The Intel Core i9-9900K at 95W: Fixing The Power for SFFby Ian Cutress on November 29, 2018 8:00 AM EST
There is a lot of discussion about processor power recently. A lot of the issues stem around what exactly that TDP rating means on the box, and if it relates to anything in the real world. A summary of Intel’s official declaration boils down to TDP as the sustained processor power at long periods, however almost zero motherboards follow that guideline. As a result users will usually see much higher sustained power, although with much higher performance. Some small form factor systems rely on setting these limits, so we tested a Core i9-9900K with a 95W limit to see what would happen.
Intel and TDP
We recently published a sizeable analysis on what Intel officially means by TDP, and the associated values of PL1, PL2, and Tau. You can read it all here, although what it boils down to is this diagram:
When a processor is initially loaded, it should enter a state where PL2 describes the maximum power for a time of Tau seconds. When in this PL2 state, the CPU follows Intel’s per-core Turbo table rules, which reduces the frequency based on the number of cores loaded.
After Tau seconds, the CPU should drop down to a PL1 maximum sustained power value, which is usually identical to TDP. Depending on the CPU, this may reduce the frequency to the base frequency, or well below the all-core turbo frequency.
Technically PL2 is obtained over a moving average window, Tau, such that any low power moments on the processor will 'give budget back' to the turbo mode, however the graph above is the easiest way to see the high turbo mode on a fully loaded processor.
So while Intel defines a value for PL1, PL2, and Tau, almost zero consumer motherboard manufacturers actually follow it. There are many reasons why, mostly relating to overengineering the motherboards and wanting users to have the best performance at all times. The only times where these values follow any form of Intel guidance is in small form factor PCs.
For example, I tested an MSI Vortex G3 small form factor desktop at an event last year. It was using a processor normally rated for 65W TDP, and in a normal desktop that processor would push over 100W because the motherboard manufacturer in that system did not put any limits on the power, allowing the power to fall within Intel’s per-core turbo values. However, in this Vortex system, because of the limited thermal capabilities, the BIOS was set to run at 65W the whole time. This made sense for this form factor, but it meant that anyone looking for benchmarks of the processor would be misled – the power profile set in the BIOS was in no-way related to how that CPU would run in a standard desktop.
A Core i9-9900K with a 95W Limit
To put this into perspective, for this review we are using a Core i9-9900K which has a sustained TDP rating of 95W. When we compare the per-core frequencies of a 95W limited scenario and a normal ‘unrestricted scenario’, we get the following:
When a single core is loaded, the CPU is in 5.0 GHz mode as we are well under the power limit. There’s a slight decrease of 200 MHz in the 95W at two cores, but this disappears when 3-6 cores are loaded, with both setups being equal. The major difference happens however when we are at 7-8 cores loaded: because of the power consumption, the Core i9-9900K in 95W mode drops down to 3.6 GHz, which happens to be its base frequency.
This arguably means that we should see a correlation in most benchmarks between the two parts, but not if maximum load is ever required.
For this review, we’re putting the Core i9-9900K at a 95W power limit (as measured by the internal registers of the system) and running through our CPU test suite to see if how large the performance deficit is between the Core i9-9900K in a thermally unlimited scenario compared to a small form factor system deployment.
Pages In This Review
- Analysis and Competition
- Test Bed and Setup
- 2018 and 2019 Benchmark Suite: Spectre and Meltdown Hardened
- CPU Performance: System Tests
- CPU Performance: Rendering Tests
- CPU Performance: Office Tests
- CPU Performance: Encoding Tests
- CPU Performance: Legacy Tests
- Conclusions and Final Words
Post Your CommentPlease log in or sign up to comment.
View All Comments
edzieba - Thursday, November 29, 2018 - linkThe difference is the ARM chips being labelled with the short-term term frequencies and performance, while Intel put the steady state values on the box. Motherboard manufacturers throw the box values right out the window, but if Intel were to dictate /those/ the wailing and gnashing of teeth from the peanut gallery would be cacaphonous.
melgross - Thursday, November 29, 2018 - linkIts just a matter of semantics. It doesn’t have to be spelled out.
Targon - Thursday, November 29, 2018 - linkThere are actually three primary states. Base clocks, boost or turbo speeds, and then you can get thermal throttle which will actually lower the speed below the base clock speed. If the i9-9900k has a base of 3.6GHz, a turbo that goes up to 5GHz, but you have poor cooling, you may be seeing the CPU sticking to that 3.6GHz, or even below it if the temperatures get too high.
