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(WIN32)
|
|
|
|
|
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 ("${LIBND4J_ALL_OPS}")
|
|
|
|
|
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -DLIBND4J_ALL_OPS=true")
|
|
|
|
|
else()
|
|
|
|
|
message("_OPS: ${LIBND4J_OPS_LIST}")
|
|
|
|
|
foreach(OP "${LIBND4J_OPS_LIST}")
|
|
|
|
|
message(STATUS "${OP}")
|
|
|
|
|
endforeach()
|
|
|
|
|
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${LIBND4J_OPS_LIST}")
|
|
|
|
|
endif()
|
|
|
|
|
|
|
|
|
|
IF(${ARCH} MATCHES "arm*")
|
|
|
|
|
set(ARCH_TUNE "-march=${ARCH}")
|
|
|
|
|
ELSEIF(${ARCH} MATCHES "power*")
|
|
|
|
|
set(ARCH_TUNE "-mcpu=${ARCH} -mtune=${ARCH} -D__POWER")
|
|
|
|
|
ELSEIF(${EXTENSION} MATCHES "avx2")
|
|
|
|
|
set(ARCH_TUNE "-march=${ARCH} -mtune=${ARCH} -msse4.1 -msse4.2 -mavx -mavx2 -mfma -mf16c -D__F16C__=true")
|
|
|
|
|
ELSE()
|
|
|
|
|
if ("${ARCH}" STREQUAL "x86-64")
|
|
|
|
|
set(ARCH_TYPE "generic")
|
|
|
|
|
else()
|
|
|
|
|
set(ARCH_TYPE "${ARCH}")
|
|
|
|
|
endif()
|
|
|
|
|
|
|
|
|
|
set(ARCH_TUNE "-march=${ARCH} -mtune=${ARCH_TYPE}")
|
|
|
|
|
ENDIF()
|
|
|
|
|
|
|
|
|
|
if ("${CMAKE_CXX_COMPILER_ID}" STREQUAL "Clang")
|
|
|
|
|
# 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 "${CMAKE_CXX_FLAGS} /EHsc")
|
|
|
|
|
elseif ("${CMAKE_CXX_COMPILER_ID}" STREQUAL "GNU")
|
|
|
|
|
# using GCC
|
|
|
|
|
SET( CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${ARCH_TUNE}")
|
|
|
|
|
set(CMAKE_SHARED_LINKER_FLAGS "${CMAKE_SHARED_LINKER_FLAGS} -Wl,-rpath,$ORIGIN/")
|
|
|
|
|
endif()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
IF(${CMAKE_SYSTEM_NAME} MATCHES "Linux")
|
|
|
|
|
include_directories("/usr/include")
|
|
|
|
|
include_directories("/usr/local/include")
|
|
|
|
|
ENDIF(${CMAKE_SYSTEM_NAME} MATCHES "Linux")
|
|
|
|
|
if(!CUDA_BLAS)
|
|
|
|
|
if(!CPU_BLAS)
|
|
|
|
|
set(CUDA_BLAS FALSE)
|
|
|
|
|
set(CPU_BLAS TRUE)
|
|
|
|
|
endif()
|
|
|
|
|
endif()
|
|
|
|
|
|
|
|
|
|
# TODO: get rid of this once problem confirmed solved
|
|
|
|
|
#if (APPLE)
|
|
|
|
|
# if ("${CMAKE_CXX_COMPILER_ID}" STREQUAL "GNU")
|
|
|
|
|
# if ("${CMAKE_C_COMPILER_VERSION}" VERSION_GREATER 6.0 OR "${CMAKE_C_COMPILER_VERSION}" VERSION_EQUAL 6.0)
|
|
|
|
|
# SET( CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wa,-mavx512f,-mavx512vl,-mavx512bw,-mavx512dq,-mavx512cd ")
|
|
|
|
|
# endif()
|
|
|
|
|
# endif()
|
|
|
|
|
#endif()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
if(CUDA_BLAS)
|
|
|
|
|
message("Build cublas")
|
|
|
|
|
find_package(CUDA)
|
|
|
|
|
add_definitions(-D__CUDABLAS__=true)
|
|
|
|
|
if ("${CMAKE_CXX_COMPILER_ID}" STREQUAL "MSVC")
|
|
|
|
|
set (CMAKE_CXX_FLAGS "")
|
|
|
|
|
elseif ("${CMAKE_CXX_COMPILER_ID}" STREQUAL "GNU")
|
|
|
|
|
if ("${CMAKE_C_COMPILER_VERSION}" VERSION_GREATER 4.9 AND "$ENV{TRICK_NVCC}" STREQUAL "YES" AND CUDA_VERSION VERSION_LESS "8.0")
|
|
|
|
|
set (CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -D__GNUC__=4 -D__GNUC_MINOR__=9 -D_FORCE_INLINES -D_MWAITXINTRIN_H_INCLUDED")
|
|
|
|
|
set (CUDA_NVCC_FLAGS "${CUDA_NVCC_FLAGS} -Xcompiler -std=c++11 -Dnullptr=NULL")
|
|
|
|
|
message("TRICKING CUDA INTO SUPPORTING GCC > 4.9 YOU ARE PROCEEDING AT YOUR OWN RISK")
|
|
|
|
|
endif()
|
|
|
|
|
endif()
|
|
|
|
|
|
|
|
|
|
# we want OpenMP to be available for hybrid operations, at least for GCC
|
|
|
|
|
if("${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()
|
|
|
|
|
|
|
|
|
|
if (CUDA_FOUND)
|
|
|
|
|
message("CUDA include directory: ${CUDA_INCLUDE_DIRS}")
|
|
|
|
|
include_directories(${CUDA_INCLUDE_DIRS})
|
|
|
|
|
message("CUDA found!")
|
|
|
|
|
set( CUDA_ARCHITECTURE_MINIMUM "3.0" CACHE STRING "Minimum required CUDA compute capability" )
|
|
|
|
|
SET(CUDA_VERBOSE_BUILD ON)
|
|
|
|
|
SET(CUDA_SEPARABLE_COMPILATION OFF)
|
|
|
|
|
#set(CUDA_COMPUTE_CAPABILITY "61")
|
|
|
|
|
set(CUDA_COMPUTE_CAPABILITY "35")
|
|
|
|
|
# make NVCC more verbose to prevent timeouts on CI servers
|
|
|
|
|
#list(APPEND CUDA_NVCC_FLAGS -v)
|
|
|
|
|
if ("${EXPERIMENTAL}" STREQUAL "yes")
|
|
|
|
|
message("Experimental mode ENABLED")
|
|
|
|
|
list(APPEND CUDA_NVCC_FLAGS -D__ND4J_EXPERIMENTAL__=true)
|
|
|
|
|
set (CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -D__ND4J_EXPERIMENTAL__=true")
|
|
|
|
|
set (CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -D__ND4J_EXPERIMENTAL__=true")
|
|
|
|
|
set (EXPM " -D__ND4J_EXPERIMENTAL__=true")
|
|
|
|
|
endif()
|
|
|
|
|
if (CMAKE_BUILD_TYPE STREQUAL "Release")
|
|
|
|
|
if(CUDA_VERSION VERSION_GREATER "9.2") # cuda 10
|
|
|
|
|
if ("${COMPUTE}" STREQUAL "all")
|
|
|
|
|
if (APPLE)
|
|
|
|
|
list(APPEND CUDA_NVCC_FLAGS -DCUDA_10 ${EXPM} -w --cudart=static -O3 --expt-extended-lambda -gencode arch=compute_35,code=sm_35 -gencode arch=compute_37,code=sm_37 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61)
|
|
|
|
|
else()
|
|
|
|
|
list(APPEND CUDA_NVCC_FLAGS -DCUDA_10 ${EXPM} -w --cudart=static -O3 --expt-extended-lambda -gencode arch=compute_35,code=sm_35 -gencode arch=compute_37,code=sm_37 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=sm_75)
|
|
|
|
|
endif()
|
|
|
|
|
else()
|
|
|
|
|
list(APPEND CUDA_NVCC_FLAGS -DCUDA_10 ${EXPM} -w --cudart=static --expt-extended-lambda -O3 -arch=compute_${COMPUTE} -code=sm_${COMPUTE})
|
|
|
|
|
endif()
|
|
|
|
|
elseif(CUDA_VERSION VERSION_GREATER "8.0") # cuda 9
|
|
|
|
|
if ("${COMPUTE}" STREQUAL "all")
|
|
|
|
|
if (APPLE)
|
|
|
|
|
list(APPEND CUDA_NVCC_FLAGS -DCUDA_9 ${EXPM} -w --cudart=static -O3 --expt-extended-lambda -gencode arch=compute_35,code=sm_35 -gencode arch=compute_37,code=sm_37 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61)
|
|
|
|
|
else()
|
|
|
|
|
list(APPEND CUDA_NVCC_FLAGS -DCUDA_9 ${EXPM} -w --cudart=static -O3 --expt-extended-lambda -gencode arch=compute_35,code=sm_35 -gencode arch=compute_37,code=sm_37 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61)
|
|
|
|
|
endif()
|
|
|
|
|
else()
|
|
|
|
|
list(APPEND CUDA_NVCC_FLAGS -DCUDA_9 ${EXPM} -w --cudart=static --expt-extended-lambda -O3 -arch=compute_${COMPUTE} -code=sm_${COMPUTE})
|
|
|
|
|
endif()
|
|
|
|
|
elseif (CUDA_VERSION VERSION_GREATER "7.5") # cuda 8.0
|
|
|
|
|
if ("${COMPUTE}" STREQUAL "all")
|
|
|
|
|
list(APPEND CUDA_NVCC_FLAGS -DCUDA_8 ${EXPM} -w --cudart=static -O3 --expt-extended-lambda -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_37,code=sm_37 -gencode arch=compute_37,code=sm_37 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61)
|
|
|
|
|
else()
|
|
|
|
|
list(APPEND CUDA_NVCC_FLAGS -DCUDA_8 ${EXPM} -w --cudart=static --expt-extended-lambda -O3 -arch=compute_${COMPUTE} -code=sm_${COMPUTE})
|
|
|
|
|
endif()
|
|
|
|
|
else()
|
|
|
|
|
if ("${COMPUTE}" STREQUAL "all")
