Intel to address bug in Skylake Cpu's

[HiFlyer 9,343]

Intel has discovered that its latest 6th Gen (Skylake) Core processors have a bug that can cause the system to freeze or crash when calculating prime numbers.

 

http://www.tomshardware.com/news/skylake-prime-number-bug,30979.html

[jabloomf1230 2,445]

Whoa, now we'll all have to stop doing that. J/K, I know that the bug is a symptom of something that is wrong and could be much worse.

[HiFlyer 9,343]

Whoa, now we'll all have to stop doing that. J/K, I know that the bug is a symptom of something that is wrong and could be much worse.

 

Yup! Last time anything similar to this happened, It caused such a stink that Intel had to recall the affected processors.  https://en.wikipedia.org/wiki/Pentium_FDIV_bug

 

They are going to jump all over this to make sure that doesn't happen this time.

[Greggy_D 935]

Looks like they are doing the fix via Motherboard BIOS updates.

[vortex681 806]

Yup! Last time anything similar to this happened, It caused such a stink that Intel had to recall the affected processors.

 

Read through all the comments in the link you posted and you'll see that the old Pentium bug was a very different beast which couldn't easily be fixed with a BIOS update like this one.

[HiFlyer 9,343]

Read through all the comments in the link you posted and you'll see that the old Pentium bug was a very different beast which couldn't easily be fixed with a BIOS update like this one.

 

I'm not sure that can be decided just yet. Until the "fix" is out in the wild and tested en masse, there's no way to know if there's going to be any sort of performance (or other) penalty.

[martin-w 3,234]

"When calculating prime numbers"... so when running a synthetic stress test like Prime95 or some scientific or financial applications. And only has a "slim" chance of occurring under intense workloads.

 

Won't affect most of us then. Prime95 isn't advised for the latest processors anyway.

 

BIOS update already done, sounds like it's not going to be a big deal.

[Guest]

Looks like they are doing the fix via Motherboard BIOS updates.

 

Most likely Intel will just disable some aspect of the CPU ... prime numbers are used A LOT, especially in security/encryption, so it's definitely a significant issue.

 

What I find somewhat surprising is that the issue was brought to Intel's attention prior to the CPU being officially released, but Intel ignored it ... that's the bigger concern I have with Intel.  Not so much Intel had a problem, it's how they dealt with the problem before it became public.

 

I don't have a Skylake CPU, but regardless ... it's the trying to avoid a $475M write-down and hope "they don't notice" which I don't think was a wise management decision.

 

Cheers, Rob.

[martin-w 3,234]

But the issue has a "slim chance of occurring" and "only under intense workloads"... So probably why Intel chose to ignore it. They knew it was a rare occurrence and they knew they could fix it.

 

Still don't think it will be a significant issue. It can't be a significant issue if it's defined as rare and fixable.

[ckyliu 1,749]

Prime95 isn't advised for the latest processors anyway.

What is now? I used Prime95 to overclock my Sandybridge, and I understand it's been updated since to support Haswell instruction set.

[martin-w 3,234]

What I know is that Asus don't recommend stress tests like Prime95 or IBT.

 

Asus say they aren't fully validated for the latest CPU's, and can over stress some aspects and under stress others.. It may have been updated for Haswell but Haswell isn't Skylake. In a recent video the Asus rep once again advised against Prime95. Clearly many still use it though.

 

Personally, I haven't used it since Ivy Bridge. Aida, ROG real bench, Intel Extreme Tuning Utility I would favour. And certainly not IBT.

 

ROG Real Bench uses open source applications to test the CPU as it would be used in real life. In other words it's not synthetic like Priem95. Because Asus are using open source apps, there is clearly no bias. Asus found that no free synthetic stress test offered a rounded idea of the value of the overclock, so they created one.

[Guest]

No software should be able to "freeze/lockup" a PC at the hardware level when operating valid instruction sets.  It is possible for CPUs to get into a deadlock/contention state (especially with HT enabled) but that's not the same as a "freeze/lockup".  

