c - 链接 CUDA 运行 fastHOG 算法的问题

Question

我正在尝试在我的 Linux 服务器中设置 fastHOG 代码库，但无法完成它，因为我遇到了一堆链接错误。我在这里给出链接错误的示例部分

tmpxft_00006d91_00000000-1_HOGHistogram.cudafe1.cpp:(.text+0x910): undefined reference    to  'cudaGetErrorString'
tmpxft_00006d91_00000000-1_HOGHistogram.cudafe1.cpp:(.text+0x944): undefined reference   to  'cudaGetErrorString'
/home/n8385106/bin/contrib/qut/qutanomaly/matlab/person- detector/fasthog/obj/release/HOG/HOGHistogram.cu.o: In function 'InitHistograms(int, int, int, int, int, float)':
tmpxft_00006d91_00000000-1_HOGHistogram.cudafe1.cpp:(.text+0xac0): undefined reference   to 'cudaCreateChannelDesc'
tmpxft_00006d91_00000000-1_HOGHistogram.cudafe1.cpp:(.text+0xafe): undefined reference to  'cudaMallocArray'
tmpxft_00006d91_00000000-1_HOGHistogram.cudafe1.cpp:(.text+0xb46): undefined reference to 'cudaMemcpyToArray'
tmpxft_00006d91_00000000-1_HOGHistogram.cudafe1.cpp:(.text+0xc3d): undefined reference to 'cudaMemcpyToSymbol'
 tmpxft_00006d91_00000000-1_HOGHistogram.cudafe1.cpp:(.text+0xc63): undefined reference to 'cudaMemcpyToSymbol'
tmpxft_00006d91_00000000-1_HOGHistogram.cudafe1.cpp:(.text+0xc89): undefined reference to 'cudaMemcpyToSymbol'
tmpxft_00006d91_00000000-1_HOGHistogram.cudafe1.cpp:(.text+0xcae): undefined reference to 'cudaMemcpyToSymbol'
tmpxft_00006d91_00000000-1_HOGHistogram.cudafe1.cpp:(.text+0xccd): undefined reference to 'cudaGetErrorString'
tmpxft_00006d91_00000000-1_HOGHistogram.cudafe1.cpp:(.text+0xd01): undefined reference to 'cudaGetErrorString'
 tmpxft_00006d91_00000000-1_HOGHistogram.cudafe1.cpp:(.text+0xd15): undefined reference to 'cudaGetErrorString'
tmpxft_00006d91_00000000-1_HOGHistogram.cudafe1.cpp:(.text+0xd29): undefined reference to 'cudaGetErrorString'
tmpxft_00006d91_00000000-1_HOGHistogram.cudafe1.cpp:(.text+0xd3d): undefined reference to 'cudaGetErrorString'

链接器似乎没有意识到 make 文件中提供的任何链接器库。它没有说“无法找到这个库”之类的内容，但它避免了提供有关要链接的库的所有信息，例如

# Libs
LIB       := -L$(CUDA_INSTALL_PATH)/cuda/lib64 -L$(LIBDIR) - L$(COMMONDIR)/lib/$(OSLOWER) 

# If dynamically linking to CUDA and CUDART, we exclude the libraries from the LIB
 ifeq ($(USECUDADYNLIB),1)
 LIB += ${OPENGLLIB} $(PARAMGLLIB) $(RENDERCHECKGLLIB) $(CUDPPLIB) ${LIB} 
 else
  # static linking, we will statically link against CUDA and CUDART
 ifeq ($(USEDRVAPI),1)
 LIB += -lcuda   ${OPENGLLIB} $(PARAMGLLIB) $(RENDERCHECKGLLIB) $(CUDPPLIB) ${LIB} 
  else
 LIB += -lcudart ${OPENGLLIB} $(PARAMGLLIB) $(RENDERCHECKGLLIB) $(CUDPPLIB) ${LIB}
 endif
 endif

 ifeq ($(USECUFFT),1)
 ifeq ($(emu),1)
 LIB += -lcufftemu
 else
  LIB += -lcufft
 endif
endif

ifeq ($(USECUBLAS),1)
 ifeq ($(emu),1)
LIB += -lcublasemu
 else
  LIB += -lcublas
 endif
 endif

我能够创建所有目标文件，但在链接过程中出现问题，我是 CUDA 的新手，有人可以帮我解决这个问题吗？

我的操作系统是64位linux

编辑:我的MakeFile

# Add source files here
EXECUTABLE  := fastHOG
# C/C++ source files (compiled with gcc / c++)
 CCFILES        := \
    fastHOG.cpp \
# HOG UTILS 
 CCUTILS        := \
    ImageWindow.cpp \
# CC HOG 
 CCHOG      := \
    HOGImage.cpp \
    HOGEngine.cpp \
    HOGNMS.cpp \
# CUDA HOG 
 CUFILES        := \
    HOGEngineDevice.cu \
    HOGConvolution.cu \
    HOGHistogram.cu \
    HOGPadding.cu \
    HOGScale.cu \
    HOGSVMSlider.cu \
    HOGUtils.cu \
################################################################################
# Rules and targets

include common.mk

common.mk 文件的内容

  ################################################################################
#
# Copyright 1993-2006 NVIDIA Corporation.  All rights reserved.
#
################################################################################
#
# Common build script
#
################################################################################
 .SUFFIXES : .cu .cu_dbg.o .c_dbg.o .cpp_dbg.o .cu_rel.o .c_rel.o .cpp_rel.o .cubin

 #Add new SM Versions here as devices with new Compute Capability are released
 SM_VERSIONS := sm_10 sm_11 sm_12 sm_13

 CUDA_INSTALL_PATH ?= fasthoglib/cuda/cuda

 ifdef cuda-install
  CUDA_INSTALL_PATH := $(cuda-install)
 endif

  # detect OS
  OSUPPER = $(shell uname -s 2>/dev/null | tr [:lower:] [:upper:])
  OSLOWER = $(shell uname -s 2>/dev/null | tr [:upper:] [:lower:])
  # 'linux' is output for Linux system, 'darwin' for OS X
  DARWIN = $(strip $(findstring DARWIN, $(OSUPPER)))


# Basic directory setup for SDK
# (override directories only if they are not already defined)
SRCDIR      ?= 
SRCDIRUTILS ?= Utils
SRCDIRHOG   ?= HOG
ROOTDIR     ?= /home/n8385106/src/saivt-vxl/contrib/qut/qutanomaly/matlab/pedestrian-detector/fasthoglib/cuda/sdk
ROOTBINDIR  ?= /home/n8385106/bin/contrib/qut/qutanomaly/matlab/person-detector/fasthog/bin
BINDIR      ?= $(ROOTBINDIR)
ROOTOBJDIR  ?= /home/n8385106/bin/contrib/qut/qutanomaly/matlab/person-detector/fasthog/obj
LIBDIR      := $(ROOTDIR)/C/lib
COMMONDIR   := $(ROOTDIR)/C/common

# Compilers
NVCC       := $(CUDA_INSTALL_PATH)/bin/nvcc 
CXX        := g++
CC         := gcc
LINK       := g++ -fPIC

# Includes
INCLUDES  += -I. -I$(CUDA_INSTALL_PATH)/cuda/include -I$(COMMONDIR)/inc 
# architecture flag for cubin build
CUBIN_ARCH_FLAG := -m32

# Warning flags
CXXWARN_FLAGS := \
    -W -Wall \
    -Wimplicit \
    -Wswitch \
    -Wformat \
    -Wchar-subscripts \
    -Wparentheses \
    -Wmultichar \
    -Wtrigraphs \
    -Wpointer-arith \
    -Wcast-align \
    -Wreturn-type \
    -Wno-unused-function \
    $(SPACE)

CWARN_FLAGS := $(CXXWARN_FLAGS) \
    -Wstrict-prototypes \
    -Wmissing-prototypes \
    -Wmissing-declarations \
    -Wnested-externs \
    -Wmain \

