On Mon, Aug 07, 2017 at 09:07:46PM +0300, Thanos Baloukas wrote: > On 07/08/2017 07:09 μμ, Bruce Dubbs wrote:
> My suspicion was that if Ryzens have new instructions, and gcc did not > fully adjust yet, some packages compiled on a Ryzen could use some > optimization options that might cause illegal instruction trouble > on other cpus. That is a totally hypothetical and may be totally wrong > as well. Also it's not related at all to the thread that Ken posted and > the problems it describes. > > > In addition, the rather long thread I read indicated that the problem > > was erratic. Users would repeatedly compile mesa (or other packages) in > > a loop and it would fail at random iterations. That points to HW. > > > > My best guess that the problem is some sort of complex timing problem > > between the processor and it's support chips. > > According to phoronix, the problem has been confirmed, which I guess means it is a little closer to getting fixed. https://www.phoronix.com/scan.php?page=news_item&px=Ryzen-Segv-Response They occur with many parallel compilation workloads. But that's our (devs, testers) reason for justifying our hardware isn't it. ĸen -- I live in a city. I know sparrows from starlings. After that everything is a duck as far as I'm concerned. -- Monstrous Regiment -- http://lists.linuxfromscratch.org/listinfo/lfs-support FAQ: http://www.linuxfromscratch.org/blfs/faq.html Unsubscribe: See the above information page Do not top post on this list. A: Because it messes up the order in which people normally read text. Q: Why is top-posting such a bad thing? A: Top-posting. Q: What is the most annoying thing in e-mail? http://en.wikipedia.org/wiki/Posting_style
