News Intel: Rocket Lake's PCIe 4.0 Storage Performance is 11% Faster Than AMD Ryzen

[Redneck5439]

I am taking these Intel internal benchmarks with a pinch of salt. Independent testing will either confirm or deny this claim when these CPU's, motherboards and RAM appear on the market.

Totally agreed. From the leaked benchmarks I've seen thus far the 11900K in single core performance is on par with my overclocked / optimized 5900X. I am running a negative offset in core voltage and have further optimized the single core boost using the overclock curve in my bios and the two best cores of CCD0 and CCD1 are boosting to ~5Ghz (4.999 and 5.024 are what I typically see under load, with 5.125 reported under light loads). In single core I score between 690 and 708 in CPU-Z, between 645 and 650 in CB R20, and 1780 - 1800 in Geekbench. These are the main leaked benchmarks I've seen for the 11900K and out of them the only outlier is Geekbench where I have seen leaks of the 11900K scoring over 1900. Of course with 4 more cores and 8 more threads the 5900X will dominate the flagship 11900K in any productivity based (multi-core) tasks. I also have an all core overclock set at 4.675Ghz, which the Dark Hero allows via an OC switch, so in multi-core benchmarks my 5900X is going to far surpass anything the 11900K can muster.

Really best case for the 11900K is that it will edge out Zen 3 in single core performance, might have a 5 - 10 FPS advantage in some games. All of this while requiring more raw clock speed, using more power and requiring high end cooling solutions. As previously mentioned Intel will not have an answer for multi-core applications till at least Alder Lake.

To me this seems like a poorly placed placeholder to Alder Lake... Would make sense if Intel didn't plan to release Alder Lake till late 2021, but with their road map showing Alder Lake release of "second quarter" of this year doesn't make a whole lot of sense, and for multi-core performance is actually a step back from the 10900K. This seems like a refresh but according to Intel its a "new" arch back-ported from 10 to 14nm. Maybe I'm alone in feeling like Rocket Lake is just a rushed placeholder designed mostly to fleece more money from its own fan base... Either that or they know Alder Lake is going to be pushed back to end of 2021, beginning of 2022 and they don't want to admit it for fear of loosing market share. This would make more sense as Intel would at least be able say they have the best gaming processor again (if only by very small margins) and hopefully keep themselves relevant till the end of the year.

 

[Redneck5439]

Intel 11th Gen Rocket Lake CPU Pre-Orders Open Two Weeks Before Reviews - Full Unveil on 16th March, Sales on 30th March

Intel will be launching its 11th Gen Rocket Lake CPU lineup on 16th of March with pre-orders opening up two weeks prior to sales and reviews.

wccftech.com

Seems to go along with what I have suspected... Intel wants to sell as many of these processors as possible before independent reviews fully reveal the true performance of Rocket Lake. Intel has been afraid of benchmarks since Ryzen 3000, and now they are afraid of independent reviews. Intel has gone from the company on the cutting edge with the best of everything to the company that overclocks a cherry picked, highly binned processor on an extreme board with an industrial chiller calling it a soon to be released new product. All of that to try to diminish AMD's announcement of an actual HEDT processor, and only coming partly clean after the curtain has been pulled back to reveal the truth... That's what I hate most... the marketing tricks that all the companies (Intel, AMD, Nvidia, Apple, Samsung, ect, ect...) are guilty of.

 

[Redneck5439]

Random thoughts:

1. In my experience AMD may be a little behind in synthetic benchmarks but that is the price you pay to be first to market. If memory serves, AMD was first with SATA 3 on Bulldozer and those benches lagged by about 20-30% in my tests between AMD and Intel - I can not remember what OEM or boards, just that the configs were similar and both were fresh installs and newest drivers at the time of test. USB 3 throughput was a bit less as well.
2. Intel damn well BETTER be 10 % faster since they have 10-50x the R&D budget and resources and have had the benefit of over 18 months additional time on their hands to get this done.
3. Still, I wonder if this advantage only exists with one product from one OEM or is it large enough to measure across the board. What if I am reusing my 860 EVO? (as I did) Is it even noticeable then? Does this same performance exist in lower spec boards and CPU's or do I HAVE TO BUY a $500 board AND the top of the line CPU + 32GB RAM to get it? What if I get a mid tier ASROCK board along with a simple Quad I-5 and 16GB - as is my custom?
4. How tweaked were their settings? It's not impossible to eke out an additional 10% using every trick in the book under the hood.
5. I only ask because we know from previous experience that intel is not above a little sleight of hand in theses demos - didn't they pull a CES stunt demo with a commercial freezer under the table a couple years back to demo their ability to hit 5ghz? memory escapes me at the moment. I may not have the details right - just that there was a commercial grade freezer that you could not run off a normal 1500 watt residential 110 volt power outlet driving the show under the tablecloth.

