Intel Rocket Lake (14nm) Review: Core i9-11900K, Core i7-11700K, and Core i5-11600K
by Dr. Ian Cutress on March 30, 2021 10:03 AM EST- Posted in
- CPUs
- Intel
- LGA1200
- 11th Gen
- Rocket Lake
- Z590
- B560
- Core i9-11900K
CPU Tests: Microbenchmarks
Core-to-Core Latency
As the core count of modern CPUs is growing, we are reaching a time when the time to access each core from a different core is no longer a constant. Even before the advent of heterogeneous SoC designs, processors built on large rings or meshes can have different latencies to access the nearest core compared to the furthest core. This rings true especially in multi-socket server environments.
But modern CPUs, even desktop and consumer CPUs, can have variable access latency to get to another core. For example, in the first generation Threadripper CPUs, we had four chips on the package, each with 8 threads, and each with a different core-to-core latency depending on if it was on-die or off-die. This gets more complex with products like Lakefield, which has two different communication buses depending on which core is talking to which.
If you are a regular reader of AnandTech’s CPU reviews, you will recognize our Core-to-Core latency test. It’s a great way to show exactly how groups of cores are laid out on the silicon. This is a custom in-house test built by Andrei, and we know there are competing tests out there, but we feel ours is the most accurate to how quick an access between two cores can happen.
All three CPUs exhibit the same behaviour - one core seems to be given high priority, while the rest are not.
Frequency Ramping
Both AMD and Intel over the past few years have introduced features to their processors that speed up the time from when a CPU moves from idle into a high powered state. The effect of this means that users can get peak performance quicker, but the biggest knock-on effect for this is with battery life in mobile devices, especially if a system can turbo up quick and turbo down quick, ensuring that it stays in the lowest and most efficient power state for as long as possible.
Intel’s technology is called SpeedShift, although SpeedShift was not enabled until Skylake.
One of the issues though with this technology is that sometimes the adjustments in frequency can be so fast, software cannot detect them. If the frequency is changing on the order of microseconds, but your software is only probing frequency in milliseconds (or seconds), then quick changes will be missed. Not only that, as an observer probing the frequency, you could be affecting the actual turbo performance. When the CPU is changing frequency, it essentially has to pause all compute while it aligns the frequency rate of the whole core.
We wrote an extensive review analysis piece on this, called ‘Reaching for Turbo: Aligning Perception with AMD’s Frequency Metrics’, due to an issue where users were not observing the peak turbo speeds for AMD’s processors.
We got around the issue by making the frequency probing the workload causing the turbo. The software is able to detect frequency adjustments on a microsecond scale, so we can see how well a system can get to those boost frequencies. Our Frequency Ramp tool has already been in use in a number of reviews.
From an idle frequency of 800 MHz, It takes ~16 ms for Intel to boost to the top frequency for both the i9 and the i5. The i7 was most of the way there, but took an addition 10 ms or so.
Facebook
Twitter
RSS
279 Comments
View All Comments
Beaver M. - Wednesday, March 31, 2021 - link
Acting like GN and HUB gives them lots of AMD fanboy clicks/views.Beaver M. - Wednesday, March 31, 2021 - link
I guess living in isolation for a year makes people more and more antisocial and aggressive. And that then in turn sells well.Qasar - Wednesday, March 31, 2021 - link
so they are amd fanboys cause they told the truth ? more like you are the intel fanboy trying to defend this dud of a cpu. come on, most reviews say they same thing, just some are more harsh, and rightfully soOxford Guy - Wednesday, March 31, 2021 - link
Tech fans are continually disappointed by the lack of adequate competition in a multitude of tech markets (e.g. GPUs, CPUs, search, leading-edge lithography machines/foundries, etc. etc.)We saw, way back in the 80s, what happens when competition is shut down. The Japanese seized the DRAM market by dumping, forcing American DRAM makers out of the market — then promptly raising prices drastically.
We went from seeing revolutionary products like the Apple Lisa being replaced by years of toy-grade machines at very high prices. The Lisa shipped with 1 MB of RAM and the first Mac with just 128K. The Apple IIGS shipped with just 256K, many years after the Lisa. We can thank more than Apple's love of fat margins. We can thank inadequate competition.
We have seen that play out, time and time again. Now, it's so bad that it's worse than the bread lines of the USSR. At least if one waited in one of those one might end up with some bread. These days, you have two choices: a line to get a very overpriced product (like the latest iPhone) or you can skip waiting in line because they're nothing to buy (GPUs).
Oxford Guy - Wednesday, March 31, 2021 - link
(The Amiga 1000 only shipped with 256K of RAM, too, as I recall. It was a problem throughout the industry, not something due merely to Apple's margins.)GeoffreyA - Saturday, April 3, 2021 - link
I agree with your anti-corporation sentiment, but there's little we can do, except sigh. A worldwide boycotting of their products will work wonders but that'll never happen. As long as these rotters are out to make money---Intel, AMD, Google, the rest---it'll go on like this. Who knows, perhaps there's some vital link to entropy in all this, and why everything always goes awry on earth.Oxford Guy - Wednesday, March 31, 2021 - link
'One of the few tech sites that remained professional and didn't use click baity titles or disrespect intel.'This article uses bad spin to try to make Intel's product look better than it is.
Just one example:
‘Intel has stated that in the future it will have cores designed for multiple process nodes at the same time, and so given Rocket Lake’s efficiency at the high frequencies, doesn’t this mean the experiment has failed? I say no, because it teaches Intel a lot in how it designs its silicon’
The spin also includes the testing, using a really loud high-CFM CPU cooler in the Intel and a different quieter one on the AMD.
It's a pile of spin, like the glorified press release stuff trying to turn CEO Pat into some sort of superhero. That stuff sounds like it was written for investors.
FirstStrike - Wednesday, March 31, 2021 - link
Ian, you are missing SpecInt and SpectFp suiteOrkiton - Wednesday, March 31, 2021 - link
I'm not either Intel or AMD "fanboy" though some sympathy to AMD due to unfair, anti-competitive Intel practices in the past and AMD merit to emerge from their ashes. That said, best wishes to both in the name of progress, innovation and better value to us, the consumers.Oxford Guy - Wednesday, March 31, 2021 - link
The rated TDP is 125 W, although we saw 160 W during a regular load, 225 W peaks with an AVX2 rendering load, and 292 W peak power with an AVX-512 compute load.‘Intel’s claimed TDP’ rather than ‘that rated’. The latter implies an independent rating standard/body.
If both processors were found at these prices, then the comparison is a good one – the Ryzen 7 5800X in our testing scored +8% in CPU tests and +1% in gaming tests (1080p Max). The Ryzen is very much the more power-efficient processor, however the Intel has integrated graphics (an argument that disappears with KF at $374).
Again, no specifics about the power consumption difference.
On high-end gaming both processor performed the same, the AMD processor was ahead an average of 8% on CPU workloads, and the AMD processor came across as a lot more efficient and easy to cool, while the Intel processor scored a big lead in AVX-512 workloads.
Again, no specifics about the power consumption difference.
AGAIN, testing AMD with a weaker cooler, even though the CPU will go faster with the loud fast cooling you’re using on Intel.
Makes it APPLES to APPLES.