This site may earn affiliate commissions from the links on this page. Terms of use.

Silicon wafer

Ii days ago, Intel released a whitepaper it commissioned from Principled Technologies that contained errors and then meaning, they rise to the level of lying about its competitor'due south performance. Principled Technologies has at present released a response to these claims defending its ain work — and ExtremeTech has performed its own partial confirmation of the claims PT makes well-nigh its Intel CPU results.

In his response to various allegations and claims, the co-founder of Principled Technologies, Bill Catchings, has provided the following statement. His full statement can be read at WCCFTech, nosotros've reprinted the relevant sections below:

Use of "Game Mode" on the AMD Ryzen™ 7 2700X: Some inquiries we accept received concern the utilize of the Ryzen utility and the number of agile cores in the AMD-based systems. Based on AMD'due south recommendations and our initial testing on the Threadripper processors, nosotros found installing the AMD Ryzen Master utility and enabling the Game Mode increased about results. For consistency purposes, we did that for all AMD systems across Threadripper™ and Ryzen™. Nosotros are now doing boosted testing with the AMD systems in Creator Fashion. We will update the report with the new results.

Retentivity speeds: To have consummate parity across all systems, and to allow the Intel® Core™ i9 X-series and AMD Ryzen™ Threadripper™ to fully utilize retentiveness bandwidth, we used four 16GB DDR4 DIMMs on all configurations. We took the post-obit memory configuration steps.

The remainder of Catchings response deals with various topics nosotros didn't raise at ET and aren't as concerned well-nigh with regard to their impact on the examination results. The in a higher place two points are the major ones — and they're the ones we need to talk over in a flake more than detail.

Get-go, Principled Technologies clarifies that, in fact, information technology made a catastrophic error when configuring Game Way. It'southward true that AMD recommends enabling Game Mode for Threadripper in certain instances. Only AMD also makes it clear that Game Mode is intended for Threadripper. The following image is from Page 26 of AMD'due south Ryzen Primary Quick Reference Guide:

Ryzen-Master-Guide

Furthermore, AMD's Overclocking Guide for Ryzen Principal makes the function of Game Mode extremely articulate. Page 25: "When turned on with Ryzen or Ryzen Threadripper processors offering >4 physical processors, Legacy Compatibility Mode reduces the active logical processor resources by one-half."

There's nothing wrong with testing advanced, enthusiast features, but one typically reads the instructions commencement before activating them. The all-time caption for PT'due south piece of work is that the company failed to perform simple due diligence in this matter.

The company's explanations for its memory configurations, all the same, practice non pass elementary scrutiny. We are told that the RAM configurations used were chosen "to have complete parity across all systems."

This is a lie.

XMP was enabled on the Intel Z390, disabled on the X299-Deluxe, and enabled on the Prime Z370-A used to exam both the Core i7-8086K and the Core i7-8700K. For Threadripper, the D.O.C.P. Standard setting was used (Asus has called this "XMP by another name"). The Asus Prime X470 Pro motherboard used to test the 2700X didn't enable XMP or DOCP at all. In other words, out of five different motherboards, iii had XMP or an equivalent enabled and two did not. RAM clocks were apparently set according to maximum manufacturer specifications. Only choosing to use manufacturer-specified memory clocks and leaving XMP disabled and enabled at turns means the retention subsystems of these platforms were not configured for maximum parity.

It is remarkably surprising that the mainstream AMD organization that represents the Cadre i9-9900K's direct competition both disabled half its CPU cores and managed to employ neither XMP or DOCP with no explanation provided for this configuration decision. Continue in mind, XMP is an Intel-optimized standard to get-go with. Information technology may improve performance on AMD chips compared with whatever garbage compatibility timings are implemented by default, but information technology isn't AMD-optimized. Even enabling XMP on all systems doesn't truly constitute a level playing field, but enabling it for some AMD platforms and non for others creates an additional tilt.

If Principled wanted to configure for maximum parity, it should have tested with XMP fully enabled or disabled across all products and all systems using the same RAM clock. If it wanted to examination in a manufacturer's canonical configuration, it should have stated it was doing so and explained why XMP / DOCP was enabled or disabled in each specific circumstance relative to the best practices communicated past AMD and Intel. What nosotros got was neither.

The situation gets even stranger once you see that fifty-fifty some of PT's Intel performance claims are odd. Looking through the whitepaper, I realized Principled Technologies had used an Asus Prime number Z370-A motherboard running UEFI 1406 with a GTX 1080 Ti — which happens to correspond exactly to the system I used for our recent review of the RTX 2080 and 2080 Ti. They were even kind enough to test many of the same games.

This made me curious. Could I validate the Intel results they reported for the Core i7-8086K? For the well-nigh part, yes — with some notable and odd exceptions.

