Need help with Cuda 4 on Debian linux

Hello

Apologies if this is the wrong forum to post this.

I’ve got a Debian 7 Wheezy amd64, and I was using gcc-4.6. Apparently there is a problem with this version with nvcc ?

In any case, I’ve installed the official linux Nvidia driver (280 something), I’ve installed the cuda 4.0 toolkit, and I can verify it is working, because pyrit lists all cores.

Yet when I go into the SDK/C (4.0) and try to run make I keep getting the following error:

/usr/lib/gcc/x86_64-linux-gnu/4.4.6/include/stddef.h:212:32: error: crt/device_runtime.h: No such file or directory

threadFenceReduction_kernel.cu:143:30: error: common_functions.h: No such file or directory

make[1]: *** [obj/x86_64/release/threadFenceReduction.cu_11.o] Error 1

I’ve reverted to using gcc,cpp,g++ 4.4 instead of 4.5 or 4.6 but I still get this error.

I do have libklibc-dev installed as well as build-essentials.

EDIT:

I have also tried with cuda 3.2 which installs fine. Again pyrit list_cores works as well as benchmarking.

However when I try to compile SDK/C I get a different kind of error:

/usr/local/cuda/include/surface_functions.h:100: error: there are no arguments to ‘__surf1Dreadc1’ that depend on a template parameter, so a declaration of ‘__surf1Dreadc1’ must be available

/usr/local/cuda/include/surface_functions.h:100: note: (if you use ‘-fpermissive’, G++ will accept your code, but allowing the use of an undeclared name is deprecated)

/usr/local/cuda/include/surface_functions.h:101: error: there are no arguments to ‘__surf1Dreads1’ that depend on a template parameter, so a declaration of ‘__surf1Dreads1’ must be available

/usr/local/cuda/include/surface_functions.h:102: error: there are no arguments to ‘__surf1Dreadu1’ that depend on a template parameter, so a declaration of ‘__surf1Dreadu1’ must be available

/usr/local/cuda/include/surface_functions.h:103: error: there are no arguments to ‘__surf1Dreadu2’ that depend on a template parameter, so a declaration of ‘__surf1Dreadu2’ must be available

/usr/local/cuda/include/surface_functions.h:104: error: there are no arguments to ‘__surf1Dreadu4’ that depend on a template parameter, so a declaration of ‘__surf1Dreadu4’ must be available

/usr/local/cuda/include/surface_functions.h: In function ‘void surf2Dread(T*, surface<void, 2>, int, int, int, cudaSurfaceBoundaryMode)’:

/usr/local/cuda/include/surface_functions.h:460: error: there are no arguments to ‘__surf2Dreadc1’ that depend on a template parameter, so a declaration of ‘__surf2Dreadc1’ must be available

/usr/local/cuda/include/surface_functions.h:461: error: there are no arguments to ‘__surf2Dreads1’ that depend on a template parameter, so a declaration of ‘__surf2Dreads1’ must be available

/usr/local/cuda/include/surface_functions.h:462: error: there are no arguments to ‘__surf2Dreadu1’ that depend on a template parameter, so a declaration of ‘__surf2Dreadu1’ must be available

/usr/local/cuda/include/surface_functions.h:463: error: there are no arguments to ‘__surf2Dreadu2’ that depend on a template parameter, so a declaration of ‘__surf2Dreadu2’ must be available

/usr/local/cuda/include/surface_functions.h:464: error: there are no arguments to ‘__surf2Dreadu4’ that depend on a template parameter, so a declaration of ‘__surf2Dreadu4’ must be available

make[1]: *** [obj/x86_64/release/threadFenceReduction.cu_11.o] Error 1

make[1]: Leaving directory `/home/blah/NVIDIA_GPU_Computing_SDK/C/src/threadFenceReduction'

make: *** [src/threadFenceReduction/Makefile.ph_build] Error 2

What am I missing here ?

Thank you

It is important that you have the latest nvidia driver from the nvidia site and it is important that you have the right compiler. Please check that you have the latest version of the nvidia driver and that you have the appropriate

gcc version. I had similar problem when trying to install cuda 4.0 on ubuntu 10.04.

Hi,

I got NVIDIA-Linux-x86_64-285.05.09 which is the latest driver for linux from what I can see.
I also have tried Cuda 4.01 and Cuda 3.20. I have installed gcc-4.4, gcc-4.5, gcc-4.6 but none of them seems to work.
I have downloaded the packaged Cuda from Debian repositories (release 4.0, V0.2.1221), and gpucomputing sdk (4.0.17) and I’ve managed to compile the sdk.
I guess debian package was better suited for my case. Thank you for the reply though.

hi

your problem solved?