But yeah - 10% in a synthetic bench on Gen IV SSD's? YAWNNNNNNNNNNNNNNNNNNNNNNNNN. How's it feel to finally get a desktop CPU on 10nm after 7 years of trying?

People have been asking me if Intel is actually going to be releasing 10nm desktop this year, and if Alder Lake is actually going to be 10nm. My answer to them is... maybe, on both questions... Intel has been promising 10nm for years and has only produced generation after generation of "+". Rocket Lake was supposed to be 10nm, was going to be 10nm, is definitely going to be 10nm.... until it wasn't. Now we have a fresh new he!! of trying to figure out what the $%&* "10nm back ported to 14nm" actually means (if anything other than a marketing ploy). I have my doubts if Alder Lake will actually launch this year, or if they will have a total "paper" launch with no product being actually released till holiday season (end of the year) or beginning of 2022. I also have my doubts if Alder Lake will actually be 10nm or if its going to be the the next "10nm back ported to 14nm", maybe with a + and probably (but not definitely) sporting DDR5. With Intel's track record on 10nm I wouldn't be a bit surprised if the next couple Intel "generations" are sporting the new marketing of 10nm back ported to 14nm and we don't see a true 10nm till end of 2022.

 

[InvalidError]

Now we have a fresh new he!! of trying to figure out what the $%&* "10nm back ported to 14nm" actually means

There is nothing to figure out there. 10nm is not getting "back ported" to 14nm, Sunny Cove which was designed for 10nm is getting back-ported (adapted) to 14nm as Cypress Cove. Back-porting is the process of taking a design intended for production on a more advanced process and adapting it to an older process. Nothing special or controversial there, this is basically the reverse of die shrinks from the good old days where old designs got adapted to new processes to make more chips per wafer.

 

[Why_Me]

Seems to go along with what I have suspected... Intel wants to sell as many of these processors as possible before independent reviews fully reveal the true performance of Rocket Lake. Intel has been afraid of benchmarks since Ryzen 3000, and now they are afraid of independent reviews. Intel has gone from the company on the cutting edge with the best of everything to the company that overclocks a cherry picked, highly binned processor on an extreme board with an industrial chiller calling it a soon to be released new product. All of that to try to diminish AMD's announcement of an actual HEDT processor, and only coming partly clean after the curtain has been pulled back to reveal the truth... That's what I hate most... the marketing tricks that all the companies (Intel, AMD, Nvidia, Apple, Samsung, ect, ect...) are guilty of.

No argument here. Rocket Lake will be decent for gaming builds and people who just want simple plug & play builds but with the graphics cards shortage I don't see many people getting new gaming builds in the near future.

 

[Redneck5439]

No argument here. Rocket Lake will be decent for gaming builds and people who just want simple plug & play builds but with the graphics cards shortage I don't see many people getting new gaming builds in the near future.

The shortages are truly a killer. I have several people interested in a new 5000 series build but some motherboards, the higher end 5000 series processors (AMD) and seemingly all GPUs right now are all very hard to obtain. I got lucky with my personal rig and had an "in" and a favor owed so I was able to get 1 each of the R9 5900X, Asus Crosshair VIII Dark Hero, and an MSI RTX 3080 (Gaming X Trio) at MSRP. Even with that I was limited to getting only 1 of each, so building anyone else a custom rig right now is all but impossible (unless you deal with the freaking scalpers). Intel releasing their new Rocket Lake processors may help to take some of the demand issues off of AMD's 5000 series, but I have a feeling they too will sell out extremely quickly and be out of stock just like everything else.