[FUD] Nehalem also has a TLB bug

[Mumak]

This story is a complete crap!
The TLB bug in AMD is different from Intel's Clarification on how to handle TLB Invalidation.
Moreover what FUD says doesn't affect just Nehalem but nearly all previous generations as well

[Donnie27]

IIRC the same sensationalist crap was posted by FUD or Inq back then about "core2's tlb bug". I'm confident that sandy bridge and westmere will too have some kind of errata relating to the TLB and I'm sure FUD is going to post the same crap all over again. Just because it's such a catchy headline.

QFT! I guess this news sent "AMD dancing in the isles" LOL!

[Ghostbuster]

QFT! I guess this news sent "AMD dancing in the isles" LOL!

"isles" or "aisles"?

Anyway, which reminds me http://www.theinquirer.net/en/inquir...l-ceo-confirms Charlie in the bunny suit is much funnier...

"It's a good thing you write better than you gamble otherwise you'll be living in that outfit."

[kl0012]

How does FUD assume that this is a bug? In the linked document it is labeled as "clarification", not errata.

[Katzenschleuder]

Sounds unlikely. I'm waiting for official statement.

Why?
The list of known bugs for every individual Intel (and AMD) CPU type is pages long.

The whole hype around AMDs TLB bug was just another demonstration on how the common IT consumer web community lacks respectable wisdom.

[Rammsteiner]

Indeed, AFAIK this TLB bug is already in documentation from Intel right at their own site. And if it ain't a big issue, then I dont think they'll make some sort of huge announcement about it.

Although, depends on how FUD & Co blow it up

[AuDioFreaK39]

FK.

[Particle]

No, it won't be a problem for i7 prospectors. And no, I don't think this means AMD fans will be dancing in the aisles. More likely, it will just be met with head shakers as the response to this will likely be muted in comparison. Both TLB bugs involve data corruption and both can be fixed in the same BIOS patch manner. Both can be experienced in rare circumstances. Both are unlikely to ever be encountered by normal end-users. Response: "But Intel's is different! It isn't a big deal but AMD's was the end of the f'king universe!"

Bleh. They're both over-hyped issues that we aren't going to experience.

[AuDioFreaK39]

When do you guys think the X58 motherboard vendors will get around to addressing this issue?

[Hornet331]

seems fuad needs some money for his christmas presents.

[flippin_waffles]

Hmm I wonder if this is why so many review sites have gone out of their way to avoid any virtualization tests on Shanghai, which is where it stands head and shoulders above the competition's current and next gen hardware. There'd be no comparison to the current gen Xeon, and if this affects Nehalem performance, Intel wouldn't have a leg to stand on.

Granted, there's alot of if, and's, and but's in there and a bit of a conspiracy theory, but still!

[Ghostbuster]

When do you guys think the X58 motherboard vendors will get around to addressing this issue?

It can also be fixed in the operating system because this only happens when it does an improper TLB invalidation.

EDIT: Refer to the first page of this thread...

[Chad Boga]

No, it won't be a problem for i7 prospectors. And no, I don't think this means AMD fans will be dancing in the aisles. More likely, it will just be met with head shakers as the response to this will likely be muted in comparison. Both TLB bugs involve data corruption and both can be fixed in the same BIOS patch manner. Both can be experienced in rare circumstances. Both are unlikely to ever be encountered by normal end-users. Response: "But Intel's is different! It isn't a big deal but AMD's was the end of the f'king universe!"

Bleh. They're both over-hyped issues that we aren't going to experience.

Tier 1 Server OEM's weren't prepared to risk it with Barcelona, no doubt based on their own testing.

If they are with Nehalem, that will say whether the TLB bugs are of similar severity, not posters on a forum, that's for sure.

[soundood]

what goes around comes around?

swings and roundabouts?

lol it just makes me laugh

but hey to fair to Intel, i think errata is the new buzz word now a days, as has been said before, there are hundreds.

[justapost]

So this bug is fixed with an bios update. Soemhone here compared a fixed with an unfixed bios? I don't think so.

[AuDioFreaK39]

It can also be fixed in the operating system because this only happens when it does an improper TLB invalidation.

EDIT: Refer to the first page of this thread...

