* 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>
353 lines
20 KiB
CMake
Executable File
353 lines
20 KiB
CMake
Executable File
################################################################################
|
|
# 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 (APPLE_BUILD)
|
|
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -DAPPLE_BUILD=true")
|
|
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -DAPPLE_BUILD=true")
|
|
endif()
|
|
|
|
if (ANDROID_BUILD)
|
|
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -DANDROID_BUILD=true")
|
|
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -DANDROID_BUILD=true")
|
|
endif()
|
|
|
|
if (IOS_BUILD)
|
|
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -DIOS_BUILD=true")
|
|
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -DIOS_BUILD=true")
|
|
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 "${CMAKE_CXX_FLAGS} /EHsc /w")
|
|
elseif ("${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(${CMAKE_SYSTEM_NAME} MATCHES "Linux")
|
|
if(!CUDA_BLAS)
|
|
if(!CPU_BLAS)
|
|
set(CUDA_BLAS FALSE)
|
|
set(CPU_BLAS TRUE)
|
|
endif()
|
|
endif()
|
|
|
|
if(CUDA_BLAS)
|
|
message("Build cublas")
|
|
find_package(CUDA)
|
|
add_definitions(-D__CUDABLAS__=true)
|
|
if ("${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 -Xfatbin -compress-all -gencode arch=compute_35,code=sm_35 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60)
|
|
else()
|
|
list(APPEND CUDA_NVCC_FLAGS -DCUDA_10 ${EXPM} -w --cudart=static -O3 --expt-extended-lambda -Xfatbin -compress-all -gencode arch=compute_35,code=sm_35 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=sm_70)
|
|
endif()
|
|
else()
|
|
list(APPEND CUDA_NVCC_FLAGS -DCUDA_10 ${EXPM} -w --cudart=static --expt-extended-lambda -O3 -Xfatbin -compress-all -arch=compute_${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 -Xfatbin -compress-all -gencode arch=compute_35,code=sm_35 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60)
|
|
else()
|
|
list(APPEND CUDA_NVCC_FLAGS -DCUDA_9 ${EXPM} -w --cudart=static -O3 --expt-extended-lambda -Xfatbin -compress-all -gencode arch=compute_35,code=sm_35 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60)
|
|
endif()
|
|
else()
|
|
list(APPEND CUDA_NVCC_FLAGS -DCUDA_9 ${EXPM} -w --cudart=static --expt-extended-lambda -O3 -Xfatbin -compress-all -arch=compute_${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 -Xfatbin -compress-all -gencode arch=compute_30,code=sm_30 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60)
|
|
else()
|
|
list(APPEND CUDA_NVCC_FLAGS -DCUDA_8 ${EXPM} -w --cudart=static --expt-extended-lambda -O3 -Xfatbin -compress-all -arch=compute_${COMPUTE} -code=sm_${COMPUTE})
|
|
endif()
|
|
else()
|
|
if ("${COMPUTE}" STREQUAL "all")
|
|
list(APPEND CUDA_NVCC_FLAGS -DCUDA_75 ${EXPM} --cudart=static --expt-extended-lambda -O3 -Xfatbin -compress-all -gencode arch=compute_30,code=sm_30 -gencode arch=compute_52,code=sm_52 )
|
|
else()
|
|
