Intel bug incoming? Meltdown and Spectre exploits

mid_gen · 3 Jan 2018 at 17:42

Bad day for my Intel CPUs....good day for my AMD stocks

mattyfez · 3 Jan 2018 at 17:44

Intel now at -4.4%

But AMD still climbing at +8.2%

Dayam I wish I had shares in AMD.

Andromeda1983 · 3 Jan 2018 at 17:49

Oh well, lets see how this all plays out

robfosters · 3 Jan 2018 at 18:01

If the patches turn out to gimp performance, what’s the chances of intel offering nice discounts on new cpus for affected customers?

pete910 · 3 Jan 2018 at 18:03

AndreiD said:
@pete910 but that's not dumping stock, 10b5-1 plans have predetermined dates when a predetermined number of shares are sold in order for insiders (like CEOs) of publicly traded companies to avoid insider trading related issues. That sale was going to happen regardless of any variation in Intel's stock value, most CEOs do 10b5-1s.
That fool.com article is pure fud and they should know better if they're a finance outlet.

To be fair stock/shares are not my thing. To me looks like dumping a shed load .

gavinh87 · 3 Jan 2018 at 18:03

Perfect_Chaos · 3 Jan 2018 at 18:10

robfosters said:
If the patches turn out to gimp performance, what’s the chances of intel offering nice discounts on new cpus for affected customers?

I would prefer it if they bring Icelake sooner

discounts would be nice but probably unlikely.

Cromulent · 3 Jan 2018 at 18:14

Ignore.

Nasher · 3 Jan 2018 at 18:19

Hmm, it says the fix will significantly slow down CPU performance. I guess we need to avoid that patch on gaming PCs. It will be something really specific that only effects certain tasks that 95% of people won't be doing. Yet the update will be pushed on everyone.

But let me guess. The next generation will have the fix and be just as fast?

ultralaser · 3 Jan 2018 at 18:20

Really interesting. And it's not like you can avoid it without seriously compromising the security of your PC. I'd imagine Ryzen availability might be problematic soon!

Hotwired · 3 Jan 2018 at 18:23

.

mattyfez said:
Meanwhile at AMD HQ

This scene is so over the top it will never die.

Nasher · 3 Jan 2018 at 18:24

No word on if AMD are affected or not yet...

pete910 · 3 Jan 2018 at 18:26

AmateurExpert said:
I think you mean reference 6 "Gruss, D., Maurice, C., Fogh, A., Lipp, M., Mangard, S.: Prefetch Side-Channel Attacks: Bypassing SMAP and Kernel ASLR. In: CCS’16 (2016)" that the KAISER research paper cites. The KAISER paper itself is an interesting read - what I want to know if whether KAISER is actually a more feasible solution than KPTI, but haven't yet delved in deep enough.

Edit: just to answer myself - KPTI is derived from KAISER. What prompted my question is that the KAISER paper claims "the performance impact of KAISER is only 0.28%" but in practice there can be a rather larger performance penalty for some apps/benchmarks.

That sounds the one, I have/had the pdf of it somewhere.

Edit: Found it https://www.blackhat.com/docs/us-16...Layout-Randomization-KASLR-With-Intel-TSX.pdf

Nasher said:
No word on if AMD are affected or not yet...

No, there not. The security flaw that is .

JGBR · 3 Jan 2018 at 18:27

Intel: a confusing product line, mediocre improvement year on year, dropping tick tock, forced socket changes when arch barely changed...and so on.... Is the turn of the tide here aka Pentium 4 V AMD Athlon? Lets see.

mattyfez · 3 Jan 2018 at 18:35

Nasher said:
Hmm, it says the fix will significantly slow down CPU performance. I guess we need to avoid that patch on gaming PCs. It will be something really specific that only effects certain tasks that 95% of people won't be doing. Yet the update will be pushed on everyone.

But let me guess. The next generation will have the fix and be just as fast?

Initial indication is that it won't really affect home users, but enterprise level stuff takes a big hit, VMs, SQL servers etc. But still very bad for Intel, that represents a huge customer base.

AmateurExpert · 3 Jan 2018 at 18:35

JGBR said:
Intel: a confusing product line, mediocre improvement year on year, dropping tick tock, forced socket changes when arch barely changed...and so on.... Is the turn of the tide here aka Pentium 4 V AMD Athlon? Lets see.

Tempting though it is to tot up the missteps and stick the boot in - remember they are bound to have some missteps, such is their reach and scale. While I hope it helps the competitive landscape somewhat, I expect it'd take rather more to turn the tide - they are so profitable they can afford lots of mistakes that their competitors cannot.

JGBR · 3 Jan 2018 at 18:38

AmateurExpert said:
Tempting though it is to tot up the missteps and stick the boot in - remember they are bound to have some missteps, such is their reach and scale. While I hope it helps the competitive landscape somewhat, I expect it'd take rather more to turn the tide - they are so profitable they can afford lots of mistakes that their competitors cannot.

Indeed but im all for turning the heat up on intel and levelling the playing field. Hard times and competition serves as a motivator. !

ultralaser · 3 Jan 2018 at 18:40

mattyfez said:
Initial indication is that it won't really affect home users, but enterprise level stuff takes a big hit, VMs, SQL servers etc. But still very bad for Intel, that represents a huge customer base.

Nope.

mattyfez · 3 Jan 2018 at 18:42

ultralaser said:
Nope.

Insightfull. Source?

mattyfez · 3 Jan 2018 at 18:46

Intel shares still taking a pounding, but if you look at the previous performance, 3 years to date, it doesn't look quite so catastrophic... yet.