nvidia geforce gtx 560 ti Cuda error: invalid device symbol

[mrstrauss]

Hello
I've got a brandnew NVidia GeForce GTX 560 ti. On the NVidia page it says, it has 384 CUDA cores. http://www.nvidia.com/object/product-ge ... ti-us.html
I started the CUDA-Multiforcer on my Ubuntu 11.10 64-bit system and got the following output.

Code: Select all

jan@hadabanana:~/CUDA-Multiforcer-Linux$ ./CUDA-Multiforcer -c charsets/charsetfull -f hash --min 0 --max 14 -h NTLM -d 0 --autotune
Launching 64-bit binary
Cryptohaze.com CUDA Multiforcer (multiple hash brute forcer)
by Bitweasil
Version 0.61 beta, length 0-14
Currently supported hash types: MD5 MD4 NTLM
Hash type: NTLM
CUDA Device Information:
Device 0: "GeForce GTX 560"
  Number of cores:                               56
  Clock rate:                                    1.85 GHz
Charset loaded (96 characters)
Hashes loaded (5 hashes)
Launching CPU kernel for password length 0
Launching CPU kernel for password length 1
Launching CPU kernel for password length 2
Launching CPU kernel for password length 3
Cuda error: invalid device symbol.
jan@hadabanana:~/CUDA-Multiforcer-Linux$


Why do I get the invalid device symbol? I installed the propriteary NVidia drivers and the CUDA files according to this tutorial. http://www.dickscheid.net/2011/10/19-cuda-ubuntu-1110/

[Bitweasil]

Where on earth did you find that? That's an absolutely ancient version that I'm stunned even starts anymore. And I'm not at *all* surprised it fails like you've seen. I specifically fixed that issue... a year or two ago.

Download the newest version from here:
https://sourceforge.net/projects/crypto ... -Combined/

See if that works for you. I'm running the latest drivers on Ubuntu 10.04 64-bit and it works fine.

[mrstrauss]

Oh yeah, now it works I'm very sorry I don't know where I got that version from but now everything's okay
And a very big compliment for your work!

[Bitweasil]

Glad it works now.

Donation button is on the main website if the tools are useful - it goes to development hardware & GPUs.