Intel's Chip Bug

[Barnabas]

Admission of your error by ad-hominem attack duly noted.

I didn't say a damn thing about wether they patched it or not. I said AMD broke the street date on the embargo, which is a plain old fact.

You were the one being "AMD was just tell da troof man!" and i pointed out that ... yeah, they were not, in fact, telling the truth.

Literally every CPU under the sun is vulnerable to SPECTRE.

ARM, Intel, AMD, IBM (POWER, formerly PowerPC, which has about a 60-70% market share in big iron), you name it. Everything.

The ONLY saving grace about SPECTRE is that the parts that cant be patched around require physical access to the machine to implement. Otherwise itd be a total shit-show (for -everyone-) from start to finish.

- - - Updated - - -



This goes to show why i both generally keep you on ignore (unfortunately, other people quoted you... bleh) and how a little knowledge makes dumb people dumber.

It has NOTHING to do with wether a game is "CPU heavy" or not. NOTHING. It has to do with what type of memory operations the software uses. Full stop. If it doesn't do a lot of memory swaps into the affected areas, it wont be affected at all. Not one bit. If you DO make a lot of operations like that, itll affect you a lot. Virtualization and server tasks make these swaps A LOT, so those areas (may) be heavily hit. I think Epic showed that their back-end server took a pretty severe hit after the patch.



Due entirely to the fact that WINE is virtualization. That simple. Nothing to do with "CPU intensity".



About as long as AMD did, as well. They aren't un-guilty here. Their CPUs of the same era use the same technology. The only reason that later architectures aren't vulnerable to MELTDOWN is because of the janky way they cobbled together their CPUs by stitching together multiple CPU dies. Same with Ryzen; the Infinity Fabric is what makes them not vulnerable, because of the way they had to staple multiple full-up CPU dies together to create the core counts they wanted on Ryzen. That's not a dig - with FX-series chips it was a failure but with Ryzen they got it working right. But it wasn't some intentional way of making their CPU not vulnerable to this since they had no clue this kind of vulnerability was even possible when they started to design Ryzen. Its basically a happy accident.



Uh.. K. Even if my CPU -DID- take a flat 30% performance hit.... it'd still be as fast or faster than a Ryzen chip. Since i definitely haven't taken anything near a 30% performance hit (or any perceptable performance hit at all; i dont have an pre-patch benches to compare to, unfortunately), im still doing better using Intel than AMD.



If you consider "fully vulnerable to the more dangerous of the two exploits" to be "minimal effects", sure. SPECTRE is far more dangerous than MELTDOWN. MELTDOWN can only read protected memory; SPECTRE can actually inject code.



How screwed am I? I'm not. Most people aren't. They aren't affected at all. This may affect their server division (heavy virtualization and server loads take the only significant hit)... but i hate to break it to you, most people wont turn to AMD to fix that problem. Theyll turn to POWER. A huge (majority) portion of the server infrastructure world-wide is already using POWER and has been for a looooonnnnggg time. POWER isn't vulnerable to Meltdown that i'm aware of, but it is fully vulnerable to SPECTRE. If they dont need a high-power server solution, theyll turn to ARM instead.



For.... what? Producing a product that is vulnerable to something that was so hard to find it took over 10 years to find it? Its not like theyve known all this time; they just found out last summer.



It does work as designed. Just like every CPU with branch prediction. Its why even some ARM chips (only a few lines) are also vulnerable to MELTDOWN. NO ONE in the CPU world thought this kind of thing was possible. Not Intel, not ARM, not AMD, not IBM. AMD's chips are immune to Meltdown by a happy accident, not deliberate design. The guy who designed Ryzen for AMD was pretty shocked when he found out. (Hes also done work for Intel and is responsible for a lot of their chip designs or large parts of them). So this guy who designs these cutting edge chips, had no idea this kind of thing would be possible.



... and that shows how out of fucking touch Linus is. The two major ARM64 lines used for servers? Yeah, vulnerable to MELTDOWN. And SPECTRE, like every other CPU in the world. Though the newer revisions of the ARM64 lines coming out mid-late this year should be immune to MELTDOWN.

