Memory management bug in Intel CPUs threatens massive performance hits.

[Mr. Scram]

Ménage à trois ?

https://www.globalresearch.ca/a-well-kept-open-secret-washington-is-behind-indias-brutal-demonetization-project/5566167

https://www.citizen.org/sites/default/files/memo-gats-conflict-with-bank-size-limits-may-10-2011.pdf

https://fas.org/sgp/crs/misc/india-wto.pdf

I'll ask you again. Will you please stop the tin foil hat posts? At least in this thread, but preferably elsewhere too. There are a few threads where it can't get much worse, like the dowsing thread or the 5G one. Those would be good threads to get it all out.

These vulnerabilities already confuse people a lot, no need for muddying the waters more. People understanding what's going on might very well soften the impact a lot.

[timb]

As of 5 years ago there were still bank ATMs running OS/2 Warp! I think they’re all gone by this point, however, some critical banking software is still based around OS/2, obviously it has to run in VM, but it’s still there; the kicker is that some of these OS/2 applications are in and of themselves virtualized environments, which were created in the 1990’s to run software originally created in the 1970’s! This is why I keep my money in my mattress.

For heavens sake dude, dont tell people who know your physical IP location you have your Fiat money in your mattress!

That’s why I keep the mattress itself in the back of a Fiat, which I park in a different location each night.

[bd139]

As a Fiat owner, that's probably the most secure place to leave it. No one is going to steal that pile of shit.

[Monkeh]

As a Fiat owner, that's probably the most secure place to leave it. No one is going to steal that pile of shit.

And if they tried it probably wouldn't start anyway. Or get up the first hill they encounter.

[bd139]

Yes. It's the only car I've ever had that the OBD2 cable gets used as much as the key.

[SparkyFX]

Given the complexity of your typical personal computer, plus the whole operating system, plus gear needed to connect it to a network that´s obviously too much knowledge needed for a single person to be an expert in all these areas, which means there must be a dependency of or problem with trust all along the way.
OTOH, no one ever said you can securely connect something to a network without someone else being able to interact with it, because the whole purpose of the connection is an interaction with other nodes.

Is this now a big problem? No, it made the news and everyone goes ape, but in effect it means an additional test case for anti-virus software, which you need anyway if you want to protect such a system.

[wraper]

Is this now a big problem? No, it made the news and everyone goes ape, but in effect it means an additional test case for anti-virus software, which you need anyway if you want to protect such a system.

It's a big problem for servers, as some are hit with up to 50% CPU performance drop after security patch like some Epic games servers. If you think that antivirus is effective against such flaw, then you are clueless.

[andersm]

Wasn't AMD working on something to replace the x86-Architecture for consumer-computers? I remember reading something like that one or two years back. Would be the perfect time to present the new CPU-Architecture now

The K12 core is AFAIK supposed to be based on the same Zen architecture as Ryzen and friends, but it was postponed after AMD saw how good performance they were getting out of Ryzen. But Spectre and Meltdown are implementation issues, not architecture issues.

[David Hess]

Wasn't AMD working on something to replace the x86-Architecture for consumer-computers? I remember reading something like that one or two years back. Would be the perfect time to present the new CPU-Architecture now

The K12 core is AFAIK supposed to be based on the same Zen architecture as Ryzen and friends, but it was postponed after AMD saw how good performance they were getting out of Ryzen. But Spectre and Meltdown are implementation issues, not architecture issues.

AMD was going to make a desktop performance ARM ISA processor at some point which shared the x86 infrastructure (sort of like DEC Alpha and AMD Athon?) but I do not remember why it was cancelled.

Intel intended the Pentium 4 to be the last x86 processor series to be replaced by Itanium until AMD rained on their parade with their 64 bit Opteron and Athlon64 processors.

[andersm]

AMD was going to make a desktop performance ARM ISA processor at some point which shared the x86 infrastructure (sort of like DEC Alpha and AMD Athon?) but I do not remember why it was cancelled.

Yes, that is the K12. It is not officially cancelled, but AMD have understandably decided to focus on Ryzen for now.

[Towger]

lots of windows servers (RBS/Natwest anyway)

Ah yes, the bank which managed to f*ck up both their main and backup mainframes and had no backups of the scripts they lost.  The fallout from this is still ongoing years later.  Takes a long time to take customers to court after they have runaround between branchs/ATMs taking out money.

A fine example of outsourcing at its best...

[bd139]

Yes but that was not the fault of the technology. Merely the humans which I outlined elsewhere in another post.

[Ampera]

Alright guys, I have an almost pointless CPU-Z benchmark done on my i7-4790k before and after the meltdown patch:

Before:


After:


As you guys, gals, and various species of intelligent cephalopod can clearly see, straight performance has not really gone down, and this makes sense. This affects specific workloads, which I have not measured at the moment, but I honestly don't use. My day to day performance isn't ruined, but your mileage may vary, especially if you are using VMs.

