changes to Makefile.cpu, Makefile.gpu and CPUMatrix.cpp to have it compile in linux with ACML library.
This commit is contained in:
Hakan Erdogan
Родитель
de39c79e4f
Коммит
09afb0dd9e
28
Makefile.cpu
28
Makefile.cpu
|
|
@ -22,12 +22,25 @@
|
|||
# This makefile will be extended/completed as we go.
|
||||
|
||||
CC = g++
|
||||
OBJDIR = .obj.cpu
|
||||
|
||||
# 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
|
||||
MKL_INCLUDE = $(MKL_PATH)/mkl/include
|
||||
MKL_LIB = -L$(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 -lm
|
||||
MATHLIB_INCLUDE = $(MKL_PATH)/mkl/include
|
||||
MATHLIB_LIB = -L$(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
|
||||
|
||||
INCFLAGS = -I Common/Include -I Math/Math -I MachineLearning/cn -I $(MKL_INCLUDE)
|
||||
INCFLAGS = -I Common/Include -I Math/Math -I MachineLearning/cn -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
|
||||
|
|
@ -54,13 +67,14 @@ CORE_SRC = $(CN_SRC) $(MATH_SRC) $(COMMON_SRC)
|
|||
|
||||
SRC = $(READER_SRC) $(CORE_SRC)
|
||||
|
||||
CFLAGS = -std=c++0x -std=c++11 -DCPUONLY -D_POSIX_SOURCE -D_XOPEN_SOURCE=600 -D__USE_XOPEN2K -DUSE_MKL -fopenmp -fpermissive -fPIC
|
||||
CFLAGS = -std=c++0x -std=c++11 -DCPUONLY -D_POSIX_SOURCE -D_XOPEN_SOURCE=600 -D__USE_XOPEN2K $(MATHLIB_DEFINE) -fopenmp -fpermissive -fPIC
|
||||
|
||||
DEBUG = -g
|
||||
|
||||
all: cn.exe UCIFastReader SequenceReader LUSequenceReader
|
||||
mkdir -p bin
|
||||
mv cn.exe *.so bin/
|
||||
mkdir -p bin.cpu
|
||||
mv cn.exe *.so bin.cpu/
|
||||
ln -sf bin.cpu bin
|
||||
|
||||
UCIFastReader: ${UCIFASTREADER_SRC:.cpp=.o} ${CORE_SRC:.cpp=.o}
|
||||
$(CC) $(DEBUG) -fPIC -shared -o $(addsuffix .so, $@) $^
|
||||
|
|
@ -78,7 +92,7 @@ LUSequenceReader: ${LUSEQUENCEREADER_SRC:.cpp=.o} ${CORE_SRC:.cpp=.o}
|
|||
# $(CC) -o $(addsuffix .so, $@) $^ -fPIC -shared
|
||||
|
||||
cn.exe: ${CORE_SRC:.cpp=.o}
|
||||
$(CC) $(DEBUG) -o $@ $^ $(MKL_LIB) -fopenmp -ldl
|
||||
$(CC) $(DEBUG) -o $@ $^ $(MATHLIB_LIB) -fopenmp -ldl
|
||||
|
||||
-include ${SRC:.cpp=.d}
|
||||
|
||||
|
|
|
|||
31
Makefile.gpu
31
Makefile.gpu
|
|
@ -24,15 +24,27 @@
|
|||
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
|
||||
|
||||
MKL_PATH = /opt/intel/composer_xe_2013_sp1.0.080
|
||||
MKL_INCLUDE = $(MKL_PATH)/include
|
||||
MKL_LIB = -L$(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 -lm
|
||||
|
||||
INCFLAGS = -I Common/Include -I Math/Math -I MachineLearning/cn -I $(CUDA_INCLUDE) -I $(MKL_INCLUDE)
|
||||
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
|
||||
|
|
