Friday, December 10, 2010

Windows and CUDA; enabling TCC with nvidia-smi

Like in Linux you can use nvidia-smi to set different modes on the TESLA GPUs.
nvidia-smi is located usually at: C:\Program Files\NVIDIA Corporation\NVSMI\nvidia-smi.exe

Go there with a command prompt and administrative privileges and type nvidia-smi -s. This gives you the current status and the status of TCC mode after reboot.
Set exclusive compute mode enabled for the first GPU by nvidia-smi -g 0 -c 1
Set exclusive compute mode disabled for the first GPU by nvidia-smi -g 0 -c 0
For other GPUs increment the number after -g

/edit 24.12.2010:
Also look at the first comment on how to change between WDDM and TCC driver model.
Thanky Francoise for reporting my mistake. I corrected it above

3 comments:

  1. I would say it's -dm instead of -c .
    To change in between TCC and WDDM mode, you can use the NVIDIA smi utility as follows:
    nvidia-smi -g (GPU ID) -dm (0 for WDDM, 1 for TCC)

    ReplyDelete
  2. Hi,
    I'm have a Win7 x64 system with a C2050 as the primary display card. When i run nvidia-smi -g 0 -dm 1, it returns "GPU 0 has display attached, skipping device". Any idea?
    Thanks!

    ReplyDelete
  3. Most probably you already gave the answer. I assume that you can only switch to TCC if the GPU is not the primary display adapter.
    In our case we only access the device via RDP and no screen ist attached. I would suggest to try to add another card to the system and set the bios to boot up the non C2070 first.

    ReplyDelete