This is where those very thin laptops may have Ryzen versions performing better than Intel, because of the temperatures keeping the chip running at or even below base speeds. For a small form factor machine, will the 9900k be running at base speeds ALL THE TIME due to temperatures/TDP/cooling? In the same small form factor case, would a Ryzen 7 2700X end up having a similar level of performance after several hours(to allow the heat generation to stabilize)? If you start when things are COLD, you could turn the machine on and run benchmarks, and see better numbers than if the machine were already on and you had been running intensive applications for several hours prior to running the benchmarks.
eastcoast_pete - Thursday, November 29, 2018 - link@Ian: Thanks for this informative test and review. One comment, one question/request. Comment: I continue to be struck by Intel's prowess when AVX512/AVX2 comes into play. I am also (negatively) impressed by the thermal load use of these instructions causes. The reduction in performance when using AVX512/AVX2 under strict adherence to a TdP of 95 Wh speaks volumes. Did you ever have a chance to ask Intel why running AVX makes their chips so power-hungry? Even if not, I'd appreciate your thoughts on why AVX makes Intel's chips run so hot.
Here my question/request: I now that you/Anandtech have a large dataset on x264 video encoding speeds. However, especially for i7s and AMD's six-core and up Zen chips, I'd like to know how they fare when encoding/transcoding a 2160p 10bit video, as that is now in increasing demand, and really makes the processor sweat (and slow down, a lot). Any chance you and your colleagues can add that to the encoding tests? If space is an issue, I suggest to dump the x264 720p speed test; even a lowly Athlon or Celeron chip does that quite well, and at good speed.
HStewart - Thursday, November 29, 2018 - linkI believe you can turn off AVX512 in bios - it use in special application that need the speed
Also I would think the external GPU's is another major factor in considering power requirements on a system.
I don't belkieve there is any power needs or reduction in topp speed for AVX2 only that AVX512 uses extra power on system and top frequency are reduce if being used.
One thing about AVX2 - on Intel it is 256bit and AMD has dual 128 bits currently - not sure about new Zen's coming out next year. But at least with PowerDirector, it give you significantly performance increase
GreenReaper - Saturday, December 1, 2018 - linkIt's pretty simple, really: the more data the CPU has to process in parallel, the more horsepower it uses. It's like doubling or quadrupling the number of active cylinders in an engine - you gain performance, but it requires more power and produces more heat. That's why they're off if not in use.
Dedicated GPU blocks for video coding will also use more power, but are likely to be far more efficient than doing the operations with general code - as long as it's within their defined capabilities. (Similarly, if you had to do the equivalent of the AVX operations without the relevant hardware, it would probably use even more power than it currently does, at least over the extra time it took.)
Davenreturns - Thursday, November 29, 2018 - linkI have found much confusion among the readers on hardware review websites when it comes to this issue. So I would like to present some information from Anandtech's Bench tool in order to clarify the situation for me and others hopefully:
Looking at the CPU Power Bench
The following two processors have these results under full package, full load:
i7-6700k 82.55W First mainstream desktop 14 nm processor, 95W TDP according to Intel
i9-9900k 168.48W Latest mainstream desktop 14 nm processor, 95W TDP according to Intel
I assume that these two values were measured in unlimited mode. If this is the case, this means that the power listed above is when all cores/threads are loaded at full max turbo mode. So if you are expecting a certain level of performance given that Intel advertises 95W for both CPUs, then you are being misled and may not get the performance you are expecting when upgrading the CPU but not your cooling.
This is a CHANGE from the past in how Intel uses TDP without telling the customer. It also highlights that Intel use to be conservative with cores/clocks/turbo when they had no competition and were able to shrink nodes between Nehalem and Skylake. Now they are PRETENDING that they can just double the cores and raise clocks on the same node and not increase power. Please correct me if I'm wrong, but it doesn't look like this is the case anymore.
AlyxSharkBite - Thursday, November 29, 2018 - linkReally interesting how when you limit it to 95W it’s really close to the 2700X
4800z - Thursday, November 29, 2018 - linkA power unlimited 2700x. Also this article doesn't include any games. If it did you'd see the 9900k still does much better, because games don't use all 8 cores.
schujj07 - Thursday, November 29, 2018 - link2700X - 117.18W Max = 11.6% over stated TDP
9900K - 168.48W Nax = 77.3% over stated TDP
Don't forget not everyone views gaming and the end all be all form of benchmarking. Would it be interesting to see if it affects the gaming sure. It most certainly would affect those who game and stream at the same time.