# Compiler-specific flags
NVCCFLAGS :=   
CXXFLAGS  := $(CXXWARN_FLAGS)
CFLAGS    := $(CWARN_FLAGS)

# Common flags
COMMONFLAGS += $(INCLUDES) -DUNIX

# Debug/release configuration
ifeq ($(dbg),1)
    COMMONFLAGS += -g
    NVCCFLAGS   += -D_DEBUG
    BINSUBDIR   := debug
    LIBSUFFIX   := D
else 
    COMMONFLAGS += -O3 
    BINSUBDIR   := release
    LIBSUFFIX   :=
    NVCCFLAGS   += --compiler-options -fno-strict-aliasing
    CXXFLAGS    += -fno-strict-aliasing
    CFLAGS      += -fno-strict-aliasing
endif

# append optional arch/SM version flags (such as -arch sm_11)
#NVCCFLAGS += $(SMVERSIONFLAGS)

# architecture flag for cubin build
CUBIN_ARCH_FLAG := -m32

# detect if 32 bit or 64 bit system
HP_64 = $(shell uname -m | grep 64)

# OpenGL is used or not (if it is used, then it is necessary to include GLEW)
ifeq ($(USEGLLIB),1)

    ifneq ($(DARWIN),)
        OPENGLLIB := -L/System/Library/Frameworks/OpenGL.framework/Libraries -lGL -lGLU $(COMMONDIR)/lib/$(OSLOWER)/libGLEW.a
    else
        OPENGLLIB := -lGL -lGLU -lX11 -lXi -lXmu

        ifeq "$(strip $(HP_64))" ""
            OPENGLLIB += -lGLEW -L/usr/X11R6/lib
        else
            OPENGLLIB += -lGLEW_x86_64 -L/usr/X11R6/lib64
        endif
    endif

    CUBIN_ARCH_FLAG := -m64
endif

ifeq ($(USEGLUT),1)
    ifneq ($(DARWIN),)
        OPENGLLIB += -framework GLUT
    else
        OPENGLLIB += -lglut
    endif
endif

ifeq ($(USEPARAMGL),1)
    PARAMGLLIB := -lparamgl$(LIBSUFFIX)
endif

ifeq ($(USERENDERCHECKGL),1)
    RENDERCHECKGLLIB := -lrendercheckgl$(LIBSUFFIX)
endif
USECUDPP := 1;
ifeq ($(USECUDPP), 1)
    ifeq "$(strip $(HP_64))" ""
        CUDPPLIB := -lcudpp
    else
        CUDPPLIB := -lcudpp64
    endif

    CUDPPLIB := $(CUDPPLIB)$(LIBSUFFIX)

    ifeq ($(emu), 1)
        CUDPPLIB := $(CUDPPLIB)_emu
    endif
endif

# Libs
LIB       := -L$(CUDA_INSTALL_PATH)/cuda/lib64 -L$(LIBDIR) -L$(COMMONDIR)/lib/$(OSLOWER) 

# If dynamically linking to CUDA and CUDART, we exclude the libraries from the LIB
ifeq ($(USECUDADYNLIB),1)
     LIB += ${OPENGLLIB} $(PARAMGLLIB) $(RENDERCHECKGLLIB) $(CUDPPLIB) ${LIB} 
else
# static linking, we will statically link against CUDA and CUDART
  ifeq ($(USEDRVAPI),1)
     LIB += -lcuda   ${OPENGLLIB} $(PARAMGLLIB) $(RENDERCHECKGLLIB) $(CUDPPLIB) ${LIB} 
  else
     LIB += -lcudart ${OPENGLLIB} $(PARAMGLLIB) $(RENDERCHECKGLLIB) $(CUDPPLIB) ${LIB}
  endif
endif

ifeq ($(USECUFFT),1)
  ifeq ($(emu),1)
    LIB += -lcufftemu
  else
    LIB += -lcufft
  endif
endif

ifeq ($(USECUBLAS),1)
  ifeq ($(emu),1)
    LIB += -lcublasemu
  else
    LIB += -lcublas
  endif
endif

