Unable to build application outside cuda sdk directory sdk makefile fails; independent makefile fail

I’m using cuda 2.1 in linux.

I was able to install the sdk successfully (and yes, I’ve ran some applications).

Now I’m trying to build an application in a directory outside the sdk. I tried 3 different ways but they all failed. I’ve been trying this for some days now :(

For each approach I copied matrixMul to a directory outside the sdk dir.


Edited the matrixMul Makefile to point to the correct cuda sdk dir.

I followed these instructions: http://www.acooke.org/cute/ReusingCUD0.html

I get this error:

$ make

make: *** No rule to make target `obj/debug/matrixMul_gold.cpp.o', needed by ``pwd`//debug/matrixMul.exe'.  Stop.

(Don’t pay attention to the .exe file extension for my target, my host system is linux).

Even though this seems to be a makefile/shell issue, the question remains on how to re-use the sdk makefiles.


I tried using an independent makefile.

I used the one in http://www.eecs.berkeley.edu/~mjmurphy/makefile

My adapted makefile:

# vim:comments=


# I don't like the Cuda SDK makefiles. Here's my own! This makefile should

# allow you to build Cuda programs independent of the NVidia Cuda SDK. Its

# simplicity makes it easy for you to put objects, binaries, etc where you want

# them. There is even some boiler-plate Makefile magic that you can copy

# into other Makefiles.


# Mark Murphy 2008

# Fill in the name of the output binary here

target	:= matrixMul.exe

# List of sources, with .c, .cu, and .cc extensions

sources   := matrixMul.cu matrixMul_gold.cpp matrixMul_kernel.cu

# Other things that need to be built, e.g. .cubin files

extradeps := 

# Flags common to all compilers. You can set these on the comamnd line, e.g:

# $ make opt="" dbg="-g" warn="-Wno-deptrcated-declarations -Wall -Werror"

opt  ?= -O3

dbg  ?= 

warn ?= -Wall -Werror

# This is where the cuda runtime libraries and includes reside on the

# berkeley millennium/rad clusters. It may be different on your machine.

cudaroot  := /usr/local/cuda

cudasdkroot := /usr/local/cuda-sdk

#----- C compilation options ------

gcc		:= /usr/bin/gcc

cflags	 += $(opt) $(dbg) $(warn)

clib_paths :=

cinc_paths :=

clibraries :=

#----- C++ compilation options ------

gpp		 := /usr/bin/g++

ccflags	 += $(opt) $(dbg) $(warn)

cclib_paths :=

ccinc_paths := 

cclibraries :=

#----- CUDA compilation options -----

nvcc		:= $(cudaroot)/bin/nvcc

cuflags	 += $(opt) $(dbg) 

culib_paths := -L$(cudaroot)/lib -L$(cudasdkroot)/lib

cuinc_paths := -I$(cudaroot)/include -I$(cudasdkroot)/common/inc

culibraries := -lcuda -lcudart -lcutil

lib_paths   := $(culib_paths) $(cclib_paths) $(clib_paths)

libraries   := $(culibraries) $(cclibraries) $(clibraries)

#----- Generate source file and object file lists

# This code separates the source files by filename extension into C, C++,

# and Cuda files.

csources  := $(filter %.c ,$(sources))

ccsources := $(filter %.cc,$(sources))

cusources := $(filter %.cu,$(sources))

# This code generates a list of object files by replacing filename extensions

objects := $(patsubst %.c,%.o ,$(csources))  \

		   $(patsubst %.cu,%.o,$(cusources)) \

		   $(patsubst %.cc,%.o,$(ccsources))

#----- Build rules ------

$(target): $(extradeps) 

$(target): $(objects) 

	$(gcc) -o $@ $(lib_paths) $(libraries) $(objects)

%.o: %.cu

	$(nvcc) -c $^ $(cuflags) $(cuinc_paths) -o $@ 

%.cubin: %.cu

	$(nvcc) -cubin $(cuflags) $(cuinc_paths) $^

%.o: %.cc

	$(gpp) -c $^ $(ccflags) $(ccinc_paths) -o $@

%.o: %.c

	$(gcc) -c $^ $(cflags) $(cinc_paths) -o $@


	rm -f *.o $(target) makefile.*dep

#----- Dependency Generation -----


# If a particular set of sources is non-empty, then have rules for

# generating the necessary dep files.


ccdep := ccdep.mk

cdep  := cdep.mk

cudep := cudep.mk

depfiles =

ifneq ($(ccsources),)

depfiles += $(ccdep)

$(ccdep): $(ccsources)

	$(gpp) -MM $(ccsources) > $(ccdep)




ifneq ($(cusources),)

depfiles += $(cudep)


	$(gpp) -MM -x c++ $(cusources) > $(cudep)




ifneq ($(csources),)

depfiles += $(cdep)

$(cdep): $(csources)

	$(gcc) -MM -x c $(csources) > $(cdep)




.PHONY: dep

dep: $(depfiles)

ifneq ($(MAKECMDGOALS),dep)

 ifneq ($(MAKECMDGOALS),clean)

  ifneq ($(ccsources),)

   include $(ccdep)


  ifneq ($(cusources),)

   include $(cudep)


  ifneq ($(csources),)

   include $(cdep)




My error message:

$ make

/usr/local/cuda/bin/nvcc -c matrixMul.cu -O3   -I/usr/local/cuda/include -I/usr/local/cuda-sdk/common/inc -o matrixMul.o

/usr/local/cuda/bin/nvcc -c matrixMul_kernel.cu matrixMul.h -O3   -I/usr/local/cuda/include -I/usr/local/cuda-sdk/common/inc -o matrixMul_kernel.o

nvcc fatal   : A single input file is required for a non-link phase when an outputfile is specified

make: *** [matrixMul_kernel.o] Error 255


Building it directly from command line.

$ nvcc -o matrixMul.exe   matrixMul.cu  matrixMul_gold.cpp  matrixMul_kernel.cu	 -I/usr/local/cuda-sdk/common/inc/   -L/usr/local/cuda-sdk/lib/		  -lcuda -lcudart -lcutil

/tmp/tmpxft_00002d58_00000000-25_matrixMul_kernel.o: In function `__device_stub__Z9matrixMulPfS_S_ii':

tmpxft_00002d58_00000000-24_matrixMul_kernel.ii:(.text+0x126): multiple definition of `__device_stub__Z9matrixMulPfS_S_ii'

/tmp/tmpxft_00002d58_00000000-15_matrixMul.o:tmpxft_00002d58_00000000-14_matrixMul.ii:(.text+0x126): first defined here

collect2: ld returned 1 exit status

Can anyone help with the fix for each of these methods.

I only need to have a working makefile in order to start developing my own application, however I would like to be able to understand the cause of the problems for each case and its respective solutions.

Thank you very much for your time.