|
|
|
|
|
list(APPEND CUDA_NVCC_FLAGS -DCUDA_75 ${EXPM} --cudart=static --expt-extended-lambda -O3 -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_37,code=sm_37 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52)
|
|
|
|
|
else()
|
|
|
|
|
list(APPEND CUDA_NVCC_FLAGS -DCUDA_75 ${EXPM} --cudart=static --expt-extended-lambda -O3 -arch=compute_${COMPUTE} -code=sm_${COMPUTE})
|
|
|
|
|
endif()
|
|
|
|
|
endif()
|
|
|
|
|
|
|
|
|
|
else()
|
|
|
|
|
# debug only
|
|
|
|
|
if (LINUX)
|
|
|
|
|
SET(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wl,--export-dynamic -rdynamic")
|
|
|
|
|
SET(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} --export-dynamic")
|
|
|
|
|
endif()
|
|
|
|
|
|
|
|
|
|
if(CUDA_VERSION VERSION_GREATER "9.2") # cuda 9
|
|
|
|
|
message("CUDA 10 Debug build")
|
|
|
|
|
if ("${COMPUTE}" STREQUAL "all")
|
|
|
|
|
if (APPLE)
|
|
|
|
|
list(APPEND CUDA_NVCC_FLAGS -DCUDA_10 ${EXPM} -w -G -g --cudart=static --expt-extended-lambda -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_37,code=sm_37 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_53,code=sm_53 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_62,code=sm_62)
|
|
|
|
|
elseif()
|
|
|
|
|
list(APPEND CUDA_NVCC_FLAGS -DCUDA_10 ${EXPM} -w -G -g --cudart=static --expt-extended-lambda -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_37,code=sm_37 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_53,code=sm_53 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_62,code=sm_62 -gencode arch=compute_70,code=sm_70)
|
|
|
|
|
endif()
|
|
|
|
|
else()
|
|
|
|
|
list(APPEND CUDA_NVCC_FLAGS -DCUDA_10 ${EXPM} -w -G -g --cudart=static --expt-extended-lambda -arch=compute_${COMPUTE} -code=sm_${COMPUTE})
|
|
|
|
|
endif()
|
|
|
|
|
elseif(CUDA_VERSION VERSION_GREATER "8.0") # cuda 9
|
|
|
|
|
if ("${COMPUTE}" STREQUAL "all")
|
|
|
|
|
if (APPLE)
|
|
|
|
|
list(APPEND CUDA_NVCC_FLAGS -DCUDA_9 ${EXPM} -w -G -g --cudart=static --expt-extended-lambda -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_37,code=sm_37 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_53,code=sm_53 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_62,code=sm_62)
|
|
|
|
|
elseif()
|
|
|
|
|
list(APPEND CUDA_NVCC_FLAGS -DCUDA_9 ${EXPM} -w -G -g --cudart=static --expt-extended-lambda -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_37,code=sm_37 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_53,code=sm_53 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_62,code=sm_62 -gencode arch=compute_70,code=sm_70)
|
|
|
|
|
endif()
|
|
|
|
|
else()
|
|
|
|
|
list(APPEND CUDA_NVCC_FLAGS -DCUDA_9 ${EXPM} -w -G -g --cudart=static --expt-extended-lambda -arch=compute_${COMPUTE} -code=sm_${COMPUTE})
|
|
|
|
|
endif()
|
|
|
|
|
elseif (CUDA_VERSION VERSION_GREATER "7.5") # cuda 8
|
|
|
|
|
if ("${COMPUTE}" STREQUAL "all")
|
|
|
|
|
list(APPEND CUDA_NVCC_FLAGS -DCUDA_8 ${EXPM} -w -G -g --cudart=static --expt-extended-lambda -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_37,code=sm_37 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_53,code=sm_53 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_62,code=sm_62)
