[Boards: 3 / a / aco / adv / an / asp / b / biz / c / cgl / ck / cm / co / d / diy / e / fa / fit / g / gd / gif / h / hc / his / hm / hr / i / ic / int / jp / k / lgbt / lit / m / mlp / mu / n / news / o / out / p / po / pol / qa / qst / r / r9k / s / s4s / sci / soc / sp / t / tg / toy / trash / trv / tv / u / v / vg / vip /vp / vr / w / wg / wsg / wsr / x / y ] [Search | Home]
4Archive logo
SKYLAKE CAN'T HANDLE PRIME NUMBERS INTEL...
If images are not shown try to refresh the page. If you like this website, please disable any AdBlock software!

You are currently reading a thread in /g/ - Technology

Thread replies: 53
Thread images: 4
File: Intel.png (32 KB, 512x512) Image search: [iqdb] [SauceNao] [Google]
Intel.png
32 KB, 512x512
SKYLAKE CAN'T HANDLE PRIME NUMBERS INTEL IS FINISHED

http://hexus.net/tech/news/cpu/89636-intel-skylake-bug-seizes-pcs-running-complex-workloads/?utm_source=dlvr.it&utm_medium=facebook
>>
>>52361855
Top fucking kek.
>>
>>52361855
>http://hexus.net/tech/news/cpu/89636-intel-skylake-bug-seizes-pcs-running-complex-workloads/?utm_source=dlvr.it&utm_medium=facebook

it also said they are going to patch it in the bios update they are using a workaround so the faulty numbers can't be read.

a few weeks untill the patch

Ouch for intel.
>>
>>52361965
>it also said they are going to patch it in the bios update they are using a workaround so the faulty numbers can't be read.
Wouldn't that mean it's still an architecture issue?
>>
>>52361965
Never forget f00f, the Pentium prime bug, the SATA 2 controller bug. or broken TSX in Haswell.

>>52361982
Yes.
>>
The moment the shitposter generation starts working.
>>
>>52362180
Ground zero thread right here, intelfags will never live it down
>>
>>52362164
Don't forget the sandy bridge sata 3 callback fiasco
>>
>>52361982
Its a X86 instruction set yes it was used on Obsolite ISA bus
it was the Orginal one that can't hanngle prime numbers because there is one memory countroler instuction set that can make intel machines freeze
Older versions had no problem because the north brigde was not commected to the cpu and was redirected to a error control chip that stopped the error,
now that everything is on the CPU they have to patch it up.

yes that's right, faggots skylel still has support for ISA bus.
AMD already Blocked this code in their systems.

IBM didn't have a fix for this x86 bug back in 1990 so i don't expect it to be fixed anytime soon.
>>
It's almost like they want AMD to catch up lmao
>>
>>52362203
Sorry, I fucked up my post, the SATA 2 bug was the one I was thinking of.

Also it's not like AMD has had their fair share of problems, the Phenom TLB bug was way worse as the only way to fix it was to decrease the performance by 20%
>>
>>52362227
What south Auckland school did you go to to end up make so many spelling mistakes?
>>
>>52362271
Papatoetoe east primary.

its the worse school for learning writing back in 1993.
>>
>>52362291
It's not like our literacy rates have gotten any higher since then, New Zealand probably has one of the lowest pass rates for English for OECD countries.

Too many coconuts now, if you ask me.
>>
hopefully it's a hardware bug designed to fuck over communist research in non-us countries
>>
>>52361855
prime numbers are a form of harassment
>>
File: geeze.png (4 KB, 157x163) Image search: [iqdb] [SauceNao] [Google]
geeze.png
4 KB, 157x163
>>52362291
>its the worse school
sigh
>>
>>52362396
he can learn to write better, you can't learn to rise your IQ to double digits tho
>>
>feels good to use only "tock" cpus
>>
>>52361855
This'll be a good time to slip in the microcode update that disables overclocking on non-K chips again. Either you take the update or deal with your bugged CPU. :^)
>>
File: sid.jpg (30 KB, 408x632) Image search: [iqdb] [SauceNao] [Google]
sid.jpg
30 KB, 408x632
>>52363033
>>
>>52361855
desu, this does not affect any usecase apart from load testing

you'll never hit this bug under everyday conditions, or even stuff like running games or compiling software projects.
>>
>>52361855
FDIV 2.0, it's ogre
>>
>>52363188
> apart from load testing
which is the only thing skylels are used for: testing overclocked skylake-setups.
>>
>>52361855
>Wait for the inevitable disabling of BCLK overclocking piggybacking this update

Absolute madmen.
>>
This is all AMD's fault
>>
>>52361855
Well, who needs prime numbers anyhow... there is a infinite amount off composite numbers it can use instead. Need 5 of something? Get 4 or 6, it's 2016...
>>
Okay, so it looks like a simple microcode bug with an easy and imminent fix.

