD CPU fix Signed-off-by: raver119 <raver119@gmail.com> * - rewrite cpu code for usampling2d/3d - write cuda code for usampling2d/3d Signed-off-by: Yurii <yurii@skymind.io> * dynamic_stitch CUDA vector case Signed-off-by: raver119 <raver119@gmail.com> * dynamic_stitch CUDA TAD case concept Signed-off-by: raver119 <raver119@gmail.com> * dynamic_stitch CUDA TAD case impl Signed-off-by: raver119 <raver119@gmail.com> * Added tests for dynamic_stitch 3D-4D cases. * minor tests tweaks Signed-off-by: raver119 <raver119@gmail.com> * Fixed type check for dynamic stitch. * min/max bp Signed-off-by: raver119 <raver119@gmail.com> * rewrite code for upsampling2d/3d cpu Signed-off-by: Yurii <yurii@skymind.io> * reduce min/max/norm_max bp Signed-off-by: raver119 <raver119@gmail.com> * lup implementation. Additional enhancements. * provide code for upsamling2d/3d backprop Signed-off-by: Yurii <yurii@skymind.io> * weightedCrossEntropyWithLogits Signed-off-by: raver119 <raver119@gmail.com> * Fixed template math atomicMul for 64bit ints. * Refactored dynamic_partition_bp op. * inverseBroadcast fix Signed-off-by: raver119 <raver119@gmail.com> * DynamicPartitionBP test datatype fixed. * - nd4j_atomicMul Windows fix - cpu/NDArrayLambda.hpp excluded from CUDA Signed-off-by: raver119 <raver119@gmail.com>
2019-06-27 17:37:04 +02:00
file(GLOB_RECURSE LOOPS_SOURCES_CUDA false ../include/loops/*.cu)
2019-06-06 14:21:15 +02:00
file(GLOB_RECURSE COMPILATION_UNITS false ../include/loops/cuda/compilation_units/*.cu.in
../include/ops/impl/compilation_units/*.cpp.in)
foreach(FL_ITEM ${COMPILATION_UNITS})
genCompilation(FL_ITEM)
endforeach()
cuDNN integration (#150) * initial commit Signed-off-by: raver119 <raver119@gmail.com> * one file Signed-off-by: raver119 <raver119@gmail.com> * few more includes Signed-off-by: raver119 <raver119@gmail.com> * m? Signed-off-by: raver119 <raver119@gmail.com> * const Signed-off-by: raver119 <raver119@gmail.com> * cudnn linkage in tests Signed-off-by: raver119 <raver119@gmail.com> * culibos Signed-off-by: raver119 <raver119@gmail.com> * static reminder Signed-off-by: raver119 <raver119@gmail.com> * platform engine tag Signed-off-by: raver119 <raver119@gmail.com> * HAVE_CUDNN moved to config.h.in Signed-off-by: raver119 <raver119@gmail.com> * include Signed-off-by: raver119 <raver119@gmail.com> * include Signed-off-by: raver119 <raver119@gmail.com> * skip cudnn handle creation if there's not cudnn Signed-off-by: raver119 <raver119@gmail.com> * meh Signed-off-by: raver119 <raver119@gmail.com> * target device in context Signed-off-by: raver119 <raver119@gmail.com> * platform engines Signed-off-by: raver119 <raver119@gmail.com> * platform engines Signed-off-by: raver119 <raver119@gmail.com> * allow multiple -h args Signed-off-by: raver119 <raver119@gmail.com> * allow multiple -h args Signed-off-by: raver119 <raver119@gmail.com> * move mkldnn out of CPU block Signed-off-by: raver119 <raver119@gmail.com> * link to mkldnn on cuda Signed-off-by: raver119 <raver119@gmail.com> * less prints Signed-off-by: raver119 <raver119@gmail.com> * minor tweaks Signed-off-by: raver119 <raver119@gmail.com> * next step Signed-off-by: raver119 <raver119@gmail.com> * conv2d NCHW draft Signed-off-by: raver119 <raver119@gmail.com> * conv2d biasAdd Signed-off-by: raver119 <raver119@gmail.com> * test for MKL/CUDNN combined use Signed-off-by: raver119 <raver119@gmail.com> * - provide additional code for conv2d ff based on cudnn api, not tested yet Signed-off-by: Yurii <iuriish@yahoo.com> * - further work on conv2d helper based on using cudnn api Signed-off-by: Yurii <iuriish@yahoo.com> * - fixing several cuda bugs which appeared after cudnn lib had been started to use Signed-off-by: Yurii <iuriish@yahoo.com> * - implementation of conv2d backprop op based on cudnn api Signed-off-by: Yurii <iuriish@yahoo.com> * - implementaion of conv3d and conv3d_bp ops based on cudnn api Signed-off-by: Yurii <iuriish@yahoo.com> * - bugs fixing in conv3d/conv3d_bp ops (cudnn in use) Signed-off-by: Yurii <iuriish@yahoo.com> * - implementation of depthwiseConv2d (ff/bp) op based on cudnn api Signed-off-by: Yurii <iuriish@yahoo.com> * - implementation of batchnorm ff op based on cudnn api Signed-off-by: Yurii <iuriish@yahoo.com> * - disable cudnn batchnorm temporary Signed-off-by: Yurii <iuriish@yahoo.com> * - add minor change in cmake Signed-off-by: Yurii <iuriish@yahoo.com> * engine for depthwise mkldnn Signed-off-by: raver119 <raver119@gmail.com> * couple of includes Signed-off-by: raver119 <raver119@gmail.com> * - provide permutation to cudnn batchnorm ff when format is NHWC Signed-off-by: Yurii <iuriish@yahoo.com> * lgamma fix Signed-off-by: raver119 <raver119@gmail.com> * - eliminate memory leak in two tests Signed-off-by: Yurii <iuriish@yahoo.com> Co-authored-by: Yurii Shyrma <iuriish@yahoo.com>
2020-01-20 19:32:46 +01:00
if (HAVE_CUDNN)
message("cuDNN included")
file(GLOB_RECURSE CUSTOMOPS_CUDNN_SOURCES false ../include/ops/declarable/platform/cudnn/*.cu)
endif()
add_library(samediff_obj OBJECT ${LOOPS_SOURCES_CUDA} ${LEGACY_SOURCES}
2019-06-06 14:21:15 +02:00
${CUSTOMOPS_HELPERS_SOURCES} ${HELPERS_SOURCES} ${EXEC_SOURCES}
${LOOPS_SOURCES} ${ARRAY_SOURCES} ${TYPES_SOURCES}
${MEMORY_SOURCES} ${GRAPH_SOURCES} ${CUSTOMOPS_SOURCES} ${INDEXING_SOURCES} ${EXCEPTIONS_SOURCES} ${OPS_SOURCES} ${PERF_SOURCES} ${CUSTOMOPS_CUDNN_SOURCES} ${CUSTOMOPS_MKLDNN_SOURCES}
${CUSTOMOPS_GENERIC_SOURCES}
)
2019-06-06 14:21:15 +02:00
cuDNN integration (#150) * initial commit Signed-off-by: raver119 <raver119@gmail.com> * one file Signed-off-by: raver119 <raver119@gmail.com> * few more includes Signed-off-by: raver119 <raver119@gmail.com> * m? Signed-off-by: raver119 <raver119@gmail.com> * const Signed-off-by: raver119 <raver119@gmail.com> * cudnn linkage in tests Signed-off-by: raver119 <raver119@gmail.com> * culibos Signed-off-by: raver119 <raver119@gmail.com> * static reminder Signed-off-by: raver119 <raver119@gmail.com> * platform engine tag Signed-off-by: raver119 <raver119@gmail.com> * HAVE_CUDNN moved to config.h.in Signed-off-by: raver119 <raver119@gmail.com> * include Signed-off-by: raver119 <raver119@gmail.com> * include Signed-off-by: raver119 <raver119@gmail.com> * skip cudnn handle creation if there's not cudnn Signed-off-by: raver119 <raver119@gmail.com> * meh Signed-off-by: raver119 <raver119@gmail.com> * target device in context Signed-off-by: raver119 <raver119@gmail.com> * platform engines Signed-off-by: raver119 <raver119@gmail.com> * platform engines Signed-off-by: raver119 <raver119@gmail.com> * allow multiple -h args Signed-off-by: raver119 <raver119@gmail.com> * allow multiple -h args Signed-off-by: raver119 <raver119@gmail.com> * move mkldnn out of CPU block Signed-off-by: raver119 <raver119@gmail.com> * link to mkldnn on cuda Signed-off-by: raver119 <raver119@gmail.com> * less prints Signed-off-by: raver119 <raver119@gmail.com> * minor tweaks Signed-off-by: raver119 <raver119@gmail.com> * next step Signed-off-by: raver119 <raver119@gmail.com> * conv2d NCHW draft Signed-off-by: raver119 <raver119@gmail.com> * conv2d biasAdd Signed-off-by: raver119 <raver119@gmail.com> * test for MKL/CUDNN combined use Signed-off-by: raver119 <raver119@gmail.com> * - provide additional code for conv2d ff based on cudnn api, not tested yet Signed-off-by: Yurii <iuriish@yahoo.com> * - further work on conv2d helper based on using cudnn api Signed-off-by: Yurii <iuriish@yahoo.com> * - fixing several cuda bugs which appeared after cudnn lib had been started to use Signed-off-by: Yurii <iuriish@yahoo.com> * - implementation of conv2d backprop op based on cudnn api Signed-off-by: Yurii <iuriish@yahoo.com> * - implementaion of conv3d and conv3d_bp ops based on cudnn api Signed-off-by: Yurii <iuriish@yahoo.com> * - bugs fixing in conv3d/conv3d_bp ops (cudnn in use) Signed-off-by: Yurii <iuriish@yahoo.com> * - implementation of depthwiseConv2d (ff/bp) op based on cudnn api Signed-off-by: Yurii <iuriish@yahoo.com> * - implementation of batchnorm ff op based on cudnn api Signed-off-by: Yurii <iuriish@yahoo.com> * - disable cudnn batchnorm temporary Signed-off-by: Yurii <iuriish@yahoo.com> * - add minor change in cmake Signed-off-by: Yurii <iuriish@yahoo.com> * engine for depthwise mkldnn Signed-off-by: raver119 <raver119@gmail.com> * couple of includes Signed-off-by: raver119 <raver119@gmail.com> * - provide permutation to cudnn batchnorm ff when format is NHWC Signed-off-by: Yurii <iuriish@yahoo.com> * lgamma fix Signed-off-by: raver119 <raver119@gmail.com> * - eliminate memory leak in two tests Signed-off-by: Yurii <iuriish@yahoo.com> Co-authored-by: Yurii Shyrma <iuriish@yahoo.com>
2020-01-20 19:32:46 +01:00
if (WIN32)
message("MSVC runtime for library: ${MSVC_RT_LIB}")
endif()
# build shared library by default or when it's explicitly requested
if(NOT SD_STATIC_LIB OR SD_SHARED_LIB)
add_library(${SD_LIBRARY_NAME} SHARED $<TARGET_OBJECTS:samediff_obj>)
endif()
if (SD_STATIC_LIB AND SD_SHARED_LIB)
# if both static and shared library are going to be built - static library will have special suffix
add_library(${SD_LIBRARY_NAME}static STATIC $<TARGET_OBJECTS:samediff_obj>)
set_property(TARGET ${SD_LIBRARY_NAME}static PROPERTY MSVC_RUNTIME_LIBRARY "${MSVC_RT_LIB}$<$<CONFIG:Debug>:Debug>")
install(TARGETS ${SD_LIBRARY_NAME}static DESTINATION .)
