CNTK/Makefile

1722 строки
70 KiB
Makefile
Исходник Обычный вид История

# Makefile for a Linux/GCC build of CNTK
#
# The Linux and Windows versions are not different branches, but rather build off the same
# source files, using different makefiles. This current makefile has the purpose of enabling
# work to make all sources compile with GCC, and also to check for GCC-compat regressions due to
# modifications which are currently done under Windows.
#
# To use this Makefile, create a directory to build in and make a Config.make in the directory
# that provides
# BUILDTYPE= One of release or debug
# defaults to release
# BUILD_VERSION= CNTK version number to be used while building
# BUILD_PUBLIC= One of yes or no
# MKL_PATH= path to MKLML installation
# only needed if MATHLIB=mkl
# GDK_INCLUDE_PATH= path to CUDA GDK include path, so $(GDK_INCLUDE_PATH)/nvml.h exists
# defaults to /usr/include/nvidia/gdk
# GDK_NVML_LIB_PATH= path to CUDA GDK (stub) library path, so $(GDK_NVML_LIB_PATH)/libnvidia-ml.so exists
# defaults to /usr/src/gdk/nvml/lib
2016-08-16 15:59:15 +03:00
# MATHLIB= mkl
# defaults to mkl
# CUDA_PATH= Path to CUDA
# If not specified, GPU will not be enabled
# CUB_PATH= path to NVIDIA CUB installation, so $(CUB_PATH)/cub/cub.cuh exists
# defaults to /usr/local/cub-1.4.1
# CUDNN_PATH= path to NVIDIA cuDNN installation so $(CUDNN_PATH)/cuda/include/cudnn.h exists
# CuDNN version needs to be 5.0 or higher.
# KALDI_PATH= Path to Kaldi
# If not specified, Kaldi plugins will not be built
# OPENCV_PATH= path to OpenCV 3.1.0 installation, so $(OPENCV_PATH) exists
# defaults to /usr/local/opencv-3.1.0
2016-10-25 01:33:31 +03:00
# PROTOBUF_PATH= path to Protocol Buffers 3.1.0 installation, so $(PROTOBUF_PATH) exists
# defaults to /usr/local/protobuf-3.1.0
# LIBZIP_PATH= path to libzip installation, so $(LIBZIP_PATH) exists
# defaults to /usr/local/
# BOOST_PATH= path to Boost installation, so $(BOOST_PATH)/include/boost/test/unit_test.hpp
# defaults to /usr/local/boost-1.60.0
# PYTHON_SUPPORT=true iff CNTK v2 Python module should be build
# PYTHON_WITH_DEPS=1 Adds third party libraries in the python package (e.g. CUDA). Must be equal to 1 or unset
# PYTHON_WITH_DEBUG=1 Do not strip libraries for the python package. Must be equal to 1 or unset
# SWIG_PATH= path to SWIG (>= 3.0.10)
# PYTHON_VERSIONS= list of Python versions to build for
2018-01-27 01:55:22 +03:00
# A Python version is identified by "27", "35", or "36".
2016-12-19 15:49:05 +03:00
# PYTHON27_PATH= path to Python 2.7 interpreter
# PYTHON34_PATH= path to Python 3.4 interpreter
# PYTHON35_PATH= path to Python 3.5 interpreter
2017-03-11 16:35:49 +03:00
# PYTHON36_PATH= path to Python 3.6 interpreter
2016-03-29 17:16:50 +03:00
# MPI_PATH= path to MPI installation, so $(MPI_PATH) exists
# defaults to /usr/local/mpi
# These can be overridden on the command line, e.g. make BUILDTYPE=debug
CNTK support for CUDA 9 CNTK now supports CUDA 9/cuDNN 7. This requires an update to build environment to Ubuntu 16/GCC 5 for Linux, and Visual Studio 2017/VCTools 14.11 for Windows. With CUDA 9, CNTK also added a preview for 16-bit floating point (a.k.a FP16) computation. Please check out the example of FP16 in ResNet50 at /Examples/Image/Classification/ResNet/Python/TrainResNet_ImageNet_Distributed.py Notes on FP16 preview: * FP16 implementation on CPU is not optimized, and it's not supposed to be used in CPU inference directly. User needs to convert the model to 32-bit floating point before running on CPU. * Loss/Criterion for FP16 training needs to be 32bit for accumulation without overflow, using cast function. Please check the example above. * Readers do not have FP16 output unless using numpy to feed data, cast from FP32 to FP16 is needed. Please check the example above. * FP16 gradient aggregation is currently only implemented on GPU using NCCL2. Distributed training with FP16 with MPI is not supported. * FP16 math is a subset of current FP32 implementation. Some model may get Feature Not Implemented exception using FP16. * FP16 is currently not supported in BrainScript. Please use Python for FP16. To setup build and runtime environment on Windows: * Install [Visual Studio 2017](https://www.visualstudio.com/downloads/) with following workloads and components. From command line (use Community version installer as example): vs_community.exe --add Microsoft.VisualStudio.Workload.NativeDesktop --add Microsoft.VisualStudio.Workload.ManagedDesktop --add Microsoft.VisualStudio.Workload.Universal --add Microsoft.Component.PythonTools --add Microsoft.VisualStudio.Component.VC.Tools.14.11 * Install [NVidia CUDA 9](https://developer.nvidia.com/cuda-90-download-archive?target_os=Windows&target_arch=x86_64) * From PowerShell, run: /Tools/devInstall/Windows/DevInstall.ps1 * Start VCTools 14.11 command line, run: cmd /k "%VS2017INSTALLDIR%\VC\Auxiliary\Build\vcvarsall.bat" x64 --vcvars_ver=14.11 * Open /CNTK.sln from the VCTools 14.11 command line. Note that starting CNTK.sln other than VCTools 14.11 command line, would causes CUDA 9 [build error](https://developercommunity.visualstudio.com/content/problem/163758/vs-2017-155-doesnt-support-cuda-9.html). To setup build and runtime environment on Linux using docker, please build Unbuntu 16.04 docker image using Dockerfiles /Tools/docker. For other Linux systems, please refer to the Dockerfiles to setup dependent libraries for CNTK.
2018-01-23 03:58:56 +03:00
# TODO: Build static libraries for common dependencies that are shared by multiple
# targets, e.g. eval and CNTK.
ARCH=$(shell uname)
ifndef BUILD_TOP
BUILD_TOP=.
endif
ifneq ("$(wildcard $(BUILD_TOP)/Config.make)","")
include $(BUILD_TOP)/Config.make
else
2017-06-07 17:50:37 +03:00
$(error Cannot find $(BUILD_TOP)/Config.make. Please see the CNTK documentation at https://docs.microsoft.com/en-us/cognitive-toolkit/Setup-CNTK-on-Linux for configuration instructions.)
endif
ifndef BUILDTYPE
$(info Defaulting BUILDTYPE=release)
BUILDTYPE=release
endif
ifndef MATHLIB
2016-08-16 15:59:15 +03:00
$(info DEFAULTING MATHLIB=mkl)
MATHLIB = mkl
endif
#### Configure based on options above
DEFAULT_CXX:= $(CXX)
# The mpic++ wrapper only adds MPI specific flags to the g++ command line.
# The actual compiler/linker flags added can be viewed by running 'mpic++ --showme:compile' and 'mpic++ --showme:link'
2016-11-04 18:38:55 +03:00
ifneq ($(HAS_MPI),0)
CXX = $(MPI_PATH)/bin/mpic++
2016-11-04 18:38:55 +03:00
endif
SSE_FLAGS = -msse4.1 -mssse3
2016-10-25 01:33:31 +03:00
PROTOC = $(PROTOBUF_PATH)/bin/protoc
# Settings for ARM64 architectures that use a crosscompiler on a host machine.
#CXX = aarch64-linux-gnu-g++
#SSE_FLAGS =
2015-12-15 11:58:24 +03:00
SOURCEDIR:= Source
2018-06-05 02:35:49 +03:00
GSL_PATH:=$(SOURCEDIR)/../external/gsl
2018-06-28 18:38:36 +03:00
ONNX_PATH:=$(SOURCEDIR)/CNTKv2LibraryDll/proto/onnx
ONNX_REPO_PATH:=$(SOURCEDIR)/CNTKv2LibraryDll/proto/onnx/onnx_repo
INCLUDEPATH:= $(addprefix $(SOURCEDIR)/, Common/Include CNTKv2LibraryDll CNTKv2LibraryDll/API CNTKv2LibraryDll/Generated/Linux CNTKv2LibraryDll/proto ../Examples/Extensibility/CPP Math CNTK ActionsLib ComputationNetworkLib SGDLib SequenceTrainingLib CNTK/BrainScript Readers/ReaderLib PerformanceProfilerDll)
2016-10-25 01:33:31 +03:00
INCLUDEPATH+=$(PROTOBUF_PATH)/include
2018-06-05 02:35:49 +03:00
INCLUDEPATH+=$(GSL_PATH)/include
2018-06-28 18:38:36 +03:00
INCLUDEPATH+=$(ONNX_PATH)
INCLUDEPATH+=$(ONNX_REPO_PATH)
# COMMON_FLAGS include settings that are passed both to NVCC and C++ compilers.
COMMON_FLAGS:= $(COMMON_FLAGS) -DONNX_NAMESPACE=onnx -DONNX_ML=1 -DHAS_MPI=$(HAS_MPI) -D_POSIX_SOURCE -D_XOPEN_SOURCE=600 -D__USE_XOPEN2K -std=c++14 -DCUDA_NO_HALF -D__CUDA_NO_HALF_OPERATORS__
CNTK support for CUDA 9 CNTK now supports CUDA 9/cuDNN 7. This requires an update to build environment to Ubuntu 16/GCC 5 for Linux, and Visual Studio 2017/VCTools 14.11 for Windows. With CUDA 9, CNTK also added a preview for 16-bit floating point (a.k.a FP16) computation. Please check out the example of FP16 in ResNet50 at /Examples/Image/Classification/ResNet/Python/TrainResNet_ImageNet_Distributed.py Notes on FP16 preview: * FP16 implementation on CPU is not optimized, and it's not supposed to be used in CPU inference directly. User needs to convert the model to 32-bit floating point before running on CPU. * Loss/Criterion for FP16 training needs to be 32bit for accumulation without overflow, using cast function. Please check the example above. * Readers do not have FP16 output unless using numpy to feed data, cast from FP32 to FP16 is needed. Please check the example above. * FP16 gradient aggregation is currently only implemented on GPU using NCCL2. Distributed training with FP16 with MPI is not supported. * FP16 math is a subset of current FP32 implementation. Some model may get Feature Not Implemented exception using FP16. * FP16 is currently not supported in BrainScript. Please use Python for FP16. To setup build and runtime environment on Windows: * Install [Visual Studio 2017](https://www.visualstudio.com/downloads/) with following workloads and components. From command line (use Community version installer as example): vs_community.exe --add Microsoft.VisualStudio.Workload.NativeDesktop --add Microsoft.VisualStudio.Workload.ManagedDesktop --add Microsoft.VisualStudio.Workload.Universal --add Microsoft.Component.PythonTools --add Microsoft.VisualStudio.Component.VC.Tools.14.11 * Install [NVidia CUDA 9](https://developer.nvidia.com/cuda-90-download-archive?target_os=Windows&target_arch=x86_64) * From PowerShell, run: /Tools/devInstall/Windows/DevInstall.ps1 * Start VCTools 14.11 command line, run: cmd /k "%VS2017INSTALLDIR%\VC\Auxiliary\Build\vcvarsall.bat" x64 --vcvars_ver=14.11 * Open /CNTK.sln from the VCTools 14.11 command line. Note that starting CNTK.sln other than VCTools 14.11 command line, would causes CUDA 9 [build error](https://developercommunity.visualstudio.com/content/problem/163758/vs-2017-155-doesnt-support-cuda-9.html). To setup build and runtime environment on Linux using docker, please build Unbuntu 16.04 docker image using Dockerfiles /Tools/docker. For other Linux systems, please refer to the Dockerfiles to setup dependent libraries for CNTK.
2018-01-23 03:58:56 +03:00
CPPFLAGS:=
CXXFLAGS:= $(SSE_FLAGS) $(CXXFLAGS) -fopenmp -fpermissive -fPIC -Werror -fcheck-new
LIBPATH:=
LIBS_LIST:=
LDFLAGS:=
CXXVER_GE480:= $(shell expr `$(CXX) -dumpversion | sed -e 's/\.\([0-9][0-9]\)/\1/g' -e 's/\.\([0-9]\)/0\1/g' -e 's/^[0-9]\{3,4\}$$/&00/'` \>= 40800)
ifeq ($(CXXVER_GE480),1)
CXXFLAGS += -Wno-error=literal-suffix
endif
SEPARATOR = "=-----------------------------------------------------------="
ALL:=
ALL_LIBS:=
PYTHON_LIBS:=
JAVA_LIBS:=
2018-06-06 18:38:29 +03:00
CSHARP_LIBS:=
LIBS_FULLPATH:=
SRC:=
# Make sure all is the first (i.e. default) target, but we can't actually define it
# this early in the file, so let buildall do the work.
all : buildall
# Set up basic nvcc options and add CUDA targets from above
CUFLAGS = -m 64
ifdef CUDA_PATH
ifndef GDK_INCLUDE_PATH
GDK_INCLUDE_PATH=/usr/include/nvidia/gdk
$(info defaulting GDK_INCLUDE_PATH to $(GDK_INCLUDE_PATH))
endif
ifndef GDK_NVML_LIB_PATH
GDK_NVML_LIB_PATH=/usr/src/gdk/nvml/lib
$(info defaulting GDK_NVML_LIB_PATH to $(GDK_NVML_LIB_PATH))
2015-10-13 02:36:40 +03:00
endif
ifndef CUB_PATH
$(info defaulting CUB_PATH to /usr/local/cub-1.4.1)
CUB_PATH=/usr/local/cub-1.4.1
endif
DEVICE = gpu
NVCC = $(CUDA_PATH)/bin/nvcc
INCLUDEPATH+=$(GDK_INCLUDE_PATH)
2015-10-13 02:36:40 +03:00
INCLUDEPATH+=$(CUB_PATH)
# Set up CUDA includes and libraries
INCLUDEPATH += $(CUDA_PATH)/include
LIBPATH += $(CUDA_PATH)/lib64
LIBS_LIST += cublas cudart cuda curand cusparse nvidia-ml
# Set up cuDNN if needed
ifdef CUDNN_PATH
INCLUDEPATH += $(CUDNN_PATH)/cuda/include
LIBPATH += $(CUDNN_PATH)/cuda/lib64
LIBS_LIST += cudnn
COMMON_FLAGS +=-DUSE_CUDNN
endif
# Set up NCCL if needed
ifdef NCCL_PATH
INCLUDEPATH += $(NCCL_PATH)/include
LIBPATH += $(NCCL_PATH)/lib
LIBS_LIST += nccl
COMMON_FLAGS += -DUSE_NCCL
endif
else
DEVICE = cpu
COMMON_FLAGS +=-DCPUONLY
endif
ifeq ("$(MATHLIB)","mkl")
INCLUDEPATH += $(MKL_PATH)/include
# disable MKL-DNN until we pick up the fix for AMD cache size https://github.com/intel/mkl-dnn/commit/ccfbf83ab489b42f7452b6701498b07c28cdb502
#LIBS_LIST += m iomp5 pthread mklml_intel mkldnn
LIBS_LIST += m iomp5 pthread mklml_intel
MKL_LIB_PATH := $(MKL_PATH)/lib
2017-07-17 18:45:47 +03:00
LIBPATH += $(MKL_LIB_PATH)
#COMMON_FLAGS += -DUSE_MKL -DUSE_MKLDNN
COMMON_FLAGS += -DUSE_MKL
endif
ifeq ($(CUDA_GDR),1)
COMMON_FLAGS += -DUSE_CUDA_GDR
endif
ifeq ("$(MATHLIB)","openblas")
INCLUDEPATH += $(OPENBLAS_PATH)/include
LIBPATH += $(OPENBLAS_PATH)/lib
LIBS_LIST += openblas m pthread
CPPFLAGS += -DUSE_OPENBLAS
endif
ifdef KALDI_PATH
########## Copy includes and defines from $(KALDI_PATH)/src/kaldi.mk ##########
FSTROOT = $(KALDI_PATH)/tools/openfst
ATLASINC = $(KALDI_PATH)/tools/ATLAS/include
INCLUDEPATH += $(KALDI_PATH)/src $(ATLASINC) $(FSTROOT)/include
CPPFLAGS += -DKALDI_DOUBLEPRECISION=0 -DHAVE_POSIX_MEMALIGN -DHAVE_EXECINFO_H=1 -DHAVE_CXXABI_H -DHAVE_ATLAS -DHAVE_OPENFST_GE_10400
KALDI_LIBPATH += $(KALDI_PATH)/src/lib
KALDI_LIBS_LIST := kaldi-util kaldi-matrix kaldi-base kaldi-hmm kaldi-cudamatrix kaldi-nnet kaldi-lat
KALDI_LIBS := $(addprefix -l,$(KALDI_LIBS_LIST))
endif
ifdef SUPPORT_AVX2
CPPFLAGS += -mavx2
endif
2015-09-03 22:17:17 +03:00
# Set up nvcc target architectures (will generate code to support them all, i.e. fat-binary, in release mode)
2017-07-07 17:44:48 +03:00
# In debug mode we only include cubin/PTX for 30 and rely on PTX / JIT to generate the required native cubin format
# see also http://docs.nvidia.com/cuda/pascal-compatibility-guide/index.html#building-applications-with-pascal-support
2015-09-03 22:17:17 +03:00
GENCODE_SM30 := -gencode arch=compute_30,code=\"sm_30,compute_30\"
GENCODE_SM35 := -gencode arch=compute_35,code=\"sm_35,compute_35\"
GENCODE_SM50 := -gencode arch=compute_50,code=\"sm_50,compute_50\"
GENCODE_SM52 := -gencode arch=compute_52,code=\"sm_52,compute_52\"
GENCODE_SM60 := -gencode arch=compute_60,code=\"sm_60,compute_60\"
GENCODE_SM61 := -gencode arch=compute_61,code=\"sm_61,compute_61\"
CNTK support for CUDA 9 CNTK now supports CUDA 9/cuDNN 7. This requires an update to build environment to Ubuntu 16/GCC 5 for Linux, and Visual Studio 2017/VCTools 14.11 for Windows. With CUDA 9, CNTK also added a preview for 16-bit floating point (a.k.a FP16) computation. Please check out the example of FP16 in ResNet50 at /Examples/Image/Classification/ResNet/Python/TrainResNet_ImageNet_Distributed.py Notes on FP16 preview: * FP16 implementation on CPU is not optimized, and it's not supposed to be used in CPU inference directly. User needs to convert the model to 32-bit floating point before running on CPU. * Loss/Criterion for FP16 training needs to be 32bit for accumulation without overflow, using cast function. Please check the example above. * Readers do not have FP16 output unless using numpy to feed data, cast from FP32 to FP16 is needed. Please check the example above. * FP16 gradient aggregation is currently only implemented on GPU using NCCL2. Distributed training with FP16 with MPI is not supported. * FP16 math is a subset of current FP32 implementation. Some model may get Feature Not Implemented exception using FP16. * FP16 is currently not supported in BrainScript. Please use Python for FP16. To setup build and runtime environment on Windows: * Install [Visual Studio 2017](https://www.visualstudio.com/downloads/) with following workloads and components. From command line (use Community version installer as example): vs_community.exe --add Microsoft.VisualStudio.Workload.NativeDesktop --add Microsoft.VisualStudio.Workload.ManagedDesktop --add Microsoft.VisualStudio.Workload.Universal --add Microsoft.Component.PythonTools --add Microsoft.VisualStudio.Component.VC.Tools.14.11 * Install [NVidia CUDA 9](https://developer.nvidia.com/cuda-90-download-archive?target_os=Windows&target_arch=x86_64) * From PowerShell, run: /Tools/devInstall/Windows/DevInstall.ps1 * Start VCTools 14.11 command line, run: cmd /k "%VS2017INSTALLDIR%\VC\Auxiliary\Build\vcvarsall.bat" x64 --vcvars_ver=14.11 * Open /CNTK.sln from the VCTools 14.11 command line. Note that starting CNTK.sln other than VCTools 14.11 command line, would causes CUDA 9 [build error](https://developercommunity.visualstudio.com/content/problem/163758/vs-2017-155-doesnt-support-cuda-9.html). To setup build and runtime environment on Linux using docker, please build Unbuntu 16.04 docker image using Dockerfiles /Tools/docker. For other Linux systems, please refer to the Dockerfiles to setup dependent libraries for CNTK.
