AMD Confirms Linux Performance Marginality Problem Affecting Some, Doesn't Affect Epyc / TR

[Mr. Octus]

Thank you for your work Michael, as a recent Ryzen buyer I got worried with your initial articles. It's nice to see AMD this proactive. It seems like a very niche issue but still an issue regardless.

Also looking forward to those Epyc & Threadrpper test

[RyzenNewbie]

[...] (internal signals)

thank you, that's the phrase I was missing for understanding...

[bug77]

Oh, really, they confirm? We can all rest easy now

[Holograph]

Could you explain more about what is meant by "performance marginality?" It seems open to several different meanings and I'm not sure what you or AMD means by it.

What that means is "we still don't respect you and think you should buy Intel instead"

Coffee Lake here I come

"performance marginality" is nowhere near as bad as AMD thinking they could ignore all of these users until Phoronix stepped in. Thanks Michael, you saved a lot of us a terrible purchase.

It seriously pisses me off that it took Phoronix articles for AMD to realize they needed to look into this. I don't care if they claim they've done it. Too little, too late. What happens next time there is a problem? AMD will ignore their customers unless they feel pressured enough to fix the problems. And if they are pressured into it, they will make a press release marginalizing the problems their customers had. And they will delay talking about anything as long as they can because they don't want to look bad, without realizing that the only way they could look worse would be to say they wouldn't look into the problem at all.

I'm sure at least one person will call this a troll, but I can't support this kind of behavior from a company with my money. Quality of support is extremely important.

[Nille_kungen]

Yes they have now said I will be receiving Threadripper and Epyc samples (contrary to previous communications saying not) and also looks like some more Ryzen models too.

Maybe you get one of those pelican cases with two threadripper and a threadripper in glass with your logo on it.
Those review kits was awesome.
I'm personally more interested about epyc i would really like to see how it works with linux.

[Beherit]

I'm very glad AMD went from handling this horrendously bad when the initial reports surfaced, to doing everything that can be expected from them. PR wise that is - from a technical standpoint, a fix still remains.

[Sethox]

There are always going to a Troll in the comment section... shish.

2 Things, new releases almost never go smoothly but thank god for good communication from the company and the reviewers to find some solid ground to land on (and not be screwed over). Let's just see where this goes, all I know is that my next purchase is AMD all around (CPU and GPU) without a doubt.

[Holograph]

I'm very glad AMD went from handling this horrendously bad when the initial reports surfaced, to doing everything that can be expected from them. PR wise that is - from a technical standpoint, a fix still remains.

No, good PR would have been listening to the customers initially, many of whom have directly reported the problem with AMD, have tried to work with AMD to either get a fix or updates on the issue, and have gotten absolute silence. I followed the thread on AMD's forum every single day. Many of the people on the forum either also had tickets open with AMD or were trying to open tickets. The kill-ryzen and ryzen-segv-test programs have been around for a while now.

They aren't doing everything expected of them. We expect them to look into issues when we, their customers, report those issues. We expect them to give us updates even if the updates are just "we apologize for the ongoing issues and we're still looking into this." We expect them to look into it before Phoronix has to put in the effort to make sure a bunch of people know about it. Any corporation cares about their bottom line a lot, but AMD has demonstrated that it ONLY cares about its bottom line, and not about its products, its support, or its customers until they're in a position where they're going to lose money.

Admitting this is an improvement in how they are handling this issue, but it would literally be impossible for them to do everything expected of them, because they already screwed up.

Not sure why some people are willing to give corporations a free pass on terrible support. Even if you still buy their product (because, let's face it, Intel is a corrupt company as well), to go and pretend they didn't create this problem to begin with? Crazy.

Go ahead, call me a troll. You can't stop the truth.

[birdie]

I really doubt this problem is specific to Linux (and *BSDs) but let's give AMD some breathing room here. Hopefully a BIOS update can solve it because we don't need another fiasco akin to the translation lookaside buffer issue which plagued the K10 CPUs.

[RyzenNewbie]

PR wise that is - from a technical standpoint, a fix still remains.

word - I asked the FreeBSD devs 20 minutes ago whether this CPU's internal signal issue can be fixed by the operating system (me thinks: perhaps by artificial throttling, I don't know) - but I fear that in the end a real fix means a new CPU...