elseif(SD_STATIC_LIB)
# if we only build static library - use this name
add_library(${SD_LIBRARY_NAME} STATIC $<TARGET_OBJECTS:samediff_obj>)
set_property(TARGET ${SD_LIBRARY_NAME} PROPERTY MSVC_RUNTIME_LIBRARY "${MSVC_RT_LIB}$<$<CONFIG:Debug>:Debug>")
install(TARGETS ${SD_LIBRARY_NAME} DESTINATION .)
endif()
# on windows we want to make sure we use MT or MD, but since we use it in one lib, we must use it everywhere to avoid conflicts
set_property(TARGET samediff_obj PROPERTY MSVC_RUNTIME_LIBRARY "${MSVC_RT_LIB}$<$<CONFIG:Debug>:Debug>")
set_property(TARGET ${SD_LIBRARY_NAME} PROPERTY MSVC_RUNTIME_LIBRARY "${MSVC_RT_LIB}$<$<CONFIG:Debug>:Debug>")
2019-06-06 14:21:15 +02:00
if(WIN32)
message("CUDA on Windows: enabling /EHsc")
SET(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /EHsc /bigobj /std:c++14")
2019-06-06 14:21:15 +02:00
endif()
target_link_libraries(${SD_LIBRARY_NAME} ${CUDA_LIBRARIES} ${CUDA_CUBLAS_LIBRARIES} ${CUDA_cusolver_LIBRARY} ${CUDNN} ${MKLDNN})
2019-06-06 14:21:15 +02:00
set(CMAKE_LIBRARY_OUTPUT_DIRECTORY ${PROJECT_BINARY_DIR}/cuda)
install(TARGETS ${SD_LIBRARY_NAME} DESTINATION .)
2019-06-06 14:21:15 +02:00
endif(CUDA_FOUND)
elseif(SD_CPU)
2019-06-06 14:21:15 +02:00
if ("${SD_EXPERIMENTAL}" STREQUAL "yes")
2019-06-06 14:21:15 +02:00
message("Experimental mode ENABLED")
set (CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -D__ND4J_EXPERIMENTAL__=true")
set (CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -D__ND4J_EXPERIMENTAL__=true")
endif()
file(GLOB_RECURSE PERF_SOURCES false ../include/performance/*.cpp ../include/performance/*.h)
2019-06-06 14:21:15 +02:00
file(GLOB_RECURSE EXCEPTIONS_SOURCES false ../include/exceptions/*.cpp ../include/exceptions/*.h)
file(GLOB_RECURSE EXEC_SOURCES false ../include/execution/*.cpp ../include/execution/*.h)
file(GLOB_RECURSE TYPES_SOURCES false ../include/types/*.cpp ../include/types/*.h)
file(GLOB_RECURSE ARRAY_SOURCES false ../include/array/*.cpp ../include/array/*.h)
file(GLOB_RECURSE MEMORY_SOURCES false ../include/memory/*.cpp ../include/memory/*.h)
file(GLOB_RECURSE GRAPH_SOURCES false ../include/graph/*.cpp ../include/graph/*.h)
file(GLOB_RECURSE CUSTOMOPS_SOURCES false ../include/ops/declarable/generic/*.cpp)
Platform helpers (#8216) * platform helpers draft Signed-off-by: raver119 <raver119@gmail.com> * typo Signed-off-by: raver119 <raver119@gmail.com> * disable platform cmake Signed-off-by: raver119 <raver119@gmail.com> * another draft Signed-off-by: raver119 <raver119@gmail.com> * mkldnn convolution refactored Signed-off-by: raver119 <raver119@gmail.com> * minor tweaks Signed-off-by: raver119 <raver119@gmail.com> * one more safety check Signed-off-by: raver119 <raver119@gmail.com> * prototype works Signed-off-by: raver119 <raver119@gmail.com> * meh Signed-off-by: raver119 <raver119@gmail.com> * force static library mode for mkldnn Signed-off-by: raver119 <raver119@gmail.com> * - ismax fix - experimental arg fix - don't enforce openblas on Apple hardware Signed-off-by: raver119 <raver119@gmail.com> * bunch of small fixes Signed-off-by: raver119@gmail.com <raver119@gmail.com> * declare concurrent Signed-off-by: raver119@gmail.com <raver119@gmail.com> * - MKLDNN version upgrade to 1.0.2 - avgpool2d/maxpool2d APIs update Signed-off-by: raver119 <raver119@gmail.com> * - avgpool2d_bp/maxpool2d_bp APIs update Signed-off-by: raver119 <raver119@gmail.com> * - conv2d/batchnorm APIs update Signed-off-by: raver119 <raver119@gmail.com> * - lrn/conv2d_bp/conv3d/conv3d_bp APIs update Signed-off-by: raver119 <raver119@gmail.com> * all ops converted to MKLDNN 1.x Signed-off-by: raver119 <raver119@gmail.com> * bunch of tweaks Signed-off-by: raver119 <raver119@gmail.com> * namespace for platform helpers Signed-off-by: raver119 <raver119@gmail.com> * make sure platform helpers aren't opimized out Signed-off-by: raver119 <raver119@gmail.com> * build cpu_features on x86 systems Signed-off-by: raver119 <raver119@gmail.com> * build cpu_features on x86 systems Signed-off-by: raver119 <raver119@gmail.com> * more of cpu_features Signed-off-by: raver119 <raver119@gmail.com> * - mkldnn removed from java - cpu_features checks in CpuNDArrayFactory Signed-off-by: raver119 <raver119@gmail.com> * F16C definition renamed Signed-off-by: raver119 <raver119@gmail.com> * some mkldnn rearrangements Signed-off-by: raver119 <raver119@gmail.com> * check supported instructions before doing anything Signed-off-by: raver119 <raver119@gmail.com> * typo Signed-off-by: raver119 <raver119@gmail.com> * missied impl Signed-off-by: raver119 <raver119@gmail.com> * BUILD_PIC option Signed-off-by: raver119 <raver119@gmail.com> * conv2d fix Signed-off-by: raver119 <raver119@gmail.com> * avgpool3d fix Signed-off-by: raver119 <raver119@gmail.com> * avgpool3d_bp fix Signed-off-by: raver119 <raver119@gmail.com> * avgpool2d_bp leak fix Signed-off-by: raver119 <raver119@gmail.com> * avgpool3d_bp leak fix Signed-off-by: raver119 <raver119@gmail.com> * maxpool bp leaks fixed Signed-off-by: raver119 <raver119@gmail.com> * printf removed Signed-off-by: raver119 <raver119@gmail.com> * batchnorm fix Signed-off-by: raver119 <raver119@gmail.com> * AVX warning/error polishing Signed-off-by: AlexDBlack <blacka101@gmail.com> * Fix Signed-off-by: AlexDBlack <blacka101@gmail.com> * More polish Signed-off-by: AlexDBlack <blacka101@gmail.com> * Polish Signed-off-by: AlexDBlack <blacka101@gmail.com> * remove previous MKL-DNN support layer Signed-off-by: raver119 <raver119@gmail.com> * avx2 tweak Signed-off-by: raver119 <raver119@gmail.com> * allow static for apple Signed-off-by: raver119@gmail.com <raver119@gmail.com> * exclude mkldnn in one more place Signed-off-by: raver119 <raver119@gmail.com> * exclude mkldnn in one more place Signed-off-by: raver119 <raver119@gmail.com> * restore OPENBLAS_PATH use Signed-off-by: raver119 <raver119@gmail.com> * add runtime check for avx/avx2 support Signed-off-by: raver119 <raver119@gmail.com> * convolution_auto Signed-off-by: raver119 <raver119@gmail.com> * Add logic for helper argument * minor test fix Signed-off-by: raver119 <raver119@gmail.com> * few tweaks Signed-off-by: raver119 <raver119@gmail.com> * few tweaks Signed-off-by: raver119 <raver119@gmail.com> * skip OpTracker props for non-x86 builds Signed-off-by: raver119 <raver119@gmail.com> * linux arm isn't x86 :) Signed-off-by: raver119 <raver119@gmail.com> * avx-512 Signed-off-by: raver119 <raver119@gmail.com> * CUDA presets fix Signed-off-by: raver119 <raver119@gmail.com> * BUILD_PIC Signed-off-by: raver119 <raver119@gmail.com> * prefetchw for avx2 Signed-off-by: raver119 <raver119@gmail.com> * BUILD_PIC again Signed-off-by: raver119 <raver119@gmail.com>
2019-09-11 20:50:28 +02:00
file(GLOB_RECURSE CUSTOMOPS_GENERIC_SOURCES false ../include/ops/declarable/helpers/cpu/*.cpp ../include/ops/declarable/helpers/impl/*.cpp)
2019-06-06 14:21:15 +02:00
file(GLOB_RECURSE OPS_SOURCES false ../include/ops/impl/*.cpp ../include/ops/declarable/impl/*.cpp ../include/ops/*.h)
file(GLOB_RECURSE INDEXING_SOURCES false ../include/indexing/*.cpp ../include/indexing/*.h)
file(GLOB_RECURSE HELPERS_SOURCES false ../include/helpers/*.cpp ../include/helpers/*.h)
file(GLOB_RECURSE LEGACY_SOURCES false ../include/legacy/impl/*.cpp ../include/legacy/cpu/*.cpp ../include/legacy/*.h)
2019-06-06 14:21:15 +02:00
file(GLOB_RECURSE LOOPS_SOURCES false ../include/loops/*.cpp ../include/loops/*.h)
file(GLOB_RECURSE COMPILATION_UNITS false ../include/ops/declarable/helpers/cpu/compilation_units/*.cpp.in
../include/loops/cpu/compilation_units/*.cpp.in ../include/helpers/cpu/loops/*.cpp.in
../include/ops/impl/compilation_units/*.cpp.in)
foreach(FL_ITEM ${COMPILATION_UNITS})
genCompilation(FL_ITEM)
endforeach()
if (SD_X86_BUILD)