Validating Principled Technologies' Results

This isn't a consummate validation cycle; merely office of our benchmark family overlaps. I re-tested the Core i7-8086K and GeForce GTX 1080 Ti according to the game settings, Windows configuration details, and UEFI settings detailed in the PT whitepaper. I too tested them with a single setting changed. It turns out that if you alter the "Power Saving and Performance Mode" UEFI option to "Performance Mode" and away from "Auto," y'all too disable all C-states and lock the CPU at a flat 4.3GHz constant clock with no Turbo whatsoever. It seems odd to lock a chip at a single static frequency in a "Performance Mode," only I wanted to see what divergence information technology might be making to the final results.

I tested our Core i7-8086K in two unlike configurations: One configuration corresponds exactly to the steps described in Principled Technologies' whitepaper — no more, no less. One configuration corresponds to those configuration steps, just with one change: I left the "Performance Mode" setting on Auto. And, of course, nosotros've included Principled Technologies' own results. Hither are the results, graphed to two charts for readability:

Things mostly bank check out fine, with 2 glaring oddities and one smaller 1. Both of the major problems are in Warhammer Ii. Showtime of all, Warhammer Ii shouldn't exist tested in DirectX 12 with an Nvidia GPU, every bit we discussed earlier this week. But second, the results reported for the Skaven benchmark are far as well depression. Our own Core i7-8086K + GeForce GTX 1080 Ti scored 87fps when run through that benchmark in Ultra mode. Principled Technologies reports simply 83fps at "Loftier" particular, our re-tests of the scene at that quality level put our score 1.25x higher.

WarhammerII-DX12

In this case, the result y'all care about is the GeForce GTX 1080 Ti at 1080p. DX12 performance is badly compressed on NV in DX12, which is why the GPUs acme out at 87fps — merely keep in mind, we're testing Ultra Detail here, not High Particular. Result from our RTX 2080 and RTX 2080 Ti review

At that place's a similar trouble in the Warhammer 2: Laboratory test. Nosotros're told to wait a result of 41; our actual result was 48 or 49, a gain of 1.17x – 1.19x.

Finally, in the Final Fantasy Xv benchmark, the score of 10,858 reported by PT was 7-8 percentage higher than our own results in both configurations. In that location was no articulate advantage or disadvantage to enabling or disabling Functioning Mode in the tests we could verify, just we were unable to confirm benchmark results in 3 out of the 13 tests we investigated. That's not a not bad finding for a project when we already know the AMD CPU was blatantly misconfigured. I don't know why I tin can't replicate PT's results in every test — but I know I've washed similar validation of benchmark results by using Reviewer Guides provided past Intel and AMD on many occasions. Something is incorrect here.

This Is Intel's Responsibility

I don't know if Principled Technologies is responsible for this fault or if Intel is — by which I mean, I don't know if Principled Technologies simply misunderstood how AMD's utility worked or if they were told to misunderstand how AMD's utility worked. Ryzen Master's UI isn't identical for Threadripper versus Ryzen 7; the Legacy Compatibility Mode choice has additional switches that don't appear if you're only running information technology on an eight-cadre. This should've clued PT in to the fact that the adequacy functioned differently on different microprocessors. Both of AMD's documents make it plain that "Game Mode" will disable CPU cores. Coverage of Ryzen since launch has made this clear besides.

Companies are typically extremely careful when they talk nearly their competition because it tin open them up to legal liability if they're found to exist making imitation claims. In many cases, companies prefer to simply talk near "the contest" even when they literally compete with one other company. Engaging a 3rd-party to write a whitepaper is i mode of offer additional information that isn't seen as coming straight from Intel itself. But make no fault — Principled Technologies is a visitor writing a document for a customer, which means the customer has oversight and input into both the test conditions and the terminal production. If Intel doesn't like a setting, game, or performance test, that test isn't in this document.

Neither Intel nor Principled Technologies have responded to our emails. Could this exist the consequence of an honest fault or oversight? Of form. It wouldn't be the first fourth dimension someone flipped a incorrect switch and and so spent x hours cheerfully benchmarking the wrong hardware configuration, believe me. Just there are problems, plural, with this whitepaper, its information, Intel's failure to respond to it, and the fact that Principled Technologies is still trying to slide out of from acknowledging that it published verifiably simulated results with a lame reference to retesting AMD CPUs that information technology should have known were misconfigured in the starting time place. The company continues advancing a simulated narrative about its memory configuration and how information technology supposedly established retention configuration parity between testbeds when it did nothing of the sort.

At a time when Intel needs to exist building a narrative around the Core i9-9900K as its first mainstream eight-core desktop processor, a demonstration of forward progress, and a lark from its own security concerns and manufacturing delays, nosotros're instead having an extended conversation about whether the chip giant attempted to lie to consumers by proxy. It'south non a good look.

Now Read: The Cadre i9 Gaming Benchmarks Intel Commissioned Against AMD Are a Flat Lie, Intel Announces New Core i9 Family, 9th Generation CPUs, and Intel Core i7-9700K, 9900K Confirmed to Use Solder, Not Paste