There is no device supporting CUDA.

I have used CUDA for one month on my computer and it works good all the time, yesterday I found that it can not find CUDA, when I runned deviceQuery, the results comes out as:

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

There is no device supporting CUDA.

Device 0: "Device Emulation (CPU)"

  CUDA Capability Major revision number:		 9999

  CUDA Capability Minor revision number:		 9999

  Total amount of global memory:				 4294967295 bytes

  Number of multiprocessors:					 16

  Number of cores:							   128

  Total amount of constant memory:			   65536 bytes

  Total amount of shared memory per block:	   16384 bytes

  Total number of registers available per block: 8192

  Warp size:									 1

  Maximum number of threads per block:		   512

  Maximum sizes of each dimension of a block:	512 x 512 x 64

  Maximum sizes of each dimension of a grid:	 65535 x 65535 x 1

  Maximum memory pitch:						  262144 bytes

  Texture alignment:							 256 bytes

  Clock rate:									1.35 GHz

  Concurrent copy and execution:				 No

  Run time limit on kernels:					 No

  Integrated:									Yes

  Support host page-locked memory mapping:	   Yes

  Compute mode:								  Default (multiple host threads can use this device simultaneously)


I have updated the SDK and tried reinstall driver after toolkit, but it fails anyway. Is there any reason that can result in such a situation.

PS: GTX 285 for Mac Pro and Mac OS X 10.5.7

check your cable connection/reboot/etc

Connection is good, and I rebooted it several times, the error is still there, anyone has any idea?

I am not a MAC users but I had similar problems under Linux.

The trick is to load the X server with all the windows managers and than log out of the X. In console mode, the nvidia driver will still be loaded and the cuda device will be on. I had to use this to get the cuda-dbg working.

When you first boot up the system in console mode, the nvidia driver is not loaded and the GPU device is not available. One benifit of this , is that more host memory is free.

Or the card has to be remove and inserted back. This happened also. :mellow:

A bad setting of the attributes of the device file /dev/nvidia* is likely to generate a similar problem on a linux box (maybe on a macosx box too).
Be sure the users that are using cuda have a read/write access on the /dev/nvidia* device files.