# Lib/exe configuration
ifneq ($(STATIC_LIB),)
    TARGETDIR := $(LIBDIR)
    TARGET   := $(subst .a,$(LIBSUFFIX).a,$(LIBDIR)/$(STATIC_LIB))
    LINKLINE  = ar rucv $(TARGET) $(OBJS) 
else
    LIB += -lcutil$(LIBSUFFIX)
    # Device emulation configuration
    ifeq ($(emu), 1)
        NVCCFLAGS   += -deviceemu
        CUDACCFLAGS += 
        BINSUBDIR   := emu$(BINSUBDIR)
        # consistency, makes developing easier
        CXXFLAGS        += -D__DEVICE_EMULATION__
        CFLAGS          += -D__DEVICE_EMULATION__
    endif
    TARGETDIR := $(BINDIR)/$(BINSUBDIR)
    TARGET    := $(TARGETDIR)/$(EXECUTABLE)
    #fltk

    LIB += -lfltk2 -lXft -lfltk2_images -lXext -lXinerama -lXi
    #boost thread for interface
    LIB += -lboost_thread
    #read images in HOGImage from file
    LIB := /pkg/suse11/cuda/4.2/sdk/CUDALibraries/common/FreeImage/lib/linux/libfreeimage64.a
    LINKLINE  = $(LINK) -o $(TARGET) $(OBJS) $(LIB)
endif

# check if verbose 
ifeq ($(verbose), 1)
    VERBOSE := 
else
    VERBOSE := @
endif

################################################################################
# Check for input flags and set compiler flags appropriately
################################################################################
ifeq ($(fastmath), 1)
    NVCCFLAGS += -use_fast_math
endif

ifeq ($(keep), 1)
    NVCCFLAGS += -keep
    NVCC_KEEP_CLEAN := *.i* *.cubin *.cu.c *.cudafe* *.fatbin.c *.ptx
endif

ifdef maxregisters
    NVCCFLAGS += -maxrregcount $(maxregisters)
endif

# Add cudacc flags
NVCCFLAGS += $(CUDACCFLAGS)

# workaround for mac os x cuda 1.1 compiler issues
ifneq ($(DARWIN),)
    NVCCFLAGS += --host-compilation C
endif

# Add common flags
NVCCFLAGS += $(COMMONFLAGS)
CXXFLAGS  += $(COMMONFLAGS)
CFLAGS    += $(COMMONFLAGS)

ifeq ($(nvcc_warn_verbose),1)
    NVCCFLAGS += $(addprefix --compiler-options ,$(CXXWARN_FLAGS)) 
    NVCCFLAGS += --compiler-options -fno-strict-aliasing
endif

################################################################################
# Set up object files
################################################################################
OBJDIR := $(ROOTOBJDIR)/$(BINSUBDIR)
OBJS  +=  $(patsubst %.cpp,$(OBJDIR)/%.cpp.o,$(notdir $(CCFILES)))

OBJDIRUTILS := $(ROOTOBJDIR)/$(BINSUBDIR)/$(SRCDIRUTILS)
OBJS +=  $(patsubst %.cpp,$(OBJDIRUTILS)/%.cpp.o,$(notdir $(CCUTILS)))

OBJDIRHOG := $(ROOTOBJDIR)/$(BINSUBDIR)/$(SRCDIRHOG)
OBJS +=  $(patsubst %.cu,$(OBJDIRHOG)/%.cu.o,$(notdir $(CUFILES)))
OBJS +=  $(patsubst %.cpp,$(OBJDIRHOG)/%.cpp.o,$(notdir $(CCHOG)))

################################################################################
# Set up cubin files
################################################################################
CUBINDIR := $(SRCDIR)data
CUBINS +=  $(patsubst %.cu,$(CUBINDIR)/%.cubin,$(notdir $(CUBINFILES)))

################################################################################
# Rules
################################################################################
$(OBJDIR)/%.c.o : $(SRCDIR)%.c $(C_DEPS)
    $(VERBOSE)$(CC) $(CFLAGS) -o $@ -c $<

$(OBJDIRUTILS)/%.cpp.o : $(SRCDIRUTILS)%.cpp $(C_DEPS)
    $(VERBOSE)$(CXX) $(CXXFLAGS) -o $@ -c $<

$(OBJDIR)/%.cpp.o : $(SRCDIR)%.cpp $(C_DEPS)
    $(VERBOSE)$(CXX) $(CXXFLAGS) -o $@ -c $<

