Problem in resizing the tile size

[layaout]

hello，everyone！
I am wondering resize the tile size like 8x8,32x32 as many papers researched before.
It seems that I only have to adjust the parameters BLOCK_X and BLOCK_Y, but soon I get the problem when I was running the code
"Runtime Error:CUDA error:operation not supported on global/shared address space .CUDA kernel errors might be asychronously reported at some other API call,so the stacktrace below might be incorrect"
when I turn back to 16, everything is fine,So is there any other steps I missed?And can I set the size to not the power of 2 like the size of 15?