Skip to content
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

i am getting different branch occupancy (achieved) on rtx2070 #5

Open
jdgh000 opened this issue Nov 23, 2024 · 0 comments
Open

i am getting different branch occupancy (achieved) on rtx2070 #5

jdgh000 opened this issue Nov 23, 2024 · 0 comments

Comments

@jdgh000
Copy link

jdgh000 commented Nov 23, 2024

I know book uses m2070, but that is too old, so I used slight newer rtx2070 fe.
I coded everything and observed the achived branch occupancy and got followings:
achieved occupancies: active warps / SM
kernel1 60.72% 19.48%
kernel2 86.09% 27.55%
kernel3 57.77% 19.49%
kernel4 60.65% 19.41%

For kernel2 and 4 makes no sense because it should be 100% utilization...
kernel2:

if (tid % warpsize)/2==0)

kernel4:
itid = tid >> 5

I wonder why?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant