Intel bug incoming? Meltdown and Spectre exploits

Randomface74 · 4 Jan 2018 at 10:49

I ran windows update but it didn't show up?

AndreiD · 4 Jan 2018 at 10:52

They're staggered updates, so you should get it eventually within the next few days.

SiDeards73 · 4 Jan 2018 at 10:58

Ooops https://www.businesswire.com/news/home/20180103006309/en/

Cant imagine anything really coming from that though..

darael · 4 Jan 2018 at 11:02

Cromulent said:
Just patched Windows 10 with the latest patch and ran the Heaven 4 benchmark and my results at 1080p were almost exactly the same as my results prior to installing the patch.

I did upgrade my Samsung 840 Pro SSD to the latest firmware in between though but I doubt that made much of a difference.

Which firmware do you have installed now? I've had DXM06B0Q installed for several years now.

AndreiD · 4 Jan 2018 at 11:02

I wonder if Krzanich will weather this storm, Intel's quarterly reports are really good, but then again they keep taking PR hits, 14/10nm difficulties, vulnerabilities keep piling up, plus these accusations of insider trading (which seem unfounded but who knows at this point...).

Silent_Scone · 4 Jan 2018 at 11:03

https://newsroom.intel.com/news/intel-responds-to-security-research-findings/

Not sure if this was posted already.

AndreiD · 4 Jan 2018 at 11:05

Most of it is just PR speak.

SiDeards73 · 4 Jan 2018 at 11:05

Silent_Scone said:
https://newsroom.intel.com/news/intel-responds-to-security-research-findings/

That was from yesterday and was already scoffed at by pretty much every tech site, not to mention AMD released their own statement... Intel are basically trying to take everyone else down with them...

Notice they omit the "Read" fuction from their statement when talking about what the exploit can do? its laughable at best, some of the biggest PR tripe ive ever read.

It must be full panic station mode at Intel right now.

drunkenmaster · 4 Jan 2018 at 11:06

Rroff said:
Intel are going to have to up their game - this isn't the only serious and long standing hardware vulnerability that has come to light lately with their hardware - there have been at least 2 AMT disclosures in the last 6 months - and people seem to have quickly forgotten about stuff like https://www.theregister.co.uk/2017/05/01/intel_amt_me_vulnerability/

Not a fan of AMD's position though - they seem to just deny any problem before there has even been any testing and/or make a big deal about "close to zero" when it isn't zero and seems based on only preliminary testing - I'm not sure I trust them any more than Intel when it comes to security and they have less resources to get on top of patching issues like this if they do arise.

Why are you saying based on no or preliminary testing? Near zero means, we've tested exhaustively but we can't be 100% sure so if we say zero and someone finds one vector for attack 10 years from now we can get sued, so we say near zero, nothing more or less. AMD have known about this issue at least as long as since Google brought it up a year ago to these companies... you think they've done zero testing between now and then? Also google themselves who found the exploit said that they couldn't only make Zen vulnerable to a non malicious attack they wrote, the three malicious attacks were only vulnerable on older AMD architectures (in a non default state) and everything Intel.

Implying they haven't tested is crazy.

Also the linux patch is hilarious. The check in english basically says, if it's an AMD processor, assume it's secure, otherwise enable the patch.

Rroff · 4 Jan 2018 at 11:10

drunkenmaster said:
Implying they haven't tested is crazy.

I was talking about testing in a contextual fashion not saying there hasn't been any testing at all. Some of the things where they are saying close to or near zero are binary situations where either they should be fully proof against the known vectors in the situation talked about or vulnerable - near zero is the same as vulnerable just not as easily exploited within those specific parameters.

Devrij · 4 Jan 2018 at 11:16

Uh oh:

Intel Inside(er trading)

Intel CEO Brian Krzanich sold off a major stake in the company in November, months after the chip maker learned of a significant security flaw in its chips.

http://uk.businessinsider.com/intel...fter-company-was-informed-of-chip-flaw-2018-1

Hades · 4 Jan 2018 at 11:16

SiDeards73 said:
Ooops https://www.businesswire.com/news/home/20180103006309/en/

Cant imagine anything really coming from that though..

As you say, probably nothing will come of it. But interesting nonetheless.

beany_bot · 4 Jan 2018 at 11:17

This is shambolic. And now we know why AMD struggled so much to match intels IPC speed.

AndreiD · 4 Jan 2018 at 11:20

beany_bot said:
This is shambolic. And now we know why AMD struggled so much to match intels IPC speed.

Based on benchmarks so far, the IPC difference hasn't really changed overall.
It does make Epyc more compelling for some datacenter tasks though.

Silent_Scone · 4 Jan 2018 at 11:21

beany_bot said:
This is shambolic. And now we know why AMD struggled so much to match intels IPC speed.

lol - little dramatic. I' wager with you now there'll be next to no if not any detriment to performance for majority of workloads.

beany_bot · 4 Jan 2018 at 11:28

Silent_Scone said:
lol - little dramatic. I' wager with you now there'll be next to no if not any detriment to performance for majority of workloads.

Dramatic yes but shows just another cheap ass intel move. save a buck here and cheat consumers there. from toothpaste thermal paste to this and beyond.

Cromulent · 4 Jan 2018 at 11:28

darael said:
Which firmware do you have installed now? I've had DXM06B0Q installed for several years now.

That is the one I have now. This was the first time I have ever updated the firmware so I was probably on a really ancient version before.

Silent_Scone · 4 Jan 2018 at 11:31

beany_bot said:
Dramatic yes but shows just another cheap ass intel move. save a buck here and cheat consumers there. from toothpaste thermal paste to this and beyond.

Eeesh, the moment to moment sensationalism that occurs on the internet is hurting your sensibilities.

drunkenmaster · 4 Jan 2018 at 11:32

Rroff said:
I was talking about testing in a contextual fashion not saying there hasn't been any testing at all. Some of the things where they are saying close to or near zero are binary situations where either they should be fully proof against the known vectors in the situation talked about or vulnerable - near zero is the same as vulnerable just not as easily exploited within those specific parameters.

Sorry but that is bull. Near zero doesn't mean they are vulnerable but it's not easily exploited. Everyone has tested Zen and no one has been able to expose it, but that doesn't mean 2 or 10 years from now someone won't find some insane method to do it and if AMD said zero risk they can be sued.

When your words can have consequences, like billion dollar lawsuits you tend to say near zero to cover your backside, not because you are vulnerable and it's just not easy to do. If AMD know they can be exploited and are saying this for just an exploit that is hard to attack they would also get sued for that. Near zero means at this time no one has found any way in which AMD is vulnerable to this variant of exploit, but legally saying zero risk is a landmine waiting to kill us in the future, nothing more or less.

jigger · 4 Jan 2018 at 11:35

beany_bot said:
Dramatic yes but shows just another cheap ass intel move. save a buck here and cheat consumers there. from toothpaste thermal paste to this and beyond.

That is a good point. Intel have been stuck with minimal gains for some time and struggled to scale.