@ -58,7 +70,7 @@ READER_SRC = $(UCIFASTREADER_SRC) $(LUSEQUENCEREADER_SRC) $(HTKMLFREADER_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 -DUSE_MKL -fopenmp -fpermissive
|
||||
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
|
||||
|
||||
|
|
@ -67,8 +79,9 @@ DEBUG = -g
|
|||
GPU_DEBUG = -G
|
||||
|
||||
all: cn.exe UCIFastReader SequenceReader LUSequenceReader
|
||||
mkdir -p bin
|
||||
mv cn.exe *.so bin/
|
||||
mkdir -p bin.gpu
|
||||
mv cn.exe *.so bin.gpu/
|
||||
ln -sf bin.gpu bin
|
||||
|
||||
tmp = ${CORE_SRC:.cpp=.o}
|
||||
|
||||
|
|
@ -88,7 +101,7 @@ LUSequenceReader: ${LUSEQUENCEREADER_SRC:.cpp=.o} ${tmp:.cu=.o}
|
|||
# $(CC) -o $(addsuffix .so, $@) $^ -fPIC -shared
|
||||
|
||||
cn.exe: ${tmp:.cu=.o}
|
||||
$(CC) $(DEBUG) -o $@ $^ $(CUDA_LIB) $(MKL_LIB) -fopenmp -ldl -fPIC
|
||||
$(CC) $(DEBUG) -o $@ $^ $(CUDA_LIB) $(MATHLIB_LIB) -fopenmp -ldl -fPIC
|
||||
|
||||
-include ${SRC:.cpp=.d}
|
||||
|
||||
|
|
|
|||
|
|
@ -3561,16 +3561,24 @@ namespace Microsoft { namespace MSR { namespace CNTK {
|
|||
const char flag = 'A';
|
||||
if (sizeof(ElemType) == sizeof(double))
|
||||
{
|
||||
#ifndef USE_MKL
|
||||
dgesvd('A', 'A', (int)m, (int)n, reinterpret_cast <double*>(A.m_pArray), (int)lda, reinterpret_cast <double*>(SIGMA.m_pArray), reinterpret_cast <double*>(U.m_pArray), (int)ldu, reinterpret_cast <double*>(VT.m_pArray), (int)ldvt, &info);
|
||||
#else
|
||||
//missing arguments fixed! --author Wengong Jin 2014/12/15
|
||||
double *work = new double[lwork];
|
||||
dgesvd(&flag, &flag, (int *) &m, (int *) &n, reinterpret_cast <double*>(A.m_pArray), (int *) &lda, reinterpret_cast <double*>(SIGMA.m_pArray), reinterpret_cast <double*>(U.m_pArray), (int *) &ldu, reinterpret_cast <double*>(VT.m_pArray), (int *) &ldvt, work, &lwork, &info);
|
||||
#endif
|
||||
}
|
||||
else
|
||||
{
|
||||
#pragma warning (suppress: 4244)
|
||||
#ifndef USE_MKL
|
||||
sgesvd('A', 'A', (int)m, (int)n, reinterpret_cast <float*>(A.m_pArray), (int)lda, reinterpret_cast <float*>(SIGMA.m_pArray), reinterpret_cast <float*>(U.m_pArray), (int)ldu, reinterpret_cast <float*>(VT.m_pArray), (int)ldvt, &info);
|
||||
#else
|
||||
//missing arguments fixed! --author Wengong Jin 2014/12/15
|
||||
float *work = new float[lwork];
|
||||
sgesvd(&flag, &flag, (int *) &m, (int *) &n, reinterpret_cast <float*>(A.m_pArray), (int *) &lda, reinterpret_cast <float*>(SIGMA.m_pArray), reinterpret_cast <float*>(U.m_pArray), (int *) &ldu, reinterpret_cast <float*>(VT.m_pArray), (int *) &ldvt, work, &lwork, &info);
|
||||
#endif
|
||||
}
|
||||
}
|
||||
|
||||
|
|
|
|||
Загрузка…
Ссылка в новой задаче