2018-01-23 03:58:56 +03:00
GENCODE_SM70 := -gencode arch=compute_70,code=\"sm_70,compute_70\"
2015-09-03 22:17:17 +03:00
# Should we relocate *.gcno and *.gcda files using -fprofile-dir option?
# Use GCOV_PREFIX and GCOV_PREFIX_STRIP if relocating:
# For example, if the object file /user/build/foo.o was built with -fprofile-arcs, the final executable will try to create the data file
# /user/build/foo.gcda when running on the target system. This will fail if the corresponding directory does not exist and it is unable
# to create it. This can be overcome by, for example, setting the environment as 'GCOV_PREFIX=/target/run' and 'GCOV_PREFIX_STRIP=1'.
# Such a setting will name the data file /target/run/build/foo.gcda
ifdef CNTK_CODE_COVERAGE
CXXFLAGS += -fprofile-arcs -ftest-coverage
LDFLAGS += -lgcov --coverage
endif
ifeq ("$(BUILDTYPE)","debug")
2017-07-07 17:44:48 +03:00
ifdef CNTK_CUDA_CODEGEN_DEBUG
GENCODE_FLAGS := $(CNTK_CUDA_CODEGEN_DEBUG)
else
GENCODE_FLAGS := $(GENCODE_SM30)
endif
2015-09-18 02:57:26 +03:00
CXXFLAGS += -g
LDFLAGS += -rdynamic
COMMON_FLAGS += -D_DEBUG -DNO_SYNC
2016-01-09 03:41:45 +03:00
CUFLAGS += -O0 -g -use_fast_math -lineinfo $(GENCODE_FLAGS)
endif
ifeq ("$(BUILDTYPE)","release")
2017-07-07 17:44:48 +03:00
ifdef CNTK_CUDA_CODEGEN_RELEASE
GENCODE_FLAGS := $(CNTK_CUDA_CODEGEN_RELEASE)
else
CNTK support for CUDA 9 CNTK now supports CUDA 9/cuDNN 7. This requires an update to build environment to Ubuntu 16/GCC 5 for Linux, and Visual Studio 2017/VCTools 14.11 for Windows. With CUDA 9, CNTK also added a preview for 16-bit floating point (a.k.a FP16) computation. Please check out the example of FP16 in ResNet50 at /Examples/Image/Classification/ResNet/Python/TrainResNet_ImageNet_Distributed.py Notes on FP16 preview: * FP16 implementation on CPU is not optimized, and it's not supposed to be used in CPU inference directly. User needs to convert the model to 32-bit floating point before running on CPU. * Loss/Criterion for FP16 training needs to be 32bit for accumulation without overflow, using cast function. Please check the example above. * Readers do not have FP16 output unless using numpy to feed data, cast from FP32 to FP16 is needed. Please check the example above. * FP16 gradient aggregation is currently only implemented on GPU using NCCL2. Distributed training with FP16 with MPI is not supported. * FP16 math is a subset of current FP32 implementation. Some model may get Feature Not Implemented exception using FP16. * FP16 is currently not supported in BrainScript. Please use Python for FP16. To setup build and runtime environment on Windows: * Install [Visual Studio 2017](https://www.visualstudio.com/downloads/) with following workloads and components. From command line (use Community version installer as example): vs_community.exe --add Microsoft.VisualStudio.Workload.NativeDesktop --add Microsoft.VisualStudio.Workload.ManagedDesktop --add Microsoft.VisualStudio.Workload.Universal --add Microsoft.Component.PythonTools --add Microsoft.VisualStudio.Component.VC.Tools.14.11 * Install [NVidia CUDA 9](https://developer.nvidia.com/cuda-90-download-archive?target_os=Windows&target_arch=x86_64) * From PowerShell, run: /Tools/devInstall/Windows/DevInstall.ps1 * Start VCTools 14.11 command line, run: cmd /k "%VS2017INSTALLDIR%\VC\Auxiliary\Build\vcvarsall.bat" x64 --vcvars_ver=14.11 * Open /CNTK.sln from the VCTools 14.11 command line. Note that starting CNTK.sln other than VCTools 14.11 command line, would causes CUDA 9 [build error](https://developercommunity.visualstudio.com/content/problem/163758/vs-2017-155-doesnt-support-cuda-9.html). To setup build and runtime environment on Linux using docker, please build Unbuntu 16.04 docker image using Dockerfiles /Tools/docker. For other Linux systems, please refer to the Dockerfiles to setup dependent libraries for CNTK.
2018-01-23 03:58:56 +03:00
GENCODE_FLAGS := $(GENCODE_SM30) $(GENCODE_SM35) $(GENCODE_SM50) $(GENCODE_SM60) $(GENCODE_SM61) $(GENCODE_SM70)
2017-07-07 17:44:48 +03:00
endif
2017-07-07 19:05:29 +03:00
CXXFLAGS += -g -O4
LDFLAGS += -rdynamic
COMMON_FLAGS += -DNDEBUG -DNO_SYNC
CUFLAGS += -O3 -g -use_fast_math $(GENCODE_FLAGS)
endif
ifdef CNTK_CUDA_DEVICE_DEBUGINFO
CUFLAGS += -G
endif
# Create the library link options for the linker.
# LIBS_LIST must not be changed beyond this point.
LIBS:= $(addprefix -l,$(LIBS_LIST))
OBJDIR:= $(BUILD_TOP)/.build
BINDIR:= $(BUILD_TOP)/bin
LIBDIR:= $(BUILD_TOP)/lib
PYTHONDIR:= $(BUILD_TOP)/python
ORIGINLIBDIR:='$$ORIGIN/../lib'
ORIGINDIR:='$$ORIGIN'
2017-03-20 17:26:29 +03:00
########################################
# Components VERSION info
########################################
# CNTK version which should be used where CNTK version is required. Ex: print version or tag CNTK binaries.
CNTK_VERSION := $(BUILD_VERSION)
# Cntk Version banner is printed wherever CNTK_VERSION should be printed. ex: python -c 'import cntk;cntk.__version__'.
CNTK_VERSION_BANNER := $(CNTK_VERSION)
ifeq ("$(BUILD_PUBLIC)","no")
CNTK_VERSION_BANNER := $(CNTK_VERSION_BANNER)+
endif
# Cntk binaries (generated by build) are appended with CNTK_COMPONENT_VERSION. Ex: libCntk.Core-$(CNTK_COMPONENT_VERSION).dll
CNTK_COMPONENT_VERSION := $(CNTK_VERSION)
2017-03-20 17:26:29 +03:00
ifeq ("$(BUILDTYPE)","debug")
CNTK_COMPONENT_VERSION := $(CNTK_COMPONENT_VERSION)d
2017-03-20 17:26:29 +03:00
endif
CPPFLAGS += -DCNTK_VERSION="$(CNTK_VERSION)"
CPPFLAGS += -DCNTK_VERSION_BANNER="$(CNTK_VERSION_BANNER)"
2017-03-20 18:56:30 +03:00
CPPFLAGS += -DCNTK_COMPONENT_VERSION="$(CNTK_COMPONENT_VERSION)"
2017-03-20 18:43:43 +03:00
2017-03-20 17:26:29 +03:00
CNTKMATH:=Cntk.Math-$(CNTK_COMPONENT_VERSION)
RPATH=-Wl,-rpath,
########################################
2015-12-15 11:58:24 +03:00
# Build info
########################################
BUILDINFO:= $(SOURCEDIR)/CNTKv2LibraryDll/Generated/Linux/buildinfo.h
GENBUILD:=Tools/generate_build_info
BUILDINFO_OUTPUT := $(shell $(GENBUILD) $(BUILD_TOP)/Config.make && echo Success)
ifneq ("$(BUILDINFO_OUTPUT)","Success")
$(error Could not generate $(BUILDINFO))
endif
########################################
# Performance profiler library
########################################
2017-03-20 17:26:29 +03:00
PERF_PROFILER:=Cntk.PerformanceProfiler-$(CNTK_COMPONENT_VERSION)
PP_SRC =\
$(SOURCEDIR)/PerformanceProfilerDll/PerformanceProfiler.cpp \
$(SOURCEDIR)/Common/File.cpp \
$(SOURCEDIR)/Common/fileutil.cpp \
$(SOURCEDIR)/Common/ExceptionWithCallStack.cpp \
PP_OBJ := $(patsubst %.cpp, $(OBJDIR)/%.o, $(PP_SRC))
PERF_PROFILER_LIB:= $(LIBDIR)/lib$(PERF_PROFILER).so
ALL_LIBS += $(PERF_PROFILER_LIB)
PYTHON_LIBS += $(PERF_PROFILER_LIB)
JAVA_LIBS += $(PERF_PROFILER_LIB)
2018-06-06 18:38:29 +03:00
CSHARP_LIBS += $(PERF_PROFILER_LIB)
SRC += $(PP_SRC)
$(PERF_PROFILER_LIB): $(PP_OBJ)
@echo $(SEPARATOR)
@echo creating $@ for $(ARCH) with build type $(BUILDTYPE)
@mkdir -p $(dir $@)
$(CXX) $(LDFLAGS) -shared $(patsubst %,$(RPATH)%, $(ORIGINDIR)) -o $@ $^
########################################
# Math library
########################################
# Define all sources that need to be built
READER_SRC =\
2016-02-02 15:31:59 +03:00
$(SOURCEDIR)/Readers/ReaderLib/BlockRandomizer.cpp \
$(SOURCEDIR)/Readers/ReaderLib/Bundler.cpp \
2016-02-02 15:31:59 +03:00
$(SOURCEDIR)/Readers/ReaderLib/NoRandomizer.cpp \
2017-07-17 19:41:28 +03:00
$(SOURCEDIR)/Readers/ReaderLib/LTNoRandomizer.cpp \
$(SOURCEDIR)/Readers/ReaderLib/LTTumblingWindowRandomizer.cpp \
$(SOURCEDIR)/Readers/ReaderLib/LocalTimelineRandomizerBase.cpp \
2016-02-02 15:31:59 +03:00
$(SOURCEDIR)/Readers/ReaderLib/ReaderShim.cpp \
$(SOURCEDIR)/Readers/ReaderLib/ChunkRandomizer.cpp \
$(SOURCEDIR)/Readers/ReaderLib/SequenceRandomizer.cpp \
$(SOURCEDIR)/Readers/ReaderLib/SequencePacker.cpp \
$(SOURCEDIR)/Readers/ReaderLib/TruncatedBpttPacker.cpp \
2016-03-30 14:06:08 +03:00
$(SOURCEDIR)/Readers/ReaderLib/PackerBase.cpp \
$(SOURCEDIR)/Readers/ReaderLib/FramePacker.cpp \
$(SOURCEDIR)/Readers/ReaderLib/ReaderBase.cpp \
$(SOURCEDIR)/Readers/ReaderLib/Index.cpp \
$(SOURCEDIR)/Readers/ReaderLib/IndexBuilder.cpp \
$(SOURCEDIR)/Readers/ReaderLib/BufferedFileReader.cpp \
$(SOURCEDIR)/Readers/ReaderLib/DataDeserializerBase.cpp \
$(SOURCEDIR)/Readers/ReaderLib/ChunkCache.cpp \
$(SOURCEDIR)/Readers/ReaderLib/ReaderUtil.cpp \
COMMON_SRC =\
2015-12-15 11:58:24 +03:00
$(SOURCEDIR)/Common/Config.cpp \
$(SOURCEDIR)/Common/Globals.cpp \
2015-12-15 11:58:24 +03:00
$(SOURCEDIR)/Common/DataReader.cpp \
$(SOURCEDIR)/Common/DataWriter.cpp \
$(SOURCEDIR)/Common/ExceptionWithCallStack.cpp \
2015-12-15 11:58:24 +03:00
$(SOURCEDIR)/Common/Eval.cpp \
$(SOURCEDIR)/Common/File.cpp \
$(SOURCEDIR)/Common/TimerUtility.cpp \
$(SOURCEDIR)/Common/fileutil.cpp \
$(SOURCEDIR)/Common/Sequences.cpp \
$(SOURCEDIR)/Common/EnvironmentUtil.cpp \
MATH_SRC =\
$(SOURCEDIR)/Math/BatchNormalizationEngine.cpp \
$(SOURCEDIR)/Math/CUDAPageLockedMemAllocator.cpp \
$(SOURCEDIR)/Math/CPUMatrixFloat.cpp \
$(SOURCEDIR)/Math/CPUMatrixDouble.cpp \
CNTK support for CUDA 9 CNTK now supports CUDA 9/cuDNN 7. This requires an update to build environment to Ubuntu 16/GCC 5 for Linux, and Visual Studio 2017/VCTools 14.11 for Windows. With CUDA 9, CNTK also added a preview for 16-bit floating point (a.k.a FP16) computation. Please check out the example of FP16 in ResNet50 at /Examples/Image/Classification/ResNet/Python/TrainResNet_ImageNet_Distributed.py Notes on FP16 preview: * FP16 implementation on CPU is not optimized, and it's not supposed to be used in CPU inference directly. User needs to convert the model to 32-bit floating point before running on CPU. * Loss/Criterion for FP16 training needs to be 32bit for accumulation without overflow, using cast function. Please check the example above. * Readers do not have FP16 output unless using numpy to feed data, cast from FP32 to FP16 is needed. Please check the example above. * FP16 gradient aggregation is currently only implemented on GPU using NCCL2. Distributed training with FP16 with MPI is not supported. * FP16 math is a subset of current FP32 implementation. Some model may get Feature Not Implemented exception using FP16. * FP16 is currently not supported in BrainScript. Please use Python for FP16. To setup build and runtime environment on Windows: * Install [Visual Studio 2017](https://www.visualstudio.com/downloads/) with following workloads and components. From command line (use Community version installer as example): vs_community.exe --add Microsoft.VisualStudio.Workload.NativeDesktop --add Microsoft.VisualStudio.Workload.ManagedDesktop --add Microsoft.VisualStudio.Workload.Universal --add Microsoft.Component.PythonTools --add Microsoft.VisualStudio.Component.VC.Tools.14.11 * Install [NVidia CUDA 9](https://developer.nvidia.com/cuda-90-download-archive?target_os=Windows&target_arch=x86_64) * From PowerShell, run: /Tools/devInstall/Windows/DevInstall.ps1 * Start VCTools 14.11 command line, run: cmd /k "%VS2017INSTALLDIR%\VC\Auxiliary\Build\vcvarsall.bat" x64 --vcvars_ver=14.11 * Open /CNTK.sln from the VCTools 14.11 command line. Note that starting CNTK.sln other than VCTools 14.11 command line, would causes CUDA 9 [build error](https://developercommunity.visualstudio.com/content/problem/163758/vs-2017-155-doesnt-support-cuda-9.html). To setup build and runtime environment on Linux using docker, please build Unbuntu 16.04 docker image using Dockerfiles /Tools/docker. For other Linux systems, please refer to the Dockerfiles to setup dependent libraries for CNTK.
2018-01-23 03:58:56 +03:00
$(SOURCEDIR)/Math/CPUMatrixHalf.cpp \
$(SOURCEDIR)/Math/CPUMatrixTensorFloat.cpp \
$(SOURCEDIR)/Math/CPUMatrixTensorDouble.cpp \
$(SOURCEDIR)/Math/CPUMatrixTensorHalf.cpp \
$(SOURCEDIR)/Math/CPUMatrixTensorSpecial.cpp \
$(SOURCEDIR)/Math/CPURNGHandle.cpp \
$(SOURCEDIR)/Math/CPUSparseMatrix.cpp \
$(SOURCEDIR)/Math/ConvolutionEngine.cpp \
2016-01-05 21:42:38 +03:00
$(SOURCEDIR)/Math/MatrixQuantizerImpl.cpp \
2015-12-15 11:58:24 +03:00
$(SOURCEDIR)/Math/MatrixQuantizerCPU.cpp \
$(SOURCEDIR)/Math/Matrix.cpp \
$(SOURCEDIR)/Math/QuantizedMatrix.cpp \
2016-09-07 16:46:20 +03:00
$(SOURCEDIR)/Math/DataTransferer.cpp \
$(SOURCEDIR)/Math/RNGHandle.cpp \
2015-12-15 11:58:24 +03:00
$(SOURCEDIR)/Math/TensorView.cpp \
$(SOURCEDIR)/Math/NcclComm.cpp \
ifdef CUDA_PATH
MATH_SRC +=\
$(SOURCEDIR)/Math/CuDnnBatchNormalization.cu \
$(SOURCEDIR)/Math/CuDnnCommon.cu \
$(SOURCEDIR)/Math/CuDnnConvolutionEngine.cu \
$(SOURCEDIR)/Math/CuDnnRNN.cpp \
$(SOURCEDIR)/Math/GPUDataTransferer.cpp \
2015-12-15 11:58:24 +03:00
$(SOURCEDIR)/Math/GPUMatrix.cu \
$(SOURCEDIR)/Math/GPUSparseMatrix.cu \
$(SOURCEDIR)/Math/GPUTensor.cu \
2015-12-15 11:58:24 +03:00
$(SOURCEDIR)/Math/GPUWatcher.cu \
$(SOURCEDIR)/Math/GPURNGHandle.cu \
2015-12-15 11:58:24 +03:00
$(SOURCEDIR)/Math/MatrixQuantizerGPU.cu \
else
MATH_SRC +=\
2015-12-15 11:58:24 +03:00
$(SOURCEDIR)/Math/NoGPU.cpp
endif
MATH_SRC+=$(COMMON_SRC)
MATH_SRC+=$(READER_SRC)
MATH_OBJ := $(patsubst %.cu, $(OBJDIR)/%.o, $(patsubst %.cpp, $(OBJDIR)/%.o, $(MATH_SRC)))
CNTKMATH_LIB:= $(LIBDIR)/lib$(CNTKMATH).so
ALL_LIBS += $(CNTKMATH_LIB)
PYTHON_LIBS += $(CNTKMATH_LIB)
JAVA_LIBS += $(CNTKMATH_LIB)
2018-06-06 18:38:29 +03:00
CSHARP_LIBS += $(CNTKMATH_LIB)
SRC+=$(MATH_SRC)
$(CNTKMATH_LIB): $(MATH_OBJ) | $(PERF_PROFILER_LIB)
@echo $(SEPARATOR)
2015-12-15 11:58:24 +03:00
@echo creating $@ for $(ARCH) with build type $(BUILDTYPE)
@mkdir -p $(dir $@)
$(CXX) $(LDFLAGS) -shared $(patsubst %,-L%, $(LIBPATH) $(LIBDIR) $(GDK_NVML_LIB_PATH)) $(patsubst %,$(RPATH)%, $(ORIGINDIR) $(LIBPATH)) -o $@ $^ $(LIBS) -fopenmp -l$(PERF_PROFILER)
CNTK support for CUDA 9 CNTK now supports CUDA 9/cuDNN 7. This requires an update to build environment to Ubuntu 16/GCC 5 for Linux, and Visual Studio 2017/VCTools 14.11 for Windows. With CUDA 9, CNTK also added a preview for 16-bit floating point (a.k.a FP16) computation. Please check out the example of FP16 in ResNet50 at /Examples/Image/Classification/ResNet/Python/TrainResNet_ImageNet_Distributed.py Notes on FP16 preview: * FP16 implementation on CPU is not optimized, and it's not supposed to be used in CPU inference directly. User needs to convert the model to 32-bit floating point before running on CPU. * Loss/Criterion for FP16 training needs to be 32bit for accumulation without overflow, using cast function. Please check the example above. * Readers do not have FP16 output unless using numpy to feed data, cast from FP32 to FP16 is needed. Please check the example above. * FP16 gradient aggregation is currently only implemented on GPU using NCCL2. Distributed training with FP16 with MPI is not supported. * FP16 math is a subset of current FP32 implementation. Some model may get Feature Not Implemented exception using FP16. * FP16 is currently not supported in BrainScript. Please use Python for FP16. To setup build and runtime environment on Windows: * Install [Visual Studio 2017](https://www.visualstudio.com/downloads/) with following workloads and components. From command line (use Community version installer as example): vs_community.exe --add Microsoft.VisualStudio.Workload.NativeDesktop --add Microsoft.VisualStudio.Workload.ManagedDesktop --add Microsoft.VisualStudio.Workload.Universal --add Microsoft.Component.PythonTools --add Microsoft.VisualStudio.Component.VC.Tools.14.11 * Install [NVidia CUDA 9](https://developer.nvidia.com/cuda-90-download-archive?target_os=Windows&target_arch=x86_64) * From PowerShell, run: /Tools/devInstall/Windows/DevInstall.ps1 * Start VCTools 14.11 command line, run: cmd /k "%VS2017INSTALLDIR%\VC\Auxiliary\Build\vcvarsall.bat" x64 --vcvars_ver=14.11 * Open /CNTK.sln from the VCTools 14.11 command line. Note that starting CNTK.sln other than VCTools 14.11 command line, would causes CUDA 9 [build error](https://developercommunity.visualstudio.com/content/problem/163758/vs-2017-155-doesnt-support-cuda-9.html). To setup build and runtime environment on Linux using docker, please build Unbuntu 16.04 docker image using Dockerfiles /Tools/docker. For other Linux systems, please refer to the Dockerfiles to setup dependent libraries for CNTK.