And in what world is an Intel CPU "shit"?

Even if they took a flat 30% hit, most of the server CPUs Intel sells would still outperform their Ryzen-based EPYC counterparts because of basic IPC gains and higher clocks.

So, absolutely the worst-case scenario.... total worst case.... its still just as good as the competition.

Huh. Now, you'd have a point about buying EPYC chips because they're cheaper for the same performance at that point, but again....

They wont be looking to switch to EPYC if they leave Intel. Itll be to a real big-boy chip series like POWER if they need big-iron muscle or (if they dont need that kind of heavyweight) theyll be looking to ARMs newer server chips. Which are quite a bit cheaper, and less power consuming, and working in large clusters can perform just as well.

Still crying are you? Need a tissue?

- - - Updated - - -

Been doing a bit more digging and this is what I understand. Firstly, there's three kinds of Spectre exploits.

Variant #1 - Basically everyone is effected and there's no real solution for any CPU without an entirely new redesigned CPU. The only real protection against this is to have a secure OS. Yea...

Variant #2 - Effects Intel and select ARM chips but not AMD. But this is mainly used for virtualization software which is not something gamers are going to worry about.

Variant #3 AKA Meltdown - Only effects Intel. This can be done through javascript to extract information from memory. It's very bad.

Intels solution for Meltdown is to disable Branch Prediction through PTI patch. This is a performance feature that modern CPUs use for a speed up. For a while people thought this would also disable AMD's branch prediction but that was a mistake and it will be just Intel. How much the average user will be effected by this is yet to be seen, but it's not good.

Keep in mind that pre-2013 Atom chips also didn't have this feature, so it isn't effected by this. Then again, a Core series CPU is becoming more like an Atom chip. That's really not good.

I wouldn't worry about any of them too much. Probably just governments would have a hack already for this not just some random group.

Infracted - Cilraaz

[Kagthul]

Still crying are you? Need a tissue?

Still unable to read plain english, i see. Sorry you’re butt hurt about being wrong, but that doesn't change the fact that youre wrong.

Dont worry, some remedial elementary school education will probably shore up those deficiencies.

[Barnabas]

Still unable to read plain english, i see. Sorry you’re butt hurt about being wrong, but that doesn't change the fact that youre wrong.

Dont worry, some remedial elementary school education will probably shore up those deficiencies.

I'm not upset at all. You've been crying since you joined this thread and now that you found one person that doesn't give a shit you keep thinking you'll change that somehow. Move on already.

[Ssateneth]

5. No - the bug does not affect the room heater, sorry AMD range of processors.

You must be misinformed. AMD hasn't been "room heaters" for 2 years now. In fact, intel is the room heater now. 700 watts just on CPU rail alone for 7980xe while air cooling. 8700k often hitting 90-95c on liquid while ryzen chips doing less than 70c on air, and amd doesn't even need a warranty-voiding delid lol.

[Kagthul]

You guys are not understanding that these benchmarks are not the final thing. Intel is still to release the microcode update that might be the most impactful thing on performance.

... you arent understanding that its already been released and given to board manufacturers and ASUS already updated their BIOS which includes the microcode patch. I already downloaded it and applied it. As did several sites like GN. And then they ran tests. Try to keep up.

- - - Updated - - -

I'm not upset at all. You've been crying since you joined this thread and now that you found one person that doesn't give a shit you keep thinking you'll change that somehow. Move on already.

Im sorry, what youre saying doesnt even make sense.

Seriously. Go read the posts, if your illiteracy isnt handicapping you.

What exactly am i “crying” about?

Im refuting misinformation with facts.

Youre making random ad-hominem and refuting nothing. “Youre crying” is not an argument or a presentation of facts. Its childishly stupid ad-hominem.

In fact, you agreed with me. How embarrassing for you.

Lulz

I wouldn't worry about any of them too much. Probably just governments would have a hack already for this not just some random group.

Whoops.

[Zenny]

Intels solution for Meltdown is to disable Branch Prediction through PTI patch. This is a performance feature that modern CPUs use for a speed up. For a while people thought this would also disable AMD's branch prediction but that was a mistake and it will be just Intel. How much the average user will be effected by this is yet to be seen, but it's not good.