[wraper]

Among home users measurable impact is for those who use NVMe SSD.
CrystalDisk 6 results Samsung 960 PRO 2TB NVMe
Before:

After:

[Refrigerator]

Alright guys, I have an almost pointless CPU-Z benchmark done on my i7-4790k before and after the meltdown patch:

Before:


After:


As you guys, gals, and various species of intelligent cephalopod can clearly see, straight performance has not really gone down, and this makes sense. This affects specific workloads, which I have not measured at the moment, but I honestly don't use. My day to day performance isn't ruined, but your mileage may vary, especially if you are using VMs.

I think i read somewhere that the fix has to be enabled to take effect, you might want to check if that's true.

[Mr. Scram]

Alright guys, I have an almost pointless CPU-Z benchmark done on my i7-4790k before and after the meltdown patch:

Before:


After:


As you guys, gals, and various species of intelligent cephalopod can clearly see, straight performance has not really gone down, and this makes sense. This affects specific workloads, which I have not measured at the moment, but I honestly don't use. My day to day performance isn't ruined, but your mileage may vary, especially if you are using VMs.

What does CPU-Z actually test? You can't just translate that to your personal use.

[Refrigerator]

What does CPU-Z actually test? You can't just translate that to your personal use.

Word processing, image processing, web browsing and some other stuff, if i remember correctly.

[Ampera]

It does something. Idk, I said this wasn't a great benchmark, was just something I had lying around.

I've overclocked to 4.7ghz if on 2 cores and 4.6ghz if on 4 cores, and it seems to be working fine, and that should counteract any issues I'm having.

As for the SSD, that almost seems to be within some strange margin of error, as the writes have gone up, but the reads have gone down. I don't really see how NVMe drives would be affected, but who knows, maybe I'm sniffing snot.

[wraper]

It does something. Idk, I said this wasn't a great benchmark, was just something I had lying around.

I've overclocked to 4.7ghz if on 2 cores and 4.6ghz if on 4 cores, and it seems to be working fine, and that should counteract any issues I'm having.

As for the SSD, that almost seems to be within some strange margin of error, as the writes have gone up, but the reads have gone down. I don't really see how NVMe drives would be affected, but who knows, maybe I'm sniffing snot.

Don't look at sequential read/write. Those are not typical loads and also highly vary during test iterations as well. Look how 4kiB Q32 went down by 30%.

[Ampera]

It does something. Idk, I said this wasn't a great benchmark, was just something I had lying around.

I've overclocked to 4.7ghz if on 2 cores and 4.6ghz if on 4 cores, and it seems to be working fine, and that should counteract any issues I'm having.

As for the SSD, that almost seems to be within some strange margin of error, as the writes have gone up, but the reads have gone down. I don't really see how NVMe drives would be affected, but who knows, maybe I'm sniffing snot.

Don't look at sequential read/write. Those are not typical loads and also highly vary during test iterations as well. Look how 4kiB Q32 went down by 30%.

That's gotta suck. I run a SATA SSD so I'm not affected, but damn.

[Mr. Scram]

That's gotta suck. I run a SATA SSD so I'm not affected, but damn.

I doubt SATA is going to be less affected. If so, only because its inherent slower performance might be hiding the actual performance hit. The underlying kernel calls aren't going to be much different.

[Ampera]

That's gotta suck. I run a SATA SSD so I'm not affected, but damn.

I doubt SATA is going to be less affected. If so, only because its inherent slower performance might be hiding the actual performance hit. The underlying kernel calls aren't going to be much different.

I haven't noticed anything

[Marco]

I wonder how they are going to solve Spectre.

If there just happen to be microcode instructions available to wipe the BTB that would be awfully convenient.

[SparkyFX]

Is this now a big problem? No, it made the news and everyone goes ape, but in effect it means an additional test case for anti-virus software, which you need anyway if you want to protect such a system.

It's a big problem for servers, as some are hit with up to 50% CPU performance drop after security patch like some Epic games servers. If you think that antivirus is effective against such flaw, then you are clueless.

Antivirus is always ineffective against the vulnerability itself, it won´t magically patch that. But it can always scan for code that follows a pattern or for specific exploits, and yes, there are self-encrypting ones and yes, it´s always high profile.

Nevertheless can an impact on CPU load only be measured after a patch has been applied.
I come to think it might even be a problem to give a definite number, as this is speculative execution.

[andersm]

Among home users measurable impact is for those who use NVMe SSD.

I'd say there's a measurable impact for those who run storage benchmarks (with fast media), since those will be issuing a very large number of syscalls, while a CPU benchmark will be negligibly affected since they hardly issue any syscalls at all.