The Intel 9th Gen Review: Core i9-9900K, Core i7-9700K and Core i5-9600K Tested
by Ian Cutress on October 19, 2018 9:00 AM EST- Posted in
- CPUs
- Intel
- Coffee Lake
- 14++
- Core 9th Gen
- Core-S
- i9-9900K
- i7-9700K
- i5-9600K
Power Consumption
TDP or not the TDP, That is The Question
Notice: When we initially posted this page, we ran numbers with an ASRock Z370 board. We have since discovered that the voltage applied by the board was super high, beyond normal expectations. We have since re-run the numbers using the MSI MPG Z390 Gaming Edge AC motherboard, which does not have this issue.
As shown above, Intel has given each of these processors a Thermal Design Power of 95 Watts. This magic value, as mainstream processors have grown in the last two years, has been at the center of a number of irate users.
By Intel’s own definitions, the TDP is an indicator of the cooling performance required for a processor to maintain its base frequency. In this case, if a user can only cool 95W, they can expect to realistically get only 3.6 GHz on a shiny new Core i9-9900K. That magic TDP value does not take into account any turbo values, even if the all-core turbo (such as 4.7 GHz in this case) is way above that 95W rating.
In order to make sense of this, Intel uses a series of variables called Power Levels: PL1, PL2, and PL3.
That slide is a bit dense, so we should focus on the graph on the right. This is a graph of power against time.
Here we have four horizontal lines from bottom to top: cooling limit (PL1), sustained power delivery (PL2), battery limit (PL3), and power delivery limit.
The bottom line, the cooling limit, is effectively the TDP value. Here the power (and frequency) is limited by the cooling at hand. It is the lowest sustainable frequency for the cooling, so for the most part TDP = PL1. This is our ‘95W’ value.
The PL2 value, or sustained power delivery, is what amounts to the turbo. This is the maximum sustainable power that the processor can take until we start to hit thermal issues. When a chip goes into a turbo mode, sometimes briefly, this is the part that is relied upon. The value of PL2 can be set by the system manufacturer, however Intel has its own recommended PL2 values.
In this case, for the new 9th Generation Core processors, Intel has set the PL2 value to 210W. This is essentially the power required to hit the peak turbo on all cores, such as 4.7 GHz on the eight-core Core i9-9900K. So users can completely forget the 95W TDP when it comes to cooling. If a user wants those peak frequencies, it’s time to invest in something capable and serious.
Luckily, we can confirm all this in our power testing.
For our testing, we use POV-Ray as our load generator then take the register values for CPU power. This software method, for most platforms, includes the power split between the cores, the DRAM, and the package power. Most users cite this method as not being fully accurate, however compared to system testing it provides a good number without losses, and it forms the basis of the power values used inside the processor for its various functions.
Starting with the easy one, maximum CPU power draw.
Focusing on the new Intel CPUs we have tested, both of them go beyond the TDP value, but do not hit PL2. At this level, the CPU is running all cores and threads at the all-core turbo frequency. Both 168.48W for the i9-9900K and 124.27W for the i7=9700K is far and above that ‘TDP’ rating noted above.
Should users be interested, in our testing at 4C/4T and 3.0 GHz, the Core i9-9900K only hit 23W power. Doubling the cores and adding another 50%+ to the frequency causes an almost 7x increase in power consumption. When Intel starts pushing those frequencies, it needs a lot of juice.
If we break out the 9900K into how much power is consumed as we load up the threads, the results look very linear.
This is as we load two threads onto one core at a time. The processor slowly adds power to the cores when threads are assigned.
Comparing to the other two ‘95W’ processors, we can see that the Core i9-9900K pushes more power as more cores are loaded. Despite Intel officially giving all three the same TDP at 95W, and the same PL2 at 210W, there are clear differences due to the fixed turbo tables embedded in each BIOS.
So is TDP Pointless? Yes, But There is a Solution
If you believe that TDP is the peak power draw of the processor under default scenarios, then yes, TDP is pointless, and technically it has been for generations. However under the miasma of a decade of quad core processors, most parts didn’t even reach the TDP rating even under full load – it wasn’t until we started getting higher core count parts, at the same or higher frequency, where it started becoming an issue.
But fear not, there is a solution. Or at least I want to offer one to both Intel and AMD, to see if they will take me up on the offer. The solution here is to offer two TDP ratings: a TDP and a TDP-Peak. In Intel lingo, this is PL1 and PL2, but basically the TDP-Peak takes into account the ‘all-core’ turbo. It doesn’t have to be covered under warranty (because as of right now, turbo is not), but it should be an indication for the nature of the cooling that a user needs to purchase if they want the best performance. Otherwise it’s a case of fumbling in the dark.
Facebook
Twitter
RSS
274 Comments
View All Comments
vext - Friday, October 19, 2018 - link
Very good article, but here are my beefs.Why is there no mention of temperatures?
According to Techspot the 9900k runs ridiculously hot under heavy loads. At stock clocks under a heavy Blender load it reaches 85C with a Corsair H100i Pro, or Noctua NH-D15. Pushed to 5Ghz, it hits 100C. At 5.1 Ghz it FAILS. I suggest that Anandtech has failed by not discussing this.