2018-01-23 03:58:56 +03:00
# Any executable using Common or ReaderLib needs to link these libraries.
READER_LIBS := $(CNTKMATH_LIB) $(PERF_PROFILER_LIB)
L_READER_LIBS := -l$(CNTKMATH) -l$(PERF_PROFILER)
########################################
2016-06-11 22:21:15 +03:00
# CNTKLibrary
########################################
2016-06-11 22:21:15 +03:00
CNTK_COMMON_SRC =\
$(SOURCEDIR)/Common/BestGpu.cpp \
$(SOURCEDIR)/Common/MPIWrapper.cpp \
COMPUTATION_NETWORK_LIB_SRC =\
$(SOURCEDIR)/ComputationNetworkLib/ComputationNode.cpp \
$(SOURCEDIR)/ComputationNetworkLib/ComputationNodeScripting.cpp \
$(SOURCEDIR)/ComputationNetworkLib/InputAndParamNodes.cpp \
$(SOURCEDIR)/ComputationNetworkLib/RecurrentNodes.cpp \
$(SOURCEDIR)/ComputationNetworkLib/LinearAlgebraNodes.cpp \
2016-06-11 22:21:15 +03:00
$(SOURCEDIR)/ComputationNetworkLib/ReshapingNodes.cpp \
$(SOURCEDIR)/ComputationNetworkLib/RNNNodes.cpp \
2016-06-11 22:21:15 +03:00
$(SOURCEDIR)/ComputationNetworkLib/SpecialPurposeNodes.cpp \
$(SOURCEDIR)/ComputationNetworkLib/ComputationNetwork.cpp \
$(SOURCEDIR)/ComputationNetworkLib/ComputationNetworkEvaluation.cpp \
$(SOURCEDIR)/ComputationNetworkLib/ComputationNetworkAnalysis.cpp \
$(SOURCEDIR)/ComputationNetworkLib/ComputationNetworkEditing.cpp \
$(SOURCEDIR)/ComputationNetworkLib/ComputationNetworkBuilder.cpp \
$(SOURCEDIR)/ComputationNetworkLib/ComputationNetworkScripting.cpp \
2016-09-30 18:05:00 +03:00
$(SOURCEDIR)/ComputationNetworkLib/TrainingNodes.cpp \
2016-06-11 22:21:15 +03:00
SEQUENCE_TRAINING_LIB_SRC =\
$(SOURCEDIR)/SequenceTrainingLib/latticeforwardbackward.cpp \
$(SOURCEDIR)/SequenceTrainingLib/parallelforwardbackward.cpp \
ifdef CUDA_PATH
SEQUENCE_TRAINING_LIB_SRC +=\
$(SOURCEDIR)/Math/cudalatticeops.cu \
$(SOURCEDIR)/Math/cudalattice.cpp \
$(SOURCEDIR)/Math/cudalib.cpp \
else
SEQUENCE_TRAINING_LIB_SRC +=\
$(SOURCEDIR)/SequenceTrainingLib/latticeNoGPU.cpp \
endif
CNTKLIBRARY_COMMON_SRC =\
$(SOURCEDIR)/CNTKv2LibraryDll/BackCompat.cpp \
2016-06-11 22:21:15 +03:00
$(SOURCEDIR)/CNTKv2LibraryDll/Common.cpp \
$(SOURCEDIR)/CNTKv2LibraryDll/Function.cpp \
$(SOURCEDIR)/CNTKv2LibraryDll/PrimitiveFunction.cpp \
$(SOURCEDIR)/CNTKv2LibraryDll/CompositeFunction.cpp \
$(SOURCEDIR)/CNTKv2LibraryDll/UserDefinedFunction.cpp \
2016-06-11 22:21:15 +03:00
$(SOURCEDIR)/CNTKv2LibraryDll/NDArrayView.cpp \
$(SOURCEDIR)/CNTKv2LibraryDll/NDMask.cpp \
$(SOURCEDIR)/CNTKv2LibraryDll/Trainer.cpp \
2017-03-08 18:08:57 +03:00
$(SOURCEDIR)/CNTKv2LibraryDll/Evaluator.cpp \
2016-06-11 22:21:15 +03:00
$(SOURCEDIR)/CNTKv2LibraryDll/Utils.cpp \
$(SOURCEDIR)/CNTKv2LibraryDll/Value.cpp \
$(SOURCEDIR)/CNTKv2LibraryDll/Variable.cpp \
$(SOURCEDIR)/CNTKv2LibraryDll/Learner.cpp \
$(SOURCEDIR)/CNTKv2LibraryDll/Serialization.cpp \
$(SOURCEDIR)/CNTKv2LibraryDll/DistributedCommunicator.cpp \
2016-11-28 13:44:21 +03:00
$(SOURCEDIR)/CNTKv2LibraryDll/DistributedLearnerBase.cpp \
$(SOURCEDIR)/CNTKv2LibraryDll/DataParallelDistributedLearner.cpp \
2017-02-04 01:14:12 +03:00
$(SOURCEDIR)/CNTKv2LibraryDll/ProgressWriter.cpp \
$(SOURCEDIR)/CNTKv2LibraryDll/CNTKLibraryC.cpp \
$(SOURCEDIR)/CNTKv2LibraryDll/EvaluatorWrapper.cpp \
2016-10-25 01:33:31 +03:00
$(SOURCEDIR)/CNTKv2LibraryDll/proto/CNTK.pb.cc \
$(SOURCEDIR)/CNTKv2LibraryDll/tensorboard/tensorboard.pb.cc \
$(SOURCEDIR)/CNTKv2LibraryDll/tensorboard/TensorBoardFileWriter.cpp \
$(SOURCEDIR)/CNTKv2LibraryDll/tensorboard/TensorBoardUtils.cpp \
2018-06-28 18:38:36 +03:00
$(SOURCEDIR)/CNTKv2LibraryDll/proto/onnx/core/common/logging/capture.cc \
$(SOURCEDIR)/CNTKv2LibraryDll/proto/onnx/core/common/logging/logging.cc \
$(SOURCEDIR)/CNTKv2LibraryDll/proto/onnx/core/common/status.cc \
$(SOURCEDIR)/CNTKv2LibraryDll/proto/onnx/core/graph/graph.cc \
$(SOURCEDIR)/CNTKv2LibraryDll/proto/onnx/core/graph/graph_transformer.cc \
$(SOURCEDIR)/CNTKv2LibraryDll/proto/onnx/core/graph/model.cc \
$(SOURCEDIR)/CNTKv2LibraryDll/proto/onnx/core/graph/op.cc \
$(SOURCEDIR)/CNTKv2LibraryDll/proto/onnx/core/graph/tensorutils.cc \
$(SOURCEDIR)/CNTKv2LibraryDll/proto/onnx/onnx_repo/onnx/checker.cpp \
$(SOURCEDIR)/CNTKv2LibraryDll/proto/onnx/onnx_repo/onnx/common/assertions.cc \
$(SOURCEDIR)/CNTKv2LibraryDll/proto/onnx/onnx_repo/onnx/defs/controlflow/defs.cc \
$(SOURCEDIR)/CNTKv2LibraryDll/proto/onnx/onnx_repo/onnx/defs/experiments/defs.cc \
$(SOURCEDIR)/CNTKv2LibraryDll/proto/onnx/onnx_repo/onnx/defs/generator/defs.cc \
$(SOURCEDIR)/CNTKv2LibraryDll/proto/onnx/onnx_repo/onnx/defs/logical/defs.cc \
$(SOURCEDIR)/CNTKv2LibraryDll/proto/onnx/onnx_repo/onnx/defs/logical/old.cc \
$(SOURCEDIR)/CNTKv2LibraryDll/proto/onnx/onnx_repo/onnx/defs/math/defs.cc \
$(SOURCEDIR)/CNTKv2LibraryDll/proto/onnx/onnx_repo/onnx/defs/math/old.cc \
$(SOURCEDIR)/CNTKv2LibraryDll/proto/onnx/onnx_repo/onnx/defs/nn/defs.cc \
$(SOURCEDIR)/CNTKv2LibraryDll/proto/onnx/onnx_repo/onnx/defs/nn/old.cc \
$(SOURCEDIR)/CNTKv2LibraryDll/proto/onnx/onnx_repo/onnx/defs/reduction/defs.cc \
$(SOURCEDIR)/CNTKv2LibraryDll/proto/onnx/onnx_repo/onnx/defs/rnn/defs.cc \
$(SOURCEDIR)/CNTKv2LibraryDll/proto/onnx/onnx_repo/onnx/defs/rnn/old.cc \
$(SOURCEDIR)/CNTKv2LibraryDll/proto/onnx/onnx_repo/onnx/defs/tensor/defs.cc \
$(SOURCEDIR)/CNTKv2LibraryDll/proto/onnx/onnx_repo/onnx/defs/tensor/old.cc \
$(SOURCEDIR)/CNTKv2LibraryDll/proto/onnx/onnx_repo/onnx/defs/traditionalml/defs.cc \
$(SOURCEDIR)/CNTKv2LibraryDll/proto/onnx/onnx_repo/onnx/defs/data_type_utils.cc \
$(SOURCEDIR)/CNTKv2LibraryDll/proto/onnx/onnx_repo/onnx/defs/schema.cc \
$(SOURCEDIR)/CNTKv2LibraryDll/proto/onnx/onnx_repo/onnx/onnx-ml.pb.cc \
$(SOURCEDIR)/CNTKv2LibraryDll/proto/onnx/onnx_repo/onnx/onnx-operators-ml.pb.cc \
2017-10-10 11:01:43 +03:00
$(SOURCEDIR)/CNTKv2LibraryDll/proto/onnx/Operators.cpp \
2018-03-06 00:13:03 +03:00
$(SOURCEDIR)/CNTKv2LibraryDll/proto/onnx/RNNHelper.cpp \
$(SOURCEDIR)/CNTKv2LibraryDll/proto/onnx/CNTKToONNX.cpp \
2017-10-10 11:01:43 +03:00
$(SOURCEDIR)/CNTKv2LibraryDll/proto/onnx/ONNXToCNTK.cpp \
$(SOURCEDIR)/CNTKv2LibraryDll/proto/onnx/ONNX.cpp \
CNTKLIBRARY_SRC =\
$(SOURCEDIR)/CNTKv2LibraryDll/ComputeInputStatistics.cpp \
$(SOURCEDIR)/CNTKv2LibraryDll/MinibatchSource.cpp \
$(SOURCEDIR)/CNTKv2LibraryDll/TrainingSession.cpp \
2016-06-11 22:21:15 +03:00
CNTKLIBRARY_SRC+=$(CNTKLIBRARY_COMMON_SRC)
2016-06-11 22:21:15 +03:00
CNTKLIBRARY_SRC+=$(CNTK_COMMON_SRC)
CNTKLIBRARY_SRC+=$(COMPUTATION_NETWORK_LIB_SRC)
CNTKLIBRARY_SRC+=$(SEQUENCE_TRAINING_LIB_SRC)
CNTKLIBRARY:=Cntk.Core-$(CNTK_COMPONENT_VERSION)
2016-06-11 22:21:15 +03:00
2016-10-25 01:33:31 +03:00
CNTKLIBRARY_OBJ:=\
$(patsubst %.cu, $(OBJDIR)/%.o, $(filter %.cu, $(CNTKLIBRARY_SRC))) \
$(patsubst %.pb.cc, $(OBJDIR)/%.pb.o, $(filter %.pb.cc, $(CNTKLIBRARY_SRC))) \
2018-06-28 18:38:36 +03:00
$(patsubst %.cpp, $(OBJDIR)/%.o, $(filter %.cpp, $(CNTKLIBRARY_SRC))) \
$(patsubst %.cc, $(OBJDIR)/%.o, $(filter %.cc, $(CNTKLIBRARY_SRC)))
2016-06-11 22:21:15 +03:00
CNTKLIBRARY_LIB:=$(LIBDIR)/lib$(CNTKLIBRARY).so
ALL_LIBS+=$(CNTKLIBRARY_LIB)
PYTHON_LIBS+=$(CNTKLIBRARY_LIB)
JAVA_LIBS+=$(CNTKLIBRARY_LIB)
2018-06-06 18:38:29 +03:00
CSHARP_LIBS+=$(CNTKLIBRARY_LIB)
2016-06-11 22:21:15 +03:00
SRC+=$(CNTKLIBRARY_SRC)
$(CNTKLIBRARY_LIB): $(CNTKLIBRARY_OBJ) | $(CNTKMATH_LIB)
@echo $(SEPARATOR)
@mkdir -p $(dir $@)
2016-10-25 01:33:31 +03:00
@echo building $@ for $(ARCH) with build type $(BUILDTYPE)
$(CXX) $(LDFLAGS) -shared $(patsubst %,-L%, $(LIBDIR) $(LIBPATH) $(GDK_NVML_LIB_PATH)) $(patsubst %,$(RPATH)%, $(ORIGINDIR) $(LIBPATH)) -o $@ $^ $(LIBS) -l$(CNTKMATH) $(PROTOBUF_PATH)/lib/libprotobuf.a -ldl -fopenmp
########################################
# C++ extensibility examples library
########################################
CPP_EXTENSIBILITY_EXAMPLES_LIBRARY_SRC =\
$(SOURCEDIR)/../Examples/Extensibility/CPPLib/CPPExtensibilityExamplesLibrary.cpp \
CPP_EXTENSIBILITY_EXAMPLES_LIBRARY_OBJ := $(patsubst %.cpp, $(OBJDIR)/%.o, $(CPP_EXTENSIBILITY_EXAMPLES_LIBRARY_SRC))
CPP_EXTENSIBILITY_EXAMPLES_LIB:= $(LIBDIR)/Cntk.ExtensibilityExamples-$(CNTK_COMPONENT_VERSION).so
ALL_LIBS += $(CPP_EXTENSIBILITY_EXAMPLES_LIB)
PYTHON_LIBS += $(CPP_EXTENSIBILITY_EXAMPLES_LIB)
SRC += $(CPP_EXTENSIBILITY_EXAMPLES_LIBRARY_SRC)
$(CPP_EXTENSIBILITY_EXAMPLES_LIB): $(CPP_EXTENSIBILITY_EXAMPLES_LIBRARY_OBJ) | $(CNTKLIBRARY_LIB)
@echo $(SEPARATOR)
@echo creating $@ for $(ARCH) with build type $(BUILDTYPE)
@mkdir -p $(dir $@)
$(CXX) $(LDFLAGS) -shared $(patsubst %,-L%, $(LIBDIR)) $(patsubst %,$(RPATH)%, $(LIBDIR) $(ORIGINDIR)) -o $@ $^ -l$(CNTKLIBRARY)
2016-06-11 22:21:15 +03:00
##############################################
# Binary convolution library
##############################################
2018-01-27 04:17:58 +03:00
ifdef HALIDE_PATH
INCLUDEPATH += $(HALIDE_PATH)/include
BINARY_CONVOLUTION_LIBRARY_SRC =\
$(SOURCEDIR)/Extensibility/BinaryConvolutionLib/BinaryConvolutionLib.cpp \
BINARY_CONVOLUTION_LIBRARY_OBJ := $(patsubst %.cpp, $(OBJDIR)/%.o, $(BINARY_CONVOLUTION_LIBRARY_SRC))
BINARY_CONVOLUTION_LIB:= $(LIBDIR)/Cntk.BinaryConvolution-$(CNTK_COMPONENT_VERSION).so
ALL_LIBS += $(BINARY_CONVOLUTION_LIB)
PYTHON_LIBS += $(BINARY_CONVOLUTION_LIB)
SRC += $(BINARY_CONVOLUTION_LIBRARY_SRC)
$(BINARY_CONVOLUTION_LIB): $(BINARY_CONVOLUTION_LIBRARY_OBJ) | $(CNTKLIBRARY_LIB)
@echo $(SEPARATOR)
@echo creating $@ for $(ARCH) with build type $(BUILDTYPE)
@mkdir -p $(dir $@)
$(CXX) $(LDFLAGS) -shared $(patsubst %,-L%, $(LIBDIR)) $(patsubst %,$(RPATH)%, $(LIBDIR) $(ORIGINDIR)) -o $@ $^ -l$(CNTKLIBRARY) $(HALIDE_PATH)/bin/libHalide.so
endif
2017-08-07 19:34:57 +03:00
##############################################
# Native implementation of the Proposal Layer
##############################################
PROPOSAL_LAYER_LIBRARY_SRC =\
$(SOURCEDIR)/../Examples/Extensibility/ProposalLayer/ProposalLayerLib/ProposalLayerLib.cpp \
PROPOSAL_LAYER_LIBRARY_OBJ := $(patsubst %.cpp, $(OBJDIR)/%.o, $(PROPOSAL_LAYER_LIBRARY_SRC))
PROPOSAL_LAYER_LIB:= $(LIBDIR)/Cntk.ProposalLayerLib-$(CNTK_COMPONENT_VERSION).so
ALL_LIBS += $(PROPOSAL_LAYER_LIB)
PYTHON_LIBS += $(PROPOSAL_LAYER_LIB)
SRC += $(PROPOSAL_LAYER_LIBRARY_SRC)
$(PROPOSAL_LAYER_LIB): $(PROPOSAL_LAYER_LIBRARY_OBJ) | $(CNTKLIBRARY_LIB)
@echo $(SEPARATOR)
@echo creating $@ for $(ARCH) with build type $(BUILDTYPE)
@mkdir -p $(dir $@)
$(CXX) $(LDFLAGS) -shared $(CXXFLAGS) $(patsubst %,-L%, $(LIBDIR) $(LIBPATH)) $(patsubst %,$(RPATH)%, $(LIBDIR) $(LIBPATH) $(ORIGINDIR)) -o $@ $^ -l$(CNTKLIBRARY)
2017-08-07 19:34:57 +03:00
########################################
# LibEval
########################################
2017-03-20 17:26:29 +03:00
EVAL:=Cntk.Eval-$(CNTK_COMPONENT_VERSION)
SGDLIB_SRC=\
2016-11-01 16:59:10 +03:00
$(SOURCEDIR)/SGDLib/ASGDHelper.cpp \
$(SOURCEDIR)/SGDLib/Profiler.cpp \
$(SOURCEDIR)/SGDLib/SGD.cpp \
$(SOURCEDIR)/SGDLib/PostComputingActions.cpp \
2016-10-25 01:33:31 +03:00
SGDLIB_SRC+=$(CNTKLIBRARY_COMMON_SRC)
EVAL_SRC=\
$(SOURCEDIR)/EvalDll/CNTKEval.cpp \
$(SOURCEDIR)/CNTK/BrainScript/BrainScriptEvaluator.cpp \
$(SOURCEDIR)/CNTK/BrainScript/BrainScriptParser.cpp \
$(SOURCEDIR)/CNTK/ModelEditLanguage.cpp \
$(SOURCEDIR)/ActionsLib/EvalActions.cpp \
$(SOURCEDIR)/ActionsLib/NetworkFactory.cpp \
$(SOURCEDIR)/ActionsLib/NetworkDescriptionLanguage.cpp \
$(SOURCEDIR)/ActionsLib/SimpleNetworkBuilder.cpp \
$(SOURCEDIR)/ActionsLib/NDLNetworkBuilder.cpp \
EVAL_SRC+=$(SGDLIB_SRC)
EVAL_SRC+=$(COMPUTATION_NETWORK_LIB_SRC)
EVAL_SRC+=$(CNTK_COMMON_SRC)
EVAL_SRC+=$(SEQUENCE_TRAINING_LIB_SRC)
EVAL_OBJ:=\
$(patsubst %.cu, $(OBJDIR)/%.o, $(filter %.cu, $(EVAL_SRC))) \
$(patsubst %.pb.cc, $(OBJDIR)/%.pb.o, $(filter %.pb.cc, $(EVAL_SRC))) \
2018-06-28 18:38:36 +03:00
$(patsubst %.cpp, $(OBJDIR)/%.o, $(filter %.cpp, $(EVAL_SRC))) \
$(patsubst %.cc, $(OBJDIR)/%.o, $(filter %.cc, $(CNTKLIBRARY_SRC)))
EVAL_LIB:=$(LIBDIR)/lib$(EVAL).so
ALL_LIBS+=$(EVAL_LIB)
SRC+=$(EVAL_SRC)
# only set lib name when asgd is true
ifeq ("$(CNTK_ENABLE_ASGD)","true")
MULTIVERSO_LIB:=$(LIBDIR)/libmultiverso.so
endif
