Seems like a measurable improvement although not dramatic in most benchmarks.
I think we may be looking at these wrong. Yes there’s a visible throughput/latency improvement here but what about other factors? Power savings? Cache efficiency? CPU cycles saved for other co-running processes?
These are going to be pretty hard to measure without an x86_64 simulator. So I don’t fault them for not including such benches. But there might be more to the story here.
This is the best summary I could come up with:
One of the exciting innovations currently being explored by Canonical ahead of the Ubuntu 24.04 LTS release is an x86-64-v3 build of the OS / packages.
As part of Ubuntu exploring the x86-64-v3 micro-architecture feature level they produced an Ubuntu 23.04 based ISO built with x86-64-v3 packages and also setup a static archive of the packages as well so using APT on the experimental build will also fetch the optimized binaries.
While no official announcement has been made by Canonical with their plans, it is my hope at least that they will decide to offer an Ubuntu Server ISO in x86-64-v3 flavor moving forward…
There at least they can hopefully make it easier to target the right folks (knowledgeable server administrators) and less end-user confusion not sure of x86-64 micro-architecture feature levels or CPU brand/model information, etc.
So those still using old Intel/AMD x86_64 hardware shouldn’t be concerned about losing Ubuntu compatibility for this upcoming Long Term Support release.
On the software side was the same Linux 6.2 kernel, GCC 12, and other components from the aging Ubuntu 23.04 state.
The original article contains 402 words, the summary contains 180 words. Saved 55%. I’m a bot and I’m open source!