$(OBJDIRHOG)/%.cpp.o : $(SRCDIRHOG)%.cpp $(C_DEPS)
    $(VERBOSE)$(CXX) $(CXXFLAGS) -o $@ -c $<

$(OBJDIR)/%.cu.o : $(SRCDIR)%.cu $(CU_DEPS)
    $(VERBOSE)$(NVCC) $(NVCCFLAGS) $(SMVERSIONFLAGS) -o $@ -c $<

$(OBJDIRHOG)/%.cu.o : $(SRCDIRHOG)%.cu $(CU_DEPS)
    $(VERBOSE)$(NVCC) $(NVCCFLAGS) $(SMVERSIONFLAGS) -o $@ -c $<

$(CUBINDIR)/%.cubin : $(SRCDIR)%.cu cubindirectory
    $(VERBOSE)$(NVCC) $(CUBIN_ARCH_FLAG) $(NVCCFLAGS) $(SMVERSIONFLAGS) -o $@ -cubin $<

#
# The following definition is a template that gets instantiated for each SM
# version (sm_10, sm_13, etc.) stored in SMVERSIONS.  It does 2 things:
# 1. It adds to OBJS a .cu_sm_XX.o for each .cu file it finds in CUFILES_sm_XX.
# 2. It generates a rule for building .cu_sm_XX.o files from the corresponding 
#    .cu file.
#
# The intended use for this is to allow Makefiles that use common.mk to compile
# files to different Compute Capability targets (aka SM arch version).  To do
# so, in the Makefile, list files for each SM arch separately, like so:
#
# CUFILES_sm_10 := mycudakernel_sm10.cu app.cu
# CUFILES_sm_12 := anothercudakernel_sm12.cu
#
define SMVERSION_template
OBJS += $(patsubst %.cu,$(OBJDIR)/%.cu_$(1).o,$(notdir $(CUFILES_$(1))))
$(OBJDIR)/%.cu_$(1).o : $(SRCDIR)%.cu $(CU_DEPS)
    $(VERBOSE)$(NVCC) -o $$@ -c $$< $(NVCCFLAGS) -arch $(1)
endef

# This line invokes the above template for each arch version stored in
# SM_VERSIONS.  The call function invokes the template, and the eval
# function interprets it as make commands.
$(foreach smver,$(SM_VERSIONS),$(eval $(call SMVERSION_template,$(smver))))

$(TARGET): makedirectories $(OBJS) $(CUBINS) Makefile
    $(VERBOSE)$(LINKLINE)

cubindirectory:
    $(VERBOSE)mkdir -p $(CUBINDIR)

makedirectories:
    $(VERBOSE)mkdir -p $(LIBDIR)
    $(VERBOSE)mkdir -p $(OBJDIR)
    $(VERBOSE)mkdir -p $(OBJDIRUTILS)   
    $(VERBOSE)mkdir -p $(OBJDIRHOG)     
    $(VERBOSE)mkdir -p $(TARGETDIR)

tidy :-lboost_thread 
    $(VERBOSE)find . | egrep "#" | xargs rm -f
    $(VERBOSE)find . | egrep "\~" | xargs rm -f

clean : tidy
    $(VERBOSE)rm -f $(OBJS)
    $(VERBOSE)rm -f $(CUBINS)
    $(VERBOSE)rm -f $(TARGET)
    $(VERBOSE)rm -f $(NVCC_KEEP_CLEAN)

clobber : clean
    $(VERBOSE)rm -rf $(ROOTOBJDIR)

Answer 1

common.mk 已被破坏(可能是您对其进行了修改):

LIB := /pkg/suse11/cuda/4.2/sdk/CUDALibraries/common/FreeImage/lib/linux/libfreeimage64.a

这无疑不是您想要的，它正在破坏上面分配的所有精心设计的库依赖项。我猜你的意图是这样的

LIB += /pkg/suse11/cuda/4.2/sdk/CUDALibraries/common/FreeImage/lib/linux/libfreeimage64.a