Tesla problem - only 1 GPU detected

I’ve installed a tesla C1060 in linux server (i.e. no display), but the problem is that it seems to be detected as a single GPU.

For example, when I run the simpleMultiGPU example, cudaGetDeviceCount returns 1, is this correct? Surely it should be possible to select and use the 4 gpus on the card independently?

Also, nvidia-settings throws up an error when I try and run it, saying I’m not using the nvidia driver, although I think this could be because I’m running it over X forwarded SSH?

I’m using the latest drivers/toolkit/SDK, and running on ubuntu 8.10.

If help or suggestion to get it working correctly would be greatly appreciated!



The output of lspci:
01:00.0 3D controller: nVidia Corporation Unknown device 05e7 (rev a1)

Output of x.org:
() NVIDIA(0): Depth 24, (–) framebuffer bpp 32
(==) NVIDIA(0): RGB weight 888
(==) NVIDIA(0): Default visual is TrueColor
(==) NVIDIA(0): Using gamma correction (1.0, 1.0, 1.0)
) NVIDIA(0): Option “NoLogo” “True”
() NVIDIA(0): Option “MultiGPU” “On”
) NVIDIA(0): Option “ProbeAllGpus” “True”
() NVIDIA(0): Enabling RENDER acceleration
) NVIDIA(0): NVIDIA Multi-GPU auto-select rendering option.
(II) NVIDIA(0): Support for GLX with the Damage and Composite X extensions is
(II) NVIDIA(0): enabled.
(WW) NVIDIA(0): Failed to initialize Multi-GPU! Reason: Only one GPU
(WW) NVIDIA(0): detected. Only one GPU will be used for this X screen.
(II) NVIDIA(0): Implicitly enabling NoScanout
(II) NVIDIA(0): NVIDIA GPU Tesla C1060 (GT200) at PCI:1:0:0 (GPU-0)
(–) NVIDIA(0): Memory: 4194304 kBytes
(–) NVIDIA(0): VideoBIOS:
(II) NVIDIA(0): Detected PCI Express Link width: 16X
(–) NVIDIA(0): Interlaced video modes are supported on this GPU
(–) NVIDIA(0): Connected display device(s) on Tesla C1060 at PCI:1:0:0:
(II) NVIDIA(0): Validated modes:
(II) NVIDIA(0): “nvidia-auto-select”
(II) NVIDIA(0): Virtual screen size determined to be 640 x 480
(==) NVIDIA(0): DPI set to (75, 75); computed from built-in default
(==) NVIDIA(0): Enabling 32-bit ARGB GLX visuals.
(–) Depth 24 pixmap format is 32 bpp
(II) do I need RAC? No, I don’t.
(II) resource ranges after preInit:

(II) NVIDIA(0): Initialized GPU GART.
(II) NVIDIA(0): Setting mode “nvidia-auto-select”
(II) Loading extension NV-GLX
(II) NVIDIA(0): NVIDIA 3D Acceleration Architecture Initialized
(==) NVIDIA(0): Disabling shared memory pixmaps
(II) NVIDIA(0): Using the NVIDIA 2D acceleration architecture
(==) NVIDIA(0): Backing store disabled
(==) NVIDIA(0): Silken mouse enabled
() Option “dpms”
) NVIDIA(0): DPMS enabled
(II) Loading extension NV-CONTROL
(==) RandR enabled
(II) Setting vga for screen 0.
(II) Initializing built-in extension MIT-SHM
(II) Initializing built-in extension XInputExtension
(II) Initializing built-in extension XTEST
(II) Initializing built-in extension XKEYBOARD
(II) Initializing built-in extension XC-APPGROUP
(II) Initializing built-in extension XAccessControlExtension
(II) Initializing built-in extension SECURITY
(II) Initializing built-in extension XINERAMA
(II) Initializing built-in extension XFIXES
(II) Initializing built-in extension XFree86-Bigfont
(II) Initializing built-in extension RENDER
(II) Initializing built-in extension RANDR
(II) Initializing built-in extension COMPOSITE
(II) Initializing built-in extension DAMAGE
(II) Initializing built-in extension XEVIE
(II) Initializing extension GLX

The Telsa C1060 only has a single G200 GPU on a double width PCI-e x16 card.

:wacko: Lol! well that explains it then! I was getting confused with the S1060.