Question

这是我的第一个使用动态并行的程序，我无法编译代码。我需要能够为我在大学的研究项目运行这个项目，我们将非常感谢任何帮助：

我收到以下错误：

/cm/shared/apps/cuda50/toolkit/5.0.35/bin/nvcc -m64 -dc  -gencode arch=compute_35,code=sm_35 -rdc=true -dlink -po maxrregcount=16 -I/cm/shared/apps/cuda50/toolkit/5.0.35 -I. -I.. -I../../common/inc -o BlackScholes.o -c BlackScholes.cu
g++ -m64 -I/cm/shared/apps/cuda50/toolkit/5.0.35 -I. -I.. -I../../common/inc -o BlackScholes_gold.o -c BlackScholes_gold.cpp
g++ -m64 -o BlackScholes BlackScholes.o BlackScholes_gold.o -L/cm/shared/apps/cuda50/toolkit/5.0.35/lib64 -lcudart -lcudadevrt
BlackScholes.o: In function `__sti____cudaRegisterAll_47_tmpxft_000059cb_00000000_6_BlackScholes_cpp1_ii_c58990ec()':
tmpxft_000059cb_00000000-3_BlackScholes.cudafe1.cpp:(.text+0x1354): undefined reference to `__cudaRegisterLinkedBinary_47_tmpxft_000059cb_00000000_6_BlackScholes_cpp1_ii_c58990ec'
collect2: ld returned 1 exit status
make: *** [BlackScholes] Error 1

我有一个cpp文件，一个cu文件和一个cuh文件。我的makefile的重要部分如下：

# CUDA code generation flags
#GENCODE_SM10    := -gencode arch=compute_10,code=sm_10
GENCODE_SM20     := -gencode arch=compute_20,code=sm_20
GENCODE_SM30     := -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35
GENCODE_SM35     := -gencode arch=compute_35,code=sm_35
#GENCODE_FLAGS    := $(GENCODE_SM10) $(GENCODE_SM20) $(GENCODE_SM30)
GENCODE_FLAGS    := $(GENCODE_SM35)

# OS-specific build flags
ifneq ($(DARWIN),)
      LDFLAGS   := -Xlinker -rpath $(CUDA_LIB_PATH) -L$(CUDA_LIB_PATH) -lcudart -lcudadevrt
      CCFLAGS   := -arch $(OS_ARCH)
else
  ifeq ($(OS_SIZE),32)
      LDFLAGS   := -L$(CUDA_LIB_PATH) -lcudart -lcudadevrt
      CCFLAGS   := -m32
  else
      LDFLAGS   := -L$(CUDA_LIB_PATH) -lcudart -lcudadevrt
      CCFLAGS   := -m64
  endif
endif

# OS-architecture specific flags
ifeq ($(OS_SIZE),32)
      NVCCFLAGS := -m32 -dc
else
      NVCCFLAGS := -m64 -dc
endif

# Debug build flags
ifeq ($(dbg),1)
      CCFLAGS   += -g
      NVCCFLAGS += -g -G
      TARGET := debug
else
      TARGET := release
endif


# Common includes and paths for CUDA
INCLUDES      := -I$(CUDA_INC_PATH) -I. -I.. -I../../common/inc

# Additional parameters
MAXRREGCOUNT  :=  -po maxrregcount=16

# Target rules
all: build

build: BlackScholes

BlackScholes.o: BlackScholes.cu
        $(NVCC) $(NVCCFLAGS) $(EXTRA_NVCCFLAGS) $(GENCODE_FLAGS) -rdc=true -dlink $(MAXRREGCOUNT) $(INCLUDES) -o $@ -c $<

BlackScholes_gold.o: BlackScholes_gold.cpp
        $(GCC) $(CCFLAGS) $(INCLUDES) -o $@ -c $<

BlackScholes: BlackScholes.o BlackScholes_gold.o
        $(GCC) $(CCFLAGS) -o $@ $+ $(LDFLAGS) $(EXTRA_LDFLAGS)
        mkdir -p ../../bin/$(OSLOWER)/$(TARGET)
        cp $@ ../../bin/$(OSLOWER)/$(TARGET)
    enter code here

run: build
        ./BlackScholes

Answer 1

使用主机链接器（g++）进行可执行文件的最终链接时，以及使用可重定位设备代码（nvcc -dc）时，必须执行中间设备代码链接步骤。

来自documentation：

If you want to invoke the device and host linker separately, you can do:

nvcc –arch=sm_20 –dc a.cu b.cu
nvcc –arch=sm_20 –dlink a.o b.o –o link.o
g++ a.o b.o link.o –L<path> -lcudart

由于您在编译行中指定-dc，因此您将获得仅编译操作（就像您已将-c指定为g ++一样）。

这是一个修改/精简Makefile，应该向您展示所涉及的内容：

GENCODE_SM35     := -gencode arch=compute_35,code=sm_35
GENCODE_FLAGS    := $(GENCODE_SM35)

LDFLAGS   := -L/usr/local/cuda/lib64 -lcudart -lcudadevrt
CCFLAGS   := -m64

NVCCFLAGS := -m64 -dc

NVCC := nvcc
GCC := g++

# Debug build flags
ifeq ($(dbg),1)
      CCFLAGS   += -g
      NVCCFLAGS += -g -G
      TARGET := debug
else
      TARGET := release
endif


# Common includes and paths for CUDA
INCLUDES      := -I/usr/local/cuda/include -I. -I..

# Additional parameters
MAXRREGCOUNT  :=  -po maxrregcount=16

# Target rules
all: build

build: BlackScholes

BlackScholes.o: BlackScholes.cu
        $(NVCC) $(NVCCFLAGS) $(EXTRA_NVCCFLAGS) $(GENCODE_FLAGS) $(MAXRREGCOUNT) $(INCLUDES) -o $@ $<
        $(NVCC) -dlink  $(GENCODE_FLAGS) $(MAXRREGCOUNT)  -o bs_link.o $@

BlackScholes_gold.o: BlackScholes_gold.cpp
        $(GCC) $(CCFLAGS) $(INCLUDES) -o $@ -c $<

BlackScholes: BlackScholes.o BlackScholes_gold.o bs_link.o
        $(GCC) $(CCFLAGS) -o $@ $+ $(LDFLAGS) $(EXTRA_LDFLAGS)

run: build
        ./BlackScholes

CUDA动态并行MakeFile

1 个答案: