Commissioning Misleading Core i9-9900K Benchmarks (techspot.com)

On Monday, Intel unveiled the 9th Gen Core i9-9900K, which will rival AMD's Ryzen 2700X when it goes on sale in two weeks. We will soon be reading reviews of the 9th Gen Core i9-9900K, which Intel claims is the "world's best gaming processor," to see how exactly it fares against its AMD counterpart. But as reviewers test the new CPU and comply with an NDA/embargo (non-disclosure agreement) with Intel, which requires them to not share performance data of Intel's new CPU for another few days, surprisingly, one publication has already made a bold claim. In a story published this week, news outlet PCGamesN said, "Intel's Core i9 9900K is up to 50% faster than AMD's Ryzen 7 2700X in games." The publication cites data from an Intel-commissioned report [PDF] by third-party firm Principle Technologies to make the claim. TechSpot explains the issues with this: So Intel can go and publish their own "testing" done suspiciously through a third party ten days before reviews, while reviewers are prohibited from refuting the claims due to the NDA. First bad sign. Scrolling down PCGamesN says the following when looking over Intel's commissioned benchmarks. "But the real point of all this is for Intel to be able to hold out the 9900K as hands down the best gaming processor compared with the AMD competition, and in that it seems to have excelled. On some games, such as Civ 6 and PUBG, the performance delta isn't necessarily that great, but for the most part you're looking at between 30 and 50% higher frame rates from the 9900K versus the 2700X."

Right away many of the results looked very suspect to me, having spent countless hours benchmarking both the 2700X and 8700K, I have a good idea of how they compare in a wide range of titles and these results looked very off. Having spotted a few dodgy looking results my next thought was, why is PCGamesN publishing this misleading data and why aren't they not tearing the paid benchmark report apart? Do they simply not know better?

Over at the Principled Technologies website you can find the full report which states how they tested and the hardware used. Official memory speeds were used which isn't a particularly big deal, though they have gone out of their way to handicap Ryzen, or at the very least expose its weaknesses. Ryzen doesn't perform that well with fully populated memory DIMMs, two modules is optimal. However timings are also important and they used Corsair Vengeance memory without loading the extreme memory profile or XMP setting, instead they just set the memory frequency to 2933 and left the ridiculously loose default memory timings in place. These loose timings ensure compatibility so systems will boot up, but after that point you need to enable the memory profile. It's misleading to conduct benchmarks without executing this crucial step.

Comments

Intel any thing to win other then more pci-e or

[Joe_Dragon]

Intel any thing to win other then more pci-e lanes or no raid keys

Re:Intel any thing to win other then more pci-e or

[Solandri]

What you need to understand is that Intel's CPU business (and thus the bulk of their profit margin) is extremely fragile. The silicon needed for a typical CPU only costs about $5 - similar size ARM processors with similar transistor counts typically cost about $10-$20. So when Intel sells a CPU for $300+, over 95% of that is profit. Admittedly a lot of it is used to recoup their enormous R&D costs (typically over 20% of revenue). But the fact remains that if their CPU sales start dropping, the business model they've been using for 30+ years (overpriced CPUs to generate enormous revenue which they sink into R&D to develop leading CPUs so they can sell them overpriced) stops working.

So they will do anything to protect their CPU sales. Not saying this justifies some of their shenanigans, just explaining why the motivation for them to do illegal/immoral things is so high.

Re:Intel any thing to win other then more pci-e or

[TomR teh Pirate]

It may be $5.00 worth of silicon, but the $1billion+ factory and the thousands of employees it took to design and QA that silicon must be amortized across each and every piece of silicon sold. It's not as though CPUs and software have similar capital expenses.

Desperation...

[Type44Q]

Desperation calls for desperate measures.

Re:it's a no brainer.

[butzwonker]

I switched from intel to some Amd box with 1800X CPU and it works very fine. I could have never gotten the bang for bucks with another Intel machine, and then there were also the serious security flaws of Intel chips. My machine handles everything including flight simulation and every game very well, so getting even more speed would be pointless at this time.

It's a pragmatic decision and it's stupid to get emotionally attached to companies. A PC is nothing but a tool (or a fun toy, when we speak about gaming). If Intel produces something better in 5 years from now, maybe I'll switch back to them.

Re:Corporate shills

[Anonymous Coward]

I'm not sure why this is news. Have manufacturer supplied benchmarks EVER been a reliable measure of real world performance?

TL;DR

[rsilvergun]

Modern RAM settings need to be tweaked a bit or the performance is meh. The company did the tweaks on the Intel platform but not the AMD one.

They had to know they'd be called out by the benchmarking community. That and Youtubers hungry for video content.

Re:Are tuned benchmarks really applicable

[thegarbz]

is it more or less representative to tune every aspect of the system like this?

To tune it like this? Less representative. They've effectively overclocked one system while underclocked the other. Not to mention disabled half the cores on AMD chip.

Is that with or without Meltdown & TLBleed?

[Lady Galadriel]

So, does the new chip require Meldown and TLBleed mitigation?
That would be;

• - Meltdown mitigation envolves kernel page table isolation
• - TLBleed mitigation requires disabling Hyperthreading

Neither Meltdown nor TLBleed affect AMD and AMD's Ryzen processors, as far as we know now...

So any benchmark of an Intel CPU without those security mitigations, (if needed), would be showing that they still want to abuse security for the performance gain. Something AMD appears not to want to do.