Fedora currently uses the original K8 micro-architecture (without 3DNow! and other AMD-specific parts) as the baseline for its x86_64 architecture. This baseline dates back to 2003 and has not been updated since. As a result, performance of Fedora is not as good as it could be on current CPUs.
This change to update the micro-architecture level for the architecture to something more recent.
As discussed on the devel list, I'm -1 to this proposal. I'd prefer to see an approach to improving performance based on adjusting the compilation flags for specific workloads. Bumping the minimum requirements of the OS above what most of our users have available is unreasonable.
Yeah, -1 to the proposal as written. I'd prefer:
-1 as well
There are many ways how to deal with this: create new architecture and build all packages in it, do same but only for selected packages, build packages inside one module.
So I would like to see more information about performance gain and then decide on specific implementation.
Happy to help with RPM and libsolv if that would be needed.
-1 to the change as written. I still like the idea of having a capabilities flag in RPM that can be interpreted by dnf as a preference. So you can have alternative versions of packages which do take advantage of this, and systems which support that capability would prefer the package version which is built with it.
By FESCo policy, any issue with negative votes should be added to the meeting agenda, however this has been discussed at length and currently has -5 votes meaning that it cannot pass anyway, so I'm going to mark it rejected.
Metadata Update from @sgallagh:
- Issue close_status updated to: Rejected
- Issue status updated to: Closed (was: Open)
to comment on this ticket.