Someone want to tell me why I'm wrong and it's actually a huge deal?
>>
>>52363437
It wasn't there in haswell
>>
>>52363451
Okay, so? New chip has a bug, it gets found, fix rolls out.

Unless there's something I'm missing (for example if the fix necessitates a performance penalty), I don't see why it's a big deal. Processors have errata and microcode revisions all the time.
>>
>>52363483
>if the fix necessitates a performance penalty

Well, it will do for those naughty goyim who dared to not pay extra for overclocking, yet thought they could overclock anyway.
>>
>>52361855
>utm_medium=facebook
and so is /g/
>>
File: 4b3.jpg (48 KB, 620x387) Image search: [iqdb] [SauceNao] [Google]
4b3.jpg
48 KB, 620x387
>Tfw I bought Skylake
>>
>>52363575
Are you in a hurry to start calculating prime numbers or something?
>>
>Implying Intel was ever significant
>>
>>52363615
considering this is central to most crypto, I'd say Intel indeed just shots their heads off
>>
>ricerfags try to test their overclock for stability on prime95
>always crashes
>>
>>52363615
>Implying you have the slightest clue about what kind of computations your CPU does in the background
>>
>>52363615
>not x99
>%5 improvement over haswell
You bought memelake, didn't you?
>>
>>52363437
>simple microcode bug with an easy and imminent fix.
200 shekerus have been transfered.
>>
>>52361855
Intel can never be finished as long as AMD's products remain being worthless shit. :^)
>>
This could explain the amount of crashes and issues people are having with Skykikes.
Good fucking job Intel.
>>
>>52361855
Intel quality manufacturing. Can't wait for ARM to take over completely.
>>
>>52362198
Yep, this is a 1.7% meme in the making.
>>
>>52364001
And no matter what bullshit thread AMD shills make they can't escape the truth.
>>
>>52365119
Sanjay, get over to the Nvidia thread! We need reinforcements!
>>
>>52365119
At least AMD processors can calculate primes
>>
>>52365160
Damage Control
>>
Glad I'm sticking to my 3570k. Love this thing
>>
Good thing I've got a Haswell Xeon.

Oh wait, that got hit by the broken TSX bug.
>>
>>52362405
>learn to rise
Sounds like the title for a good action movie, dummy.
>>
>>52365322
How is bashing AMD in an 'intel fucked up' thread not damage control?
>>
>>52363821
>memlake
or
>x99 intel house fire edition
Thread replies: 53
Thread images: 4
Thread DB ID: 399769



[Boards: 3 / a / aco / adv / an / asp / b / biz / c / cgl / ck / cm / co / d / diy / e / fa / fit / g / gd / gif / h / hc / his / hm / hr / i / ic / int / jp / k / lgbt / lit / m / mlp / mu / n / news / o / out / p / po / pol / qa / qst / r / r9k / s / s4s / sci / soc / sp / t / tg / toy / trash / trv / tv / u / v / vg / vip /vp / vr / w / wg / wsg / wsr / x / y] [Search | Home]

[Boards: 3 / a / aco / adv / an / asp / b / biz / c / cgl / ck / cm / co / d / diy / e / fa / fit / g / gd / gif / h / hc / his / hm / hr / i / ic / int / jp / k / lgbt / lit / m / mlp / mu / n / news / o / out / p / po / pol / qa / qst / r / r9k / s / s4s / sci / soc / sp / t / tg / toy / trash / trv / tv / u / v / vg / vip /vp / vr / w / wg / wsg / wsr / x / y] [Search | Home]

All trademarks and copyrights on this page are owned by their respective parties. Images uploaded are the responsibility of the Poster. Comments are owned by the Poster.
This is a 4chan archive - all of the shown content originated from that site. This means that 4Archive shows their content, archived. If you need information for a Poster - contact them.
If a post contains personal/copyrighted/illegal content, then use the post's [Report] link! If a post is not removed within 24h contact me at [email protected] with the post's information.