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

Investigate drop in average fps on 4K@60 #35

Open
Proryanator opened this issue Sep 29, 2023 · 4 comments
Open

Investigate drop in average fps on 4K@60 #35

Proryanator opened this issue Sep 29, 2023 · 4 comments
Labels
bug Something isn't working

Comments

@Proryanator
Copy link
Owner

Noticed with recent runs on main that on the original 1660 Super that was used to build this project, that it's average fps is ~39 or so (instead of topping up around 75-90).

This may be specific to my system but, this could also be an underlying issue with how fps is calculated and requires a bit more investigation.

@Proryanator Proryanator added the bug Something isn't working label Sep 29, 2023
@Proryanator
Copy link
Owner Author

Tested this on the latest release as well as what is in main, it appears both have had a drop in performance. Might be a driver update, or any other factor :/

@e-dong
Copy link
Contributor

e-dong commented Oct 2, 2023

Not sure if this is related, but I notice a drop in FPS on the first run. When running the benchmark again, I get must higher FPS. Not sure if the system needs to "warmup" when trying to run the benchmark from an idle system state.

2023-10-01-211743_1224x918_scrot

@Proryanator
Copy link
Owner Author

That's an interesting finding, it could be. I noticed that too while running the permutor tool.

I bet that was always a possibility (I recall talking to Xaymar and his concerns for a benchmark being that you may need repetitive runs to get a good feel).

@e-dong
Copy link
Contributor

e-dong commented Oct 5, 2023

That's an interesting finding, it could be. I noticed that too while running the permutor tool.

I bet that was always a possibility (I recall talking to Xaymar and his concerns for a benchmark being that you may need repetitive runs to get a good feel).

Hmm maybe instead of processing the source file once, perhaps a "permutation" would run x amount of times on the source file and average all the instantaneous fps.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working
Projects
None yet
Development

No branches or pull requests

2 participants