-
Notifications
You must be signed in to change notification settings - Fork 540
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Add call stack management #3651
Conversation
a506459
to
26c2cc4
Compare
38d2787
to
8d5b771
Compare
6ebbb51
to
ed54ad1
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This could also additionally benefit from a section explaining, that the higher memory requirement of the GPUs call stack is why the call stack per thread is small compared to that of a CPU, and that this is the reason why (deep) recursion is not recommended, even if it's possible.
It would also be good to mention, that most device function calls are inlined to prevent excessive stack growth (and maybe for performance reasons)
8d5b771
to
96cf3a6
Compare
8c5264e
to
73894e3
Compare
8dcbdcc
to
507ebf1
Compare
eb41cb1
to
7cb026c
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Left some comments, but looks good to me overall.
0c52420
to
31fa125
Compare
bc51f5b
to
0fa1614
Compare
No description provided.