$(EVAL_LIB): $(EVAL_OBJ) | $(CNTKMATH_LIB) $(MULTIVERSO_LIB)
@echo $(SEPARATOR)
@mkdir -p $(dir $@)
@echo Building $(EVAL_LIB) for $(ARCH) with build type $(BUILDTYPE)
$(CXX) $(LDFLAGS) -shared $(patsubst %,-L%, $(LIBDIR) $(LIBPATH) $(GDK_NVML_LIB_PATH)) $(patsubst %,$(RPATH)%, $(ORIGINDIR) $(LIBPATH)) -o $@ $^ $(LIBS) -l$(CNTKMATH) -ldl $(lMULTIVERSO) $(PROTOBUF_PATH)/lib/libprotobuf.a
########################################
# Eval Sample clients
########################################
EVAL_CLIENT:=$(BINDIR)/cppevalclient
EVAL_CLIENT_SRC=\
2017-07-18 19:25:03 +03:00
$(SOURCEDIR)/../Examples/Evaluation/LegacyEvalDll/CPPEvalClient/CPPEvalClient.cpp
EVAL_CLIENT_OBJ:=$(patsubst %.cpp, $(OBJDIR)/%.o, $(EVAL_CLIENT_SRC))
ALL+=$(EVAL_CLIENT)
SRC+=$(EVAL_CLIENT_SRC)
$(EVAL_CLIENT): $(EVAL_CLIENT_OBJ) | $(EVAL_LIB) $(READER_LIBS)
@echo $(SEPARATOR)
@mkdir -p $(dir $@)
@echo building $(EVAL_CLIENT) for $(ARCH) with build type $(BUILDTYPE)
$(CXX) $(LDFLAGS) $(patsubst %,-L%, $(LIBDIR) $(LIBPATH) $(GDK_NVML_LIB_PATH)) $(patsubst %,$(RPATH)%, $(ORIGINLIBDIR) $(LIBPATH)) -o $@ $^ $(LIBS) -l$(EVAL) $(L_READER_LIBS) $(lMULTIVERSO)
2016-06-11 22:21:15 +03:00
EVAL_EXTENDED_CLIENT:=$(BINDIR)/cppevalextendedclient
2016-06-11 22:21:15 +03:00
EVAL_EXTENDED_CLIENT_SRC=\
2017-07-18 19:25:03 +03:00
$(SOURCEDIR)/../Examples/Evaluation/LegacyEvalDll/CPPEvalExtendedClient/CPPEvalExtendedClient.cpp
EVAL_EXTENDED_CLIENT_OBJ:=$(patsubst %.cpp, $(OBJDIR)/%.o, $(EVAL_EXTENDED_CLIENT_SRC))
ALL+=$(EVAL_EXTENDED_CLIENT)
SRC+=$(EVAL_EXTENDED_CLIENT_SRC)
$(EVAL_EXTENDED_CLIENT): $(EVAL_EXTENDED_CLIENT_OBJ) | $(EVAL_LIB) $(READER_LIBS)
@echo $(SEPARATOR)
@mkdir -p $(dir $@)
@echo building $(EVAL_EXTENDED_CLIENT) for $(ARCH) with build type $(BUILDTYPE)
$(CXX) $(LDFLAGS) $(patsubst %,-L%, $(LIBDIR) $(LIBPATH) $(GDK_NVML_LIB_PATH)) $(patsubst %,$(RPATH)%, $(ORIGINLIBDIR) $(LIBPATH)) -o $@ $^ $(LIBS) -l$(EVAL) $(L_READER_LIBS) $(lMULTIVERSO)
2016-10-20 21:19:28 +03:00
########################################
# Eval V2 Sample client
########################################
CNTKLIBRARY_CPP_EVAL_EXAMPLES:=$(BINDIR)/CNTKLibraryCPPEvalExamples
2016-10-20 21:19:28 +03:00
2018-01-12 11:34:03 +03:00
ifdef CUDA_PATH
CNTKLIBRARY_CPP_EVAL_EXAMPLES_SRC=\
$(SOURCEDIR)/../Examples/Evaluation/CNTKLibraryCPPEvalGPUExamples/CNTKLibraryCPPEvalGPUExamples.cpp\
$(SOURCEDIR)/../Examples/Evaluation/CNTKLibraryCPPEvalCPUOnlyExamples/CNTKLibraryCPPEvalExamples.cpp
2018-01-12 11:34:03 +03:00
else
CNTKLIBRARY_CPP_EVAL_EXAMPLES_SRC=\
$(SOURCEDIR)/../Examples/Evaluation/CNTKLibraryCPPEvalCPUOnlyExamples/CNTKLibraryCPPEvalCPUOnlyExamples.cpp\
$(SOURCEDIR)/../Examples/Evaluation/CNTKLibraryCPPEvalCPUOnlyExamples/CNTKLibraryCPPEvalExamples.cpp
2018-01-12 11:34:03 +03:00
endif
2016-10-20 21:19:28 +03:00
CNTKLIBRARY_CPP_EVAL_EXAMPLES_OBJ:=$(patsubst %.cpp, $(OBJDIR)/%.o, $(CNTKLIBRARY_CPP_EVAL_EXAMPLES_SRC))
2016-10-20 21:19:28 +03:00
ALL+=$(CNTKLIBRARY_CPP_EVAL_EXAMPLES)
SRC+=$(CNTKLIBRARY_CPP_EVAL_EXAMPLES_SRC)
2016-10-20 21:19:28 +03:00
$(CNTKLIBRARY_CPP_EVAL_EXAMPLES): $(CNTKLIBRARY_CPP_EVAL_EXAMPLES_OBJ) | $(CNTKLIBRARY_LIB) $(READER_LIBS)
2016-10-20 21:19:28 +03:00
@echo $(SEPARATOR)
@mkdir -p $(dir $@)
@echo building $(CNTKLIBRARY_CPP_EVAL_EXAMPLES) for $(ARCH) with build type $(BUILDTYPE)
$(CXX) $(LDFLAGS) $(patsubst %,-L%, $(LIBDIR) $(LIBPATH) $(GDK_NVML_LIB_PATH)) $(patsubst %,$(RPATH)%, $(ORIGINLIBDIR) $(LIBPATH)) -o $@ $^ $(LIBS) -l$(CNTKLIBRARY) $(L_READER_LIBS)
########################################
CNTK support for CUDA 9 CNTK now supports CUDA 9/cuDNN 7. This requires an update to build environment to Ubuntu 16/GCC 5 for Linux, and Visual Studio 2017/VCTools 14.11 for Windows. With CUDA 9, CNTK also added a preview for 16-bit floating point (a.k.a FP16) computation. Please check out the example of FP16 in ResNet50 at /Examples/Image/Classification/ResNet/Python/TrainResNet_ImageNet_Distributed.py Notes on FP16 preview: * FP16 implementation on CPU is not optimized, and it's not supposed to be used in CPU inference directly. User needs to convert the model to 32-bit floating point before running on CPU. * Loss/Criterion for FP16 training needs to be 32bit for accumulation without overflow, using cast function. Please check the example above. * Readers do not have FP16 output unless using numpy to feed data, cast from FP32 to FP16 is needed. Please check the example above. * FP16 gradient aggregation is currently only implemented on GPU using NCCL2. Distributed training with FP16 with MPI is not supported. * FP16 math is a subset of current FP32 implementation. Some model may get Feature Not Implemented exception using FP16. * FP16 is currently not supported in BrainScript. Please use Python for FP16. To setup build and runtime environment on Windows: * Install [Visual Studio 2017](https://www.visualstudio.com/downloads/) with following workloads and components. From command line (use Community version installer as example): vs_community.exe --add Microsoft.VisualStudio.Workload.NativeDesktop --add Microsoft.VisualStudio.Workload.ManagedDesktop --add Microsoft.VisualStudio.Workload.Universal --add Microsoft.Component.PythonTools --add Microsoft.VisualStudio.Component.VC.Tools.14.11 * Install [NVidia CUDA 9](https://developer.nvidia.com/cuda-90-download-archive?target_os=Windows&target_arch=x86_64) * From PowerShell, run: /Tools/devInstall/Windows/DevInstall.ps1 * Start VCTools 14.11 command line, run: cmd /k "%VS2017INSTALLDIR%\VC\Auxiliary\Build\vcvarsall.bat" x64 --vcvars_ver=14.11 * Open /CNTK.sln from the VCTools 14.11 command line. Note that starting CNTK.sln other than VCTools 14.11 command line, would causes CUDA 9 [build error](https://developercommunity.visualstudio.com/content/problem/163758/vs-2017-155-doesnt-support-cuda-9.html). To setup build and runtime environment on Linux using docker, please build Unbuntu 16.04 docker image using Dockerfiles /Tools/docker. For other Linux systems, please refer to the Dockerfiles to setup dependent libraries for CNTK.
2018-01-23 03:58:56 +03:00
# Eval V2 Sample test
########################################
CNTKLIBRARY_CPP_EVAL_TEST:=$(BINDIR)/CNTKLibraryCPPEvalExamplesTest
CNTKLIBRARY_CPP_EVAL_TEST_SRC=\
$(SOURCEDIR)/../Examples/Evaluation/CNTKLibraryCPPEvalCPUOnlyExamples/CNTKLibraryCPPEvalExamples.cpp\
$(SOURCEDIR)/../Tests/EndToEndTests/EvalClientTests/CNTKLibraryCPPEvalExamplesTest/CNTKLibraryCPPEvalExamplesTest.cpp\
$(SOURCEDIR)/../Tests/EndToEndTests/EvalClientTests/CNTKLibraryCPPEvalExamplesTest/EvalMultithreads.cpp\
$(SOURCEDIR)/../Tests/EndToEndTests/CNTKv2Library/Common/Common.cpp
CNTKLIBRARY_CPP_EVAL_TEST_OBJ:=$(patsubst %.cpp, $(OBJDIR)/%.o, $(CNTKLIBRARY_CPP_EVAL_TEST_SRC))
ALL+=$(CNTKLIBRARY_CPP_EVAL_TEST)
SRC+=$(CNTKLIBRARY_CPP_EVAL_TEST_SRC)
$(CNTKLIBRARY_CPP_EVAL_TEST): $(CNTKLIBRARY_CPP_EVAL_TEST_OBJ) | $(CNTKLIBRARY_LIB) $(READER_LIBS)
@mkdir -p $(dir $@)
@echo building $(CNTKLIBRARY_CPP_EVAL_TEST) for $(ARCH) with build type $(BUILDTYPE)
$(CXX) $(LDFLAGS) $(patsubst %,-L%, $(LIBDIR) $(LIBPATH) $(GDK_NVML_LIB_PATH)) $(patsubst %,$(RPATH)%, $(ORIGINLIBDIR) $(LIBPATH)) -o $@ $^ $(LIBS) -l$(CNTKLIBRARY) $(L_READER_LIBS)
2016-10-20 21:19:28 +03:00
########################################
# HTKMLFReader plugin
########################################
HTKMLFREADER_SRC =\
$(SOURCEDIR)/Readers/HTKMLFReader/Exports.cpp \
$(SOURCEDIR)/Readers/HTKMLFReader/DataWriterLocal.cpp \
2015-12-15 11:58:24 +03:00
$(SOURCEDIR)/Readers/HTKMLFReader/HTKMLFReader.cpp \
$(SOURCEDIR)/Readers/HTKMLFReader/HTKMLFWriter.cpp \
2015-12-15 11:58:24 +03:00
HTKMLFREADER_OBJ := $(patsubst %.cpp, $(OBJDIR)/%.o, $(HTKMLFREADER_SRC))
2017-03-20 17:26:29 +03:00
HTKMLFREADER:=$(LIBDIR)/Cntk.Reader.HTKMLF-$(CNTK_COMPONENT_VERSION).so
ALL_LIBS+=$(HTKMLFREADER)
2015-12-15 11:58:24 +03:00
SRC+=$(HTKMLFREADER_SRC)
2017-03-20 17:26:29 +03:00
$(HTKMLFREADER): $(HTKMLFREADER_OBJ) | $(CNTKMATH_LIB)
@echo $(SEPARATOR)
$(CXX) $(LDFLAGS) -shared $(patsubst %,-L%, $(LIBDIR) $(LIBPATH)) $(patsubst %,$(RPATH)%, $(ORIGINDIR) $(LIBPATH)) -o $@ $^ -l$(CNTKMATH)
2016-04-28 16:50:37 +03:00
########################################
# CompositeDataReader plugin
########################################
COMPOSITEDATAREADER_SRC =\
$(SOURCEDIR)/Readers/CompositeDataReader/CompositeDataReader.cpp \
2016-04-29 14:54:54 +03:00
$(SOURCEDIR)/Readers/CompositeDataReader/Exports.cpp \
2016-04-28 16:50:37 +03:00
COMPOSITEDATAREADER_OBJ := $(patsubst %.cpp, $(OBJDIR)/%.o, $(COMPOSITEDATAREADER_SRC))
2017-03-21 22:39:28 +03:00
COMPOSITEDATAREADER:=$(LIBDIR)/Cntk.Composite-$(CNTK_COMPONENT_VERSION).so
ALL_LIBS+=$(COMPOSITEDATAREADER)
PYTHON_LIBS+=$(COMPOSITEDATAREADER)
2016-04-28 16:50:37 +03:00
SRC+=$(COMPOSITEDATAREADER_SRC)
2017-03-20 17:26:29 +03:00
$(COMPOSITEDATAREADER): $(COMPOSITEDATAREADER_OBJ) | $(CNTKMATH_LIB)
2016-04-28 16:50:37 +03:00
@echo $(SEPARATOR)
$(CXX) $(LDFLAGS) -shared $(patsubst %,-L%, $(LIBDIR) $(LIBPATH)) $(patsubst %,$(RPATH)%, $(ORIGINDIR) $(LIBPATH)) -o $@ $^ -l$(CNTKMATH)
########################################
2016-06-06 16:23:39 +03:00
# HTKDeserializers plugin
########################################
2016-06-06 16:23:39 +03:00
HTKDESERIALIZERS_SRC =\
$(SOURCEDIR)/Readers/HTKMLFReader/DataWriterLocal.cpp \
$(SOURCEDIR)/Readers/HTKMLFReader/HTKMLFWriter.cpp \
2016-06-06 16:23:39 +03:00
$(SOURCEDIR)/Readers/HTKDeserializers/ConfigHelper.cpp \
$(SOURCEDIR)/Readers/HTKDeserializers/Exports.cpp \
$(SOURCEDIR)/Readers/HTKDeserializers/HTKDeserializer.cpp \
2017-11-25 04:25:58 +03:00
$(SOURCEDIR)/Readers/HTKDeserializers/LatticeDeserializer.cpp \
2017-12-27 06:31:56 +03:00
$(SOURCEDIR)/Readers/HTKDeserializers/LatticeIndexBuilder.cpp \
2016-06-06 16:23:39 +03:00
$(SOURCEDIR)/Readers/HTKDeserializers/HTKMLFReader.cpp \
2017-03-10 17:23:55 +03:00
$(SOURCEDIR)/Readers/HTKDeserializers/MLFDeserializer.cpp \
$(SOURCEDIR)/Readers/HTKDeserializers/MLFIndexBuilder.cpp \
2018-06-06 05:37:28 +03:00
$(SOURCEDIR)/Readers/HTKDeserializers/MLFBinaryDeserializer.cpp \
$(SOURCEDIR)/Readers/HTKDeserializers/MLFBinaryIndexBuilder.cpp \
2017-03-10 17:23:55 +03:00
$(SOURCEDIR)/Readers/HTKDeserializers/MLFUtils.cpp \
2016-06-06 16:23:39 +03:00
HTKDESERIALIZERS_OBJ := $(patsubst %.cpp, $(OBJDIR)/%.o, $(HTKDESERIALIZERS_SRC))
2017-03-21 19:34:43 +03:00
HTKDESERIALIZERS:=$(LIBDIR)/Cntk.Deserializers.HTK-$(CNTK_COMPONENT_VERSION).so
ALL_LIBS+=$(HTKDESERIALIZERS)
PYTHON_LIBS+=$(HTKDESERIALIZERS)
2016-06-06 16:23:39 +03:00
SRC+=$(HTKDESERIALIZERS_SRC)
2017-03-20 17:26:29 +03:00
$(HTKDESERIALIZERS): $(HTKDESERIALIZERS_OBJ) | $(CNTKMATH_LIB)
@echo $(SEPARATOR)
$(CXX) $(LDFLAGS) -shared $(patsubst %,-L%, $(LIBDIR) $(LIBPATH)) $(patsubst %,$(RPATH)%, $(ORIGINDIR) $(LIBPATH)) -o $@ $^ -l$(CNTKMATH)
########################################
# LMSequenceReader plugin
########################################
LMSEQUENCEREADER_SRC =\
2015-12-15 11:58:24 +03:00
$(SOURCEDIR)/Readers/LMSequenceReader/Exports.cpp \
$(SOURCEDIR)/Readers/LMSequenceReader/SequenceParser.cpp \
$(SOURCEDIR)/Readers/LMSequenceReader/SequenceReader.cpp \
$(SOURCEDIR)/Readers/LMSequenceReader/SequenceWriter.cpp \
LMSEQUENCEREADER_OBJ := $(patsubst %.cpp, $(OBJDIR)/%.o, $(LMSEQUENCEREADER_SRC))
2017-03-20 17:26:29 +03:00
LMSEQUENCEREADER:= $(LIBDIR)/Cntk.Reader.LMSequence-$(CNTK_COMPONENT_VERSION).so
ALL_LIBS+=$(LMSEQUENCEREADER)
SRC+=$(LMSEQUENCEREADER_SRC)
$(LMSEQUENCEREADER): $(LMSEQUENCEREADER_OBJ) | $(CNTKMATH_LIB)
@echo $(SEPARATOR)
$(CXX) $(LDFLAGS) -shared $(patsubst %,-L%, $(LIBDIR) $(LIBPATH)) $(patsubst %,$(RPATH)%, $(ORIGINDIR) $(LIBPATH)) -o $@ $^ -l$(CNTKMATH)
########################################
# LUSequenceReader plugin
########################################
LUSEQUENCEREADER_SRC =\
2015-12-15 11:58:24 +03:00
$(SOURCEDIR)/Readers/LUSequenceReader/Exports.cpp \
$(SOURCEDIR)/Readers/LUSequenceReader/DataWriterLocal.cpp \
