120 строки
4.9 KiB
Makefile
120 строки
4.9 KiB
Makefile
# WORK IN PROGRESS, not currently complete nor usable
|
|
|
|
# makefile for a Linux/GCC build of CNTK
|
|
# This needs ACML_PATH. E.g. in tcsh, say: setenv ACML_PATH C:/AMD/acml5.3.1/ifort64_mp
|
|
|
|
# This is work in progress and not at all complete or usable.
|
|
#
|
|
# 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.
|
|
#
|
|
# The planned steps are:
|
|
# - runnable non-GPU GCC-built version under Cygwin
|
|
# - get all CPU-only sources to compile with GCC/x64 under Cygwin --currently ongoing work
|
|
# - port the dynamic-loading mechanism
|
|
# - runnable non-GPU version on actual Linux
|
|
# - enable CUDA on Linux (=makefile code and figuring out the right compiler options)
|
|
#
|
|
# Any help is welcome, of course!
|
|
#
|
|
# This makefile will be extended/completed as we go.
|
|
|
|
CC = g++
|
|
NVCC = nvcc
|
|
|
|
# comment following and uncomment the next one to enable MKL library
|
|
USE_ACML=1
|
|
#USE_MKL=1
|
|
|
|
ifdef USE_MKL
|
|
MKL_PATH = /opt/intel/composer_xe_2013_sp1.0.080
|
|
MATHLIB_INCLUDE = $(MKL_PATH)/include
|
|
MATHLIB_LIB = -L$(MKL_PATH)/compiler/lib/intel64 -L$(MKL_PATH)/mkl/lib/intel64 -L$(MKL_PATH)/compiler/lib/mic -L$(MKL_PATH)/mkl/lib/mic -lmkl_intel_lp64 -lmkl_intel_thread -lmkl_core -lm -liomp5 -lpthread
|
|
MATHLIB_DEFINE = -DUSE_MKL
|
|
else
|
|
ACML_PATH = /usr/local/acml5.3.0/gfortran64
|
|
MATHLIB_INCLUDE = $(ACML_PATH)/include
|
|
MATHLIB_LIB = -L$(ACML_PATH)/lib -lacml -lm
|
|
MATHLIB_DEFINE = -DUSE_ACML
|
|
endif
|
|
|
|
CUDA_PATH = /usr/local/cuda-6.5
|
|
CUDA_INCLUDE = $(CUDA_PATH)/include
|
|
CUDA_LIB = -L$(CUDA_PATH)/lib64 -lcublas -lcudart -lcuda -lcurand -lcusparse -lnvidia-ml
|
|
|
|
INCFLAGS = -I Common/Include -I Math/Math -I MachineLearning/cn -I $(CUDA_INCLUDE) -I $(MATHLIB_INCLUDE)
|
|
|
|
COMMON_SRC = Common/fileutil.cpp Common/DataWriter.cpp Common/ConfigFile.cpp Common/DataReader.cpp \
|
|
Common/Eval.cpp Common/File.cpp Common/BestGpu.cpp
|
|
|
|
MATH_SRC = Math/Math/Matrix.cpp Math/Math/GPUMatrix.cu Math/Math/GPUMatrixCUDAKernels.cu Math/Math/GPUSparseMatrix.cu Math/Math/GPUWatcher.cu \
|
|
Math/Math/CPUMatrix.cpp Math/Math/CPUSparseMatrix.cpp #Math/Math/InstantiateTemplates.cu
|
|
|
|
CN_SRC = MachineLearning/cn/NetworkDescriptionLanguage.cpp MachineLearning/cn/cn.cpp MachineLearning/cn/ComputationNode.cpp \
|
|
MachineLearning/cn/ModelEditLanguage.cpp MachineLearning/cn/PTaskGraphBuilder.cpp \
|
|
MachineLearning/cn/SimpleNetworkBuilder.cpp MachineLearning/cn/tests.cpp MachineLearning/CNTKEval/CNTKEval.cpp
