More Intel leaks.. this one is not good though

[Drak3]

15 minutes ago, Hellion said:

Read your post.

Someone has to. Clearly you won't.

[.spider.]

6 hours ago, porina said:

Had posted it not long ago, but the link again...

 

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

 

I don't think that is the full list. For example Core2Duo is missing and it is not really different from the listed CPUs. I do not think Intel is honest at all.

 

 

[porina]

33 minutes ago, .spider. said:

I don't think that is the full list. For example Core2Duo is missing and it is not really different from the listed CPUs. I do not think Intel is honest at all.

I haven't followed the specific blocks of the CPU implicated in the recent but certainly there were significant performance gains around/after that time. 

[TheCherryKing]

My mining computer did not have much of a performance hit. Single Thread performance is actually better! CPU-Z is not the best benchmark but it good enough to show the marginal difference. 

Before:

 

After:

[porina]

19 hours ago, porina said:

I also did a single run on the SSD before and after, using CrystalDiskMark. I'm not presenting the results as I want to run more tests in the "after" state to check if there may be some other impact at work. Most results were not significantly changed, but sequential writes saw a big drop. The caution I have here is this contradicts other testing by Hardware Unboxed, suggesting it was actually 4k reads that were impacted. A possible mechanism is that smaller operations have more management overhead. On the plus side, I didn't see a change in my 4k read rate. If my results are repeatable, that may be due to some bottleneck, such that higher write speeds are impacted, yet smaller ones are not. This'll take more looking at.

Back to testing... started by repeating the CrystalDiskMark result, and this time got same or actually a bit higher than I did before the patch! Having had some time to think about it, I'm guessing I might have been hitting thermal throttling when doing the first test after patch. The system was in heavy CPU workload so the mobo might have got rather warm by then. Because of that, now I can't be sure the "before" results were as good as they can be either, so I'm still not going to present the detail results in case they get misinterpreted. I don't believe this will impact the CPU or GPU results as they have direct cooling on them, unlike the SSD.

[Hellion]

2 hours ago, SC2Mitch said:

Yeah you do? Anyone has the legal right to criticize a company for their shitty actions.

That's exactly my point.

 

Mr moose is claiming that unless you have the same, if not better, credentials then the engineers that designed the CPU's then you can't.

 

Probably the most ridiculous notion I've seen mentioned on this forum and there have been a lot.

[Hellion]

2 hours ago, Drak3 said:

Someone has to. Clearly you won't.

Are you lost?

[Drak3]

4 minutes ago, Hellion said:

Mr moose is claiming that unless you have the same, if not better, credentials then the engineers that designed the CPU's then you can't.

No, he's not.

He's stating that without evidence, no one can claim that the bug was being hidden by Intel.

4 minutes ago, Hellion said:

Are you lost?

No, I'm fully aware of my surroundings. And what Moose is actually saying.

[NumLock21]

Here are my results for the 8th Gen Core i5 8250U.

 

Before update

 

After update

 

Performance actually increase for my cpu, but gpu took a major hit.

Rest in Pepperoni @ Nvidia

F....

[pas008]

I find it funny people think intel intentionally did this or hid this, they continually fix their security problems

 

and also find it funny ryzen pro has tsme which does what?

so are they admitting to a vulnerability in regular ryzen?

 

in this article states

dram encryption w/o software mod

https://www.anandtech.com/show/11591/amd-launches-ryzen-pro-cpus-enhanced-security-longer-warranty-better-quality

 

 

[Jito463]

5 minutes ago, NumLock21 said:

Here are my results for the 8th Gen Core i5 8250U.

 

Before update

*snip*

 

After update

*snip*

 

Performance actually increase for my cpu, but gpu took a major hit.

Rest in Pepperoni @ Nvidia

F....

What is that MP ratio under the single core test?

[NumLock21]

7 minutes ago, Jito463 said:

What is that MP ratio under the single core test?

It's the performance ratio between single core and multi-core. In the prepatch, multi-core is 7.96x faster when compared to single core performance.

[luigi90210]

23 minutes ago, NumLock21 said:

Here are my results for the 8th Gen Core i5 8250U.

 

Before update

 

After update

 

Performance actually increase for my cpu, but gpu took a major hit.

Rest in Pepperoni @ Nvidia

F....

im not surprised at this result, the way nvidia performs their draw calls are 100% reliant on CPU performance so if that goes down, your frame rate also goes down

[TheCherryKing]

1 minute ago, luigi90210 said:

im not surprised at this result, the way nvidia performs their draw calls are 100% reliant on CPU performance so if that goes down, your frame rate also goes down

Does this apply to AMD graphics cards too?

[luigi90210]

2 minutes ago, TheCherryKing said:

Does this apply to AMD graphics cards too?

no, amd graphics cards since GCN1.1 have used a hardware based scheduler to perform all draw calls so AMD performance should remain the same

 

the keyword being should

 

EDIT the GTX 480 performance should also remain the same as the 480 was the last card from nvidia to have a hardware based scheduler

[NumLock21]

5 minutes ago, luigi90210 said:

im not surprised at this result, the way nvidia performs their draw calls are 100% reliant on CPU performance so if that goes down, your frame rate also goes down

but my cpu went up.

[luigi90210]

Just now, NumLock21 said:

but my cpu went up.

ya i just rechecked your scores and they are up, idk what the issue is then

as far as i understand how nvidia drivers and amd drivers work the nvidia draw calls use your cpu to perform them so CPU performance is 100% linked to how well your GPU will perform 

have you tried rerunning the tests? 

[Xirhanna]

Should I just throw away my computer now?

[NvidiaIntelAMDLoveTriangle]

Just now, Xirhanna said:

Should I just throw away my computer now?

Yes.

[Xirhanna]

Just now, NvidiaIntelAMDLoveTriangle said:

Yes.

I'm actually considering buying an AMD processor and AMD motherboard now.

[luigi90210]

9 minutes ago, Xirhanna said:

I'm actually considering buying an AMD processor and AMD motherboard now.

well if your computer doesnt do what you want it to do as fast as you want to do it then upgrade, but if you only want to upgrade because of this then thats a little silly 

[Xirhanna]

1 minute ago, luigi90210 said:

well if your computer doesnt do what you want it to do as fast as you want to do it then upgrade, but if you only want to upgrade because of this then thats a little silly 

I mean this thing effects processors made by Intel in the last 20 years.  Shouldn't we be a little more concerned than we are?

[apm]

they are either NSA backdoors or intel is just fucking incompetent.

im not sure whats worse.

[luigi90210]

1 minute ago, Xirhanna said:

I mean this thing effects processors made by Intel in the last 20 years.  Shouldn't we be a little more concerned than we are?

oh trust me, im concerned, i have a home business i run on all intel machines so there is a potential that i can lose thousands of not hundred of thousands if there is a data breach because of this

if it was financially viable for me id switch all my computers to AMD just for the security reason alone

 

Just now, apm said:

they are either NSA backdoors or intel is just fucking incompetent.

im not sure whats worse.

this is intel being incompetent, the NSA released an outline on how to secure intel based PCs and literally the first step was to disable IME and these vulnerabilities were discussed at REcon14 and intel basically blew off that whole discussion 

[porina]

21 hours ago, porina said:

System is my gaming laptop: MSI GE62 6QF. This has a i7-6700HQ with 16GB ram (DDR4 2133, dual channel, dual rank). The storage has been replaced, and is now a single Crucial MX300 525GB SATA SSD.

More test results:

 

Firestrike: 6458 before, 6423 after, -0.5% (2 runs)

TimeSpy: 2360 before, 2355 after, -0.2% (1 run)

FFXIV Stormblood bench, Laptop High 1080p, 10413, 10275, -1.3% (1 run)

FFXIV Stormblood bench load time: 23.337s, 23.700s, -1.6% (1 run)

 

I didn't bother doing repeats to maximise the "after" score since it was close enough to the "before" scores.

 

Forgot to say, GPU is 970M.

 

55 minutes ago, NumLock21 said:

Here are my results for the 8th Gen Core i5 8250U.

Did you try multiple runs to make sure?