2015-12-15 11:58:24 +03:00
$(SOURCEDIR)/Readers/LUSequenceReader/LUSequenceParser.cpp \
$(SOURCEDIR)/Readers/LUSequenceReader/LUSequenceReader.cpp \
$(SOURCEDIR)/Readers/LUSequenceReader/LUSequenceWriter.cpp \
LUSEQUENCEREADER_OBJ := $(patsubst %.cpp, $(OBJDIR)/%.o, $(LUSEQUENCEREADER_SRC))
2017-03-20 17:26:29 +03:00
LUSEQUENCEREADER:=$(LIBDIR)/Cntk.Reader.LUSequence-$(CNTK_COMPONENT_VERSION).so
ALL_LIBS+=$(LUSEQUENCEREADER)
SRC+=$(LUSEQUENCEREADER_SRC)
$(LUSEQUENCEREADER): $(LUSEQUENCEREADER_OBJ) | $(CNTKMATH_LIB)
@echo $(SEPARATOR)
$(CXX) $(LDFLAGS) -shared $(patsubst %,-L%, $(LIBDIR) $(LIBPATH)) $(patsubst %,$(RPATH)%, $(ORIGINDIR) $(LIBPATH)) -o $@ $^ -l$(CNTKMATH)
########################################
# UCIFastReader plugin
########################################
UCIFASTREADER_SRC =\
2015-12-15 11:58:24 +03:00
$(SOURCEDIR)/Readers/UCIFastReader/Exports.cpp \
$(SOURCEDIR)/Readers/UCIFastReader/UCIFastReader.cpp \
$(SOURCEDIR)/Readers/UCIFastReader/UCIParser.cpp \
UCIFASTREADER_OBJ := $(patsubst %.cpp, $(OBJDIR)/%.o, $(UCIFASTREADER_SRC))
2017-03-20 17:26:29 +03:00
UCIFASTREADER:=$(LIBDIR)/Cntk.Reader.UCIFast-$(CNTK_COMPONENT_VERSION).so
ALL_LIBS += $(UCIFASTREADER)
SRC+=$(UCIFASTREADER_SRC)
$(UCIFASTREADER): $(UCIFASTREADER_OBJ) | $(CNTKMATH_LIB)
@echo $(SEPARATOR)
$(CXX) $(LDFLAGS) -shared $(patsubst %,-L%, $(LIBDIR) $(LIBPATH)) $(patsubst %,$(RPATH)%, $(ORIGINDIR) $(LIBPATH)) -o $@ $^ -l$(CNTKMATH)
########################################
# LibSVMBinaryReader plugin
########################################
LIBSVMBINARYREADER_SRC =\
$(SOURCEDIR)/Readers/LibSVMBinaryReader/Exports.cpp \
$(SOURCEDIR)/Readers/LibSVMBinaryReader/LibSVMBinaryReader.cpp \
LIBSVMBINARYREADER_OBJ := $(patsubst %.cpp, $(OBJDIR)/%.o, $(LIBSVMBINARYREADER_SRC))
2017-03-20 17:26:29 +03:00
LIBSVMBINARYREADER:=$(LIBDIR)/Cntk.Reader.SVMBinary-$(CNTK_COMPONENT_VERSION).so
ALL_LIBS += $(LIBSVMBINARYREADER)
SRC+=$(LIBSVMBINARYREADER_SRC)
$(LIBSVMBINARYREADER): $(LIBSVMBINARYREADER_OBJ) | $(CNTKMATH_LIB)
@echo $(SEPARATOR)
$(CXX) $(LDFLAGS) -shared $(patsubst %,-L%, $(LIBDIR) $(LIBPATH)) $(patsubst %,$(RPATH)%, $(ORIGINDIR) $(LIBPATH)) -o $@ $^ -l$(CNTKMATH)
########################################
# SparsePCReader plugin
########################################
SPARSEPCREADER_SRC =\
$(SOURCEDIR)/Readers/SparsePCReader/Exports.cpp \
$(SOURCEDIR)/Readers/SparsePCReader/SparsePCReader.cpp \
SPARSEPCREADER_OBJ := $(patsubst %.cpp, $(OBJDIR)/%.o, $(SPARSEPCREADER_SRC))
2017-03-20 17:26:29 +03:00
SPARSEPCREADER:=$(LIBDIR)/Cntk.Reader.SparsePC-$(CNTK_COMPONENT_VERSION).so
ALL_LIBS += $(SPARSEPCREADER)
SRC+=$(SPARSEPCREADER_SRC)
$(SPARSEPCREADER): $(SPARSEPCREADER_OBJ) | $(CNTKMATH_LIB)
@echo $(SEPARATOR)
$(CXX) $(LDFLAGS) -shared $(patsubst %,-L%, $(LIBDIR) $(LIBPATH)) $(patsubst %,$(RPATH)%, $(ORIGINDIR) $(LIBPATH)) -o $@ $^ -l$(CNTKMATH)
########################################
# CNTKBinaryReader plugin
########################################
2016-12-01 04:29:29 +03:00
CNTKBINARYREADER_SRC =\
$(SOURCEDIR)/Readers/CNTKBinaryReader/Exports.cpp \
$(SOURCEDIR)/Readers/CNTKBinaryReader/BinaryChunkDeserializer.cpp \
$(SOURCEDIR)/Readers/CNTKBinaryReader/BinaryConfigHelper.cpp \
$(SOURCEDIR)/Readers/CNTKBinaryReader/CNTKBinaryReader.cpp \
2016-12-01 04:29:29 +03:00
CNTKBINARYREADER_OBJ := $(patsubst %.cpp, $(OBJDIR)/%.o, $(CNTKBINARYREADER_SRC))
2016-12-01 04:29:29 +03:00
2017-03-21 19:34:43 +03:00
CNTKBINARYREADER:=$(LIBDIR)/Cntk.Deserializers.Binary-$(CNTK_COMPONENT_VERSION).so
ALL_LIBS += $(CNTKBINARYREADER)
PYTHON_LIBS += $(CNTKBINARYREADER)
SRC+=$(CNTKBINARYREADER_SRC)
2016-12-01 04:29:29 +03:00
$(CNTKBINARYREADER): $(CNTKBINARYREADER_OBJ) | $(CNTKMATH_LIB)
@echo $(SEPARATOR)
$(CXX) $(LDFLAGS) -shared $(patsubst %,-L%, $(LIBDIR) $(LIBPATH)) $(patsubst %,$(RPATH)%, $(ORIGINDIR) $(LIBPATH)) -o $@ $^ -l$(CNTKMATH)
2016-12-01 04:29:29 +03:00
2016-03-17 17:11:44 +03:00
########################################
# CNTKTextFormatReader plugin
########################################
CNTKTEXTFORMATREADER_SRC =\
$(SOURCEDIR)/Readers/CNTKTextFormatReader/Exports.cpp \
$(SOURCEDIR)/Readers/CNTKTextFormatReader/TextParser.cpp \
$(SOURCEDIR)/Readers/CNTKTextFormatReader/CNTKTextFormatReader.cpp \
$(SOURCEDIR)/Readers/CNTKTextFormatReader/TextConfigHelper.cpp \
CNTKTEXTFORMATREADER_OBJ := $(patsubst %.cpp, $(OBJDIR)/%.o, $(CNTKTEXTFORMATREADER_SRC))
2017-03-21 19:34:43 +03:00
CNTKTEXTFORMATREADER:=$(LIBDIR)/Cntk.Deserializers.TextFormat-$(CNTK_COMPONENT_VERSION).so
ALL_LIBS += $(CNTKTEXTFORMATREADER)
PYTHON_LIBS += $(CNTKTEXTFORMATREADER)
2016-03-17 17:11:44 +03:00
SRC+=$(CNTKTEXTFORMATREADER_SRC)
$(CNTKTEXTFORMATREADER): $(CNTKTEXTFORMATREADER_OBJ) | $(CNTKMATH_LIB)
@echo $(SEPARATOR)
$(CXX) $(LDFLAGS) -shared $(patsubst %,-L%, $(LIBDIR) $(LIBPATH)) $(patsubst %,$(RPATH)%, $(ORIGINDIR) $(LIBPATH)) -o $@ $^ -l$(CNTKMATH)
########################################
# Kaldi plugins
########################################
ifdef KALDI_PATH
KALDI2READER_SRC = \
2015-12-15 11:58:24 +03:00
$(SOURCEDIR)/Readers/Kaldi2Reader/DataReader.cpp \
$(SOURCEDIR)/Readers/Kaldi2Reader/DataWriter.cpp \
$(SOURCEDIR)/Readers/Kaldi2Reader/HTKMLFReader.cpp \
$(SOURCEDIR)/Readers/Kaldi2Reader/HTKMLFWriter.cpp \
$(SOURCEDIR)/Readers/Kaldi2Reader/KaldiSequenceTrainingDerivative.cpp \
$(SOURCEDIR)/Readers/Kaldi2Reader/UtteranceDerivativeBuffer.cpp \
KALDI2READER_OBJ := $(patsubst %.cpp, $(OBJDIR)/%.o, $(KALDI2READER_SRC))
2017-03-21 19:34:43 +03:00
KALDI2READER:=$(LIBDIR)/Cntk.Reader.Kaldi2-$(CNTK_COMPONENT_VERSION).so
ALL_LIBS+=$(KALDI2READER)
SRC+=$(KALDI2READER_SRC)
$(KALDI2READER): $(KALDI2READER_OBJ) | $(CNTKMATH_LIB)
@echo $(SEPARATOR)
$(CXX) $(LDFLAGS) -shared $(patsubst %,-L%, $(LIBDIR) $(KALDI_LIBPATH) $(LIBPATH)) $(patsubst %,$(RPATH)%, $(ORIGINDIR) $(KALDI_LIBPATH) $(LIBPATH)) -o $@ $^ -l$(CNTKMATH) $(KALDI_LIBS)
endif
2015-10-13 22:02:35 +03:00
########################################
# ImageReader plugin
########################################
ifdef OPENCV_PATH
2016-08-17 16:27:15 +03:00
ifdef BOOST_PATH
INCLUDEPATH += $(BOOST_PATH)/include
2016-02-20 04:41:40 +03:00
IMAGEREADER_LIBS_LIST := opencv_core opencv_imgproc opencv_imgcodecs
2016-02-20 04:41:40 +03:00
ifdef LIBZIP_PATH
CPPFLAGS += -DUSE_ZIP
# Both directories are needed for building libzip
INCLUDEPATH += $(LIBZIP_PATH)/include $(LIBZIP_PATH)/lib/libzip/include
2016-09-28 12:31:03 +03:00
LIBPATH += $(LIBZIP_PATH)/lib
IMAGEREADER_LIBS_LIST += zip
2016-02-20 04:41:40 +03:00
endif
IMAGEREADER_LIBS:= $(addprefix -l,$(IMAGEREADER_LIBS_LIST))
2015-10-13 22:02:35 +03:00
IMAGEREADER_SRC =\
2016-09-30 17:27:53 +03:00
$(SOURCEDIR)/Readers/ImageReader/Base64ImageDeserializer.cpp \
$(SOURCEDIR)/Readers/ImageReader/ImageDeserializerBase.cpp \
2016-02-25 21:48:13 +03:00
$(SOURCEDIR)/Readers/ImageReader/Exports.cpp \
$(SOURCEDIR)/Readers/ImageReader/ImageConfigHelper.cpp \
$(SOURCEDIR)/Readers/ImageReader/ImageDataDeserializer.cpp \
$(SOURCEDIR)/Readers/ImageReader/ImageTransformers.cpp \
$(SOURCEDIR)/Readers/ImageReader/ImageReader.cpp \
$(SOURCEDIR)/Readers/ImageReader/ZipByteReader.cpp \
2015-12-15 11:58:24 +03:00
2015-10-13 22:02:35 +03:00
IMAGEREADER_OBJ := $(patsubst %.cpp, $(OBJDIR)/%.o, $(IMAGEREADER_SRC))
2017-03-21 19:34:43 +03:00
IMAGEREADER:=$(LIBDIR)/Cntk.Deserializers.Image-$(CNTK_COMPONENT_VERSION).so
ALL_LIBS += $(IMAGEREADER)
PYTHON_LIBS += $(IMAGEREADER)
2018-01-29 23:44:29 +03:00
JAVA_LOAD_DEPS += $(IMAGEREADER_LIBS)
2015-10-13 22:02:35 +03:00
SRC+=$(IMAGEREADER_SRC)
INCLUDEPATH += $(OPENCV_PATH)/include
2016-02-01 15:10:43 +03:00
LIBPATH += $(OPENCV_PATH)/lib $(OPENCV_PATH)/release/lib
2015-10-13 22:02:35 +03:00
$(IMAGEREADER): $(IMAGEREADER_OBJ) | $(CNTKMATH_LIB)
@echo $(SEPARATOR)
2016-10-12 21:51:17 +03:00
$(CXX) $(LDFLAGS) -shared $(patsubst %,-L%, $(LIBDIR) $(LIBPATH)) $(patsubst %,$(RPATH)%, $(ORIGINDIR) $(LIBPATH)) -o $@ $^ -l$(CNTKMATH) $(IMAGEREADER_LIBS)
2015-10-13 22:02:35 +03:00
endif
2016-08-17 16:27:15 +03:00
endif
2015-10-13 22:02:35 +03:00
########################################
# DelayLoadedExtensions plugin
########################################
ifdef OPENCV_PATH
DELAY_LOADED_EXTENSIONS_LIBS_LIST := opencv_core opencv_imgproc opencv_imgcodecs
DELAY_LOADED_EXTENSIONS_LIBS:= $(addprefix -l,$(DELAY_LOADED_EXTENSIONS_LIBS_LIST))
DELAY_LOADED_EXTENSIONS_SRC =\
$(SOURCEDIR)/DelayLoadedExtensionsDll/ImageWriter.cpp \
DELAY_LOADED_EXTENSIONS_OBJ := $(patsubst %.cpp, $(OBJDIR)/%.o, $(DELAY_LOADED_EXTENSIONS_SRC))
DELAY_LOADED_EXTENSIONS:=$(LIBDIR)/Cntk.DelayLoadedExtensions-$(CNTK_COMPONENT_VERSION).so
ALL_LIBS += $(DELAY_LOADED_EXTENSIONS)
PYTHON_LIBS += $(DELAY_LOADED_EXTENSIONS)
JAVA_LOAD_DEPS += $(DELAY_LOADED_EXTENSIONS_LIBS)
SRC+=$(DELAY_LOADED_EXTENSIONS_SRC)
INCLUDEPATH += $(OPENCV_PATH)/include
LIBPATH += $(OPENCV_PATH)/lib $(OPENCV_PATH)/release/lib
$(DELAY_LOADED_EXTENSIONS): $(DELAY_LOADED_EXTENSIONS_OBJ)
@echo $(SEPARATOR)
$(CXX) $(LDFLAGS) -shared $(patsubst %,-L%, $(LIBDIR) $(LIBPATH)) $(patsubst %,$(RPATH)%, $(ORIGINDIR) $(LIBPATH)) -o $@ $^ $(DELAY_LOADED_EXTENSIONS_LIBS)
endif
########################################
# 1bit SGD setup
########################################
INCLUDEPATH += $(SOURCEDIR)/1BitSGD
COMMON_FLAGS += -DCNTK_PARALLEL_TRAINING_SUPPORT
# temporarily adding to 1bit, need to work with others to fix it
CNTK support for CUDA 9 CNTK now supports CUDA 9/cuDNN 7. This requires an update to build environment to Ubuntu 16/GCC 5 for Linux, and Visual Studio 2017/VCTools 14.11 for Windows. With CUDA 9, CNTK also added a preview for 16-bit floating point (a.k.a FP16) computation. Please check out the example of FP16 in ResNet50 at /Examples/Image/Classification/ResNet/Python/TrainResNet_ImageNet_Distributed.py Notes on FP16 preview: * FP16 implementation on CPU is not optimized, and it's not supposed to be used in CPU inference directly. User needs to convert the model to 32-bit floating point before running on CPU. * Loss/Criterion for FP16 training needs to be 32bit for accumulation without overflow, using cast function. Please check the example above. * Readers do not have FP16 output unless using numpy to feed data, cast from FP32 to FP16 is needed. Please check the example above. * FP16 gradient aggregation is currently only implemented on GPU using NCCL2. Distributed training with FP16 with MPI is not supported. * FP16 math is a subset of current FP32 implementation. Some model may get Feature Not Implemented exception using FP16. * FP16 is currently not supported in BrainScript. Please use Python for FP16. To setup build and runtime environment on Windows: * Install [Visual Studio 2017](https://www.visualstudio.com/downloads/) with following workloads and components. From command line (use Community version installer as example): vs_community.exe --add Microsoft.VisualStudio.Workload.NativeDesktop --add Microsoft.VisualStudio.Workload.ManagedDesktop --add Microsoft.VisualStudio.Workload.Universal --add Microsoft.Component.PythonTools --add Microsoft.VisualStudio.Component.VC.Tools.14.11 * Install [NVidia CUDA 9](https://developer.nvidia.com/cuda-90-download-archive?target_os=Windows&target_arch=x86_64) * From PowerShell, run: /Tools/devInstall/Windows/DevInstall.ps1 * Start VCTools 14.11 command line, run: cmd /k "%VS2017INSTALLDIR%\VC\Auxiliary\Build\vcvarsall.bat" x64 --vcvars_ver=14.11 * Open /CNTK.sln from the VCTools 14.11 command line. Note that starting CNTK.sln other than VCTools 14.11 command line, would causes CUDA 9 [build error](https://developercommunity.visualstudio.com/content/problem/163758/vs-2017-155-doesnt-support-cuda-9.html). To setup build and runtime environment on Linux using docker, please build Unbuntu 16.04 docker image using Dockerfiles /Tools/docker. For other Linux systems, please refer to the Dockerfiles to setup dependent libraries for CNTK.