|
|
|
|
|
else()
|
|
|
|
|
list(APPEND CUDA_NVCC_FLAGS -DCUDA_8 ${EXPM} -w -G -g --cudart=static --expt-extended-lambda -arch=compute_${COMPUTE} -code=sm_${COMPUTE})
|
|
|
|
|
endif()
|
|
|
|
|
else()
|
|
|
|
|
if ("${COMPUTE}" STREQUAL "all")
|
|
|
|
|
list(APPEND CUDA_NVCC_FLAGS -DCUDA_75 ${EXPM} -w -G -g --cudart=static --expt-extended-lambda -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_37,code=sm_37 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_53,code=sm_53)
|
|
|
|
|
else()
|
|
|
|
|
list(APPEND CUDA_NVCC_FLAGS -DCUDA_75 ${EXPM} -w -G -g --cudart=static --expt-extended-lambda -arch=compute_${COMPUTE} -code=sm_${COMPUTE})
|
|
|
|
|
endif()
|
|
|
|
|
endif()
|
|
|
|
|
endif()
|
|
|
|
|
|
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)
|
|
|
|
|
file(GLOB_RECURSE LOOPS_SOURCES false ../include/loops/*.cpp ../include/loops/*.h)
|
|
|
|
|
file(GLOB_RECURSE LOOPS_SOURCES_CUDA false ../include/loops/*.cu)
|
2019-06-06 14:21:15 +02:00
|
|
|
|
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
|
|
|
if (NOT BUILD_TESTS)
|
2019-06-06 14:21:15 +02:00
|
|
|
CUDA_ADD_LIBRARY(${LIBND4J_NAME} SHARED cuda/NativeOps.cu cuda/NativeOpExecutioner.cu ${LOOPS_SOURCES_CUDA}
|
|
|
|
|
${CUSTOMOPS_HELPERS_SOURCES} ${HELPERS_SOURCES} ${EXEC_SOURCES}
|
|
|
|
|
../include/cnpy/cnpy.cpp ../include/nd4jmemset.h ../include/nd4jmalloc.h
|
|
|
|
|
cpu/GraphExecutioner.cpp cuda/NDArray.cu cpu/NDArrayFactory.cpp
|
|
|
|
|
Environment.cpp Environment.h ${LOOPS_SOURCES} ${ARRAY_SOURCES} ${TYPES_SOURCES}
|
|
|
|
|
${MEMORY_SOURCES} ${GRAPH_SOURCES} ${CUSTOMOPS_SOURCES} ${INDEXING_SOURCES} ${EXCEPTIONS_SOURCES} ${OPS_SOURCES})
|
|
|
|
|
else()
|
|
|
|
|
set (CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -DBUILD_TESTS=true")
|
|
|
|
|
|
|
|
|
|
CUDA_ADD_LIBRARY(${LIBND4J_NAME} STATIC cuda/NativeOps.cu cuda/NativeOpExecutioner.cu ${LOOPS_SOURCES_CUDA}
|
|
|
|
|
${CUSTOMOPS_HELPERS_SOURCES} ${HELPERS_SOURCES} ${EXEC_SOURCES}
|
|
|
|
|
../include/cnpy/cnpy.cpp ../include/nd4jmemset.h ../include/nd4jmalloc.h
|
|
|
|
|
cpu/GraphExecutioner.cpp cuda/NDArray.cu cpu/NDArrayFactory.cpp
|
|
|
|
|
Environment.cpp Environment.h ${LOOPS_SOURCES} ${ARRAY_SOURCES} ${TYPES_SOURCES}
|
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
|
|
|
${MEMORY_SOURCES} ${GRAPH_SOURCES} ${CUSTOMOPS_SOURCES} ${INDEXING_SOURCES} ${EXCEPTIONS_SOURCES} ${OPS_SOURCES})
|
2019-06-06 14:21:15 +02:00
|
|
|
endif()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
if(WIN32)
|
|
|
|
|
message("CUDA on Windows: enabling /EHsc")
|
|
|
|
|
SET(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /EHsc /bigobj")
|
|
|
|
|
SET_TARGET_PROPERTIES(${LIBND4J_NAME} PROPERTIES COMPILER_FLAGS "/EHsc /bigobj")
|
|
|
|
|
endif()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
target_link_libraries(${LIBND4J_NAME} ${CUDA_LIBRARIES} ${CUDA_CUBLAS_LIBRARIES})
|
|
|
|
|
set(CMAKE_LIBRARY_OUTPUT_DIRECTORY ${PROJECT_BINARY_DIR}/cuda)
|
|
|
|
|
|
|
|
|
|
install(TARGETS ${LIBND4J_NAME} DESTINATION .)