 

Malicious software may try to "crash" a PC or put it in vulnerable state but again that's not the same as a "freeze/lockup".  Prime95 is a rather simple program executing valid instructions (it's not malware) ... for Intel or Asus to say one "shouldn't run" any valid software is VERY dubious.

 

Asus have warned that Prime95 can damage a CPU ... if that claim is accurate (which I don't see how or why it could be), then there is either a problem with the CPU and/or other components (motherboard/chipset/RAM).

 

Analogy would be like me saying P3D caused my PSU to fail.

 

Cheers, Rob.

[gboz 157]

What is now? I used Prime95 to overclock my Sandybridge, and I understand it's been updated since to support Haswell instruction set.

http://www.aida64.com

(Payware unfortunately)

 

Or http://www.ocbase.com

(Freeware)

 

gb.

[martin-w 3,234]

Malicious software may try to "crash" a PC or put it in vulnerable state but again that's not the same as a "freeze/lockup". Prime95 is a rather simple program executing valid instructions (it's not malware) ... for Intel or Asus to say one "shouldn't run" any valid software is VERY dubious.

It isn't valid though Rob. It isn't validated for the latest architectures. Thus it doesn't test certain newer instruction sets.

 

 

Asus have warned that Prime95 can damage a CPU ... if that claim is accurate (which I don't see how or why it could be), then there is either a problem with the CPU and/or other components (motherboard/chipset/RAM).

 

They haven't warned it can damage CPU's. Simply that when a new architecture is released, it doesn't test newer instruction sets and could possibly over stress others. That doesn't necessarily equate to damaged CPU's, BSOD, lockup's maybe.

 

It isn't dubious Rob. They simply don't recommend it's use for stress testing. ROG Real Bench is free of course, so it's no skin of Asus's nose if we use it or not, no bias. Asus have nothing against the creator of Prime95, just that in their experience it's not ideal. Asus also point out that it's a synthetic stress test, thus, it doesn't stress a CPU the way the vast majority of us utilise our PC's 24/7. Which was why they created ROG Real Bench. It's not just Prime95, Asus aren't fans of any of the synthetic stress tests.

 

My Ivy Bridge system for example was 100% stable in Prime95. as soon as I fired up Battlefield, BSOD. Therefore was forced to tweak my overclock further to achieve "real" stability, stability that reflected real world use. Asus are correct, Prime95 and the other synthetic stress tests aren't ideal, as they bare little resemblance to how the vast majority of us use our PC's.

 

If Prime 95 isn't validated for the latest architecture, then it makes perfect sense to me that it's not the ideal choice. If it doesn't stress a CPU the way I do 24/7, then it makes perfect sense to me that it's not the ideal choice.

 

We build and overclock our PC's to be stable when running our favoured applications, to be stable in "real world use"... we don't build and overclock our PC's to be "Prime95 machines", or "IBT machines".

 

Asus have been saying this since Ivy Bridge, I'm surprised you've not heard it before.

 

Asus are pretty good at this stuff, it's what they do. They literally test thousands of CPU's. Therefore I give their opinions consideration, and on this occasion, I agree with them.

 

 

http://rog.asus.com/275272013/overclocking/realbench-benchmarking-stress-test-insights/

[Guest]

I wasn't contending that Prime95 is not using "new instruction sets" ... but, Prime95 operates valid instructions, a CPU should be able to handle those instructions.  Not contending what should or shouldn't be used for Stress testing (I use a combination of many different products for stress testing) either, RealBench, Prime95, SiSoftware Sandra, etc. etc. 

 

From Asus:

 

http://rog.asus.com/365052014/overclocking/rog-overclocking-guide-core-for-5960x-5930k-5820k/

 

 

Stress Testing

Users should avoid running Prime95 small FFTs on 5960X CPUs when overclocked. Over 4.4GHz, the Prime software pulls 400W of power through the CPU. It is possible this can cause internal degradation of processor components.

 

The above statement is not accurate and is dubious.  I agree that no "single" application should be used when stress testing (overclocked or not).

 

Cheers, Rob.