RHEL9 Likely To Drop Older x86_64 CPUs, Fedora Can Better Prepare With "Enterprise Linux Next"

[Isedonde]

Well, I feel like my Phenom 2 X4 955 is still good enough, so I haven't gotten anything newer yet. If my distro of choice starts dropping hardware support, I will get hardware that is a bit more modern, maybe something from 2015. No big deal.

[kpedersen]

As others have said, RHEL is for servers anyway, not outdated and/or low end consumer machines.

https://www.redhat.com/en/store/red-...ux-workstation

Can you explain why that URL has "workstation" on the end?

Perhaps RH made a typo? XD

We have RHEL on all of the HR machines and none on the servers. This is because we have an explicit license with them for thin clients. The thing about thin clients is that they don't need to be running the latest hardware.

That said, since Wayland is going to completely fsck up remote sessions...

[hotaru]

Came here expecting people to be defending their ancient hardware (like usual with these articles) and wasn't let down.

Coffee Lake Pentiums and Celerons are ancient?

[drakonas777]

Yes, it implies those, but it excludes a lot of currently working hardware. That is why the first AVX is a far better compromise for the near future. Up to now all x64 distros supported cpus since Pentium 4 era, it is a little too large of a step to get from that to AVX2 only so suddenly.

I do not agree. Benefits of using AVX2 instead AVX are more important, than extra few years in backwards compatibility for already quite old hardware. I would 100% agree with you if this restriction would apply to all (I mean literally all, not RH based) distros. However, we are basically talking one server distro here (and it's beta testing companion (joke)). So it's fine in my opinion - tradeoff is adequate.

TBH either way the most affected group of people by this most likely would be users of entry level PC hardware, which even now does not support AVX due market segmentation.

Also, I saw someone's comment about being consistent with big iron OS. Being consistent with big iron ISA should also be a part of this philosophy IMHO.

[Delgarde]

Enterprises are slow to upgrade processors.

While true, they're also slow to upgrade the OS as long as it remains supported... so if RHEL 9 imposes this limitation, it won't really matter since most of their users will continue with RHEL7 or 8 until they replace the hardware anyway. Related to this, enterprise vendors can be quite slow to support new OS versions (e.g. I don't think Oracle supports RHEL 8 yet), so even new hardware installations today may not be using the latest OS...

[TemplarGR]

AVX2 is a better cut-off point, as it implies a few other extensions as well: BMI1/2, FMA + F16C, MOVBE, ...

Yes, it implies those, but it excludes a lot of currently working hardware. That is why the first AVX is a far better compromise for the near future. Up to now all x64 distros supported cpus since Pentium 4 era, it is a little too large of a step to get from that to AVX2 only so suddenly.

[mlau]

I don't think they are going to cut off older architectures in order to benefit from modern SIMD instructions. Well, obviously they will, but i think their primary target is using the instruction set as a cutoff point for old cpus. I was promoting the first AVX mainly on that grounds, since i think cpus first released during 2011 would be a nice balanced minimum for a distro released in 2023. 12 years is not too old for a baseline, and does not cutoff useful hardware either.

AVX2 is a better cut-off point, as it implies a few other extensions as well: BMI1/2, FMA + F16C, MOVBE, ...

[TemplarGR]

Much like the first version of SSE (back when it was still called ISSE), the first version of AVX isn't all that useful for accelerating generic software. Requiring AVX over e.g. SSE4.1 would just exclude a number of CPUs with no real benefit.

I don't think they are going to cut off older architectures in order to benefit from modern SIMD instructions. Well, obviously they will, but i think their primary target is using the instruction set as a cutoff point for old cpus. I was promoting the first AVX mainly on that grounds, since i think cpus first released during 2011 would be a nice balanced minimum for a distro released in 2023. 12 years is not too old for a baseline, and does not cutoff useful hardware either.

[NateHubbard]

Came here expecting people to be defending their ancient hardware (like usual with these articles) and wasn't let down.

As others have said, RHEL is for servers anyway, not outdated and/or low end consumer machines.

[Marc Driftmeyer]

Enterprises are slow to upgrade processors. The SSE4.1 makes sense. AVX when most tools were never written for it to push vendors to buy new hardware will see more vendors moving away from RHEL, not towards it.