# we disable platform optimizations for certains files for linux/macos
Platform helpers (#8216) * platform helpers draft Signed-off-by: raver119 <raver119@gmail.com> * typo Signed-off-by: raver119 <raver119@gmail.com> * disable platform cmake Signed-off-by: raver119 <raver119@gmail.com> * another draft Signed-off-by: raver119 <raver119@gmail.com> * mkldnn convolution refactored Signed-off-by: raver119 <raver119@gmail.com> * minor tweaks Signed-off-by: raver119 <raver119@gmail.com> * one more safety check Signed-off-by: raver119 <raver119@gmail.com> * prototype works Signed-off-by: raver119 <raver119@gmail.com> * meh Signed-off-by: raver119 <raver119@gmail.com> * force static library mode for mkldnn Signed-off-by: raver119 <raver119@gmail.com> * - ismax fix - experimental arg fix - don't enforce openblas on Apple hardware Signed-off-by: raver119 <raver119@gmail.com> * bunch of small fixes Signed-off-by: raver119@gmail.com <raver119@gmail.com> * declare concurrent Signed-off-by: raver119@gmail.com <raver119@gmail.com> * - MKLDNN version upgrade to 1.0.2 - avgpool2d/maxpool2d APIs update Signed-off-by: raver119 <raver119@gmail.com> * - avgpool2d_bp/maxpool2d_bp APIs update Signed-off-by: raver119 <raver119@gmail.com> * - conv2d/batchnorm APIs update Signed-off-by: raver119 <raver119@gmail.com> * - lrn/conv2d_bp/conv3d/conv3d_bp APIs update Signed-off-by: raver119 <raver119@gmail.com> * all ops converted to MKLDNN 1.x Signed-off-by: raver119 <raver119@gmail.com> * bunch of tweaks Signed-off-by: raver119 <raver119@gmail.com> * namespace for platform helpers Signed-off-by: raver119 <raver119@gmail.com> * make sure platform helpers aren't opimized out Signed-off-by: raver119 <raver119@gmail.com> * build cpu_features on x86 systems Signed-off-by: raver119 <raver119@gmail.com> * build cpu_features on x86 systems Signed-off-by: raver119 <raver119@gmail.com> * more of cpu_features Signed-off-by: raver119 <raver119@gmail.com> * - mkldnn removed from java - cpu_features checks in CpuNDArrayFactory Signed-off-by: raver119 <raver119@gmail.com> * F16C definition renamed Signed-off-by: raver119 <raver119@gmail.com> * some mkldnn rearrangements Signed-off-by: raver119 <raver119@gmail.com> * check supported instructions before doing anything Signed-off-by: raver119 <raver119@gmail.com> * typo Signed-off-by: raver119 <raver119@gmail.com> * missied impl Signed-off-by: raver119 <raver119@gmail.com> * BUILD_PIC option Signed-off-by: raver119 <raver119@gmail.com> * conv2d fix Signed-off-by: raver119 <raver119@gmail.com> * avgpool3d fix Signed-off-by: raver119 <raver119@gmail.com> * avgpool3d_bp fix Signed-off-by: raver119 <raver119@gmail.com> * avgpool2d_bp leak fix Signed-off-by: raver119 <raver119@gmail.com> * avgpool3d_bp leak fix Signed-off-by: raver119 <raver119@gmail.com> * maxpool bp leaks fixed Signed-off-by: raver119 <raver119@gmail.com> * printf removed Signed-off-by: raver119 <raver119@gmail.com> * batchnorm fix Signed-off-by: raver119 <raver119@gmail.com> * AVX warning/error polishing Signed-off-by: AlexDBlack <blacka101@gmail.com> * Fix Signed-off-by: AlexDBlack <blacka101@gmail.com> * More polish Signed-off-by: AlexDBlack <blacka101@gmail.com> * Polish Signed-off-by: AlexDBlack <blacka101@gmail.com> * remove previous MKL-DNN support layer Signed-off-by: raver119 <raver119@gmail.com> * avx2 tweak Signed-off-by: raver119 <raver119@gmail.com> * allow static for apple Signed-off-by: raver119@gmail.com <raver119@gmail.com> * exclude mkldnn in one more place Signed-off-by: raver119 <raver119@gmail.com> * exclude mkldnn in one more place Signed-off-by: raver119 <raver119@gmail.com> * restore OPENBLAS_PATH use Signed-off-by: raver119 <raver119@gmail.com> * add runtime check for avx/avx2 support Signed-off-by: raver119 <raver119@gmail.com> * convolution_auto Signed-off-by: raver119 <raver119@gmail.com> * Add logic for helper argument * minor test fix Signed-off-by: raver119 <raver119@gmail.com> * few tweaks Signed-off-by: raver119 <raver119@gmail.com> * few tweaks Signed-off-by: raver119 <raver119@gmail.com> * skip OpTracker props for non-x86 builds Signed-off-by: raver119 <raver119@gmail.com> * linux arm isn't x86 :) Signed-off-by: raver119 <raver119@gmail.com> * avx-512 Signed-off-by: raver119 <raver119@gmail.com> * CUDA presets fix Signed-off-by: raver119 <raver119@gmail.com> * BUILD_PIC Signed-off-by: raver119 <raver119@gmail.com> * prefetchw for avx2 Signed-off-by: raver119 <raver119@gmail.com> * BUILD_PIC again Signed-off-by: raver119 <raver119@gmail.com>
