More Intel leaks.. this one is not good though

[WereCatf]

3 minutes ago, mr moose said:

Is there any evidence Intel knew about this for the last ten years or do we just have the typical armchair experts again pontificating Intel's ineptitude and evilness?

Pfft. If they knew about this, someone there would have leaked the information already years ago. Don't listen to tinfoil-hat wearing conspiracy-theorists.

7 minutes ago, mr moose said:

could even come close to engineering a cpu let

Hell, I can barely engineer myself some breakfast.

[Mira Yurizaki]

15 minutes ago, WereCatf said:

I could totally see smaller ones doing that, but e.g. Microsoft and Amazon, no. They just cannot afford such a risk, they have high-end customers from all sorts of fields, including physics, medical and military -- those customers would disappear instantly if it came out that Amazon/Microsoft was risking the security of their stuff like that, let alone if something actually did leak for real.

The landscape isn't as pretty as the picture you paint it to be.

9 minutes ago, mr moose said:

Is there any evidence Intel knew about this for the last ten years or do we just have the typical armchair experts again pontificating Intel's ineptitude and evilness?

 

No one can escape the law of averages. And I am damn sure no one posting in this thread could even come close to engineering a cpu let alone perfectly avoiding every single exploit/bug you might encounter in doing so.

That's what I was pondering. Like nobody can do anything against Intel unless they have some proof that they knew about this prior and did nothing about it. Up until now this is considered a screw up. With CPUs as complex as they are, it's infeasible to test every single possible combination of test cases unless you don't mind waiting 10 years for the product to come out.

 

And I'm rolling my eyes every time I see a "AMD is going to be rolling in money" or similar. Again, AMD isn't any more open about its security features and other things than Intel. From that Blackhat video I posted, the presenter felt that AMD's processors could also be vulnerable to Sinkhole (which means every processor before Ryzen is at risk, considering the presentation was made in 2015, but even I wouldn't be that optimistic). And if AMD starts becoming more popular, people are going to start poking it for security holes and who knows? Maybe three years down the road we'll find a massive back door like flaw in Ryzen.

[Tannah]

6 minutes ago, mr moose said:

Is there any evidence Intel knew about this for the last ten years or do we just have the typical armchair experts again pontificating Intel's ineptitude and evilness?

 

No one can escape the law of averages. And I am damn sure no one posting in this thread could even come close to engineering a cpu let alone perfectly avoiding every single exploit/bug you might encounter in doing so.

 

The Cynical side of myself suspects: That if there was any strong evidence it has been destroyed, or strangely lost.
But I would expect this action from any company the size of Intel.

[ItsMitch]

Just now, WereCatf said:

Hell, I can barely engineer myself some breakfast

there are... other methods for getting breakfast cooked

[Mira Yurizaki]

1 minute ago, Tannah said:

The Cynical side of myself suspects: That if there was any strong evidence it has been destroyed, or strangely lost.
But I would expect this action from any company the size of Intel.

Unless we're living in some cyberpunk thriller, or the reporter was paid handsomely, I'd imagine there would've been a whistle blower over this.

[WereCatf]

2 minutes ago, SC2Mitch said:

there are... other methods for getting breakfast cooked

The pizza-place isn't open yet

[NumLock21]

1 hour ago, PianoPlayer88Key said:

 

 

So maybe the tables might be turned in this scenario?

 

Or, maybe my desktop's 4790K will drop performance to this level?

C'mon man at least make it believable. You can't even fake properly.

 

[mr moose]

7 minutes ago, Tannah said:

The Cynical side of myself suspects: That if there was any strong evidence it has been destroyed, or strangely lost.
But I would expect this action from any company the size of Intel.

At the end of the day if this is as bad as it seems, then you can bet your arse they didn't do it on purpose and had they known earlier they would have been looking to fix it before anyone found out. So in all likelihood the very last generation or two would not have the bug.

 

Given how complex these processors are becoming (which is why it is so hard for new players to enter the game), it is not beyond reason that it was a genuine oversight. Hopefully they find a decent fix soon.   

[Tannah]

I would hope that AMD would be looking into its processors to see if there are any manufacturing flaws like this one. But it took 10 years for the community to find this one. How long would it take them to find simaler in AMD?

 

If this could have been fixed by a microcode update, I suspect it already would have already been fixed in a very quiet manner.

[Tannah]

7 minutes ago, M.Yurizaki said:

Unless we're living in some cyberpunk thriller, or the reporter was paid handsomely, I'd imagine there would've been a whistle blower over this.

True, tho sometimes reality is stranger than fiction.

[WereCatf]

1 minute ago, mr moose said:

At the end of the day if this is as bad as it seems, then you can bet your arse they didn't do it on purpose and would have been looking to fix it before anyone found out So in all likelihood the very last generation or two would not have the bug.

