Problems in testing CUDA samples !

Hello.
I’ve downloaded the last CUDA tool kit 5, and digited “make” in order to compile the samples, but
i am obtaining the following outputs.

here is one output:

######################################

alechand@pcsantos2:~/NVIDIA_CUDA-5.0_Samples/0_Simple/matrixMul$ make
/usr/local/cuda-5.0/bin/nvcc -m64 -gencode arch=compute_10,code=sm_10 -gencode arch=compute_20,code=sm_20 -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -I/usr/local/cuda-5.0/include -I. -I… -I…/…/common/inc -o matrixMul.o -c matrixMul.cu
g++ -m64 -o matrixMul matrixMul.o -L/usr/local/cuda-5.0/lib64 -lcudart
mkdir -p …/…/bin/linux/release
cp matrixMul …/…/bin/linux/release

#######################################

and here is other:

#####################################

alechand@pcsantos2:~/NVIDIA_CUDA-5.0_Samples/6_Advanced/segmentationTreeThrust$ make
/usr/local/cuda-5.0/bin/nvcc -m64 -gencode arch=compute_13,code=sm_13 -gencode arch=compute_20,code=sm_20 -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -I/usr/local/cuda-5.0/include -I. -I… -I…/…/common/inc -o segmentationTree.o -c segmentationTree.cu
g++ -m64 -o segmentationTreeThrust segmentationTree.o -L/usr/local/cuda-5.0/lib64 -lcudart
mkdir -p …/…/bin/linux/release
cp segmentationTreeThrust …/…/bin/linux/release

###########################################

Considering my driver is installed,
what kind of problems am i facing ?
Thanks

My system:
Intel I7
4Gb Ram
Nvidia GTX-680
Ubuntu 11.10

There are no errors in those outputs. The executables should be in the …/…/bin/linux/release folder.

Sorry , i did not note it …
here is the output from release folder:

#####################################################

alechand@pcsantos2:~/NVIDIA_CUDA-5.0_Samples/bin/linux/release$ ./matrixMul
./matrixMul: error while loading shared libraries: libcudart.so.5.0: cannot open shared object file: No such file or directory
alechand@pcsantos2:~/NVIDIA_CUDA-5.0_Samples/bin/linux/release$ ./segmentationTreeThrust
./segmentationTreeThrust: error while loading shared libraries: libcudart.so.5.0: cannot open shared object file: No such file or directory
alechand@pcsantos2:~/NVIDIA_CUDA-5.0_Samples/bin/linux/release$

####################################################################

Can you help with this ?
thanks

i corrected these errors with the command :

“sudo ldconfig /usr/local/cuda/lib64”

But now i am facing these problems:
ps: i compiled two more programs, clock and inlinePTX.

###############################################################

alechand@pcsantos2:~/NVIDIA_CUDA-5.0_Samples/bin/linux/release$ ./matrixMul
[Matrix Multiply Using CUDA] - Starting…
GPU Device 0: “GeForce GTX 680” with compute capability 3.0

MatrixA(320,320), MatrixB(640,320)
Computing result using CUDA Kernel…
done
Failed to create start event (error code unspecified launch failure)!
alechand@pcsantos2:~/NVIDIA_CUDA-5.0_Samples/bin/linux/release$ ./segmentationTreeThrust
./segmentationTreeThrust Starting…

GPU Device 0: “GeForce GTX 680” with compute capability 3.0

  • Building segmentation tree… Algorithm failed (unspecified launch failure)
    alechand@pcsantos2:~/NVIDIA_CUDA-5.0_Samples/bin/linux/release$ ./clock
    CUDA Clock sample
    GPU Device 0: “GeForce GTX 680” with compute capability 3.0

CUDA error at clock.cu:127 code=4(cudaErrorLaunchFailure) “cudaMemcpy(timer, dtimer, sizeof(clock_t) * NUM_BLOCKS * 2, cudaMemcpyDeviceToHost)”
CUDA error at clock.cu:129 code=4(cudaErrorLaunchFailure) “cudaFree(dinput)”
CUDA error at clock.cu:130 code=4(cudaErrorLaunchFailure) “cudaFree(doutput)”
CUDA error at clock.cu:131 code=4(cudaErrorLaunchFailure) “cudaFree(dtimer)”
Total clocks = -1536394840
alechand@pcsantos2:~/NVIDIA_CUDA-5.0_Samples/bin/linux/release$
alechand@pcsantos2:~/NVIDIA_CUDA-5.0_Samples/bin/linux/release$ ./inlinePTX
CUDA inline PTX assembler sample
GPU Device 0: “GeForce GTX 680” with compute capability 3.0

CUDA error at inlinePTX.cu:70 code=4(cudaErrorLaunchFailure) “cudaDeviceSynchronize()”
CUDA error at inlinePTX.cu:75 code=4(cudaErrorLaunchFailure) “cudaMallocHost(&h_d_ptr, N *sizeof(int))”
CUDA error at inlinePTX.cu:76 code=4(cudaErrorLaunchFailure) “cudaMemcpy(h_d_ptr, d_ptr, N *sizeof(int), cudaMemcpyDeviceToHost)”
Segmentation fault
alechand@pcsantos2:~/NVIDIA_CUDA-5.0_Samples/bin/linux/release$

#######################################################

These 4 programs are not working…
Do you think it can be a problem at my GPU ?
Thanks a lot

Check to make sure that the PCI-E power connectors plugged into the GPU. Other than trying a reboot I am at a loss with the errors… it sounds like the GPU might be bad. See if you can test the GPU on another system to see if the problem persists… if so, RMA it.

Edit: If you’re using anything above GCC 4.4, try to install it and make it the default, and recompile again. That would be my only other suggestion, but I don’t think it’s a likely solution.