2018-01-23 03:58:56 +03:00
########################################
# ASGD(multiverso) setup
########################################
2016-09-27 06:37:31 +03:00
ifeq ("$(CNTK_ENABLE_ASGD)","true")
2016-02-15 15:01:04 +03:00
ifeq (,$(wildcard Source/Multiverso/include/multiverso/*.h))
2017-06-07 17:50:37 +03:00
$(error Build with Multiverso was requested but cannot find the code. Please check https://docs.microsoft.com/en-us/cognitive-toolkit/Multiple-GPUs-and-machines#8-data-parallel-training-with-parameter-server to learn more.)
endif
2016-10-10 06:18:17 +03:00
lMULTIVERSO:=-lmultiverso
2016-09-27 06:37:31 +03:00
2016-09-19 13:07:15 +03:00
INCLUDEPATH += $(SOURCEDIR)/Multiverso/include
2016-11-03 12:31:28 +03:00
COMMON_FLAGS += -DASGD_PARALLEL_SUPPORT
2016-09-19 13:07:15 +03:00
# MULTIVERSO_LIB has been set above
2016-09-19 13:07:15 +03:00
2016-11-06 08:11:20 +03:00
ALL_LIBS+=$(MULTIVERSO_LIB)
ifeq ("$(BUILDTYPE)","release")
2016-11-08 14:59:19 +03:00
MULTIVERSO_CMAKE_BUILDTYPE=Release
endif
ifeq ("$(BUILDTYPE)","debug")
2016-11-08 14:59:19 +03:00
MULTIVERSO_CMAKE_BUILDTYPE=Debug
endif
# TODO need to align Multiverso OpenMP with the one we use (libiomp). For now, disabled.
CNTK support for CUDA 9 CNTK now supports CUDA 9/cuDNN 7. This requires an update to build environment to Ubuntu 16/GCC 5 for Linux, and Visual Studio 2017/VCTools 14.11 for Windows. With CUDA 9, CNTK also added a preview for 16-bit floating point (a.k.a FP16) computation. Please check out the example of FP16 in ResNet50 at /Examples/Image/Classification/ResNet/Python/TrainResNet_ImageNet_Distributed.py Notes on FP16 preview: * FP16 implementation on CPU is not optimized, and it's not supposed to be used in CPU inference directly. User needs to convert the model to 32-bit floating point before running on CPU. * Loss/Criterion for FP16 training needs to be 32bit for accumulation without overflow, using cast function. Please check the example above. * Readers do not have FP16 output unless using numpy to feed data, cast from FP32 to FP16 is needed. Please check the example above. * FP16 gradient aggregation is currently only implemented on GPU using NCCL2. Distributed training with FP16 with MPI is not supported. * FP16 math is a subset of current FP32 implementation. Some model may get Feature Not Implemented exception using FP16. * FP16 is currently not supported in BrainScript. Please use Python for FP16. To setup build and runtime environment on Windows: * Install [Visual Studio 2017](https://www.visualstudio.com/downloads/) with following workloads and components. From command line (use Community version installer as example): vs_community.exe --add Microsoft.VisualStudio.Workload.NativeDesktop --add Microsoft.VisualStudio.Workload.ManagedDesktop --add Microsoft.VisualStudio.Workload.Universal --add Microsoft.Component.PythonTools --add Microsoft.VisualStudio.Component.VC.Tools.14.11 * Install [NVidia CUDA 9](https://developer.nvidia.com/cuda-90-download-archive?target_os=Windows&target_arch=x86_64) * From PowerShell, run: /Tools/devInstall/Windows/DevInstall.ps1 * Start VCTools 14.11 command line, run: cmd /k "%VS2017INSTALLDIR%\VC\Auxiliary\Build\vcvarsall.bat" x64 --vcvars_ver=14.11 * Open /CNTK.sln from the VCTools 14.11 command line. Note that starting CNTK.sln other than VCTools 14.11 command line, would causes CUDA 9 [build error](https://developercommunity.visualstudio.com/content/problem/163758/vs-2017-155-doesnt-support-cuda-9.html). To setup build and runtime environment on Linux using docker, please build Unbuntu 16.04 docker image using Dockerfiles /Tools/docker. For other Linux systems, please refer to the Dockerfiles to setup dependent libraries for CNTK.
2018-01-23 03:58:56 +03:00
$(MULTIVERSO_LIB):
2016-11-02 04:52:25 +03:00
@echo "Build Multiverso lib"
@mkdir -p $(LIBDIR)
@mkdir -p $(BINDIR)
2016-11-08 14:59:19 +03:00
@mkdir -p $(SOURCEDIR)/Multiverso/build/$(BUILDTYPE)
2016-11-02 04:52:25 +03:00
@cmake -DCMAKE_VERBOSE_MAKEFILE=TRUE \
-DCMAKE_CXX_COMPILER=$(DEFAULT_CXX) \
-DOpenMP_CXX_FLAGS="" \
-DOpenMP_C_FLAGS="" \
2016-11-02 04:52:25 +03:00
-DBoost_NO_BOOST_CMAKE=TRUE \
-DBoost_NO_SYSTEM_PATHS=TRUE \
-DBOOST_ROOT:PATH=$(BOOST_PATH) \
-DBOOST_LIBRARY_DIRS:PATH=$(BOOST_PATH) \
2016-11-02 04:52:25 +03:00
-DLIBRARY_OUTPUT_PATH=$(shell readlink -f $(LIBDIR)) \
-DEXECUTABLE_OUTPUT_PATH=$(shell readlink -f $(BINDIR)) \
2016-11-08 14:59:19 +03:00
-DCMAKE_BUILD_TYPE=$(MULTIVERSO_CMAKE_BUILDTYPE) \
-B./Source/Multiverso/build/$(BUILDTYPE) -H./Source/Multiverso
@make VERBOSE=1 -C ./Source/Multiverso/build/$(BUILDTYPE) -j multiverso
2016-02-15 15:01:04 +03:00
2016-10-10 06:18:17 +03:00
UNITTEST_MULTIVERSO_SRC = \
$(SOURCEDIR)/Multiverso/Test/unittests/test_array.cpp \
$(SOURCEDIR)/Multiverso/Test/unittests/test_blob.cpp \
$(SOURCEDIR)/Multiverso/Test/unittests/test_kv.cpp \
$(SOURCEDIR)/Multiverso/Test/unittests/test_message.cpp \
$(SOURCEDIR)/Multiverso/Test/unittests/test_multiverso.cpp \
$(SOURCEDIR)/Multiverso/Test/unittests/test_node.cpp \
$(SOURCEDIR)/Multiverso/Test/unittests/test_sync.cpp \
UNITTEST_MULTIVERSO_OBJ := $(patsubst %.cpp, $(OBJDIR)/%.o, $(UNITTEST_MULTIVERSO_SRC))
UNITTEST_MULTIVERSO := $(BINDIR)/multiversotests
ALL += $(UNITTEST_MULTIVERSO)
$(UNITTEST_MULTIVERSO): $(UNITTEST_MULTIVERSO_OBJ) | $(MULTIVERSO_LIB)
@echo $(SEPARATOR)
@mkdir -p $(dir $@)
@echo building $@ for $(ARCH) with build type $(BUILDTYPE)
$(CXX) $(LDFLAGS) $(patsubst %,-L%, $(LIBDIR) $(BOOSTLIB_PATH)) $(patsubst %, $(RPATH)%, $(ORIGINLIBDIR) $(BOOSTLIB_PATH)) -o $@ $^ $(BOOSTLIBS) $(lMULTIVERSO) -ldl
endif
########################################
# cntk
########################################
CNTK_SRC =\
2015-12-15 11:58:24 +03:00
$(SOURCEDIR)/CNTK/CNTK.cpp \
$(SOURCEDIR)/CNTK/ModelEditLanguage.cpp \
$(SOURCEDIR)/CNTK/tests.cpp \
$(SOURCEDIR)/ActionsLib/TrainActions.cpp \
$(SOURCEDIR)/ActionsLib/EvalActions.cpp \
$(SOURCEDIR)/ActionsLib/OtherActions.cpp \
$(SOURCEDIR)/ActionsLib/SpecialPurposeActions.cpp \
$(SOURCEDIR)/ActionsLib/NetworkFactory.cpp \
$(SOURCEDIR)/ActionsLib/NetworkDescriptionLanguage.cpp \
$(SOURCEDIR)/ActionsLib/SimpleNetworkBuilder.cpp \
$(SOURCEDIR)/ActionsLib/NDLNetworkBuilder.cpp \
2015-12-15 11:58:24 +03:00
$(SOURCEDIR)/CNTK/BrainScript/BrainScriptEvaluator.cpp \
$(SOURCEDIR)/CNTK/BrainScript/BrainScriptParser.cpp \
CNTK_SRC+=$(SGDLIB_SRC)
2016-06-11 22:21:15 +03:00
CNTK_SRC+=$(CNTK_COMMON_SRC)
CNTK_SRC+=$(COMPUTATION_NETWORK_LIB_SRC)
CNTK_SRC+=$(SEQUENCE_TRAINING_LIB_SRC)
CNTK_OBJ :=\
$(patsubst %.cu, $(OBJDIR)/%.o, $(filter %.cu, $(CNTK_SRC))) \
$(patsubst %.pb.cc, $(OBJDIR)/%.pb.o, $(filter %.pb.cc, $(CNTK_SRC))) \
2018-06-28 18:38:36 +03:00
$(patsubst %.cpp, $(OBJDIR)/%.o, $(filter %.cpp, $(CNTK_SRC))) \
$(patsubst %.cc, $(OBJDIR)/%.o, $(filter %.cc, $(CNTKLIBRARY_SRC)))
CNTK:=$(BINDIR)/cntk
ALL+=$(CNTK)
SRC+=$(CNTK_SRC)
$(CNTK): $(CNTK_OBJ) | $(READER_LIBS) $(MULTIVERSO_LIB)
@echo $(SEPARATOR)
@mkdir -p $(dir $@)
2016-10-25 01:33:31 +03:00
@echo building $@ for $(ARCH) with build type $(BUILDTYPE)
$(CXX) $(LDFLAGS) $(patsubst %,-L%, $(LIBDIR) $(LIBPATH) $(GDK_NVML_LIB_PATH)) $(patsubst %,$(RPATH)%, $(ORIGINLIBDIR) $(LIBPATH)) -o $@ $^ $(LIBS) $(L_READER_LIBS) $(lMULTIVERSO) -ldl -fopenmp $(PROTOBUF_PATH)/lib/libprotobuf.a
# deployable resources: standard library of BS
CNTK_CORE_BS:=$(BINDIR)/cntk.core.bs
ALL += $(CNTK_CORE_BS)
$(CNTK_CORE_BS): $(SOURCEDIR)/CNTK/BrainScript/CNTKCoreLib/CNTK.core.bs
@mkdir -p $(dir $@)
@echo bin-placing deployable resource files
cp -f $^ $@
########################################
# V2Library EndToEndTests
########################################
CNTKLIBRARY_END_TO_END_TESTS_PATH =\
Tests/EndToEndTests/CNTKv2Library
CNTKLIBRARY_END_TO_END_COMMON_SRC_PATH =\
$(CNTKLIBRARY_END_TO_END_TESTS_PATH)/Common
INCLUDEPATH+=$(CNTKLIBRARY_END_TO_END_COMMON_SRC_PATH)
CNTKLIBRARY_END_TO_END_TESTS_SRC_PATH =\
$(CNTKLIBRARY_END_TO_END_TESTS_PATH)/EndToEndTests
CNTKLIBRARY_END_TO_END_TESTS_SRC =\
$(CNTKLIBRARY_END_TO_END_COMMON_SRC_PATH)/Common.cpp \
$(CNTKLIBRARY_END_TO_END_TESTS_SRC_PATH)/Main.cpp \
$(CNTKLIBRARY_END_TO_END_TESTS_SRC_PATH)/CifarResNet.cpp \
$(CNTKLIBRARY_END_TO_END_TESTS_SRC_PATH)/MNISTClassifier.cpp \
$(CNTKLIBRARY_END_TO_END_TESTS_SRC_PATH)/Seq2Seq.cpp \
$(CNTKLIBRARY_END_TO_END_TESTS_SRC_PATH)/SequenceClassification.cpp \
$(CNTKLIBRARY_END_TO_END_TESTS_SRC_PATH)/TruncatedLSTMAcousticModel.cpp \
$(CNTKLIBRARY_END_TO_END_TESTS_SRC_PATH)/FrameMode.cpp \
CNTKLIBRARY_END_TO_END_TESTS:=$(BINDIR)/V2LibraryEndToEndTests
CNTKLIBRARY_END_TO_END_TESTS_OBJ := $(patsubst %.cu, $(OBJDIR)/%.o, $(patsubst %.cpp, $(OBJDIR)/%.o, $(CNTKLIBRARY_END_TO_END_TESTS_SRC)))
ALL+=$(CNTKLIBRARY_END_TO_END_TESTS)
SRC+=$(CNTKLIBRARY_END_TO_END_TESTS_SRC)
$(CNTKLIBRARY_END_TO_END_TESTS): $(CNTKLIBRARY_END_TO_END_TESTS_OBJ) | $(CNTKLIBRARY_LIB) $(READER_LIBS)
@echo $(SEPARATOR)
@mkdir -p $(dir $@)
@echo building $@ for $(ARCH) with build type $(BUILDTYPE)
$(CXX) $(LDFLAGS) $(patsubst %,-L%, $(LIBDIR) $(LIBPATH) $(GDK_NVML_LIB_PATH)) $(patsubst %,$(RPATH)%, $(ORIGINLIBDIR) $(LIBPATH)) -o $@ $^ $(LIBS) -l$(CNTKLIBRARY) $(L_READER_LIBS)
########################################
# Unit Tests
########################################
# only build unit tests when Boost is available
ifdef BOOST_PATH
INCLUDEPATH += $(BOOST_PATH)/include
BOOSTLIB_PATH = $(BOOST_PATH)/lib
BOOSTLIBS := -lboost_unit_test_framework -lboost_filesystem -lboost_system
UNITTEST_EVAL_SRC = \
$(SOURCEDIR)/../Tests/UnitTests/EvalTests/EvalExtendedTests.cpp \
$(SOURCEDIR)/../Tests/UnitTests/EvalTests/stdafx.cpp
2018-06-28 18:38:36 +03:00
UNITTEST_EVAL_OBJ := $(patsubst %.cpp, $(OBJDIR)/%.o, $(UNITTEST_EVAL_SRC)) \
$(patsubst %.cc, $(OBJDIR)/%.o, $(filter %.cc, $(CNTKLIBRARY_SRC)))
UNITTEST_EVAL := $(BINDIR)/evaltests
ALL += $(UNITTEST_EVAL)
SRC += $(UNITTEST_EVAL_SRC)
$(UNITTEST_EVAL) : $(UNITTEST_EVAL_OBJ) | $(EVAL_LIB) $(READER_LIBS)
@echo $(SEPARATOR)
@mkdir -p $(dir $@)
@echo building $@ for $(ARCH) with build type $(BUILDTYPE)
$(CXX) $(LDFLAGS) $(patsubst %,-L%, $(LIBDIR) $(LIBPATH) $(GDK_NVML_LIB_PATH) $(BOOSTLIB_PATH)) $(patsubst %, $(RPATH)%, $(ORIGINLIBDIR) $(LIBPATH) $(BOOSTLIB_PATH)) -o $@ $^ $(BOOSTLIBS) $(LIBS) -l$(EVAL) $(L_READER_LIBS) $(lMULTIVERSO)
#TODO: create project specific makefile or rules to avoid adding project specific path to the global path
INCLUDEPATH += $(SOURCEDIR)/Readers/CNTKTextFormatReader
UNITTEST_READER_SRC = \
2016-12-01 04:29:29 +03:00
$(SOURCEDIR)/../Tests/UnitTests/ReaderTests/CNTKBinaryReaderTests.cpp \
$(SOURCEDIR)/../Tests/UnitTests/ReaderTests/CNTKTextFormatReaderTests.cpp \
$(SOURCEDIR)/../Tests/UnitTests/ReaderTests/HTKLMFReaderTests.cpp \
$(SOURCEDIR)/../Tests/UnitTests/ReaderTests/ImageReaderTests.cpp \
$(SOURCEDIR)/../Tests/UnitTests/ReaderTests/ReaderLibTests.cpp \
$(SOURCEDIR)/../Tests/UnitTests/ReaderTests/ReaderUtilTests.cpp \
$(SOURCEDIR)/../Tests/UnitTests/ReaderTests/stdafx.cpp \
$(SOURCEDIR)/Readers/CNTKTextFormatReader/TextParser.cpp \
UNITTEST_READER_OBJ := $(patsubst %.cpp, $(OBJDIR)/%.o, $(UNITTEST_READER_SRC))
UNITTEST_READER := $(BINDIR)/readertests
ALL += $(UNITTEST_READER)
SRC += $(UNITTEST_READER_SRC)
$(UNITTEST_READER): $(UNITTEST_READER_OBJ) | $(HTKMLFREADER) $(HTKDESERIALIZERS) $(UCIFASTREADER) $(COMPOSITEDATAREADER) $(IMAGEREADER) $(READER_LIBS)
@echo $(SEPARATOR)
@mkdir -p $(dir $@)
@echo building $@ for $(ARCH) with build type $(BUILDTYPE)
$(CXX) $(LDFLAGS) $(patsubst %,-L%, $(LIBPATH) $(LIBDIR) $(GDK_NVML_LIB_PATH)) $(patsubst %,-L%, $(LIBDIR) $(BOOSTLIB_PATH)) $(patsubst %, $(RPATH)%, $(ORIGINLIBDIR) $(LIBPATH) $(BOOSTLIB_PATH)) -o $@ $^ $(BOOSTLIBS) $(L_READER_LIBS) $(LIBS) -ldl -fopenmp
UNITTEST_NETWORK_SRC = \
$(SOURCEDIR)/../Tests/UnitTests/NetworkTests/AccumulatorNodeTests.cpp \
$(SOURCEDIR)/../Tests/UnitTests/NetworkTests/BatchNormalizationTests.cpp \
$(SOURCEDIR)/../Tests/UnitTests/NetworkTests/CropNodeTests.cpp \
$(SOURCEDIR)/../Tests/UnitTests/NetworkTests/OperatorEvaluation.cpp \
$(SOURCEDIR)/../Tests/UnitTests/NetworkTests/stdafx.cpp \
$(SOURCEDIR)/../Tests/UnitTests/NetworkTests/TestHelpers.cpp \
2017-01-11 01:04:58 +03:00
$(SOURCEDIR)/../Tests/UnitTests/NetworkTests/EditDistanceTests.cpp \
$(SOURCEDIR)/CNTK/ModelEditLanguage.cpp \
$(SOURCEDIR)/ActionsLib/TrainActions.cpp \
$(SOURCEDIR)/ActionsLib/EvalActions.cpp \
$(SOURCEDIR)/ActionsLib/OtherActions.cpp \
$(SOURCEDIR)/ActionsLib/SpecialPurposeActions.cpp \
$(SOURCEDIR)/ActionsLib/NetworkFactory.cpp \
$(SOURCEDIR)/ActionsLib/NetworkDescriptionLanguage.cpp \
$(SOURCEDIR)/ActionsLib/SimpleNetworkBuilder.cpp \
$(SOURCEDIR)/ActionsLib/NDLNetworkBuilder.cpp \
$(SOURCEDIR)/CNTK/BrainScript/BrainScriptEvaluator.cpp \
$(SOURCEDIR)/CNTK/BrainScript/BrainScriptParser.cpp \
UNITTEST_NETWORK_SRC += $(COMPUTATION_NETWORK_LIB_SRC)
UNITTEST_NETWORK_SRC += $(CNTK_COMMON_SRC)
UNITTEST_NETWORK_SRC += $(SEQUENCE_TRAINING_LIB_SRC)
UNITTEST_NETWORK_SRC += $(SGDLIB_SRC)
UNITTEST_NETWORK_OBJ :=\
$(patsubst %.cu, $(OBJDIR)/%.o, $(filter %.cu, $(UNITTEST_NETWORK_SRC))) \
$(patsubst %.pb.cc, $(OBJDIR)/%.pb.o, $(filter %.pb.cc, $(UNITTEST_NETWORK_SRC))) \
2018-06-28 18:38:36 +03:00
$(patsubst %.cpp, $(OBJDIR)/%.o, $(filter %.cpp, $(UNITTEST_NETWORK_SRC))) \
$(patsubst %.cc, $(OBJDIR)/%.o, $(filter %.cc, $(CNTKLIBRARY_SRC)))
UNITTEST_NETWORK := $(BINDIR)/networktests
ALL += $(UNITTEST_NETWORK)
SRC += $(UNITTEST_NETWORK_SRC)
$(UNITTEST_NETWORK): $(UNITTEST_NETWORK_OBJ) | $(READER_LIBS) $(CNTKTEXTFORMATREADER) $(MULTIVERSO_LIB)
@echo $(SEPARATOR)
@mkdir -p $(dir $@)
@echo building $@ for $(ARCH) with build type $(BUILDTYPE)
$(CXX) $(LDFLAGS) $(patsubst %,-L%, $(LIBDIR) $(LIBPATH) $(GDK_NVML_LIB_PATH) $(BOOSTLIB_PATH)) $(patsubst %, $(RPATH)%, $(ORIGINLIBDIR) $(LIBPATH) $(BOOSTLIB_PATH)) -o $@ $^ $(BOOSTLIBS) $(LIBS) $(lMULTIVERSO) $(L_READER_LIBS) -ldl -fopenmp $(PROTOBUF_PATH)/lib/libprotobuf.a
UNITTEST_MATH_SRC = \
$(SOURCEDIR)/../Tests/UnitTests/MathTests/BatchNormalizationEngineTests.cpp \
$(SOURCEDIR)/../Tests/UnitTests/MathTests/constants.cpp \
$(SOURCEDIR)/../Tests/UnitTests/MathTests/ConvolutionEngineTests.cpp \
$(SOURCEDIR)/../Tests/UnitTests/MathTests/CPUMatrixTests.cpp \
$(SOURCEDIR)/../Tests/UnitTests/MathTests/CPUSparseMatrixTests.cpp \
$(SOURCEDIR)/../Tests/UnitTests/MathTests/fixtures.cpp \
$(SOURCEDIR)/../Tests/UnitTests/MathTests/QuantizersTests.cpp \
2016-11-17 05:20:50 +03:00
$(SOURCEDIR)/../Tests/UnitTests/MathTests/QuantizedOperationsTests.cpp \
$(SOURCEDIR)/../Tests/UnitTests/MathTests/TensorTests.cpp \
$(SOURCEDIR)/../Tests/UnitTests/MathTests/GPUMatrixCudaBlasTests.cpp \
$(SOURCEDIR)/../Tests/UnitTests/MathTests/GPUMatrixTests.cpp \
$(SOURCEDIR)/../Tests/UnitTests/MathTests/GPUSparseMatrixTests.cpp \
$(SOURCEDIR)/../Tests/UnitTests/MathTests/MatrixBlasTests.cpp \
$(SOURCEDIR)/../Tests/UnitTests/MathTests/MatrixDataSynchronizationTests.cpp \
$(SOURCEDIR)/../Tests/UnitTests/MathTests/MatrixFileWriteReadTests.cpp \
$(SOURCEDIR)/../Tests/UnitTests/MathTests/MatrixQuantizerTests.cpp \
