Vrayrt view one video card but two installed

[3DKodo]

Hi, I've bought two GTX670 4GB, but in the opencl selector only one of these is selectionable!
Can you help me?
Driver installed last version 301.42

Thanks

[vlado]

Is it possible that one of them is disabled for CUDA from the nVidia control panel?

Best regards,
Vlado

[Alan Iglesias]

Does he need to have a dummy plug on the non-display card for Windows to see it?

I still use one...

-Alan

[vlado]

Yes...

Best regards,
Vlado

[3DKodo]

Does he need to have a dummy plug on the non-display card for Windows to see it?

I still use one...

-Alan

sorry i don't understand...???

[3DKodo]

Is it possible that one of them is disabled for CUDA from the nVidia control panel?

Best regards,
Vlado

Hi Vlado, no the cuda is enabled and also gpu-z response is all active.
I've installed two graphic cards but not the sli bridge, it's right?

[vlado]

If you run the nVidia CUDA samples from the nVidia GPU computing SDK, do they report one GPU or two?

Best regards,
Vlado

[3DKodo]

Hi, Vlado!
After one day of test i'm still on start point!
I've installed nvidia sdk but i can choose only one graphic card.
But:
- gpu-z views two gtx 670, and if i run test render there are all gpus at work!
- in the device option i see two gtx 670, but one of these with error code 43.

I've installed the last beta driver but nothing.




Some advice?

[Alan Iglesias]

sorry i don't understand...???

In order for Windows to see the card that is not used for display, you must install a dummy plug to the card's output. I just throw a gender-changer type adapter on the card's output and it works perfectly.

And SLI is not used for GPU rendering with both cards.

-Alan

[3DKodo]

In order for Windows to see the card that is not used for display, you must install a dummy plug to the card's output. I just throw a gender-changer type adapter on the card's output and it works perfectly.

And SLI is not used for GPU rendering with both cards.

-Alan

I've inserted an adapter like this
http://www.bellaviashop.com/adattato...ogico-m-f.html
but nothing!

Or i must make this modify?
http://www.geeks3d.com/20091230/vga-...ga-dummy-plug/


And after all my problems will resolve?

[Alan Iglesias]

I've inserted an adapter like this
http://www.bellaviashop.com/adattato...ogico-m-f.html
but nothing!

Or i must make this modify?
http://www.geeks3d.com/20091230/vga-...ga-dummy-plug/


And after all my problems will resolve?

Yes, the gender changer you reference should work. It is what I am using.

No, you should not have to do any hacks like the one pictured.

You did re-boot the machine after installing the plug?

-Alan

[3DKodo]

yes i've reeboot but nothing

[Alan Iglesias]

Hmmmm...well, it's got to be something else (or the dreaded combination of two things wrong at once!). It did look like your system was seeing the other card.

Hopefully Vlado can help you get to the bottom of this....

-Alan

[vlado]

I've installed nvidia sdk but i can choose only one graphic card.

Can you run the "CUDA Device query" sample, and see if it reports two CUDA devices?

Best regards,
Vlado

[3DKodo]

Can you run the "CUDA Device query" sample, and see if it reports two CUDA devices?

Best regards,
Vlado

This is the result:


[deviceQuery.exe] starting...

C:\ProgramData\NVIDIA Corporation\NVIDIA GPU Computing SDK 4.2\C\bin\win64\Relea
se\deviceQuery.exe Starting...

CUDA Device Query (Runtime API) version (CUDART static linking)

Found 1 CUDA Capable device(s)

Device 0: "GeForce GTX 670"
CUDA Driver Version / Runtime Version 4.2 / 4.2
CUDA Capability Major/Minor version number: 3.0
Total amount of global memory: 4096 MBytes (4294967296 bytes)
( 7) Multiprocessors x (192) CUDA Cores/MP: 1344 CUDA Cores
GPU Clock rate: 706 MHz (0.71 GHz)
Memory Clock rate: 3004 Mhz
Memory Bus Width: 256-bit
L2 Cache Size: 524288 bytes
Max Texture Dimension Size (x,y,z) 1D=(65536), 2D=(65536,65536), 3
D=(4096,4096,4096)
Max Layered Texture Size (dim) x layers 1D=(16384) x 2048, 2D=(16384,16
384) x 2048
Total amount of constant memory: 65536 bytes
Total amount of shared memory per block: 49152 bytes
Total number of registers available per block: 65536
Warp size: 32
Maximum number of threads per multiprocessor: 2048
Maximum number of threads per block: 1024
Maximum sizes of each dimension of a block: 1024 x 1024 x 64
Maximum sizes of each dimension of a grid: 2147483647 x 65535 x 65535
Maximum memory pitch: 2147483647 bytes
Texture alignment: 512 bytes
Concurrent copy and execution: Yes with 1 copy engine(s)
Run time limit on kernels: Yes
Integrated GPU sharing Host Memory: No
Support host page-locked memory mapping: Yes
Concurrent kernel execution: Yes
Alignment requirement for Surfaces: Yes
Device has ECC support enabled: No
Device is using TCC driver mode: No
Device supports Unified Addressing (UVA): No
Device PCI Bus ID / PCI location ID: 2 / 0
Compute Mode:
< Default (multiple host threads can use ::cudaSetDevice() with device simu
ltaneously) >

deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 4.2, CUDA Runtime Versi
on = 4.2, NumDevs = 1, Device = GeForce GTX 670
[deviceQuery.exe] test results...
PASSED