That is not what the meltdown patch does, disabling Branch Prediction on a modern CPU would basically cripple it, we are talking about a 60% degradation across pretty much anything. KPTI works by preventing all protected locations from being mapped to user space. Which can impact Speculative Execution on Intel chips, where the impact comes from.

As for the impact on the end user? Content creation, general usage, and gaming has a non to tiny (3%) impact. The major impact's are SSD write times, Java, Databases, and VM's. Cloud Providers and Enterprise are miffed at Intel right now, so am I actually, our Redis on Elasticache usage spiked quite a bit. Still trying to determine the impact on all our Databases however.

We also don't have everything fully implemented yet, Google themselves has released a patch (Retpoline) that apparently fixes SPECTRE with very little performance loss.

[Kagthul]

You must be misinformed. AMD hasn't been "room heaters" for 2 years now. In fact, intel is the room heater now. 700 watts just on CPU rail alone for 7980xe while air cooling.

for massive overclocks and performance that the Threadripper equivalent cant even get near, yeah. At stock, theyre largely similar. Why are you comparing a massively OCed chip to a stock Threadripper? Oh, right, youre hoping people will just accept your BS. Stop being a shill.

8700k often hitting 90-95c on liquid while ryzen chips doing less than 70c on air, and amd doesn't even need a warranty-voiding delid lol.

Again, massively overclocked 8700K’s that are hitting 5.1 to 5.3 ghz vs totally stock Ryzen 7s. How many R7s are hitting 5.2ghz again? How mnay are even hitting 4.0ghz again? Oh, thats right.... zero. (Edit for clarity - zero hitting 5+; 4.0 seems doable on decent chips.)

And you're behaving like AIO water cooling is somehow more effective than a good air cooler. It provably isnt. We already had thread a few weeks back. How many dozens of links do i need to show you of a good BeQuiet! and Noctua coolers outperforming the best AIOs do you need?

Jeebus, stop being a shill.

- - - Updated - - -

That is not what the meltdown patch does, disabling Branch Prediction on a modern CPU would basically cripple it, we are talking about a 60% degradation across pretty much anything. KPTI works by preventing all protected locations from being mapped to user space. Which can impact Speculative Execution on Intel chips, where the impact comes from.

As for the impact on the end user? Content creation, general usage, and gaming has a non to tiny (3%) impact. The major impact's are SSD write times, Java, Databases, and VM's. Cloud Providers and Enterprise are miffed at Intel right now, so am I actually, our Redis on Elasticache usage spiked quite a bit. Still trying to determine the impact on all our Databases however.

We also don't have everything fully implemented yet, Google themselves has released a patch (Retpoline) that apparently fixes SPECTRE with very little performance loss.

The SSD thing isnt clear yet. So far all the tests have been on ASUS boards, and theres a thought that it might be something ASUS pocked up. However, theres no solid evidence either way. It very well COULD be caused by the patch, well have to wait and see when another board manufacturer gets an update out.

[pansertjald]

for massive overclocks and performance that the Threadripper equivalent cant even get near, yeah. At stock, theyre largely similar. Why are you comparing a massively OCed chip to a stock Threadripper? Oh, right, youre hoping people will just accept your BS. Stop being a shill.



Again, massively overclocked 8700K’s that are hitting 5.1 to 5.3 ghz vs totally stock Ryzen 7s. How many R7s are hitting 5.2ghz again? How mnay are even hitting 4.0ghz again? Oh, thats right.... zero. (Edit for clarity - zero hitting 5+; 4.0 seems doable on decent chips.)

And you're behaving like AIO water cooling is somehow more effective than a good air cooler. It provably isnt. We already had thread a few weeks back. How many dozens of links do i need to show you of a good BeQuiet! and Noctua coolers outperforming the best AIOs do you need?

Jeebus, stop being a shill.