|
|
|
|
|
endif(CUDA_FOUND)
|
|
|
|
|
elseif(CPU_BLAS)
|
|
|
|
|
|
|
|
|
|
if ("${EXPERIMENTAL}" STREQUAL "yes")
|
|
|
|
|
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 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)
|
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 CUSTOMOPS_HELPERS_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 LOOPS_SOURCES false ../include/loops/*.cpp ../include/loops/*.h)
|
|
|
|
|
|
|
|
|
|
message("CPU BLAS")
|
|
|
|
|
add_definitions(-D__CPUBLAS__=true)
|
|
|
|
|
add_library(nd4jobj OBJECT cpu/NativeOps.cpp cpu/GraphExecutioner.cpp
|
|
|
|
|
cpu/NativeOpExecutioner.cpp cpu/NDArray.cpp cpu/NDArrayFactory.cpp
|
|
|
|
|
../include/cnpy/cnpy.cpp ../include/nd4jmemset.h ../include/nd4jmalloc.h
|
|
|
|
|
Environment.cpp Environment.h ${LOOPS_SOURCES} ${HELPERS_SOURCES} ${EXEC_SOURCES} ${ARRAY_SOURCES} ${TYPES_SOURCES}
|
|
|
|
|
${MEMORY_SOURCES} ${GRAPH_SOURCES} ${CUSTOMOPS_SOURCES} ${EXCEPTIONS_SOURCES} ${INDEXING_SOURCES} ${CUSTOMOPS_HELPERS_SOURCES}
|
|
|
|
|
${OPS_SOURCES})
|
|
|
|
|
if(IOS)
|
|
|
|
|
add_library(${LIBND4J_NAME} STATIC $<TARGET_OBJECTS:nd4jobj>)
|
|
|
|
|
else()
|
|
|
|
|
add_library(${LIBND4J_NAME}static STATIC $<TARGET_OBJECTS:nd4jobj>)
|
|
|
|
|
add_library(${LIBND4J_NAME} SHARED $<TARGET_OBJECTS:nd4jobj>)
|
|
|
|
|
endif()
|
|
|
|
|
|
|
|
|
|
target_link_libraries(${LIBND4J_NAME} ${MKLDNN_LIBRARIES} ${OPENBLAS_LIBRARIES})
|
|
|
|
|
|
|
|
|
|
if ("${LIBND4J_ALL_OPS}" AND "${LIBND4J_BUILD_MINIFIER}")
|
|
|
|
|
message(STATUS "Building minifier...")
|
|
|
|
|
add_executable(minifier ../minifier/minifier.cpp ../minifier/graphopt.cpp)
|
|
|
|
|
target_link_libraries(minifier ${LIBND4J_NAME}static ${MKLDNN_LIBRARIES} ${OPENBLAS_LIBRARIES})
|
|
|
|
|
endif()
|
|
|
|
|
|
|
|
|
|
if ("${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} ${OpenMP_CXX_FLAGS}")
|
|
|
|
|
endif()
|
|
|
|
|
endif()
|
|
|
|
|
|
|
|
|
|
if (CMAKE_BUILD_TYPE STREQUAL "Debug")
|
|
|
|
|
SET(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -rdynamic -Wl,-export-dynamic")
|
|
|
|
|
SET(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -export-dynamic")
|
|
|
|
|
endif()
|
|
|
|
|
|
|
|
|
|
#install(TARGETS mySharedLib DESTINATION /some/full/path)
|
|
|
|
|
install(TARGETS ${LIBND4J_NAME} DESTINATION .)
|
|
|
|
|
set(CMAKE_LIBRARY_OUTPUT_DIRECTORY ${PROJECT_BINARY_DIR}/cpu)
|
|
|
|
|
endif()
|
