is there a limitation for total number of threads?

i have a gtx285 gpu

is there any limits?

yes,

"The maximum number of threads per block is 512;

The maximum sizes of the x-, y-, and z-dimension of a thread block are 512, 512,

and 64, respectively;

The maximum size of each dimension of a grid of thread blocks is 65535;"

taken from the programming guide.

i know about this
from
A.1.1 Specifications for Compute Capability 1.0

is it true for 1.2,1.3?

Yes, the limit of 2198956147200 threads per kernel grid applies to all current hardware. Is a limit of slightly more than two million million threads too restrictive for you application?

it is more than enough,just wanna know :rolleyes:

the deviceQuery example of CudaSdk is usefull to know our GPU limitation ;)