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

Comparison based on GHz flawed #3

Open
Lewiscowles1986 opened this issue Jul 17, 2021 · 2 comments
Open

Comparison based on GHz flawed #3

Lewiscowles1986 opened this issue Jul 17, 2021 · 2 comments

Comments

@Lewiscowles1986
Copy link

Hi, great project. Really enjoyed the write-up.

One minor bug bear. Raspberry pis are vastly less powerful than even atom line intel processors.

The xeons AWS are backed by even in VPS (time sharing) are much more compute dense than a pi. Same with DigitalOcean. Even cost per-watt I'm not sure the pi wins if scaled for MIPS, FLOPS or memory throughput.

You wouldn't need 10 VPS to deal with compute or memory load of 10 pi4's.

@pawl
Copy link
Owner

pawl commented Jul 17, 2021

I do have a note about that:

This is a tough comparison to make because the Pi CPU cores are only 1.5GHz per core.

However, the comparison gets even harder due to AWS’s cpu credits. The raspberry pi’s may actually be better under full load after several hours.

Any ideas about how to do a more accurate comparison? I’ve been thinking about running some benchmarking software for several hours to figure it out.

@Lewiscowles1986
Copy link
Author

I think avoiding a direct comparison in lieu of evidence is the most straightforward path.

It is a great write-up, but I see so many people get caught up and not realize it's on them to check their workload.

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

2 participants