Jump to content
Sign in to follow this  
Nemo

Intel/Windows 30% performance reduction

Recommended Posts

 In some extensive reading on other sites, it appears that the software, browser, and AV fixes are only a part of the whole when it comes to protecting yourself. There are also BIOS/UEFI fixes which have to come from the hardware companies to allow full coverage and implementation of all these "fixes". My guess here is that until all of that is in place you probably will not see what the actual performance hit is going to be.

I am choosing to continue my normal practices of safe surfing and usage before I jump into the fray. I am seriously wondering if this has been around for so long, how is it that we are only now finding out about it? Just doesnt pass the smell test to me and I will wait before hobbling any of my computers.

Share this post


Link to post
Share on other sites
6 hours ago, rjfry said:

Check the date and the link to Intel.

Exactly, check the revision dates at the bottom of the article. It is not for this latest security problem. Nothing about these latest Meltdown/Spectre issues are related to the Intel Management Engine issue that was discovered last fall.

Here's the correct Intel Security Center link.

https://security-center.intel.com/advisory.aspx?intelid=INTEL-SA-00088&languageid=en-fr

Edited by goates
Added link

Share this post


Link to post
Share on other sites
1 hour ago, goates said:

Exactly, check the revision dates at the bottom of the article. It is not for this latest security problem. Nothing about these latest Meltdown/Spectre issues are related to the Intel Management Engine issue that was discovered last fall.

Here's the correct Intel Security Center link.

https://security-center.intel.com/advisory.aspx?intelid=INTEL-SA-00088&languageid=en-fr

Intel new about this last year were seeing the fallout now.

Some motherboards like mine have Intel driver`s for drive`s they are releasing patches for this not just CPU`s.


 

Raymond Fry.

PMDG_Banner_747_Enthusiast.jpg

Share this post


Link to post
Share on other sites
30 minutes ago, rjfry said:

Intel new about this last year were seeing the fallout now.

Some motherboards like mine have Intel driver`s for drive`s they are releasing patches for this not just CPU`s.

Again, that issue is a different one than the current Meltdown/Spectre issue. Yes, Intel and others knew about the Meltdown/Spectre problem last year, but that link you posted and the tool posted earlier in the thread are for a different problem affecting Intel's Management Engine. They are not the same thing.

Share this post


Link to post
Share on other sites
Guest

I’m curious why this current KB will not work with some AntiVirus software ... the implications being that those AV products that are OK with this KB installed aren’t actually doing real time monitoring of kernel mode access and hence why a change to kernel mode doesn’t impact them?

Cheers, Rob.

Share this post


Link to post
Share on other sites
37 minutes ago, Rob Ainscough said:

I’m curious why this current KB will not work with some AntiVirus software ... the implications being that those AV products that are OK with this KB installed aren’t actually doing real time monitoring of kernel mode access and hence why a change to kernel mode doesn’t impact them?

Cheers, Rob.

From what I've read elsewhere it sounds like there are more official and less aggressive ways of doing this, while others get more aggressive and creative.

Share this post


Link to post
Share on other sites

So - I have installed the KB (against Meltdown) and the new ASUS 1003 UEFI (Microcodeupdate against Spectre).
I setup 2 test scenarios to benchmark before and after patching.
ASUS Z370 / i7 8700K

Good news! - no big difference

X-Plane 11.11: 44 -> 43fps
Prepar3D 4.1: 40->37fps (on the ground - mid flight no drop)

BR,
Mathias

Share this post


Link to post
Share on other sites
4 hours ago, Humpix said:

So - I have installed the KB (against Meltdown) and the new ASUS 1003 UEFI (Microcodeupdate against Spectre).
I setup 2 test scenarios to benchmark before and after patching.
ASUS Z370 / i7 8700K

Good news! - no big difference

X-Plane 11.11: 44 -> 43fps
Prepar3D 4.1: 40->37fps (on the ground - mid flight no drop)

BR,
Mathias

 

 

Good news. And it should be considered that such a small difference could be due to other random variables, so not related to the patch at all. 

  • Upvote 1

Share this post


Link to post
Share on other sites

In accordance with some oficial benchmarks Games will not see big issues:

https://www.techspot.com/article/1554-meltdown-flaw-cpu-performance-windows/

http://www.guru3d.com/articles-pages/windows-vulnerability-cpu-meltdown-patch-benchmarked,1.html

I have been running P3D with the patches and I haven't noticed any noticeable performance with my simulation experience.

Regards,
Simbol

Share this post


Link to post
Share on other sites

Lets see in the end, after Intel releases the patches, hopefully will remain the same or acceptable, only with the MS updates is too soon so say it is over. But there is hope...


Valentin Rusu

AMD Ryzen 5900x OC, EVGA RTX 3080 Ti FTW3, DDR4 32GB @3200MHz, Samsung 840 PRO Raid for Win 10 Pro, Samsung 960 PR0 512GB NVMe SSD for P3D v4.5

Share this post


Link to post
Share on other sites
Quote

only with the MS updates is too soon so say it is over

Jep, but it also looks good with the BIOS/EFI Updates too, see my test above. So I think everything will be fine for us simers. Maybe they optimize the patches. Google post some better solutions and maybe the will run into future fixes...

Share this post


Link to post
Share on other sites

Why do most people on this forum (and most journalists on the Internet) instantly go to the worst-case scenario whenever any issues arise. Rather than wait for actual facts to emerge (what a radical idea!), they just speculate about how bad things may get. Most of the tests that have been done so far, both here and on the gaming sites, show little (or no) change to desktop systems after the patches but we still get those who imply it's only a matter of time before we all slip back into the computer dark ages. I'm all for actual, proven data but what's the point of just guessing what the effect will be?

I have the patch and, apart from my system appearing to boot faster now, it doesn't seem to have affected me at all. For those saying that their FPS have dropped a little, how can you be sure? My FPS regularly change by a few FPS, just as they did before the patch. So many variables are involved that I'd consider anything less than a 20% fluctuation to be random (as long as it doesn't stay like that).

  • Upvote 2

 i7-6700k | Asus Maximus VIII Hero | 16GB RAM | MSI GTX 1080 Gaming X Plus | Samsung Evo 500GB & 1TB | WD Blue 2 x 1TB | EVGA Supernova G2 850W | AOC 2560x1440 monitor | Win 10 Pro 64-bit

Share this post


Link to post
Share on other sites
18 minutes ago, vortex681 said:

Why do most people on this forum (and most journalists on the Internet) instantly go to the worst-case scenario whenever any issues arise. Rather than wait for actual facts to emerge (what a radical idea!), they just speculate about how bad things may get. Most of the tests that have been done so far, both here and on the gaming sites, show little (or no) change to desktop systems after the patches but we still get those who imply it's only a matter of time before we all slip back into the computer dark ages. I'm all for actual, proven data but what's the point of just guessing what the effect will be?

I have the patch and, apart from my system appearing to boot faster now, it doesn't seem to have affected me at all. For those saying that their FPS have dropped a little, how can you be sure? My FPS regularly change by a few FPS, just as they did before the patch. So many variables are involved that I'd consider anything less than a 20% fluctuation to be random (as long as it doesn't stay like that).

 

Absolutely agree! 

Share this post


Link to post
Share on other sites
Guest
1 hour ago, vortex681 said:

Why do most people on this forum (and most journalists on the Internet) instantly go to the worst-case scenario whenever any issues arise.

But you've just contributed to the "issue" but stating "most people" without any facts to back that up ;)  Have you polled every single person on this forum?  But that's seems to be inherent in the human condition to use "all", "most", "everyone" when the actual poll sample is most likely < 0.001 % ... people extrapolate "a few" to mean "all". 

Journalists are providers of information to bring about awareness, it's the readers/viewers responsibility to "discover" fact from fiction (which takes work and referencing multiple sources, not just one) ... this holds true for any information you read/view.

The reports were 5-30% performance drop across a wide range of CPUs (going back 10 years) and varies by application and CPU.  Those reports are accurate within the context of the testing done.  A 5% reduction is barely noticeable ... for example if you operate at 40 FPS min - 5% less is 38 FPS ... if you Vsync to 30hz (or some type of adaptive Vsync which is the best way to remove stutters and ensure timeframe consistency) so you'll lock to 30 FPS, so you wouldn't  notice a difference at all - just ONE use case example out of many.

But a 30% reduction on a virtualized AWS (cloud servers, especially render farms) or even bitcoin miners then that number can have real financial implications.

You, me, others represent a tiny subset of the testing data sample.  Just because it has NOT impacted you as much, doesn't mean it hasn't impacted others.

Cheers, Rob.

 

Share this post


Link to post
Share on other sites

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!

Register a new account

Sign in

Already have an account? Sign in here.

Sign In Now
Sign in to follow this  

  • Tom Allensworth,
    Founder of AVSIM Online


  • Flight Simulation's Premier Resource!

    AVSIM is a free service to the flight simulation community. AVSIM is staffed completely by volunteers and all funds donated to AVSIM go directly back to supporting the community. Your donation here helps to pay our bandwidth costs, emergency funding, and other general costs that crop up from time to time. Thank you for your support!

    Click here for more information and to see all donations year to date.
×
×
  • Create New...