Going for Power

How to Manage 5.0 GHz Turbo

Intel lists the Core i9-9900KS processor as having a 127W TDP. As we’ve discussed at length [1,2] regarding what TDP means, as well as interviewing Intel Fellows about it, this means that the Core i9-9900KS is rated to require a cooling power of 127W when running at its base frequency, 4.0 GHz. Above this frequency, for example at its turbo frequency of 5.0 GHz, we are likely to see higher than 127W.

Now, I started saying in this review that the length of time that the processor will spend at 5.0 GHz will be motherboard dependent. This is true: Intel does not strictly define how long turbo should be enabled on any processor. It allows the motherboard manufacturer to ‘over-engineer’ the motherboard in order to help push the power behind the turbo higher and enable turbo for longer. The specific values that matter here are called PL2 (Power Limit 2, or peak turbo power limit), and Tau (a time for turbo).

For an Intel processor, each one has a ‘bucket’ of extra turbo energy. As the processor draws more power above its TDP (also called PL1), the bucket is drained to provide this energy. When the bucket is empty, the processor has to come back down to the PL1 power value, and eventually when the processor is less active below PL1, the bucket will refill. How big this bucket is depends on the value of PL1, PL2, and Tau. The bigger the bucket, the longer an Intel processor can hold its turbo frequency. Typically Tau isn’t so much as a time for turbo, but a scalar based on how big that bucket should be.


An example graph showing the effect of implementing Turbo on power/frequency

Motherboard manufacturers can set PL1, PL2, and Tau as they wish – they have to engineer the motherboard in order to cope with high numbers, but it means that every motherboard can have different long turbo performance. Intel even suggests testing processors on high-end and low-end motherboards to see the difference. Users can also manually adjust PL1, PL2, and Tau, based on the cooling they are providing.

For the Core i9-9900KS, Intel has given the PL1 value on the box, of 127 W. PL2 it says should at least be 1.25x the value of PL1, which is 159 W. Tau should be at least 28 seconds. This means, with a given workload (typically 95% equivalent of a power virus), the CPU should turbo up to 159 W for 28 seconds before coming back down to 127 W. A very important thing to note is that if the CPU needs more than 159 W to hit the 5.0 GHz turbo frequency, it will reduce the frequency until it hits 159 W. This might mean 4.8 GHz, or lower.

Despite giving us these numbers for PL1, PL2, and Tau, Intel also stated to us that they recommend that motherboard manufacturers determine the best values based on the hardware capabilities. The values of 127 W, 159 W, and 28 seconds are merely guidelines – most motherboards should be able to go beyond this, and Intel encourages its partners to adjust these values by default as required.

We tested Intel’s guidelines with a 10 minute run of Cinebench R20.

He we can see that at idle, the CPU sits at 5.0 GHz. But immediately when the workload comes on, it has to reduce the average CPU frequency because it goes straight up to the 159W limit – simply put, 159W isn’t enough to hit 5.0 GHz. We see the temperature slowly rise to 92C, but because the power isn’t enough the frequency keeps fluctuating.

By the end of the first Cinebench R20 section, it seems that the majority of it occurred during the turbo period. This means that this run scored almost the same as a pure 5.0 GHz run. However the subsequent runs were not as performant.

Because the turbo budget had been used up, the processor had to sit at 127 W, its PL1 value. At this power, the processor kept bouncing between 4.6 GHz and 4.7 GHz to find the balance. The temperatures in this mode kept stable, nearer 80C, but the performance of Cinebench R20 dropped around 8-10% because the CPU was now limited by its PL1/TDP value, as per Intel’s base configuration recommendation.

Going Beyond

Because motherboard manufactuers can do what they want with these values, we set the task on the motherboard we tested, the MSI Z390 Gaming Edge AC. By default, MSI has set the BIOS for the Core i9-9900KS with a simple equation. PL1 = PL2 = 255 W. When PL1 and PL2 are equal to each other, then Tau doesn’t matter. But what this setting does is state that MSI will allow the processor to consume as much power as it needs to up to 255 W. If it can hit 5.0 GHz before this value (hint, it does), then the user can turbo at 5.0 GHz forever. The only way that this processor will reduce in frequency is either at idle or due to thermal issues.