- - - Updated - - -



The SSD thing isnt clear yet. So far all the tests have been on ASUS boards, and theres a thought that it might be something ASUS pocked up. However, theres no solid evidence either way. It very well COULD be caused by the patch, well have to wait and see when another board manufacturer gets an update out.

And i quoted you on that and you just went silence. You can't use Linus test for shit. The Corsair AIO's are not made for the Threadripper. They don't cover the whole CPU, while the Air coolers used in the video does. So just stick that video up where the sun don't shine or you can just read some of all the comments on the video on YouTube. AIO's are cooler then air coolers and have allways been

[schwarzkopf]

You must be misinformed. AMD hasn't been "room heaters" for 2 years now.

A whole 2 years hey.

Anyway - I don't have any choice but to use Intel CPUs, so the discussion in moot anyway.

[Barnabas]

... you arent understanding that its already been released and given to board manufacturers and ASUS already updated their BIOS which includes the microcode patch. I already downloaded it and applied it. As did several sites like GN. And then they ran tests. Try to keep up.

- - - Updated - - -



Im sorry, what youre saying doesnt even make sense.

Seriously. Go read the posts, if your illiteracy isnt handicapping you.

What exactly am i “crying” about?

Im refuting misinformation with facts.

Youre making random ad-hominem and refuting nothing. “Youre crying” is not an argument or a presentation of facts. Its childishly stupid ad-hominem.

In fact, you agreed with me. How embarrassing for you.

Lulz



Whoops.

It makes perfect sense. In the real world on my intel machine I doubt I will see any meaningful impact from the patches. So keep crying about nothing to prove you are right about anything. Again nobody cares but you and your little ego.

[Artorius]

HEDT isn't exactly the same thing as "enthusiast", but since the word "enthusiast" is incredibly subjective arguing about it is pointless.

[mrgreenthump]

... you arent understanding that its already been released and given to board manufacturers and ASUS already updated their BIOS which includes the microcode patch. I already downloaded it and applied it. As did several sites like GN. And then they ran tests. Try to keep up.

That's funny, because GN specifically said, they didn't have the microcode update in their latest video, hence the title of it being pointless.

[Yunru]

Makes me happy that i use amd. Never trusted Intell.
Just because its cheap, it doesnt mean its better.

[Kagthul]

Makes me happy that i use amd. Never trusted Intell.
Just because its cheap, it doesnt mean its better.

... AMD is cheaper. Not sure you were making the point you wanted to make. Not that there is anything wrong with Ryzen.

- - - Updated - - -

And i quoted you on that and you just went silence. You can't use Linus test for shit. The Corsair AIO's are not made for the Threadripper. They don't cover the whole CPU, while the Air coolers used in the video does. So just stick that video up where the sun don't shine or you can just read some of all the comments on the video on YouTube. AIO's are cooler then air coolers and have allways been

Child, youre so deluded its painful. I posted DOZENS of links to testers everywhere. You were wrong. Youre still wrong. I stopped responding because i categoricaly proved you wrong a dozen times and you never once posted anything to refute it. You had to go back to a six year old benchmark with shitty testing methodology (didnt even let the AIO run long enough to heat soak and reach equilibrium)

Tildeer: AIOs arent any better than good air coolers, even on Threadripper. Every modern test done by every reputable tech site shows it. Welcome to reality. (Next answer prediction: “you cant trust any of those sites, they are all paid shills”.)

[Vash The Stampede]

That is not what the meltdown patch does, disabling Branch Prediction on a modern CPU would basically cripple it, we are talking about a 60% degradation across pretty much anything. KPTI works by preventing all protected locations from being mapped to user space. Which can impact Speculative Execution on Intel chips, where the impact comes from.

You're right, I was misinformed.

https://www.phoronix.com/scan.php?pa...ediction-Still

Remains to be seen when we finally get microcode updates to Intel processors, but I doubt daily tasks will get hit by anything bigger than 5% this round, if they find new exploits, then we may see bigger changes.

Rumor has it there's lots more vulnerabilities to be released in 2018. 2018 is starting off interesting.

