The Intel Core i9-9900K at 95W: Fixing The Power for SFF
by Ian Cutress on November 29, 2018 8:00 AM ESTCPU Performance: Office Tests
The Office test suite is designed to focus around more industry standard tests that focus on office workflows, system meetings, some synthetics, but we also bundle compiler performance in with this section. For users that have to evaluate hardware in general, these are usually the benchmarks that most consider.
All of our benchmark results can also be found in our benchmark engine, Bench.
PCMark 10: Industry Standard System Profiler
Futuremark, now known as UL, has developed benchmarks that have become industry standards for around two decades. The latest complete system test suite is PCMark 10, upgrading over PCMark 8 with updated tests and more OpenCL invested into use cases such as video streaming.
PCMark splits its scores into about 14 different areas, including application startup, web, spreadsheets, photo editing, rendering, video conferencing, and physics. We post all of these numbers in our benchmark database, Bench, however the key metric for the review is the overall score.
PCMark10 is more forgiving, as it has lots of pauses and only a few full-on power tests, emphasising single core speed. There isn't much lost when in 95W mode here.
Chromium Compile: Windows VC++ Compile of Chrome 56
A large number of AnandTech readers are software engineers, looking at how the hardware they use performs. While compiling a Linux kernel is ‘standard’ for the reviewers who often compile, our test is a little more varied – we are using the windows instructions to compile Chrome, specifically a Chrome 56 build from March 2017, as that was when we built the test. Google quite handily gives instructions on how to compile with Windows, along with a 400k file download for the repo.
In our test, using Google’s instructions, we use the MSVC compiler and ninja developer tools to manage the compile. As you may expect, the benchmark is variably threaded, with a mix of DRAM requirements that benefit from faster caches. Data procured in our test is the time taken for the compile, which we convert into compiles per day.
The 95W mode causes a small decrease in performance in our compile test, again moving it within a small margin to the Core i7-9700K.
3DMark Physics: In-Game Physics Compute
Alongside PCMark is 3DMark, Futuremark’s (UL’s) gaming test suite. Each gaming tests consists of one or two GPU heavy scenes, along with a physics test that is indicative of when the test was written and the platform it is aimed at. The main overriding tests, in order of complexity, are Ice Storm, Cloud Gate, Sky Diver, Fire Strike, and Time Spy.
Some of the subtests offer variants, such as Ice Storm Unlimited, which is aimed at mobile platforms with an off-screen rendering, or Fire Strike Ultra which is aimed at high-end 4K systems with lots of the added features turned on. Time Spy also currently has an AVX-512 mode (which we may be using in the future).
For our tests, we report in Bench the results from every physics test, but for the sake of the review we keep it to the most demanding of each scene: Cloud Gate, Sky Diver, Fire Strike Ultra, and Time Spy.
GeekBench4: Synthetics
A common tool for cross-platform testing between mobile, PC, and Mac, GeekBench 4 is an ultimate exercise in synthetic testing across a range of algorithms looking for peak throughput. Tests include encryption, compression, fast Fourier transform, memory operations, n-body physics, matrix operations, histogram manipulation, and HTML parsing.
I’m including this test due to popular demand, although the results do come across as overly synthetic, and a lot of users often put a lot of weight behind the test due to the fact that it is compiled across different platforms (although with different compilers).
We record the main subtest scores (Crypto, Integer, Floating Point, Memory) in our benchmark database, but for the review we post the overall single and multi-threaded results.
101 Comments
View All Comments
duploxxx - Thursday, November 29, 2018 - link
Interesting in a way that there are so many people that always believe in benchmarking and that in real world all cores are always idle....The world of wonders. Artificial TDP, turbo modes and decreased frequency when running multiple cores. All to fool consumers and benchmark believers.
Very nice review. Now the question:
can this also be tested on a Ryzen 2700 and a 8700K and a 9900. Put all 3 albeit in a different setup on a stock or even reduced cooling device and see how they behave....
olde94 - Thursday, November 29, 2018 - link
I see why you are intested, but both 2700 and 8700k are actually quite close in power use to their rated TDP. The issue was that the 9900k wasn't at all. If you see the power/performance graph on the last page, i think you have your answer ;)notashill - Thursday, November 29, 2018 - link
It's almost a very nice graph but could really stand to have a few more CPUs labeled. I mean even the literal headlining CPU that the entire article is about isn't labeled.And trying to compare to the POV-Ray results earlier in the article either a bunch of the CPUs are missing or the scale on the chart does not actually match the labels.
duploxxx - Thursday, November 29, 2018 - link
according anandtech measurements:2700x 105w rated buring 117.18
8700k 95w rated buring 145.71
9900k 95w rated burning 168.45
so no i ma not kidding. even the 8700k will have reduced performance with real tdp limit vs glorious benchmarking with best of best mobo and cooling.
4800z - Thursday, November 29, 2018 - link
No the 9900k and 8700k would have no lower performance on games. This only comes up when maxing out all cores for things like cinibench.TheinsanegamerN - Thursday, November 29, 2018 - link
Unless a game pushed those TDPs up. Games that can use many cores at once, like CIV and battlefield. You know, two minor franchises nobody would notice.....rhysiam - Friday, November 30, 2018 - link
There's a big difference between starting to use 6-8 cores (like Civ & BF) and hitting all those cores with a heavy load for a sustained period. Show me a game benchmark that has the 9900K literally doubling the performance of a 7700K and then you'll have a game that can push the 9900K well past its 95W tdp.Game streaming from a single PC would certainly do that, but I'd hopefully streamers are doing some research and choosing hardware carefully.
To be clear, I'm not defending Intel here, the tdp figure has become a joke, but we're a long way from this being a widespread issue for gaming workloads.
mr_fokyou - Thursday, November 29, 2018 - link
not if you are streaming while gaming than you are very much bottlenecking 9900k if u force TDP limitsbananaforscale - Saturday, December 1, 2018 - link
You are assuming no game uses all the cores (or enough that they go above TDP). The assumption is incorrect now and it will become more incorrect as quad core becomes the minimum.Samus - Saturday, December 1, 2018 - link
I think it's totally insane a CPU can use 25-27% more power than its advertised rating. Sure, that includes more performance, but as a system builder this has got to be a liability if you are putting together, say, a little 1U rack for video encoding security camera feeds. You would use a specified CPU based on its performance AND advertised TDP rating, only to find out to GET that performance, it needs to go well beyond its TDP rating, which likely wont be possible in a tiny rack with a 1U cooler (I don't believe they make 1U coolers rated beyond 105W - and those are incredibly rare, most are 73w-88w)