Now down to 7 positives on Virus Total. I think we can reasonably call it a false positive by now. (if there was any doubt considering the source is trustworthy anyway)The sophos scanner here at work has also marked this tool as malware.
I will wait for a definition update.
Great Millenium quote insert there.It's a bit of a stretch to compare intel's cpu competition with blackberry's competition though, isn't it? Intel screwed up, or, at worst, got caught trying to inflate performance by a relatively small amount. They'll no doubt suffer a bit, but this isn't end, or even the beginning of the end. It's probably not even the end of the beginning for them. Blackberry, otoh, got trucked by Steve Freakin' Jobs.
Intel has revealed that even its newer CPUs are affected by the frequent reboot problems brought about by the Spectre/Meltdown patches. The chipmaker previously said that the reboot issue affects systems running Broadwell and Haswell. Now that it has managed to reproduce the problem internally in an effort to fix it, the company found that a similar behavior can occur in platforms powered by Skylake and Kaby Lake, which are newer than Haswell and Broadwell. Ivy Bridge- and Sandy Bridge-based systems, both older cores, are also susceptible to the bug.
Bad news: microcode patches affect stability of Intel CPUs from Sandy Bridge to Kaby Lake. At this point I wouldn't be surprised if Coffee Lake was affected as well.
Intel admits Spectre patch problems also affect newer Core chips
"The problems got out" just days before the scheduled disclosure, and I bet many engineers spent the end of the year working hard on these fixes instead of spending holidays with their families. I would rather blame Intel for what I know they handled badly (initial PR stunt for example) rather than what I can only guess they could have done better.They had the bug for 6 months but clearly were in no rush to fix it until the problems got out
Looks like it's nearly under control to me. Especially with Google's solution, which customers apparently didn't notice.So... The performance hit will benfar worse than expecting... Intel just transformed Core into another Pentium 4 dissaster....
What solution ? I must have missed it.Looks like it's nearly under control to me. Especially with Google's solution, which customers apparently didn't notice.
I think soon they will have all of the problems sufficiently repaired to move on.
https://www.engadget.com/2018/01/12/google-spectre-meltdown-protection-details/What solution ? I must have missed it.
What solution ? I must have missed it.
Heh Google pat themselves on the back for no complaints about a patch nobody knew about it. Funny.
From Ars Technica:https://support.google.com/faqs/answer/7625886
It is not a reasonable solution ATM IMO as it requires you to recompile all code with a patched compiler. I haven't tested if it is performance neutral as they claim since it is a massive pain to implement.
Great Millenium quote insert there.
Yes, it looks like Google and Intel together may have a decent solution.From Ars Technica:
Using retpoline for sensitive branches doesn't work reliably on the latest (Broadwell or better) Intel processors, because those processors can, in fact, use the branch predictor instead of the return buffers. When returning from deep function nesting (function A calls function B calls function C calls function D...), the return buffers can be emptied. Broadwell-or-better don't give up in this scenario; they fall back on the BTB. This means that on Broadwell or better, even retpoline code can end up using the attacker-prepared BTB. Intel says that a microcode update will address this. Alternatively, there are ways to "refill" the return buffer.
Ah the only time I ever heard it was watching this movie called Millennium. It's not a great movie but I liked that quote at the end.Now this is not the end. It is not even the beginning of the end. But it is, perhaps, the end of the beginning. Winston Churchill
I read that years ago in Winston Churhill's suberb The Second World War.
Bad news: microcode patches affect stability of Intel CPUs from Sandy Bridge to Kaby Lake. At this point I wouldn't be surprised if Coffee Lake was affected as well.
Intel admits Spectre patch problems also affect newer Core chips
Thanks for the info.
I haven't noticed anything weird with my i7-860 and i5-8600k systems. Both patched, the second one more properly with microcode updated bios etc.
I will have my Sandy 2500k up and running some time next week I believe, so I will report back.
It must be low enough for the problem to go unseen through initial testing.I haven't noticed anything weird with my i7-860 and i5-8600k systems. Both patched, the second one more properly with microcode updated bios etc.
I will have my Sandy 2500k up and running some time next week I believe, so I will report back.
Ah the only time I ever heard it was watching this movie called Millennium. It's not a great movie but I liked that quote at the end.
And this folks is exactly how reading memory contents from another process looks like, the best real life example for these vulnerabilitiesChurchill actually won a Nobel Prize for Literature for that book. It's really a humongous serious though, like 4000 ++ pages spread out over 6 volumes.
https://www.amazon.com/Second-World...ywords=the+second+world+war+winston+churchill
If you end up buying, I would recommend against the kindle edition...there are a ton of maps/etc that really add a ton to the story, and the kindle edition (at least a few years ago when I bought it) had a bad rap for not properly displaying everything.
Maybe because not all silicone created equal ? Maybe it's affecting several batch ?
And since it was reproduced in Intel lab then it was real deal, just need to wait what CPU batch that's get affected.
So applying the patch is like a gamble, if you win it will be like before and if you loose your system will not be stable.