|
|
|
|
BINARYREADER_SRC = #DataReader/BinaryReader/BinaryWriter.cpp DataReader/BinaryReader/BinaryReader.cpp DataReader/BinaryReader/BinaryFile.cpp
|
|
|
|
HTKMLFREADER_SRC = #DataReader/HTKMLFReader/HTKMLFWriter.cpp DataReader/HTKMLFReader/latticearchive.cpp DataReader/HTKMLFReader/HTKMLFReader.cpp
|
|
|
|
SEQUENCEREADER_SRC = DataReader/SequenceReader/SequenceReader.cpp DataReader/SequenceReader/SequenceParser.cpp DataReader/SequenceReader/Exports.cpp
|
|
|
|
LUSEQUENCEREADER_SRC = DataReader/LUSequenceReader/LUSequenceReader.cpp DataReader/LUSequenceReader/LUSequenceParser.cpp DataReader/LUSequenceReader/Exports.cpp
|
|
|
|
UCIFASTREADER_SRC = DataReader/UCIFastReader/UCIParser.cpp DataReader/UCIFastReader/UCIFastReader.cpp DataReader/UCIFastReader/Exports.cpp
|
|
|
|
READER_SRC = $(UCIFASTREADER_SRC) $(LUSEQUENCEREADER_SRC) $(HTKMLFREADER_SRC) $(SEQUENCEREADER_SRC) $(BINARYREADER_SRC)
|
|
|
|
CORE_SRC = $(CN_SRC) $(MATH_SRC) $(COMMON_SRC)
|
|
|
|
CFLAGS = -std=c++0x -std=c++11 -D_POSIX_SOURCE -D_XOPEN_SOURCE=600 -D__USE_XOPEN2K $(MATHLIB_DEFINE) -fopenmp -fpermissive
|
|
|
|
NVCCFLAGS = -std=c++11 -D_POSIX_SOURCE -D_XOPEN_SOURCE=600 -D__USE_XOPEN2K -arch=compute_20
|
|
|
|
DEBUG = -g
|
|
|
|
GPU_DEBUG = -G
|
|
|
|
all: cn.exe UCIFastReader SequenceReader LUSequenceReader
|
|
mkdir -p bin.gpu
|
|
mv cn.exe *.so bin.gpu/
|
|
ln -sf bin.gpu bin
|
|
|
|
tmp = ${CORE_SRC:.cpp=.o}
|
|
|
|
UCIFastReader: ${UCIFASTREADER_SRC:.cpp=.o} ${tmp:.cu=.o}
|
|
$(CC) $(DEBUG) -fPIC -shared -o $(addsuffix .so, $@) $^
|
|
|
|
SequenceReader: ${SEQUENCEREADER_SRC:.cpp=.o} ${tmp:.cu=.o}
|
|
$(CC) $(DEBUG) -fPIC -shared -o $(addsuffix .so, $@) $^
|
|
|
|
LUSequenceReader: ${LUSEQUENCEREADER_SRC:.cpp=.o} ${tmp:.cu=.o}
|
|
$(CC) $(DEBUG) -fPIC -shared -o $(addsuffix .so, $@) $^
|
|
|
|
#HTKMLFReader: ${HTKMLFREADER_SRC:.cpp=.o} ${COMMON_SRC:.cpp=.o}
|
|
# $(CC) -o $(addsuffix .so, $@) $^ -fPIC -shared
|
|
|
|
#BinaryReader: ${BINARYREADER_SRC:.cpp=.o} ${COMMON_SRC:.cpp=.o}
|
|
# $(CC) -o $(addsuffix .so, $@) $^ -fPIC -shared
|
|
|
|
cn.exe: ${tmp:.cu=.o}
|
|
$(CC) $(DEBUG) -o $@ $^ $(CUDA_LIB) $(MATHLIB_LIB) -fopenmp -ldl -fPIC
|
|
|
|
-include ${SRC:.cpp=.d}
|
|
|
|
${MATH_SRC:.cu=.o}:%.o: %.cu
|
|
$(NVCC) -c $< -o $@ $(DEBUG) $(GPU_DEBUG) $(NVCCFLAGS) $(INCFLAGS) -Xcompiler -fPIC
|
|
|
|
%.o: %.cpp
|
|
$(CC) -c $< -o $@ $(DEBUG) $(CFLAGS) $(INCFLAGS) -fPIC -MD -MP -MF ${@:.o=.d}
|
|
|
|
.PHONY: clean
|
|
|
|
clean:
|
|
find . -name "*.o" -type f -delete
|
|
find . -name "*.d" -type f -delete
|
|
rm -rf bin
|