So is Microsoft going to release a Windows Update for this as well? How does it work..

[Hornet331]

So is Microsoft going to release a Windows Update for this as well? How does it work..

i doubt anyone is going to release anything. The same clarification is in the C2D 65nm errata since April 2007.

Have you seen any bios updates for C2 regarding to this "bug"?

[Papu]

since none of the reviewers found anything wrong with the chips , and i havent heard about instability or Bsods , makes me think its a minor issue with no real world effect..

[Ghostbuster]

So this bug is fixed with an bios update. Soemhone here compared a fixed with an unfixed bios? I don't think so.

I think there isn't any difference at all... no performance penalty with this one..


By the way...

Here's the page of the desktop Core 2 Duo E7000 and E8000 series: http://download.intel.com/design/pro...pdt/318733.pdf

It has the exact same text written on page 47.

Here's the page of the desktop Core 2 Duo X6800, E6000 and E4000 series: http://download.intel.com/design/pro...pdt/313279.pdf

It has the exact same text written on page 71.

Here's the page of the desktop Pentium Dual Core E2000 series: http://download.intel.com/design/pro...pdt/316982.pdf

It has the exact same text written on page 59.

Here's the page of the Intel Celeron 200 series: http://download.intel.com/design/pro...t/31854702.pdf

It has the exact same text written on page 53.

Maybe FUD will wanna post about all of them?

[AuDioFreaK39]

Thanks for the refresh Ghostbuster. Looks like my respect for Fud just went down another point.

[Xello]

Say what you want about Fuad, i've always liked that he seems to be unbiased

He writes just as much nonsense about Intel as he does about AMD, and same with ATI/NV

The non-discriminating Baztard.

[m^2]

Why?

Well I posted in rush, I've been thinking not of "a TLB bug" but "the TLB bug".
It would be extremely unlikely that both companies made the same mistake. Especially that Intel knew of AMD's problem.

The whole hype around AMDs TLB bug was just another demonstration on how the common IT consumer web community lacks respectable wisdom.

IMO the hype was caused by the way AMD handled the problem - they shipped flawed review samples to get better benchmark scores.

[savantu]

Well I posted in rush, I've been thinking not of "a TLB bug" but "the TLB bug".
It would be extremely unlikely that both companies made the same mistake. Especially that Intel knew of AMD's problem.

IMO the hype was caused by the way AMD handled the problem - they shipped flawed review samples to get better benchmark scores.

Huh ??

AMD's problem was huge compared to this nitpickin an errata list.AMD's problem was that K10 failed validation at major OEMs , that's HP,IBM,Fujitsu,etc.When that happens you're royally screwed.Those major OEMs didn't want to touch K10 with a 10 ft pole.
When you ship servers in mission critical areas ( industry, banking,etc ), a once in a while system crash ( which wasn't so rare in virtualized environments it seems, which btw is the current hottest trend ) is simply not acceptable.

Chips can have hundreds of errata , as long as they pass the most stringent validation requirements you're fine.
The difference is that with K10 people in the industry started whispering and gossip sites picked it up ; in this case a dude searched an errata list ( guess what genius, that's published after validation => wasn't considered a game stopper ) and sent a link a FUD.

[gOJDO]

Next rumor by FUD: "Next Nehalem stepping will be 10% faster due to TLB bug fix".

Can't get the point why people are wasting their time reading FUD.

[m^2]

Huh ??

AMD's problem was huge compared to this nitpickin an errata list.AMD's problem was that K10 failed validation at major OEMs , that's HP,IBM,Fujitsu,etc.When that happens you're royally screwed.Those major OEMs didn't want to touch K10 with a 10 ft pole.
When you ship servers in mission critical areas ( industry, banking,etc ), a once in a while system crash ( which wasn't so rare in virtualized environments it seems, which btw is the current hottest trend ) is simply not acceptable.

Chips can have hundreds of errata , as long as they pass the most stringent validation requirements you're fine.
The difference is that with K10 people in the industry started whispering and gossip sites picked it up ; in this case a dude searched an errata list ( guess what genius, that's published after validation => wasn't considered a game stopper ) and sent a link a FUD.

I might be mistaken here, but I remember that they passed validation after disabling L3, didn't they?