I am doing the online course on nVidia courses sight, on Accelerated computing CUDA.
I am using my own Tesla C2050/2075 card
When I write the basic code, I am supposed to create blocks and threads that run a global function.
Where can I find out about the maximum number of blocks and threads per block that I can allocate to run when using this card?
I found this
https://www.nvidia.com/docs/IO/43395/NV_DS_Tesla_C2050_C2070_jul10_lores.pdf
but I did not find the information here.
thanks