kernel time limitations and launch time outs

Accelerated Computing CUDA CUDA Programming and Performance
#1

I have increased the number of particles I was looking at to a reasonable number (approx 500,000) but have started to get the following error; the launch timed out and was terminated

A quick scan on the forums has revealed that in Linux there is a time limit on a kernel of 5s. Is that correct? If so, why? And how do I get around that?

#2

So that a crashing GPU doesn’t freeze your display indefinitely.

In short: shutdown X windows.

There is more information in the FAQ.