Can not install CUDA Develeper drivers!
Hi

We recently bought 2 evga gtx 560 ti card to use them with CUDA.
The latest "normal" nvidia driver installs fine.

When i try to install the cuda toolkit 3.2 [b]developer [/b] driver,
it shows this: "NVIDIA installer cannot continue. This graphics driver
could not find compatible graphics hardware."

Later i tryed to install the 4.0 cuda developer driver, it installed
succesfully, but after rebooting the device manager says that the gtx
560 ti cannot be started.

Hope someone can give me a solution,

Best Regards:


Vizsnyiczai, Gaszton
PhD student
Institute of Biophysics
Biological Research Centre
Hungarian Academy of Sciences
H-6726 Szeged, Temesvari krt. 62, Hungary
Tel.: +36 62 599 600 (ext.435) Fax.: +36 62 433 133
Hi



We recently bought 2 evga gtx 560 ti card to use them with CUDA.

The latest "normal" nvidia driver installs fine.



When i try to install the cuda toolkit 3.2 developer driver,

it shows this: "NVIDIA installer cannot continue. This graphics driver

could not find compatible graphics hardware."



Later i tryed to install the 4.0 cuda developer driver, it installed

succesfully, but after rebooting the device manager says that the gtx

560 ti cannot be started.



Hope someone can give me a solution,



Best Regards:





Vizsnyiczai, Gaszton

PhD student

Institute of Biophysics

Biological Research Centre

Hungarian Academy of Sciences

H-6726 Szeged, Temesvari krt. 62, Hungary

Tel.: +36 62 599 600 (ext.435) Fax.: +36 62 433 133

#1
Posted 01/03/2012 12:48 PM   
CUDA 3.2 predates the GTX 560 Ti, so it's not surprising the driver doesn't recognize the card. Just go with the newer driver you already have installed.
CUDA 3.2 predates the GTX 560 Ti, so it's not surprising the driver doesn't recognize the card. Just go with the newer driver you already have installed.

Always check return codes of CUDA calls for errors. Do not use __syncthreads() in conditional code unless the condition is guaranteed to evaluate identically for all threads of each block. Run your program under cuda-memcheck to detect stray memory accesses. If your kernel dies for larger problem sizes, it might exceed the runtime limit and trigger the watchdog timer.

#2
Posted 01/03/2012 09:11 PM   
Thank you, i forgot to check the 3.2 driver compatibility

To get the card working with the 4.0 driver, i had to update the card's BIOS.
Thank you, i forgot to check the 3.2 driver compatibility



To get the card working with the 4.0 driver, i had to update the card's BIOS.

#3
Posted 01/04/2012 10:39 AM   
Scroll To Top