Intel confirmed for garbage! Intel shills on a suicide watch! Intel stock sliding further down into junk status!
>TL;DR: unfixed Skylake and Kaby Lake processors could, in some
situations, dangerously misbehave when hyper-threading is enabled.
Disable hyper-threading immediately in BIOS/UEFI to work around the
problem. Read this advisory for instructions about an Intel-provided
fix.
HAHAHAHAH... basically disable the whole fucking CPU!
https://lists.debian.org/debian-devel/2017/06/msg00308.html
>unfixed skylake and kabylake cpu's
What are we even talking about here
>>61075581
>it can be fixed by updating microcode
Literally fucking nothing, intel fixes their mistakes AMD just releases garbage
Fuck off AMD shill
So glad Intel pointed out AMDs inconsistent performance, roll out complexities, and hyped up their own 'battle tested servers.
>>61075581
>Lincux
Works fine on Windows.
>>61075759
They explicitly point out the problem is the processor, and it can affect other IS as well.
>>61075614
Nope, latest reports say they can't fix it with a microcode update. Probably a huge recall (skylake has been selling for over a year) coming up.
This will kill Intel. Fucking hell.
my i5 doesn't have hyperthreading. looks like I'm sae.
>>61075581
This is what happens when you fire your QA department.
>>61075614
AMD also fixes errata with microcode updates.
>>61075823
It's already fixed in microcode.
Invest more in R&D, less in shills and bribery
I have an i5 6600 and used to have an i7 920. The i5 is superior but I swear the i7 had less latency in doing things. Maybe cause it was quad channel ram? But my current ram ddr4 2800 is so much faster than my old ddr3 1333.
>>61075581
This is what happens when you fire your whole validation team and start hiring pajeets and womyn instead
>>61075581
How retarded as you OP? The message you linked clearly says:
>Apparently, Intel had indeed found the issue, *documented it* (see below) and *fixed it*.
Unlike AMD which still purple screens on ESXi with SMT enabled.
>>61075899
>AMD also fixes errata with microcode updates.
Not on Ryzen.
>>61075581
>Hyperthreading
Yeah, it was maybe slightly useful back in the days of single-core processors, but why on earth would anyone want this shit enabled anyway? As far as I see it it's just there as a selling point, nothing more.
>>61077667
8 cores vs 4 cores is significant for certain tasks.
>>61077667
Up to 30% more performance in multi-threaded applications, such as hypervisors.
Just because noone told you yet how HT works in your elementary school doesn't mean it's just a marketing meme.
>>61077667
Hyperthreading is actually much better now than it was when it first debuted.
>>61077595
>Not on Ryzen.
Source?
>>61077753
>Just because noone told you hurrdurr...
Hyperthreading was a giant meme before (you probably even existed), and intel had even dropped it themselves until they recently decided to introduce it again. The tests used to indicate it didn't have any significant value. Maybe it's better now, but that didn't use to be the case.
>>61078144
kill yourself
>>61077667
Peep the 0.1% lows of the i5s, homie.
>>61077667
Intel's SMT is pretty crap DESU.
>>61078229
Really narrow cores compared to what ryzen and POWER are mean hyperthreading is a great way to get resource contention.
>>61075759
No it doesn't
: ^ )
>>61075581
>The Kaby Lake microcode updates that fix this issue are currently only
>available to system vendors, so you will need a BIOS/UEFI update to get
>it. Contact your system vendor: if you are lucky, such a BIOS/UEFI
>update might already be available, or undergoing beta testing.
HAHAHAHAHAHAHAHAHA
INTEL FINISHED AND BANKRUPT
>>61077753
>30%
Where did you get that number from anyway? Intel's front page? There's practically no good recent information available on performance tests or anything. Even some database/VM support pages are saying stuff like "it depends". Some newer articles are still claiming it can be detrimental in some cases. There's still plenty controversy surrounding the technology.
>>61075581
Have used my Xeon E3 v5 with hyperthreading enabled extensively for CPU mining, scripting, Mathematica, and gaming.
Hasn't broken.
Explain?
>>61078737
>Where did you get that number from anyway?
Any review site of your choice. http://www.anandtech.com/bench/product/1554?vs=1828
>>61078144
>Hyperthreading was a giant meme before
Your life's a meme.
>>61075581
Intelshills - when will they ever learn?
>>61075636
>>61077595
>Not on Ryzen.
What is AGESA
>>61079847
http://www.lmgtfy.com/?q=agesa
>>61075581
Oy Vey
Ryzen had the same issues.
>It's literally nothing
Oh man did I step into a time machine? How the fuck is Intel even alive after so many blunders?