Sandy Bridge-E VT-d Broken In C1 Stepping, Fixed In C2 Stepping, Shortly After Launch

[Sihastru]

The initial batch of C1 revision Sandy Bridge-E processors have a bug – “errata” in Intel terminology – in them with VT-d, which means that hardware accelerated virtualization doesn’t work properly with them (software only mode is unaffected). The feature when working properly, allows all hardware acceleration to work on the hosted operating system (virtual machine). This would allow things such as hard drive controllers to work, plus applications such as high-powered 3D games, typically First Person Shooters, to run at nearly full speed and the full Windows Aero desktop to be displayed on the hosted OS, as the hardware features of the graphics card can be used. Therefore, working VT-d is a critical feature for these kinds of applications.

It's one thing for "errata" to be discovered some time after a product has been released and then to manufacture a revised processor, but it doesn’t seem right for Intel to release processors with a known major feature fault like this, especially as most buyers are unlikely to know about it and Intel is even less likely to shout about it. Therefore, buyers would be wise to wait for the bug-fixed C2 version before upgrading, unless they are absolutely sure they won’t need this virtualization feature. After all, are Intel going to offer a free replacement to the fixed version for customers of the initial C1 versions? Only this gesture can make releasing such an obviously flawed product right. Intel have offered such a free replacement recently with the faulty SATA controller, so there's hope yet they'll do the right thing. And just as importantly, it's worth keeping a close watch on what significant errata C2 might harbour, before upgrading.

This part of the "news" is your own addition and has a nice scent of bias. You can say that it's your own analysis of the news bit on VR, but there are a few flaws with it.

The most important thing to note is that VT-d is not present on desktop platforms. Not only the CPU has to support VT-d, but also key motherboard components (NB/SB). On desktop consummer products these "features" are disabled. They are also disabled on desktop consummer CPUs.

Enterprise customers are not "most buyers" and they do know exactly what features they need and what they don't need. Also they would not normally buy a consumer grade desktop computer. They will buy enterprise grade workstations and servers, which is the Xeon brand, with Xeon compatible motherboards that will support VT-d if they indeed need this feature.

Games, like "first person shooters", are not an really what servers are for. Your trying to plant an idea in the minds of gullable TPU readers (I really hope they buy Bulldozers, I don't want them on the Intel camp), that SB-E has some major flaw that will affect their gaming performance. In reality this doesn't concern anyone since VT-d is disabled at the hardware level on consumer grade desktops.

So why is a bug in a disabled feature important? It's not.

By the time we get Xeons in the channel, they will all be C2. There will be no need for any recalls and "free replacements".

Sorry to lash out like this, but I thought TPU was above this.

 

[zsolt_93]

What about these?
2820QM
2600
Some i7s have vt-d and even mobile models do. So no Xeons here. Playing games on a virtual machine depends from vt-d so there was nothing wrong in the OP.

 

[Sihastru]

Mobile platforms yes, because those platforms are multi-purpose. I did say desktop platforms, also I don't think we have Sandy Bridge E on X79 motherboards laptops. Not yet anyway.

The desktop processors that do support VT-d, require a special chipset, braded as "Q", Q67 for example, for the 2600, with compatible BIOS, and that is a workstation chipset meant for enterprise. Even there you can't be sure you'll have full VT-d support, they will only give you AMT support (that requires some VT-d features).

Do not confuse VT-d with VT-x.

Also for those thinking that buying a Bulldozer is the answer, AMD-Vi is not supported on the desktop variants, you'll need to buy an "Opteron" part. Also, don't confuse AMD-V with AMD-Vi (for IOMMU). Again, you'll need a server motherboard, your desktop motherboard won't support AMD-Vi.

 

[shb-]

I see no real problem here, 2600K does not have VT-d at all, and nobody seems to have problem with that. On most mobos/bioses VT-d is disabled by default, so god only knows how many nahalems/other VT-d capable CPUs are actually running with it disabled. I think only few of those hardcore gamers/encoders/OCers who are looking towards X79, truly care about virtualization.

Its good to know of course. And it’s still nice to have it, although u don’t actually use it (for e-dicks sake).

And afaik virtual box does not support VT-d, yet:
https://www.virtualbox.org/ticket/5252
so only those who have VMWare licenses can utilize it.

 

[Disparia]

^ The 2600 and 2600 do have it, which is why you might not many people taking issue with it.

 

[[H]@RD5TUFF]

I think there's a fair bit of exaggeration going on. Intel would not release a server-class processor without VT-d functionality (equivilent of shooting one self in the foot). It has a bug, but I highly doubt it is completely dysfunctional.

Kinda how I see it.

 

[FordGT90Concept]

^ The 2600 and 2600 do have it, which is why you might not many people taking issue with it.

Only the non-K models have VT-d. How Ironic.

List of processors with VT-d.

 

[zsolt_93]

K models are missing Vt-d. Apart from that tyhere are even i5 s like the 2400 with it.

 

[FordGT90Concept]

Yeah, I just noticed that. S models have it too. Not K.

 

[Jegergrim]

Some PCI Express 3.0 devices are still likely to work, but Intel doesn’t guarantee compatibility. This doesn’t bode well for the current 6-series motherboard with gen 3 switches actually working properly once cards and especially, Ivy Bridge processors arrive. Waiting for full qualification before purchasing is therefore advised, or an expensive motherboard replacement may be required in the not too distant future.

Why doesn't this bode well with the lga 1155 6 series boards with gen 3 switches?