$(SOURCEDIR)/../Tests/UnitTests/MathTests/MatrixSparseDenseInteractionsTests.cpp \
$(SOURCEDIR)/../Tests/UnitTests/MathTests/MatrixTests.cpp \
$(SOURCEDIR)/../Tests/UnitTests/MathTests/MatrixLearnerTests.cpp \
$(SOURCEDIR)/../Tests/UnitTests/MathTests/stdafx.cpp \
CNTK support for CUDA 9 CNTK now supports CUDA 9/cuDNN 7. This requires an update to build environment to Ubuntu 16/GCC 5 for Linux, and Visual Studio 2017/VCTools 14.11 for Windows. With CUDA 9, CNTK also added a preview for 16-bit floating point (a.k.a FP16) computation. Please check out the example of FP16 in ResNet50 at /Examples/Image/Classification/ResNet/Python/TrainResNet_ImageNet_Distributed.py Notes on FP16 preview: * FP16 implementation on CPU is not optimized, and it's not supposed to be used in CPU inference directly. User needs to convert the model to 32-bit floating point before running on CPU. * Loss/Criterion for FP16 training needs to be 32bit for accumulation without overflow, using cast function. Please check the example above. * Readers do not have FP16 output unless using numpy to feed data, cast from FP32 to FP16 is needed. Please check the example above. * FP16 gradient aggregation is currently only implemented on GPU using NCCL2. Distributed training with FP16 with MPI is not supported. * FP16 math is a subset of current FP32 implementation. Some model may get Feature Not Implemented exception using FP16. * FP16 is currently not supported in BrainScript. Please use Python for FP16. To setup build and runtime environment on Windows: * Install [Visual Studio 2017](https://www.visualstudio.com/downloads/) with following workloads and components. From command line (use Community version installer as example): vs_community.exe --add Microsoft.VisualStudio.Workload.NativeDesktop --add Microsoft.VisualStudio.Workload.ManagedDesktop --add Microsoft.VisualStudio.Workload.Universal --add Microsoft.Component.PythonTools --add Microsoft.VisualStudio.Component.VC.Tools.14.11 * Install [NVidia CUDA 9](https://developer.nvidia.com/cuda-90-download-archive?target_os=Windows&target_arch=x86_64) * From PowerShell, run: /Tools/devInstall/Windows/DevInstall.ps1 * Start VCTools 14.11 command line, run: cmd /k "%VS2017INSTALLDIR%\VC\Auxiliary\Build\vcvarsall.bat" x64 --vcvars_ver=14.11 * Open /CNTK.sln from the VCTools 14.11 command line. Note that starting CNTK.sln other than VCTools 14.11 command line, would causes CUDA 9 [build error](https://developercommunity.visualstudio.com/content/problem/163758/vs-2017-155-doesnt-support-cuda-9.html). To setup build and runtime environment on Linux using docker, please build Unbuntu 16.04 docker image using Dockerfiles /Tools/docker. For other Linux systems, please refer to the Dockerfiles to setup dependent libraries for CNTK.
2018-01-23 03:58:56 +03:00
$(SOURCEDIR)/../Tests/UnitTests/MathTests/HalfGPUTests.cpp \
UNITTEST_MATH_SRC += $(CNTK_COMMON_SRC)
UNITTEST_MATH_OBJ := $(patsubst %.cpp, $(OBJDIR)/%.o, $(UNITTEST_MATH_SRC))
UNITTEST_MATH := $(BINDIR)/mathtests
ALL += $(UNITTEST_MATH)
SRC += $(UNITTEST_MATH_SRC)
$(UNITTEST_MATH): $(UNITTEST_MATH_OBJ) | $(READER_LIBS)
@echo $(SEPARATOR)
@mkdir -p $(dir $@)
@echo building $@ for $(ARCH) with build type $(BUILDTYPE)
$(CXX) $(LDFLAGS) $(patsubst %,-L%, $(LIBDIR) $(LIBPATH) $(GDK_NVML_LIB_PATH) $(BOOSTLIB_PATH)) $(patsubst %, $(RPATH)%, $(ORIGINLIBDIR) $(LIBPATH) $(BOOSTLIB_PATH)) -o $@ $^ $(BOOSTLIBS) $(LIBS) $(L_READER_LIBS) -ldl -fopenmp
2016-08-02 10:18:08 +03:00
UNITTEST_BRAINSCRIPT_SRC = \
$(SOURCEDIR)/CNTK/BrainScript/BrainScriptEvaluator.cpp \
$(SOURCEDIR)/CNTK/BrainScript/BrainScriptParser.cpp \
$(SOURCEDIR)/../Tests/UnitTests/BrainScriptTests/ParserTests.cpp \
2016-08-09 12:31:47 +03:00
$(SOURCEDIR)/../Tests/UnitTests/BrainScriptTests/ComputationNetworkTests.cpp \
2016-08-02 10:18:08 +03:00
$(SOURCEDIR)/../Tests/UnitTests/BrainScriptTests/stdafx.cpp
2016-08-09 12:31:47 +03:00
UNITTEST_BRAINSCRIPT_SRC += $(COMPUTATION_NETWORK_LIB_SRC)
UNITTEST_BRAINSCRIPT_SRC += $(SEQUENCE_TRAINING_LIB_SRC)
2016-08-02 10:18:08 +03:00
2016-08-09 12:31:47 +03:00
UNITTEST_BRAINSCRIPT_OBJ := $(patsubst %.cu, $(OBJDIR)/%.o, $(patsubst %.cpp, $(OBJDIR)/%.o, $(UNITTEST_BRAINSCRIPT_SRC)))
2016-08-02 10:18:08 +03:00
UNITTEST_BRAINSCRIPT := $(BINDIR)/brainscripttests
ALL += $(UNITTEST_BRAINSCRIPT)
SRC += $(UNITTEST_BRAINSCRIPT_SRC)
$(UNITTEST_BRAINSCRIPT): $(UNITTEST_BRAINSCRIPT_OBJ) | $(READER_LIBS)
2016-08-02 10:18:08 +03:00
@echo $(SEPARATOR)
@mkdir -p $(dir $@)
@echo building $@ for $(ARCH) with build type $(BUILDTYPE)
$(CXX) $(LDFLAGS) $(patsubst %,-L%, $(LIBDIR) $(LIBPATH) $(GDK_NVML_LIB_PATH) $(BOOSTLIB_PATH)) $(patsubst %, $(RPATH)%, $(ORIGINLIBDIR) $(LIBPATH) $(BOOSTLIB_PATH)) -o $@ $^ $(BOOSTLIBS) $(LIBS) -ldl $(L_READER_LIBS) -fopenmp
2016-08-02 10:18:08 +03:00
########################################
# CNTKLibrary tests
########################################
CNTKLIBRARY_TESTS_SRC_PATH =\
Tests/UnitTests/V2LibraryTests
CNTKLIBRARY_TESTS_SRC =\
$(CNTKLIBRARY_END_TO_END_COMMON_SRC_PATH)/Common.cpp \
$(CNTKLIBRARY_TESTS_SRC_PATH)/FeedForwardTests.cpp \
$(CNTKLIBRARY_TESTS_SRC_PATH)/NDArrayViewTests.cpp \
$(CNTKLIBRARY_TESTS_SRC_PATH)/RecurrentFunctionTests.cpp \
$(CNTKLIBRARY_TESTS_SRC_PATH)/BlockTests.cpp \
$(CNTKLIBRARY_TESTS_SRC_PATH)/TensorTests.cpp \
$(CNTKLIBRARY_TESTS_SRC_PATH)/ValueTests.cpp \
$(CNTKLIBRARY_TESTS_SRC_PATH)/SerializationTests.cpp \
Add Sequential Convolution. adding convolution over sequential axis related tests. adding convolution over sequential axis. currently additional supported parameters: auto padding strides groups support for dilation needs to be tested on GPU. updating PrimitiveOpType SerializationTests that is missing from other commits .. convert tabs to spaces. Refine cpp convolution unit tests. Add dilation tests to python convolution unit tests. more detailed comments on shape change for 1d seq conv with reduction rank 0. And other minor tweaks. add EndToEndTests of sequential convolution on MNIST add init_bias tests for seq conv minor change in comments rename ConvolutionOverSequenceAxisNode. Add comment on cudnn failed new test. add more comments, trim spaces add more comments, remove magic number, add more boundary checks. remove the last SetValue for outputSeqAxisDimValue as TensorView Unary Op has already updated the value. fix bug in python seqconv default bias shape, and add related unit tests. small tweak in seq conv to avoid additional gpu memory allocation and increase performance. Example: seq MNIST, and profiling adjust conv c++ value unit test channel size. small update on python seq mnist Sequential convolution v2. * re-designed ConvolutionSequenceShapeNode: refactored to separate out computing output sequence length from v1 node design. And refactored ConvolutionNodeBaseExtended as their common base class. (Since "ConvolutionNodeBase" is not only base class of ConvolutionNode but also PoolingNode). * Performance increase against v1. - compute sequence length by MBLayout instead of mask output from unpack. Avoiding the unnecessary cpu/gpu memory copy. not include py sequence example for now .. need to find they a correct location. add check for truncated sequences in sequential convolution improve code style. Moving sequential convolution in python to a new high level api, to maintain compatibility with previous implementation (special case 1d sequential convolution). Add ConvolutionSequenceShape OP. nit update conv_attribute test for updated convolution parameter move sequential parameter to the last update test shortcircuit for CPU convolution dilation. update endtoendtest - unittest baseline file for new convolution unittests. update makefile to include new unittest file for linux nit Update ConvolutionNode initialization code to handle TransformerNode Initialization. nit nit
2018-06-16 04:07:43 +03:00
$(CNTKLIBRARY_TESTS_SRC_PATH)/ConvolutionFunctionTests.cpp \
$(CNTKLIBRARY_TESTS_SRC_PATH)/LearnerTests.cpp \
$(CNTKLIBRARY_TESTS_SRC_PATH)/FunctionTests.cpp \
$(CNTKLIBRARY_TESTS_SRC_PATH)/DeviceSelectionTests.cpp \
$(CNTKLIBRARY_TESTS_SRC_PATH)/MinibatchSourceTest.cpp \
$(CNTKLIBRARY_TESTS_SRC_PATH)/UserDefinedFunctionTests.cpp \
$(CNTKLIBRARY_TESTS_SRC_PATH)/LoadLegacyModelTests.cpp \
$(CNTKLIBRARY_TESTS_SRC_PATH)/stdafx.cpp
CNTKLIBRARY_TESTS := $(BINDIR)/v2librarytests
CNTKLIBRARY_TESTS_OBJ := $(patsubst %.cu, $(OBJDIR)/%.o, $(patsubst %.cpp, $(OBJDIR)/%.o, $(CNTKLIBRARY_TESTS_SRC)))
ALL += $(CNTKLIBRARY_TESTS)
SRC += $(CNTKLIBRARY_TESTS_SRC)
$(CNTKLIBRARY_TESTS): $(CNTKLIBRARY_TESTS_OBJ) | $(CNTKLIBRARY_LIB) $(READER_LIBS)
@echo $(SEPARATOR)
@mkdir -p $(dir $@)
@echo building $@ for $(ARCH) with build type $(BUILDTYPE)
$(CXX) $(LDFLAGS) $(patsubst %,-L%, $(LIBDIR) $(LIBPATH) $(GDK_NVML_LIB_PATH) $(BOOSTLIB_PATH)) $(patsubst %, $(RPATH)%, $(ORIGINLIBDIR) $(LIBPATH) $(BOOSTLIB_PATH)) -o $@ $^ $(BOOSTLIBS) $(LIBS) -ldl -l$(CNTKLIBRARY) $(L_READER_LIBS)
unittests: $(UNITTEST_EVAL) $(UNITTEST_READER) $(UNITTEST_NETWORK) $(UNITTEST_MATH) $(UNITTEST_BRAINSCRIPT) $(CNTKLIBRARY_TESTS)
endif
2017-03-08 04:24:02 +03:00
ifeq ("$(PYTHON_SUPPORT)","true")
$(info Building Python package)
# Libraries needed for the run-time (i.e., excluding test binaries)
# TODO MPI doesn't appear explicitly here, hidden by mpic++ usage (but currently, it should be user installed)
PYTHON_LIBS_LIST := $(LIBS_LIST) $(IMAGEREADER_LIBS_LIST)
PYTHON_LIBS_EXCLUDE_LIST := m pthread nvidia-ml
PYTHON_SETUP_PY_ARGS :=
2018-03-08 02:57:47 +03:00
PYTHON_PROJECT_NAME:=cntk
ifndef PYTHON_WITH_DEPS
PYTHON_LIBS_EXCLUDE_LIST += cublas cudart curand cusparse cuda cudnn opencv_core opencv_imgproc opencv_imgcodecs mklml_intel mkldnn iomp5 nccl
else
$(warning Building Python package WITH dependencies)
PYTHON_SETUP_PY_ARGS += --with-deps
endif
ifdef PYTHON_WITH_DEBUG
$(warning Building Python packages WITH debug symbols)
PYTHON_SETUP_PY_ARGS += --with-debug-symbol
endif
2018-03-08 02:57:47 +03:00
ifeq ("$(DEVICE)","gpu")
PYTHON_PROJECT_NAME:=cntk-gpu
endif
PYTHON_SETUP_PY_ARGS += --project-name $(PYTHON_PROJECT_NAME)
PYTHON_EXTRA_LIBS_BASENAMES:=$(addsuffix .so,$(addprefix lib,$(filter-out $(PYTHON_LIBS_EXCLUDE_LIST),$(PYTHON_LIBS_LIST))))
# TODO dependencies
# TODO intermediate build results should go below $OBJDIR
.PHONY: python
python: $(PYTHON_LIBS)
@bash -c '\
set -x -e; \
declare -A py_paths; \
2016-12-19 15:49:05 +03:00
py_paths[27]=$(PYTHON27_PATH); \
py_paths[34]=$(PYTHON34_PATH); \
py_paths[35]=$(PYTHON35_PATH); \
2017-03-11 16:35:49 +03:00
py_paths[36]=$(PYTHON36_PATH); \
export LD_LIBRARY_PATH=$$LD_LIBRARY_PATH:$$(echo $(GDK_NVML_LIB_PATH) $(LIBPATH) | tr " " :); \
ldd $$(find $(LIBDIR) -maxdepth 1 -type f -print) | grep "not found" && false; \
export CNTK_VERSION=$(CNTK_VERSION); \
export CNTK_VERSION_BANNER=$(CNTK_VERSION_BANNER); \
2017-03-21 02:15:57 +03:00
export CNTK_COMPONENT_VERSION=$(CNTK_COMPONENT_VERSION); \
export CNTK_LIBRARIES="$(PYTHON_LIBS)"; \
export CNTK_EXTRA_LIBRARIES=$$(ldd $(LIBDIR)/* | grep "^\s.*=> " | cut -d ">" -f 2- --only-delimited | cut -d "(" -f 1 --only-delimited | sort -u | grep -Ff <(echo $(PYTHON_EXTRA_LIBS_BASENAMES) | xargs -n1)); \
test -x $(SWIG_PATH); \
export CNTK_LIB_PATH=$$(readlink -f $(LIBDIR)); \
PYTHONDIR=$$(readlink -f $(PYTHONDIR)); \
test $$? -eq 0; \
cd bindings/python; \
export PATH=$(SWIG_PATH):$$PATH; \
for ver in $(PYTHON_VERSIONS); \
do \
test -x $${py_paths[$$ver]}; \
$${py_paths[$$ver]} setup.py $(PYTHON_SETUP_PY_ARGS) \
build_ext --inplace \
bdist_wheel \
--dist-dir $$PYTHONDIR || exit $$?; \
done'
ALL += python
endif
ifeq ("$(JAVA_SUPPORT)","true")
BINDINGS_DIR=bindings
JAVA_SWIG_DIR=$(BINDINGS_DIR)/java/Swig
JAVA_TEST_DIR=Tests/EndToEndTests/EvalClientTests/JavaEvalTest
GENERATED_JAVA_DIR=$(JAVA_SWIG_DIR)/com/microsoft/CNTK
JDK_BIN_PATH=$(JDK_PATH)/bin
JDK_INCLUDE_PATH:=$(JDK_PATH)/include
JDK_INCLUDE_PATH+=$(JDK_INCLUDE_PATH)/linux
JAVA_SO_NAME=$(LIBDIR)/libCntk.Core.JavaBinding-$(CNTK_COMPONENT_VERSION).so
JAVA_LOAD_DEPS:=$(CNTKMATH_LIB) $(PERF_PROFILER_LIB) $(CNTKLIBRARY_LIB) $(JAVA_SO_NAME)
JAVA_LOAD_DEPS:=$(JAVA_LOAD_DEPS:$(LIBDIR)/%=%)
JAVA_DEP_SO_NAMES_GPU:=libcublas.so libcudart.so libcurand.so libcusparse.so
.PHONY: java
java: $(JAVA_LIBS)
@echo $(SEPARATOR)
@echo creating $@ for $(ARCH) with build type $(BUILDTYPE)
rm -rf $(GENERATED_JAVA_DIR)
mkdir -p $(GENERATED_JAVA_DIR)
$(SWIG_PATH)/swig -c++ -java -package com.microsoft.CNTK $(INCLUDEPATH:%=-I%) -I$(BINDINGS_DIR)/common -outdir $(GENERATED_JAVA_DIR) $(JAVA_SWIG_DIR)/cntk_java.i
$(CXX) $(LDFLAGS) -shared $(COMMON_FLAGS) $(CPPFLAGS) $(CXXFLAGS) $(INCLUDEPATH:%=-I%) $(JDK_INCLUDE_PATH:%=-I%) $(patsubst %,$(RPATH)%, $(ORIGINDIR)) -L$(LIBDIR) $(JAVA_SWIG_DIR)/cntk_java_wrap.cxx -l$(CNTKMATH) -l$(CNTKLIBRARY) -o $(JAVA_SO_NAME)
mkdir -p $(JAVA_SWIG_DIR)/com/microsoft/CNTK/lib/linux
echo $(JAVA_SO_NAME:$(LIBDIR)/%=%) > $(JAVA_SWIG_DIR)/com/microsoft/CNTK/lib/linux/NATIVE_LOAD_MANIFEST
2018-02-21 00:29:09 +03:00
for so in libopen-pal.so.13 libopen-rte.so.12 libmpi.so.12 libmpi_cxx.so.1; do \
cp -p $(MPI_PATH)/lib/$$so $(JAVA_SWIG_DIR)/com/microsoft/CNTK/lib/linux; \
echo $$so >> $(JAVA_SWIG_DIR)/com/microsoft/CNTK/lib/linux/NATIVE_MANIFEST; \
done
for so in libiomp5.so libmklml_intel.so; do \
2017-07-17 18:45:47 +03:00
cp -p $(MKL_LIB_PATH)/$$so $(JAVA_SWIG_DIR)/com/microsoft/CNTK/lib/linux; \
echo $$so >> $(JAVA_SWIG_DIR)/com/microsoft/CNTK/lib/linux/NATIVE_MANIFEST; \
done
for so in $(JAVA_LOAD_DEPS); do \
cp -p $(LIBDIR)/$$so $(JAVA_SWIG_DIR)/com/microsoft/CNTK/lib/linux; \
echo $$so >> $(JAVA_SWIG_DIR)/com/microsoft/CNTK/lib/linux/NATIVE_MANIFEST; \
done
ifdef CUDA_PATH
for so in $(JAVA_DEP_SO_NAMES_GPU); do \
cp -p $(CUDA_PATH)/lib64/$$so $(JAVA_SWIG_DIR)/com/microsoft/CNTK/lib/linux; \
echo $$so >> $(JAVA_SWIG_DIR)/com/microsoft/CNTK/lib/linux/NATIVE_MANIFEST; \
done
cp -p $(CUDNN_PATH)/cuda/lib64/libcudnn.so $(JAVA_SWIG_DIR)/com/microsoft/CNTK/lib/linux
echo 'libcudnn.so' >> $(JAVA_SWIG_DIR)/com/microsoft/CNTK/lib/linux/NATIVE_MANIFEST
cp -p $(GDK_NVML_LIB_PATH)/libnvidia-ml.so $(JAVA_SWIG_DIR)/com/microsoft/CNTK/lib/linux
echo 'libnvidia-ml.so' >> $(JAVA_SWIG_DIR)/com/microsoft/CNTK/lib/linux/NATIVE_MANIFEST
endif
cp -p $(JAVA_SWIG_DIR)/CNTKNativeUtils.java $(JAVA_SWIG_DIR)/com/microsoft/CNTK/CNTKNativeUtils.java
cd $(JAVA_SWIG_DIR) && $(JDK_BIN_PATH)/jar -cvf cntk-javadoc.jar README.md
cd $(JAVA_SWIG_DIR) && $(JDK_BIN_PATH)/jar -cvf cntk-sources.jar com
$(JDK_BIN_PATH)/javac $(GENERATED_JAVA_DIR)/*.java
rm -rf $(GENERATED_JAVA_DIR)/*.java
mkdir -p $(LIBDIR)/java
cd $(JAVA_SWIG_DIR) && $(JDK_BIN_PATH)/jar -cvf cntk.jar com
cp $(JAVA_SWIG_DIR)/cntk.jar $(JAVA_SWIG_DIR)/cntk-sources.jar $(LIBDIR)/java
javac -cp $(JAVA_SWIG_DIR) $(JAVA_TEST_DIR)/src/Main.java -d $(LIBDIR)/java
ALL += java
endif
2018-06-06 18:38:29 +03:00
########################################
# C# Support
########################################
2018-06-15 23:52:43 +03:00
2018-06-06 18:38:29 +03:00
ifeq ("$(CSHARP_SUPPORT)","true")