You must be misinformed. AMD hasn't been "room heaters" for 2 years now. In fact, intel is the room heater now. 700 watts just on CPU rail alone for 7980xe while air cooling. 8700k often hitting 90-95c on liquid while ryzen chips doing less than 70c on air, and amd doesn't even need a warranty-voiding delid lol.

Seems people don't know that AMD released Ryzen almost a year ago.

for massive overclocks and performance that the Threadripper equivalent cant even get near, yeah. At stock, theyre largely similar. Why are you comparing a massively OCed chip to a stock Threadripper? Oh, right, youre hoping people will just accept your BS. Stop being a shill.

Again, massively overclocked 8700K’s that are hitting 5.1 to 5.3 ghz vs totally stock Ryzen 7s. How many R7s are hitting 5.2ghz again? How mnay are even hitting 4.0ghz again? Oh, thats right.... zero. (Edit for clarity - zero hitting 5+; 4.0 seems doable on decent chips.)

Overclocking isn't always something you can use to denounce AMD. There's a reason why Intel doesn't just push their chips by 1Ghz.

http://i.4cdn.org/v/1514619843421.jpg

[Demona3]

1. The fix will mean a 30% slow down in the SPECIFIC operations affected, the net slow down will be far less than that.
2. Yes - this is a permanent slow down and fix until you upgrade your hardware to a non buggy Intel processor.
3. The bug impacts ALL Intel CPUs made in the last 10 years or so.
4. The bug impacts ALL operating systems (OSX, Linux, Windows) running on Intel
5. No - the bug does not affect the room heater, sorry AMD range of processors.
6. The fix will require a MAJOR change to the kernel level of the operating system and the effort being put in by MS, Linux central indicates that the bug is VERY serious.
7. Roughly speaking - the kernel will have to be moved to a separate 'area' from normal executing code.
8. This is a MASSIVE change.
9. This is a HUGE change.

https://www.engadget.com/2018/01/03/...l-memory-flaw/

More technical article:

https://arstechnica.com/gadgets/2018...erous-patches/

This really sucks. I just bought my Intel chip less than 6 months ago.

[Zenny]

This really sucks. I just bought my Intel chip less than 6 months ago.

What OS do you run and what do you use your PC for? There is a very good chance this won't really impact you.

[leviathonlx]

I would say 2019 at earliest. It is unlikely that Intel will be able to fix it for next cpu series release and even if they did they would have to push it back a lot - so yeah 2019 or later. For AMD side it is same story - their Ryzen 2 are done and in production so no changes can be made. Zen 2(Ryzen 3) will be 2019 and that's when you can expect fix from AMD.

In case of both Intel and AMD the next cpu is shrink/optimization and not new arch so it is rather doubtful they will fix it then, especially since as mentioned earlier it would require costly delays.

I feel like there must have been something going on behind the scenes before it became public as Cisco was already sending out FE's to replace CPU's weeks ago.

[mrgreenthump]

I feel like there must have been something going on behind the scenes before it became public as Cisco was already sending out FE's to replace CPU's weeks ago.

The affected companies were notified last June, it was only now that it was made known to the public.

[Vash The Stampede]

1. The fix will mean a 30% slow down in the SPECIFIC operations affected, the net slow down will be far less than that.
2. Yes - this is a permanent slow down and fix until you upgrade your hardware to a non buggy Intel processor, or better yet an AMD.
3. The bug impacts ALL Intel CPUs made in the last 10 years or so.
4. The bug impacts ALL operating systems (OSX, Linux, Windows) running on Intel
5. No - the bug does not affect the cooler and faster running AMD Ryzen range of processors.
6. The fix will require a MAJOR change to the kernel level of the operating system and the effort being put in by MS, Linux central indicates that the bug is VERY serious.
7. Roughly speaking - the kernel will have to be moved to a separate 'area' from normal executing code.
8. This is a MASSIVE change, against Intel.
9. This is a HUGE change, against Intel.

Thought I'd fix that for you.

So since I am a noob and my IT support is non-existant, are these patches likely the reason why my ERP at work has slowed down in the last few days?

Too early to tell cause it seems that the chips themselves haven't been patched. Intel later this month are going to release microcode updates which "could" further impact performance.