2019-09-11 20:50:28 +02:00
set_source_files_properties(cpu/NativeOps.cpp PROPERTIES COMPILE_FLAGS "-march=x86-64 -mtune=generic")
set_source_files_properties(../include/helpers/impl/OpTracker.cpp PROPERTIES COMPILE_FLAGS "-march=x86-64 -mtune=generic")
endif()
if(SD_CHECK_VECTORIZATION)
set(VECT_FILES cpu/NativeOps.cpp ${OPS_SOURCES} ${HELPERS_SOURCES} ${CUSTOMOPS_GENERIC_SOURCES} ${LOOPS_SOURCES})
if("${CMAKE_CXX_COMPILER_ID}" STREQUAL "GNU")
if (CMAKE_COMPILER_IS_GNUCC AND CMAKE_CXX_COMPILER_VERSION VERSION_GREATER 9.0)
set(CHECK_VECT_FLAGS "-ftree-vectorize -fsave-optimization-record")
#to process fsave-optimization-record we will need our cython version code
message("Build Auto vectorization helpers")
execute_process(COMMAND "python3" "${CMAKE_CURRENT_SOURCE_DIR}/../auto_vectorization/cython_setup.py" "build_ext" "--inplace" WORKING_DIRECTORY "${CMAKE_CURRENT_SOURCE_DIR}/../auto_vectorization/" RESULT_VARIABLE ret)
message("build='${ret}'")
#remove fail cases that gcc fails produce sometimes
file(GLOB_RECURSE FAILURE_CASES false ../include/loops/cpu/compilation_units/reduce3*.cpp)
#message("*****${FAILURE_CASES}")
foreach(FL_ITEM ${FAILURE_CASES})
message("Removing failure cases ${FL_ITEM}")
list(REMOVE_ITEM VECT_FILES ${FL_ITEM})
endforeach()
else()
set(CHECK_VECT_FLAGS "-ftree-vectorize -fopt-info-vec-optimized-missed")
endif()
message("CHECK VECTORIZATION ${CHECK_VECT_FLAGS}")
set_source_files_properties( ${VECT_FILES} PROPERTIES COMPILE_FLAGS "${CHECK_VECT_FLAGS}" )
endif()
endif()
2019-06-06 14:21:15 +02:00
message("CPU BLAS")
add_definitions(-D__CPUBLAS__=true)
add_library(samediff_obj OBJECT ${LEGACY_SOURCES}
${LOOPS_SOURCES} ${HELPERS_SOURCES} ${EXEC_SOURCES} ${ARRAY_SOURCES} ${TYPES_SOURCES}
cuDNN integration (#150) * initial commit Signed-off-by: raver119 <raver119@gmail.com> * one file Signed-off-by: raver119 <raver119@gmail.com> * few more includes Signed-off-by: raver119 <raver119@gmail.com> * m? Signed-off-by: raver119 <raver119@gmail.com> * const Signed-off-by: raver119 <raver119@gmail.com> * cudnn linkage in tests Signed-off-by: raver119 <raver119@gmail.com> * culibos Signed-off-by: raver119 <raver119@gmail.com> * static reminder Signed-off-by: raver119 <raver119@gmail.com> * platform engine tag Signed-off-by: raver119 <raver119@gmail.com> * HAVE_CUDNN moved to config.h.in Signed-off-by: raver119 <raver119@gmail.com> * include Signed-off-by: raver119 <raver119@gmail.com> * include Signed-off-by: raver119 <raver119@gmail.com> * skip cudnn handle creation if there's not cudnn Signed-off-by: raver119 <raver119@gmail.com> * meh Signed-off-by: raver119 <raver119@gmail.com> * target device in context Signed-off-by: raver119 <raver119@gmail.com> * platform engines Signed-off-by: raver119 <raver119@gmail.com> * platform engines Signed-off-by: raver119 <raver119@gmail.com> * allow multiple -h args Signed-off-by: raver119 <raver119@gmail.com> * allow multiple -h args Signed-off-by: raver119 <raver119@gmail.com> * move mkldnn out of CPU block Signed-off-by: raver119 <raver119@gmail.com> * link to mkldnn on cuda Signed-off-by: raver119 <raver119@gmail.com> * less prints Signed-off-by: raver119 <raver119@gmail.com> * minor tweaks Signed-off-by: raver119 <raver119@gmail.com> * next step Signed-off-by: raver119 <raver119@gmail.com> * conv2d NCHW draft Signed-off-by: raver119 <raver119@gmail.com> * conv2d biasAdd Signed-off-by: raver119 <raver119@gmail.com> * test for MKL/CUDNN combined use Signed-off-by: raver119 <raver119@gmail.com> * - provide additional code for conv2d ff based on cudnn api, not tested yet Signed-off-by: Yurii <iuriish@yahoo.com> * - further work on conv2d helper based on using cudnn api Signed-off-by: Yurii <iuriish@yahoo.com> * - fixing several cuda bugs which appeared after cudnn lib had been started to use Signed-off-by: Yurii <iuriish@yahoo.com> * - implementation of conv2d backprop op based on cudnn api Signed-off-by: Yurii <iuriish@yahoo.com> * - implementaion of conv3d and conv3d_bp ops based on cudnn api Signed-off-by: Yurii <iuriish@yahoo.com> * - bugs fixing in conv3d/conv3d_bp ops (cudnn in use) Signed-off-by: Yurii <iuriish@yahoo.com> * - implementation of depthwiseConv2d (ff/bp) op based on cudnn api Signed-off-by: Yurii <iuriish@yahoo.com> * - implementation of batchnorm ff op based on cudnn api Signed-off-by: Yurii <iuriish@yahoo.com> * - disable cudnn batchnorm temporary Signed-off-by: Yurii <iuriish@yahoo.com> * - add minor change in cmake Signed-off-by: Yurii <iuriish@yahoo.com> * engine for depthwise mkldnn Signed-off-by: raver119 <raver119@gmail.com> * couple of includes Signed-off-by: raver119 <raver119@gmail.com> * - provide permutation to cudnn batchnorm ff when format is NHWC Signed-off-by: Yurii <iuriish@yahoo.com> * lgamma fix Signed-off-by: raver119 <raver119@gmail.com> * - eliminate memory leak in two tests Signed-off-by: Yurii <iuriish@yahoo.com> Co-authored-by: Yurii Shyrma <iuriish@yahoo.com>
2020-01-20 19:32:46 +01:00
${MEMORY_SOURCES} ${GRAPH_SOURCES} ${CUSTOMOPS_SOURCES} ${EXCEPTIONS_SOURCES} ${INDEXING_SOURCES} ${CUSTOMOPS_MKLDNN_SOURCES} ${CUSTOMOPS_GENERIC_SOURCES}
${OPS_SOURCES} ${PERF_SOURCES})
2019-06-06 14:21:15 +02:00
if(IOS)
add_library(${SD_LIBRARY_NAME} STATIC $<TARGET_OBJECTS:samediff_obj>)
2019-06-06 14:21:15 +02:00
else()
# build shared library by default or when it's explicitly requested
if(NOT SD_STATIC_LIB OR SD_SHARED_LIB)
add_library(${SD_LIBRARY_NAME} SHARED $<TARGET_OBJECTS:samediff_obj>)
endif()
if (SD_STATIC_LIB AND SD_SHARED_LIB)
# if both static and shared library are going to be built - static library will have special suffix
add_library(${SD_LIBRARY_NAME}static STATIC $<TARGET_OBJECTS:samediff_obj>)
set_property(TARGET ${SD_LIBRARY_NAME}static PROPERTY MSVC_RUNTIME_LIBRARY "${MSVC_RT_LIB}$<$<CONFIG:Debug>:Debug>")
install(TARGETS ${SD_LIBRARY_NAME}static DESTINATION .)
elseif(SD_STATIC_LIB)
# if we only build static library - use this name
add_library(${SD_LIBRARY_NAME} STATIC $<TARGET_OBJECTS:samediff_obj>)
set_property(TARGET ${SD_LIBRARY_NAME} PROPERTY MSVC_RUNTIME_LIBRARY "${MSVC_RT_LIB}$<$<CONFIG:Debug>:Debug>")
install(TARGETS ${SD_LIBRARY_NAME} DESTINATION .)
endif()
2019-06-06 14:21:15 +02:00
endif()
Platform helpers (#8216) * platform helpers draft Signed-off-by: raver119 <raver119@gmail.com> * typo Signed-off-by: raver119 <raver119@gmail.com> * disable platform cmake Signed-off-by: raver119 <raver119@gmail.com> * another draft Signed-off-by: raver119 <raver119@gmail.com> * mkldnn convolution refactored Signed-off-by: raver119 <raver119@gmail.com> * minor tweaks Signed-off-by: raver119 <raver119@gmail.com> * one more safety check Signed-off-by: raver119 <raver119@gmail.com> * prototype works Signed-off-by: raver119 <raver119@gmail.com> * meh Signed-off-by: raver119 <raver119@gmail.com> * force static library mode for mkldnn Signed-off-by: raver119 <raver119@gmail.com> * - ismax fix - experimental arg fix - don't enforce openblas on Apple hardware Signed-off-by: raver119 <raver119@gmail.com> * bunch of small fixes Signed-off-by: raver119@gmail.com <raver119@gmail.com> * declare concurrent Signed-off-by: raver119@gmail.com <raver119@gmail.com> * - MKLDNN version upgrade to 1.0.2 - avgpool2d/maxpool2d APIs update Signed-off-by: raver119 <raver119@gmail.com> * - avgpool2d_bp/maxpool2d_bp APIs update Signed-off-by: raver119 <raver119@gmail.com> * - conv2d/batchnorm APIs update Signed-off-by: raver119 <raver119@gmail.com> * - lrn/conv2d_bp/conv3d/conv3d_bp APIs update Signed-off-by: raver119 <raver119@gmail.com> * all ops converted to MKLDNN 1.x Signed-off-by: raver119 <raver119@gmail.com> * bunch of tweaks Signed-off-by: raver119 <raver119@gmail.com> * namespace for platform helpers Signed-off-by: raver119 <raver119@gmail.com> * make sure platform helpers aren't opimized out Signed-off-by: raver119 <raver119@gmail.com> * build cpu_features on x86 systems Signed-off-by: raver119 <raver119@gmail.com> * build cpu_features on x86 systems Signed-off-by: raver119 <raver119@gmail.com> * more of cpu_features Signed-off-by: raver119 <raver119@gmail.com> * - mkldnn removed from java - cpu_features checks in CpuNDArrayFactory Signed-off-by: raver119 <raver119@gmail.com> * F16C definition renamed Signed-off-by: raver119 <raver119@gmail.com> * some mkldnn rearrangements Signed-off-by: raver119 <raver119@gmail.com> * check supported instructions before doing anything Signed-off-by: raver119 <raver119@gmail.com> * typo Signed-off-by: raver119 <raver119@gmail.com> * missied impl Signed-off-by: raver119 <raver119@gmail.com> * BUILD_PIC option Signed-off-by: raver119 <raver119@gmail.com> * conv2d fix Signed-off-by: raver119 <raver119@gmail.com> * avgpool3d fix Signed-off-by: raver119 <raver119@gmail.com> * avgpool3d_bp fix Signed-off-by: raver119 <raver119@gmail.com> * avgpool2d_bp leak fix Signed-off-by: raver119 <raver119@gmail.com> * avgpool3d_bp leak fix Signed-off-by: raver119 <raver119@gmail.com> * maxpool bp leaks fixed Signed-off-by: raver119 <raver119@gmail.com> * printf removed Signed-off-by: raver119 <raver119@gmail.com> * batchnorm fix Signed-off-by: raver119 <raver119@gmail.com> * AVX warning/error polishing Signed-off-by: AlexDBlack <blacka101@gmail.com> * Fix Signed-off-by: AlexDBlack <blacka101@gmail.com> * More polish Signed-off-by: AlexDBlack <blacka101@gmail.com> * Polish Signed-off-by: AlexDBlack <blacka101@gmail.com> * remove previous MKL-DNN support layer Signed-off-by: raver119 <raver119@gmail.com> * avx2 tweak Signed-off-by: raver119 <raver119@gmail.com> * allow static for apple Signed-off-by: raver119@gmail.com <raver119@gmail.com> * exclude mkldnn in one more place Signed-off-by: raver119 <raver119@gmail.com> * exclude mkldnn in one more place Signed-off-by: raver119 <raver119@gmail.com> * restore OPENBLAS_PATH use Signed-off-by: raver119 <raver119@gmail.com> * add runtime check for avx/avx2 support Signed-off-by: raver119 <raver119@gmail.com> * convolution_auto Signed-off-by: raver119 <raver119@gmail.com> * Add logic for helper argument * minor test fix Signed-off-by: raver119 <raver119@gmail.com> * few tweaks Signed-off-by: raver119 <raver119@gmail.com> * few tweaks Signed-off-by: raver119 <raver119@gmail.com> * skip OpTracker props for non-x86 builds Signed-off-by: raver119 <raver119@gmail.com> * linux arm isn't x86 :) Signed-off-by: raver119 <raver119@gmail.com> * avx-512 Signed-off-by: raver119 <raver119@gmail.com> * CUDA presets fix Signed-off-by: raver119 <raver119@gmail.com> * BUILD_PIC Signed-off-by: raver119 <raver119@gmail.com> * prefetchw for avx2 Signed-off-by: raver119 <raver119@gmail.com> * BUILD_PIC again Signed-off-by: raver119 <raver119@gmail.com>
2019-09-11 20:50:28 +02:00
# we're including {MKLDNN} here in case of building from sources. in future that'll replace {MKLDNN_LIBRARIES}. same applies to BLAS
if (NOT BLAS_LIBRARIES)
set(BLAS_LIBRARIES "")
endif()
target_link_libraries(${SD_LIBRARY_NAME} ${MKLDNN} ${MKLDNN_LIBRARIES} ${OPENBLAS_LIBRARIES} ${BLAS_LIBRARIES} ${CPU_FEATURES})
2019-06-06 14:21:15 +02:00
if ("${SD_ALL_OPS}" AND "${SD_BUILD_MINIFIER}")
2019-06-06 14:21:15 +02:00
message(STATUS "Building minifier...")
add_executable(minifier ../minifier/minifier.cpp ../minifier/graphopt.cpp)
target_link_libraries(minifier samediff_obj ${MKLDNN_LIBRARIES} ${OPENBLAS_LIBRARIES} ${MKLDNN} ${BLAS_LIBRARIES} ${CPU_FEATURES})
2019-06-06 14:21:15 +02:00
endif()
if ("${CMAKE_CXX_COMPILER_ID}" STREQUAL "GNU" AND "${CMAKE_CXX_COMPILER_VERSION}" VERSION_LESS 4.9)
message(FATAL_ERROR "You need at least GCC 4.9")
endif()
# OpenMP works well pretty much only with GCC
if("${CMAKE_CXX_COMPILER_ID}" STREQUAL "GNU")
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}")
endif()
endif()
install(TARGETS ${SD_LIBRARY_NAME} DESTINATION .)
2019-06-06 14:21:15 +02:00
set(CMAKE_LIBRARY_OUTPUT_DIRECTORY ${PROJECT_BINARY_DIR}/cpu)
endif()