2018-06-15 23:52:43 +03:00
2018-06-06 18:38:29 +03:00
# This is a short-term hack to shoehorn cmake into our build system. In the near future, we will fully migrate
# to a cmake-based system and this hack will no longer be necessary.
2018-06-15 23:52:43 +03:00
ifeq ("$(findstring debug,$(BUILDTYPE))","debug")
CSHARP_BUILDTYPE:=Debug
else ifeq ("$(findstring release,$(BUILDTYPE))","release")
CSHARP_BUILDTYPE:=Release
else
$(error '$(BUILDTYPE)' does not resemble 'debug' or 'release')
2018-06-06 18:38:29 +03:00
endif
.PHONY: csharp
csharp: $(CSHARP_LIBS)
@echo $(SEPARATOR)
@echo creating $@ for $(ARCH) with build type $(CSHARP_BUILDTYPE)
mkdir -p bindings/csharp/Swig/build/Linux/$(CSHARP_BUILDTYPE)
cd bindings/csharp/Swig/build/Linux/$(CSHARP_BUILDTYPE) && \
2018-06-15 23:52:43 +03:00
cmake ../../.. -DCNTK_VERSION=$(BUILD_VERSION) -DCMAKE_BUILD_TYPE=$(CSHARP_BUILDTYPE) -DCNTK_BUILD_LIB_DIR_HACK=$(LIBDIR) && \
make clean && \
make all
2018-06-06 18:38:29 +03:00
mkdir -p bindings/csharp/CNTKLibraryManagedDll/build/Linux/$(CSHARP_BUILDTYPE)
cd bindings/csharp/CNTKLibraryManagedDll/build/Linux/$(CSHARP_BUILDTYPE) && \
2018-06-15 23:52:43 +03:00
cmake ../../.. -DCNTK_VERSION=$(BUILD_VERSION) -DCMAKE_BUILD_TYPE=$(CSHARP_BUILDTYPE) -DCNTK_BUILD_LIB_DIR_HACK=$(LIBDIR) && \
2018-06-06 18:38:29 +03:00
make
cp --recursive bindings/csharp/CNTKLibraryManagedDll/build/Linux/$(CSHARP_BUILDTYPE)/AnyCPU/$(CSHARP_BUILDTYPE)/* $(LIBDIR)
ALL += csharp
# Note that CMakeLists.txt has not been created for this project yet. The paths created here are really ugly.
V2LibraryCSTests.dll: csharp
@echo $(SEPARATOR)
@echo creating $@ for $(ARCH) with build type $(CSHARP_BUILDTYPE)
cd Tests/UnitTests/V2LibraryCSTests && \
mkdir -p build/Linux/$(CSHARP_BUILDTYPE) && \
dotnet build --force /p:OutDirPrefix=build/Linux/$(CSHARP_BUILDTYPE) /p:PlatformName=Linux -c $(CSHARP_BUILDTYPE)
cp -f Tests/UnitTests/V2LibraryCSTests/build/Linux/$(CSHARP_BUILDTYPE)/AnyCPU/$(CSHARP_BUILDTYPE)/V2LibraryCSTests.* $(LIBDIR)
cp -f Tests/UnitTests/V2LibraryCSTests/build/Linux/$(CSHARP_BUILDTYPE)/AnyCPU/$(CSHARP_BUILDTYPE)/Microsoft.VisualStudio.* $(LIBDIR)
2018-06-06 18:38:29 +03:00
ALL += V2LibraryCSTests.dll
# Note that CMakeLists.txt has not been created for this project yet. The paths created here are really ugly.
CNTKLibraryCSTrainingTest.dll: csharp
@echo $(SEPARATOR)
@echo creating $@ for $(ARCH) with build type $(CSHARP_BUILDTYPE)
cd Tests/EndToEndTests/CNTKv2CSharp/CNTKLibraryCSTrainingTest && \
mkdir -p build/Linux/$(CSHARP_BUILDTYPE) && \
dotnet build --force /p:OutDirPrefix=build/Linux/$(CSHARP_BUILDTYPE) /p:PlatformName=Linux -c $(CSHARP_BUILDTYPE) CNTKLibraryCSTrainingTest.csproj
cp -f Tests/EndToEndTests/CNTKv2CSharp/CNTKLibraryCSTrainingTest/build/Linux/$(CSHARP_BUILDTYPE)/AnyCPU/$(CSHARP_BUILDTYPE)/*.* $(LIBDIR)
ALL += CNTKLibraryCSTrainingTest.dll
# Note that CMakeLists.txt has not been created for this project yet. The paths created here are really ugly.
CNTKLibraryCSEvalExamplesTest.dll: csharp
@echo $(SEPARATOR)
@echo creating $@ for $(ARCH) with build type $(CSHARP_BUILDTYPE)
cd Tests/EndToEndTests/EvalClientTests/CNTKLibraryCSEvalExamplesTest && \
mkdir -p build/Linux/$(CSHARP_BUILDTYPE) && \
dotnet build --force /p:OutDirPrefix=build/Linux/$(CSHARP_BUILDTYPE) /p:PlatformName=Linux -c $(CSHARP_BUILDTYPE) CNTKLibraryCSEvalExamplesTest.csproj
cp -f Tests/EndToEndTests/EvalClientTests/CNTKLibraryCSEvalExamplesTest/build/Linux/$(CSHARP_BUILDTYPE)/AnyCPU/$(CSHARP_BUILDTYPE)/*.* $(LIBDIR)
ALL += CNTKLibraryCSEvalExamplesTest.dll
2018-06-06 18:38:29 +03:00
endif
########################################
# General compile and dependency rules
########################################
ALL += $(ALL_LIBS)
VPATH := $(sort $(dir $(SRC)))
# Define object files
2016-10-25 01:33:31 +03:00
OBJ := \
$(patsubst %.cu, $(OBJDIR)/%.o, $(filter %.cu, $(SRC))) \
$(patsubst %.pb.cc, $(OBJDIR)/%.pb.o, $(filter %.pb.cc, $(SRC))) \
$(patsubst %.cpp, $(OBJDIR)/%.o, $(filter %.cpp, $(SRC)))
# C++ include dependencies generated by -MF compiler option
DEP := $(patsubst %.o, %.d, $(OBJ))
# Include all C++ dependencies, like header files, to ensure that a change in those
# will result in the rebuild.
-include ${DEP}
BUILD_CONFIGURATION := Makefile $(BUILD_TOP)/Config.make
2016-04-11 22:24:24 +03:00
2016-10-25 01:33:31 +03:00
%.pb.cc : %.proto $(BUILD_CONFIGURATION)
@echo $(SEPARATOR)
@echo compiling protobuf $<
$(PROTOC) --proto_path=$(dir $<) --cpp_out=$(dir $<) $<
$(OBJDIR)/%.o : %.cu $(BUILD_CONFIGURATION)
@echo $(SEPARATOR)
2015-12-15 11:58:24 +03:00
@echo creating $@ for $(ARCH) with build type $(BUILDTYPE)
@mkdir -p $(dir $@)
$(NVCC) -c $< -o $@ $(COMMON_FLAGS) $(CUFLAGS) $(INCLUDEPATH:%=-I%) -Xcompiler "-fPIC -Werror"
CNTK support for CUDA 9 CNTK now supports CUDA 9/cuDNN 7. This requires an update to build environment to Ubuntu 16/GCC 5 for Linux, and Visual Studio 2017/VCTools 14.11 for Windows. With CUDA 9, CNTK also added a preview for 16-bit floating point (a.k.a FP16) computation. Please check out the example of FP16 in ResNet50 at /Examples/Image/Classification/ResNet/Python/TrainResNet_ImageNet_Distributed.py Notes on FP16 preview: * FP16 implementation on CPU is not optimized, and it's not supposed to be used in CPU inference directly. User needs to convert the model to 32-bit floating point before running on CPU. * Loss/Criterion for FP16 training needs to be 32bit for accumulation without overflow, using cast function. Please check the example above. * Readers do not have FP16 output unless using numpy to feed data, cast from FP32 to FP16 is needed. Please check the example above. * FP16 gradient aggregation is currently only implemented on GPU using NCCL2. Distributed training with FP16 with MPI is not supported. * FP16 math is a subset of current FP32 implementation. Some model may get Feature Not Implemented exception using FP16. * FP16 is currently not supported in BrainScript. Please use Python for FP16. To setup build and runtime environment on Windows: * Install [Visual Studio 2017](https://www.visualstudio.com/downloads/) with following workloads and components. From command line (use Community version installer as example): vs_community.exe --add Microsoft.VisualStudio.Workload.NativeDesktop --add Microsoft.VisualStudio.Workload.ManagedDesktop --add Microsoft.VisualStudio.Workload.Universal --add Microsoft.Component.PythonTools --add Microsoft.VisualStudio.Component.VC.Tools.14.11 * Install [NVidia CUDA 9](https://developer.nvidia.com/cuda-90-download-archive?target_os=Windows&target_arch=x86_64) * From PowerShell, run: /Tools/devInstall/Windows/DevInstall.ps1 * Start VCTools 14.11 command line, run: cmd /k "%VS2017INSTALLDIR%\VC\Auxiliary\Build\vcvarsall.bat" x64 --vcvars_ver=14.11 * Open /CNTK.sln from the VCTools 14.11 command line. Note that starting CNTK.sln other than VCTools 14.11 command line, would causes CUDA 9 [build error](https://developercommunity.visualstudio.com/content/problem/163758/vs-2017-155-doesnt-support-cuda-9.html). To setup build and runtime environment on Linux using docker, please build Unbuntu 16.04 docker image using Dockerfiles /Tools/docker. For other Linux systems, please refer to the Dockerfiles to setup dependent libraries for CNTK.
2018-01-23 03:58:56 +03:00
$(OBJDIR)/%.pb.o : %.pb.cc $(BUILD_CONFIGURATION)
2016-10-25 01:33:31 +03:00
@echo $(SEPARATOR)
@echo creating $@ for $(ARCH) with build type $(BUILDTYPE)
@mkdir -p $(dir $@)
$(CXX) -c $< -o $@ $(COMMON_FLAGS) $(CPPFLAGS) $(CXXFLAGS) $(INCLUDEPATH:%=-I%) -MD -MP -MF ${@:.o=.d}
CNTK support for CUDA 9 CNTK now supports CUDA 9/cuDNN 7. This requires an update to build environment to Ubuntu 16/GCC 5 for Linux, and Visual Studio 2017/VCTools 14.11 for Windows. With CUDA 9, CNTK also added a preview for 16-bit floating point (a.k.a FP16) computation. Please check out the example of FP16 in ResNet50 at /Examples/Image/Classification/ResNet/Python/TrainResNet_ImageNet_Distributed.py Notes on FP16 preview: * FP16 implementation on CPU is not optimized, and it's not supposed to be used in CPU inference directly. User needs to convert the model to 32-bit floating point before running on CPU. * Loss/Criterion for FP16 training needs to be 32bit for accumulation without overflow, using cast function. Please check the example above. * Readers do not have FP16 output unless using numpy to feed data, cast from FP32 to FP16 is needed. Please check the example above. * FP16 gradient aggregation is currently only implemented on GPU using NCCL2. Distributed training with FP16 with MPI is not supported. * FP16 math is a subset of current FP32 implementation. Some model may get Feature Not Implemented exception using FP16. * FP16 is currently not supported in BrainScript. Please use Python for FP16. To setup build and runtime environment on Windows: * Install [Visual Studio 2017](https://www.visualstudio.com/downloads/) with following workloads and components. From command line (use Community version installer as example): vs_community.exe --add Microsoft.VisualStudio.Workload.NativeDesktop --add Microsoft.VisualStudio.Workload.ManagedDesktop --add Microsoft.VisualStudio.Workload.Universal --add Microsoft.Component.PythonTools --add Microsoft.VisualStudio.Component.VC.Tools.14.11 * Install [NVidia CUDA 9](https://developer.nvidia.com/cuda-90-download-archive?target_os=Windows&target_arch=x86_64) * From PowerShell, run: /Tools/devInstall/Windows/DevInstall.ps1 * Start VCTools 14.11 command line, run: cmd /k "%VS2017INSTALLDIR%\VC\Auxiliary\Build\vcvarsall.bat" x64 --vcvars_ver=14.11 * Open /CNTK.sln from the VCTools 14.11 command line. Note that starting CNTK.sln other than VCTools 14.11 command line, would causes CUDA 9 [build error](https://developercommunity.visualstudio.com/content/problem/163758/vs-2017-155-doesnt-support-cuda-9.html). To setup build and runtime environment on Linux using docker, please build Unbuntu 16.04 docker image using Dockerfiles /Tools/docker. For other Linux systems, please refer to the Dockerfiles to setup dependent libraries for CNTK.
2018-01-23 03:58:56 +03:00
$(OBJDIR)/%.o : %.cpp $(BUILD_CONFIGURATION)
@echo $(SEPARATOR)
2015-12-15 11:58:24 +03:00
@echo creating $@ for $(ARCH) with build type $(BUILDTYPE)
@mkdir -p $(dir $@)
$(CXX) -c $< -o $@ $(COMMON_FLAGS) $(CPPFLAGS) $(CXXFLAGS) $(INCLUDEPATH:%=-I%) -MD -MP -MF ${@:.o=.d}
2018-06-28 18:38:36 +03:00
$(OBJDIR)/%.o : %.cc $(BUILD_CONFIGURATION)
@echo $(SEPARATOR)
@echo creating $@ for $(ARCH) with build type $(BUILDTYPE)
@mkdir -p $(dir $@)
$(CXX) -c $< -o $@ $(COMMON_FLAGS) $(CPPFLAGS) $(CXXFLAGS) $(INCLUDEPATH:%=-I%) -MD -MP -MF ${@:.o=.d}
.PHONY: clean buildall all unittests
clean:
@echo $(SEPARATOR)
@rm -rf $(OBJDIR)
@rm -rf $(ALL)
2016-02-01 22:16:08 +03:00
@rm -rf $(BUILDINFO)
2015-12-15 11:58:24 +03:00
@echo finished cleaning up the project
buildall : $(ALL)
@echo $(SEPARATOR)
@echo finished building for $(ARCH) with build type $(BUILDTYPE)