CUDA runtime or driver is not supported

[xhsh]

Hello, all,

I am testing the examples coming with cula. The compilation is successful. However, when I run "gesv", I get the following messages:

-------------------
SGESV
-------------------
Allocating Matrices
Initializing CULA
CUDA runtime or driver is not supported


However, I do not have any problems when I call the cublas functions coming with the cuda-toolkit. Could anybody tell me what is wrong, please?

[john]

Please be sure that your CUDA version and CUDA driver are both updated to 3.2 and that your CULA installation is R10.

[hcula8]

Hello,

I get the same error while trying to run a program for calling sgesv. My Cuda driver version is 260.19.36 and the CUDA version is 3020, and I have CULA R11. Shouldnt it work fine with R11 ? or should I revert back to R10 ?

[john]

That should be correct, though you'll want to check that you're not somehow mistakenly loading up a different CUDA runtime from somewhere else on your system.

[hcula8]

Running the version check example gives the following output.

- CULA: 11.0
- CUDA Runtime: 3.2
- CUDA Driver: 3.2
- CUBLAS Runtime: 3.2

So my program should also be loading the 3.2 version of CUDA runtime. Could there be any other reason for the error ?

[john]

I don't see anything that would overtly cause version check to succeed and sgesv to fail. I'd like to ask for your LD_LIBRARY_PATH and if possible to try a CUDA 4 driver (you can keep toolkit 3.1 and R11 if that is your preference).

[hcula8]

[john]

This looks clean; what is the result of running ldd on the compiled executable?

[hcula8]

linux-vdso.so.1 => (0x00007fffc9370000)
libcula_pgfortran.so => /usr/local/cula/lib64/libcula_pgfortran.so (0x00007fcfe8437000)
libcudart.so.3 => /opt/pgi/linux86-64/2011/cuda/3.1/lib64/libcudart.so.3 (0x00007fcfe81fb000)
libpthread.so.0 => /lib/libpthread.so.0 (0x00007fcfe7fd0000)
librt.so.1 => /lib/librt.so.1 (0x00007fcfe7dc8000)
libm.so.6 => /lib/libm.so.6 (0x00007fcfe7b45000)
libc.so.6 => /lib/libc.so.6 (0x00007fcfe77c1000)
libstdc++.so.6 => /usr/lib/libstdc++.so.6 (0x00007fcfe74ad000)
libcula.so => /usr/local/cula/lib64/libcula.so (0x00007fcfe5a1e000)
libcublas.so.3 => /opt/pgi/linux86-64/2011/cuda/3.1/lib64/libcublas.so.3 (0x00007fcfe298b000)
libgomp.so.1 => /usr/lib/libgomp.so.1 (0x00007fcfe277d000)
libgcc_s.so.1 => /lib/libgcc_s.so.1 (0x00007fcfe2566000)
libdl.so.2 => /lib/libdl.so.2 (0x00007fcfe2361000)
/lib64/ld-linux-x86-64.so.2 (0x00007fcfe8645000)

[john]

[hcula8]

Using the compiler flag -Mcuda=cuda3.2 solves the problem ! I appreciate your help.Thank you