list(APPEND CUDA_NVCC_FLAGS -DCUDA_75 ${EXPM} --cudart=static --expt-extended-lambda -O3 -Xfatbin -compress-all -arch=compute_${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 -Xfatbin -compress-all -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 -Xfatbin -compress-all -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 ${EXPM} -w -G -g --cudart=static --expt-extended-lambda -Xfatbin -compress-all -arch=compute_${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 -Xfatbin -compress-all -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 -Xfatbin -compress-all -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 ${EXPM} -w -G -g --cudart=static --expt-extended-lambda -Xfatbin -compress-all -arch=compute_${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 -Xfatbin -compress-all -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 ${EXPM} -w -G -g --cudart=static --expt-extended-lambda -Xfatbin -compress-all -arch=compute_${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 -Xfatbin -compress-all -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 ${EXPM} -w -G -g --cudart=static --expt-extended-lambda -Xfatbin -compress-all -arch=compute_${COMPUTE} -code=sm_${COMPUTE})
|
|
endif()
|
|
endif()
|
|
endif()
|
|
|
|
file(GLOB_RECURSE PERF_SOURCES false ../include/performance/*.cpp ../include/performance/*.h)
|
|
file(GLOB_RECURSE EXCEPTIONS_SOURCES false ../include/exceptions/*.cpp ../include/exceptions/*.h)
|
|
file(GLOB_RECURSE EXEC_SOURCES false ../include/execution/impl/*.cpp ../include/execution/*.cu ../include/execution/*.h)
|
|
file(GLOB_RECURSE TYPES_SOURCES false ../include/types/*.cpp ../include/types/*.h)
|
|
file(GLOB_RECURSE ARRAY_SOURCES false ../include/array/impl/*.cpp ../include/array/cuda/*.cu ../include/array/*.h)
|
|
file(GLOB_RECURSE MEMORY_SOURCES false ../include/memory/impl/*.cpp ../include/memory/cuda/*.cu ../include/memory/*.h)
|
|
file(GLOB_RECURSE GRAPH_SOURCES false ../include/graph/*.cpp ../include/graph/*.cu ../include/graph/*.h)
|
|
file(GLOB_RECURSE CUSTOMOPS_SOURCES false ../include/ops/declarable/generic/*.cpp)
|
|
file(GLOB_RECURSE CUSTOMOPS_HELPERS_SOURCES false ../include/ops/declarable/helpers/cuda/*.cu ../include/ops/declarable/helpers/impl/*.cpp)
|
|
file(GLOB_RECURSE OPS_SOURCES false ../include/ops/impl/*.cpp ../include/ops/declarable/impl/*.cpp ../include/ops/*.h)
|
|
file(GLOB_RECURSE HELPERS_SOURCES false ../include/helpers/impl/*.cpp ../include/helpers/*.cu ../include/helpers/*.cupp ../include/helpers/*.h)
|
|
file(GLOB_RECURSE INDEXING_SOURCES false ../include/indexing/*.cpp ../include/indexing/*.h)
|
|
file(GLOB_RECURSE LOOPS_SOURCES false ../include/loops/impl/*.cpp ../include/loops/*.h)
|
|
file(GLOB_RECURSE LOOPS_SOURCES_CUDA false ../include/loops/*.cu)
|
|
|
|
if (NOT BUILD_TESTS)
|
|
CUDA_ADD_LIBRARY(${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} ${PERF_SOURCES})
|
|
else()
|
|
set (CMAKE_CXX_FLAGS "${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}
|
|
${MEMORY_SOURCES} ${GRAPH_SOURCES} ${CUSTOMOPS_SOURCES} ${INDEXING_SOURCES} ${EXCEPTIONS_SOURCES} ${OPS_SOURCES} ${PERF_SOURCES})
|
|
endif()
|
|
|
|
|
|
if(WIN32)
|
|
message("CUDA on Windows: enabling /EHsc")
|
|
SET(CMAKE_CXX_FLAGS "${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} ${CUDA_cusolver_LIBRARY})
|
|
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 PERF_SOURCES false ../include/performance/*.cpp ../include/performance/*.h)
|
|
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)
|
|
file(GLOB_RECURSE CUSTOMOPS_HELPERS_SOURCES false ../include/ops/declarable/helpers/cpu/*.cpp ../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 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} ${PERF_SOURCES})
|
|
if(IOS)
|
|
add_library(${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} ${OpenMP_CXX_FLAGS}")
|
|
endif()
|
|
endif()
|
|
|
|
if (CMAKE_BUILD_TYPE STREQUAL "Debug" AND NOT(APPLE))
|
|
SET(CMAKE_CXX_FLAGS "${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()
|