Techspot says:
"There’s simply no way you’re going to avoid thermal throttling without spending around $100 on the cooler, at least without your PC sounding like a jet about to take off. Throw in the Corsair H100i Pro and the 9900K now costs $700 and you still can’t overclock, at least not without running at dangerously high temperatures."
Why the focus on single threaded benchmarks? For the most part they are irrelevant. Yet they are posted in their own graph, at the front of each testing section, as though they were the most important data point. Just include them as a separate bar with the multi-thread benchmarks. Good Grief!
Why post MSRP prices in every single benchmark? You can't even buy them for MSRP. There should be a single chart at the front of the article with a rough retail estimate for each processor, and links to the retailers. If the MSRP is necessary, then just add a column to the chart. Sheesh.
Why no in depth cost/benefit comparison? A Ryzen 2600 with included cooler at $160 costs only one quarter of a 9900k with an aio cooler at $700. The $540 difference would buy a new RTX 2070 video card. Or three more Ryzen 2600's. For crying out loud.
I like the 9900k, it's a good processor. It's intended for hobbyists that can play with custom loop cooling. But it's not realistic for most people.
mapesdhs - Sunday, October 21, 2018 - link
All good questions... the silence is deafening. Thankfully, there's plenty of commentary on the value equation to be found. A small channel atm, but I like this guy's vids:https://www.youtube.com/watch?v=EWO5A9VMcyY
abufrejoval - Friday, October 19, 2018 - link
I needed something a little bigger for my lab two or three years ago and came across an E5-2696v3 on eBay from China, a Haswell generation 18-core at $700.That chips didn't officially exist, but after digging a little deeper I found it's basically an E5-2699v3 which clocks a little higher (3.8 instead of 3.6GHz) with 1-2 cores active. So it's basically a better chip for a fraction of the going price of the lesser one (E5-2699v3 is still listed at €4649 by my favorite e-tailer). And yes, it's a perfect chip, Prime95'd it for hours, POVrayd and Blendered for days until I was absolutely sure it was a prime quality chip.
Officially it has 145Watts TDP, but I've only ever seen it go to 110Watts on HWiNFO with Prime95 in its meanest settings: It must be a perfect bin. With the particle pusher it's never more than 93Watts while no part of the CPU exceeds 54°C with a Noctua 140mm fan practically inaudible at 1000rpm cooling it: That because the 18 cores and 36 threads never run faster than 2.8GHz fully loaded. They also don't drop below it (except for idle, 1.855 Watts minimum btw.), so you can pretty much forget about the 2.3GHz 'nominal' speed.
It gets 2968.245803 on that benchmark, slightly above the i9-9900k, somewhat below the ThreadRipper. That's 22nm Haswell against 14++/12nm current and 18 vs 8/12 cores.
This is rather typical for highly-threaded workloads: It's either cores or clocks and when the power ceiling is fixed you get higher throughput and energy efficiency when you can throw cores instead of clocks at the problem.
I think it's a data point worth highlighting in this crazy clock race somewhat reminiscent of Pentium 4 days, heat vs. efficiency, a four year old chip beating the newcomer in performance and almost 3:1 in efficiency at far too similar prices.
Yet, this specific chip will clock pretty high for a server chip, easily doing 3.6 GHz with eight cores seeing action from your game engine, while the remaining ten are often ignored: Perhaps that's a Ryzen effect, it used to be 4:14 earlier.
I've done BCLK overclock of 1.08 to have it reach the magic 4GHz at maximum turbo, but it's not noticeable in real-life neck-to-neck to an E3-1276v3 which also turbos to 4GHz on three cores out of four available, 3.9 at 4/4 with HT.
abufrejoval - Friday, October 19, 2018 - link
2968.245803 on the particle pusher benchmark... need editicoreaudience - Friday, October 19, 2018 - link
Move away from rar/lzma : the new darling of data compression is called Zstandard :https://www.zstd.net
It comes with a nice integrated benchmark, which can easily ramp up with multithreading :
zstd -b -1 -T8 fileToTest # benchmark level one on fileToTest using 8 threads
Windows user can even download a pre-compiled binary directly in the release notice :
https://github.com/facebook/zstd/releases/latest
It would be great to see some numbers using this compressor on latest Intel cores !
Kaihekoa - Friday, October 19, 2018 - link
Looks like all your gaming benchmarks are GPU bound and there pointless. Why not use a 2080 Ti to eliminate/reduce GPU bottleneck?Kaihekoa - Friday, October 19, 2018 - link
therefore*palladium - Friday, October 19, 2018 - link
Can you please run some SPEC2006 benchmarks and see if Apple's SOC really has caught on to Intel's performance (per core), as mentioned in Andrei in his iPhone XS review? ThanksVirpZ - Friday, October 19, 2018 - link
Apart from blender, your review is full Intel biased software for rendering.Hifihedgehog - Friday, October 19, 2018 - link
Hey Ian. I see your updated full load power consumptions results. Question: Why is it that the six-core i7-8086K is drawing so little power in comparison to everything else including the quad-cores? Is this due to its better binning or is this simply an error that crept in?