 

[Disparia]

Only the non-K models have VT-d. How Ironic.

List of processors with VT-d.

Yup. Gotta check per chip these days. Intel throws in an 'asterisk' or two here and there, breaking series commonality. Ex: All 34xx Xeons have HyperThreading * Except the X3430.

 

[eidairaman1]

Only the non-K models have VT-d. How Ironic.

List of processors with VT-d.

So why does the high end not have everything?

 

[Inceptor]

So why does the high end not have everything?

The SB 'K' parts are specifically marketed to home desktop users interested in overclocking. Everything else with VT-d can be sold to corporate and government customers who might have the need for such a thing.

The C1 stepping of SB-E not having VT-d will only affect users who need hardware virtualization...
Although I'm sure it will also reduce the sales of SB-E to home users who have no use for VT-d, just because of the appearance of a problem (for their usage of the chip).

 

[FordGT90Concept]

Here's the comparison of the three 2600 models. There's actually lots of pretty significant differences among them:
http://ark.intel.com/compare/52215,52214,52213

Most notable:
-S has a lower base clock (2.8 GHz vs 3.4 GHz) and as a consequences, a 65w TDP instead of 95w.
-2600 has Embedded Options Available (longer support lifecycle)
-K has HD 3000 while S and 2600 have HD 2000
-K does not have vPro, VT-d, nor Trusted Execution Technology support.

Yup. Gotta check per chip these days. Intel throws in an 'asterisk' or two here and there, breaking series commonality. Ex: All 34xx Xeons have HyperThreading * Except the X3430.

Curse them for not K.I.S.S.ing.

 

[de.das.dude]

looks like we need another new news editor.

 

[eidairaman1]

The SB 'K' parts are specifically marketed to home desktop users interested in overclocking. Everything else with VT-d can be sold to corporate and government customers who might have the need for such a thing.

The C1 stepping of SB-E not having VT-d will only affect users who need hardware virtualization...
Although I'm sure it will also reduce the sales of SB-E to home users who have no use for VT-d, just because of the appearance of a problem (for their usage of the chip).

be honest here if its a high end unit i want all the functions of it on there. TBH intel is confusing with all this crap now

 

[FordGT90Concept]

Overclock & decent integrated graphics: 2600K
Save power: 2600S
Otherwise: 2600

 

[[H]@RD5TUFF]

Intels naming scheeme isn't that hard to understand .. .

 

[qubit]

Why doesn't this bode well with the lga 1155 6 series boards with gen 3 switches?

Because when PCI-E 3.0 becomes mainstream, everything in the chain must work together to deliver it, so if some part is out of spec the whole thing fails (and falling back to spec 2.0 for partial functionality would be a failure). If Intel isn't able to qualify compatibility, then you can just see mobos released without this certification being decidedly flakey and everyone shirking responsibility when people try to claim under warranty. In short, it'll be ugly.

 

[parelem]

be honest here if its a high end unit i want all the functions of it on there. TBH intel is confusing with all this crap now

the whole 1155 platform is NOT high end, it's mid range.

 

[eidairaman1]

regardless they released a CPU that is high end for it, aka Core i7, which is on 1366 aswell, core i7 i recalled was the high end cpus.

 

[Inceptor]

regardless they released a CPU that is high end for it, aka Core i7, which is on 1366 aswell, core i7 i recalled was the high end cpus.

The operative word being 'was'.
Core i7 is now only 'high end' when associated with Sandy Bridge Extreme.
Core i7 2xxx are now only 'mid-range performance cpus'
Welcome to the present.

 

[FordGT90Concept]

Core i7 = performance
Core i5 = mainstream
Core i3/Pentium/Celeron = budget

LGA 1366/2011 = enthusiast/workstation/entry-level server (high premium on motherboards largely due to the chipset)
LGA/BGA 1156/1155 = desktop/laptop

 

[Thefumigator]

Mobile platforms yes, because those platforms are multi-purpose. I did say desktop platforms, also I don't think we have Sandy Bridge E on X79 motherboards laptops. Not yet anyway.

The desktop processors that do support VT-d, require a special chipset, braded as "Q", Q67 for example, for the 2600, with compatible BIOS, and that is a workstation chipset meant for enterprise. Even there you can't be sure you'll have full VT-d support, they will only give you AMT support (that requires some VT-d features).

Do not confuse VT-d with VT-x.

Also for those thinking that buying a Bulldozer is the answer, AMD-Vi is not supported on the desktop variants, you'll need to buy an "Opteron" part. Also, don't confuse AMD-V with AMD-Vi (for IOMMU). Again, you'll need a server motherboard, your desktop motherboard won't support AMD-Vi.

Opteron are cheap, unlike intel server platforms, you could buy a dual socket C32 motherboard with [whatever opteron available for that socket], for less than 1000$, just take a look at newegg.

On the other side, AMD-Vi seems interesting (hey, having direct access to each hardware part sounds really cool) But in my case I only know that each AMD processors in existance supports AMD-V and its the only thing I need for running my Virtual Box at decent speed. And the difference is noticeable with AMD-V turned off.

Unlike intel and its VT, all amd processors support AMD-V. Except perhaps, zacate and llano. No wait, llano supports it. Zacate too!

 

[TheGuruStud]

Comparing this to barcelona is retarded. You couldn't reproduce that TLB if you tried. This feature just doesn't work. Two entirely different things.

But don't let that stop anyone from spewing crap (about either side).