Add results: AMD EPYC Milan and Apple M4#2
Open
gopikannappan wants to merge 2 commits into
Open
Conversation
First AMD datapoint in the matrix. Hetzner CCX43 dedicated vCPU: AMD EPYC Milan, 16 vCPU (8 physical cores plus SMT), 64GB RAM, Ubuntu 24.04. Default runner settings.
First M4-generation datapoint. Scaleway M4-S: Apple M4, 4 performance + 6 efficiency cores, 16GB RAM, macOS. Default runner settings.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Two new machines for the results matrix.
AMD EPYC Milan (Hetzner CCX43 dedicated vCPU, 8 physical cores plus SMT, 64GB RAM, Ubuntu 24.04). As far as I can tell this is the first AMD entry in the results folder.
Apple M4 (Scaleway M4-S Mac mini, 4 performance + 6 efficiency cores, 16GB RAM). The results folder currently has M1 Max on the Apple side; the M4 Max figures on the roadmap dashboard look like they come from the reference runs rather than this matrix, so hopefully a base M4 here is a useful addition. Happy to relabel or drop it if I have misread how the two relate.
Both are default runner settings, nothing modified. Toolchain pins are inside each JSON.
One observation from the M4 run: flat aggregation over 1000 sigs drops to about half the throughput of the smaller batches, which looks like memory pressure on the 16GB box rather than compute.
Happy to rerun anything with different settings if that helps.