Benchmarks Of Intel's Latest Linux Microcode Update

[phoronix]

Phoronix: Benchmarks Of Intel's Latest Linux Microcode Update

With all of the confusion last week over Intel's short-lived CPU microcode license change that forbid benchmarking only for them to change it a short time later -- to a much nicer license in that the microcode files can be easily redistributed and don't curtail it in other manners (and also re-licensing their FSP too), here are some performance benchmarks when trying out this latest Intel microcode on Linux.

http://www.phoronix.com/vr.php?view=26792

[tildearrow]

I'm not upgrading my microcode.

If they find one more vulnerability I am going to legitimately cry.

[EarthMind]

Dear Phoronix admin

I represent Intel and would like to notify you that you breached our Terms of Service. You have published benchmarks of our products for which you didn't have the right to do so.

We might be considering to settle this for 10 million dollars, otherwise we'll be seeing you in court. Please let us know about your decision at [email protected]

Sincirely,
Intel lawyer™️

[andyprough]

Nearly all these results look like they are within a tiny margin of error. You can't make any clear pronouncements based on these results.

[squash]

The differences are slight, which is a great result.

[flower]

i'd like to see a benchmark which involes many context switches.
with cities skylines in a qemu win10 vm i have seen a big performance impact with spectre mitigations enabled (i haven't measured it though).

thank you Michael - looking forward to your new benachmark

[cybertraveler]

I'm not upgrading my microcode.

I think for many distros, the microcode updates will be delivered to users during normal system updates, so they'd have to go out of their way to not update.

It's my understanding that the microcode is uploaded by Linux to the CPU during boot. So Linux just uses the microcode that your distro made available to it.

[davidbepo]

I think for many distros, the microcode updates will be delivered to users during normal system updates, so they'd have to go out of their way to not update.

It's my understanding that the microcode is uploaded by Linux to the CPU during boot. So Linux just uses the microcode that your distro made available to it.

thats very easy to "fix" just uninstall intel-ucode or whatever the package is called

[flower]

thats very easy to "fix" just uninstall intel-ucode or whatever the package is called

but why? microcode updates are not a bad idea.
if it's just because of spectre i'd use a version before it was fixed (like me on my gaming pc)

[cybertraveler]

thats very easy to "fix" just uninstall intel-ucode or whatever the package is called

Careful with that. Modern Intel processes shut down after about 30 seconds if they are not fed their microcode. I don't know if removing the microcode package will mean the kernel has no microcode to feed the processor. If you're not sure, it might be a better idea to pin the version of the intel-ucode package you currently have installed instead of removing the package altogether.