Here’s the same run but done with MSI’s own settings:

The processor stayed at a constant 5.0 GHz through the whole run. The CPU started pulling around 172W on average during the test, fluctuating a little bit based on exactly which 1s and 0s were going through. The CPU temperature is obviously higher, as we used the same cooling setup as before, and peaked at 92C, but the system was fully table the entire time.

Here was our system setup – a 2kg TRUE Copper air cooler powered by an average fan running at full speed in an open test bed.

But what this means is that users are going to have to be wary of exactly what settings the motherboard manufacturers are using. For those of you reading this review on the day it goes live, you’ll likely see more than a dozen other reviews testing this chip – each one is likely using a different motherboard, and each one might be using different PL2 and Tau values. What you’ve got here are the two extremes: Intel’s recommendation and MSI’s ‘going to the max’. Be prepared for a range of results. Where time has permitted, we’ve tested both extremes.

Test Bed and Setup CPU Performance: System Tests
Comments Locked

235 Comments

View All Comments

  • Jorgp2 - Thursday, October 31, 2019 - link

    9900KS most likely does it at a lower voltage and power, plus it has hardware mitigations.
  • Korguz - Thursday, October 31, 2019 - link

    this right there... shows you didnt read this article.
  • edzieba - Friday, November 1, 2019 - link

    The 9900KS has a different hardware mitigation report to the 9900K. See Phor0nics article p.1: https://www.phoronix.com/scan.php?page=article&...
  • Khenglish - Thursday, October 31, 2019 - link

    I think it would be interesting to see how the 3700x and 3800x do if you bump their power limit up to 9900KS levels. The 3700x is probably being held back quite a bit at 65W but still is competitive.
  • imaheadcase - Thursday, October 31, 2019 - link

    "AMD also has the 16-core Ryzen 9 3950X coming around the corner, promising slightly more performance than the 3900X, and aside from the $749 MSRP, it’s going to be an unknown on availability until it gets released in November."

    Wasn't that delayed till December? I swear i saw that in the news..
  • imaheadcase - Thursday, October 31, 2019 - link

    oh nm i got months messed up. I read that last month..forgot its already Oct. LOL
  • jgarcows - Thursday, October 31, 2019 - link

    Your IGP tests aren't very useful. I'm not going to run a game at 720p with the lowest settings on my IGP if I'm getting 250+ FPS. I'm going to increase the resolution or graphics settings until I'm getting the best visuals I can while still hitting 60 FPS.

    Please compare with settings that give around 60 FPS on the IGPs so we can get an idea of how the integrated graphics performs when you actually stress it some. At 720p, you are just testing the CPU cores and not the IGP at all.
  • Slash3 - Thursday, October 31, 2019 - link

    This has been a bugaboo of mine for quite a while.
    There are *no* IGP benchmarks. What you're seeing is a benchmark detail setting that AT refers to as "IGP." In effect, "Very Low" detail. The test is still run on the GeForce GTX 1080 and not the CPU's built-in graphics.

    My other complaint is that the use of a GTX 1080 makes the High preset results entirely meaningless, as they're almost always limited by the GPU. It's a waste of graphs and a waste of test time.
  • katsetus - Friday, November 1, 2019 - link

    The gaming benchmarks as they are shown here are absolutely pointless - all they show is that the GPU is the more important factor.
    Them saying that they keep the GTX 1080 for the comparability with older results is pointless, when the variability between three generations of CPUs is 3% at best, because the whole thing is nowhere near being limited by the CPU.
  • Cellar Door - Thursday, October 31, 2019 - link

    Blender chart is missing Ryzen 3700 and 3900.

Log in

Don't have an account? Sign up now