There are plenty of engineers working at Intel who are genuinely excited about the work they do and I just cannot for the life of me imagine an engineer who enjoys their work, who is excited about their products, withholding something like and not leaking it, simply because they'd want to see it getting fixed ASAP. I mean, when you love your stuff, you most likely want everyone else to love it too and it to be as good as possible -- letting a huge issue like this lie hidden would go entirely counter to that. Besides, 10 years is a long time; it'd be hard enough to contain this for one year, let alone 10!

6 minutes ago, mr moose said:

Hopefully they find a decent fix soon.   

That doesn't seem likely, since there is no way of fixing this in microcode. Any OS-level workarounds are going to take a performance-hit, no matter how one spins it around.

[dfsdfgfkjsefoiqzemnd]

Guess I'll be back at the stock level of performance then (running roughly a 30% overclock).  Fortunately that's not really a problem for me, it was powerful enough at stock speed.

 

I wonder how this will affect older gaming machines though.  Sandy and Ivy will probably only be good for browsing the internet anymore.   

[WereCatf]

Just now, Captain Chaos said:

Guess I'll be back at the stock level of performance then (running roughly a 30% overclock).  Fortunately that's not really a problem for me, it was powerful enough at stock speed.

 

I wonder how this will affect older gaming machines though.  Sandy and Ivy will probably only be good for browsing the internet anymore.   

Um, this bug affects primarily tasks with a lot of task-switching, not your typical home-user/gamer-workloads. Do you run heavy database-operations, virtual-machines and/or serve thousands of people at all times? No? Well, then, you're unlikely to be affected much!

[dfsdfgfkjsefoiqzemnd]

I do regularly run a couple of VMs on my main rig actually.  Still, that probably won't affect things too much indeed as I don't switch over constantly. 

Good to know, I had somehow misunderstood it and thought that performance was reduced no matter the use case. 

[ItsMitch]

6 minutes ago, Captain Chaos said:

and Ivy will probably only be good for browsing the internet anymore.

Im still using Sandy Bridge and it's running fine as of now, running most games at high but let's see what this update brings (using i7 2600 for reference)

[WereCatf]

2 minutes ago, Captain Chaos said:

thought that performance was reduced no matter the use case. 

It is, but not by 30%. How much it really affects home-users/gamers/enthusiasts remains to be seen, but the worst hit is on server-loads. I'll allow for server-admins to be shitting bricks, sure, but for us home-users/gamers/enthusiasts it's best to maintain cooler heads for now and wait for the patches to actually land and people to start releasing actual results from testing.

[Guest]

32 minutes ago, WereCatf said:

It is, but not by 30%. How much it really affects home-users/gamers/enthusiasts remains to be seen, but the worst hit is on server-loads. I'll allow for server-admins to be shitting bricks, sure, but for us home-users/gamers/enthusiasts it's best to maintain cooler heads for now and wait for the patches to actually land and people to start releasing actual results from testing.

I agree with this actually. 

[D13H4RD]

Welp, I hope this doesn't turn my rig from Kaby to Haswell 

[PianoPlayer88Key]

1 hour ago, WereCatf said:

Pfft. If they knew about this, someone there would have leaked the information already years ago. Don't listen to tinfoil-hat wearing conspiracy-theorists.

Hell, I can barely engineer myself some breakfast.

 

1 hour ago, SC2Mitch said:

there are... other methods for getting breakfast cooked

 

1 hour ago, WereCatf said:

The pizza-place isn't open yet

 

      

[ravenshrike]

1 hour ago, mr moose said:

At the end of the day if this is as bad as it seems, then you can bet your arse they didn't do it on purpose and had they known earlier they would have been looking to fix it before anyone found out. So in all likelihood the very last generation or two would not have the bug.

That still leaves the amount of time after they taped out Kaby Lake(since a Covfefe/Cannon are effectively shrinks of the same architecture with the mesh memory modification) for them to have found out about it. 

45 minutes ago, WereCatf said:

How much it really affects home-users/gamers/enthusiasts remains to be seen

Interestingly, it's much more likely to affect multiplayer games than singleplayer, especially MMOs, with all the more involved anti-cheat stuff going on in the background. I expect WoW and Destiny 2 to have particularly noticable performance hits.

[Guest]

2 minutes ago, PianoPlayer88Key said:

 

The mad man is cooling the food as he cooks it!

[PianoPlayer88Key]

1 hour ago, NumLock21 said:

C'mon man at least make it believable. You can't even fake properly.

 

Well, the Cinebench R15 score of 4 was done in a VM, set at like a 1% execution cap.

The 2 laptops were running natively, though.

[LunaP0n3]

Well, if it's a critical patch we need, I guess we'll have to use it. How did Intel not pick up on this???

[Mira Yurizaki]

6 minutes ago, LunaP0n3 said:

Well, if it's a critical patch we need, I guess we'll have to use it. How did Intel not pick up on this???

You try testing at least 2^64 iterations of something.

 

And that's probably still the equivalent of taking a drop of water from the ocean.

[LunaP0n3]

3 minutes ago, M.Yurizaki said:

You try testing at least 2^64 iterations of something.

 

And that's probably still the equivalent of taking a drop of water from the ocean.

Fair enough. All the big companies will be working hard to write patches for this.