Intel Coffee Lake Conclusion

It has been a long time coming, but we finally have something bigger than a quad-core processor on Intel’s mainstream platform. Fundamentally it might be the same architecture as the processors preceded it, but after a decade of quad-core Intel parts, it comes as a welcome improvement. Intel sampled us the Core i7-8700K and the Core i5-8400 for this set of initial launch testing, with the goal of offering more high performance cores at more mainstream price points without having to invest in the company's more expensive and otherwise more complex HEDT platforms.

  

The Core i7-8700K

The Core i7-8700K in our testing was designed to be the new halo mainstream processor: many cores and the highest frequencies seen on an Intel part out of the box, with the option of overclocking thrown in. With a peak turbo frequency of 4.7 GHz, in benchmarks that could be stripped down to a single core with no other work going on, the i7-8700K took home the bacon.

The problem here is the same problem we’ve seen with big core parts and Windows 10, however: these large processors can only take so much before having to move threads around, to keep both the frequency high and the energy density low. All it takes is for a minor internal OS blip and single-threaded performance begins to diminish. Windows 10 famously kicks in a few unwanted instruction streams when you are not looking, and as a result the CPU fires up another CPU core and drops to a lower turbo bin. Consequently the average single thread performance seen on the 8700K might be equal or lower than that of the previous generation. It becomes an infuriating problem to debug as a reviewer.

Nonetheless, when software needs to take advantage of the cores, the Core i7-8700K will run through at an all-core turbo frequency of 4.3 GHz, consuming about 86W in the process. The jump up from a quad-core to a hex-core for only a $20 difference will be immediately noticeable in the software that can take advantage of it.

What is interesting to note is that the Core i7-8700K essentially kills the short-lived Kaby Lake-X parts on the X299 high-end desktop platform. Again, for a few extra dollars on the 8700K, a user can save over $100 on the motherboard, get more cores and more performance, and not have the hassle of dealing with a hybrid X299 platform. It does make me wonder why Intel released Kaby Lake-X in the first place, if they knew just how short lived they would be.

When comparing against the Core i7-7800X, a high-end desktop part at a similar price and with the same core count but a lower frequency, it really comes down to what the user needs. Performance easily favors the Core i7-8700K, however that cannot replace the quad-channel memory (up to 128GB) and the 28 PCIe lanes that the Core i7-7800X can support. In most circumstances, especially gaming, the Core i7-8700K will win out.

Intel’s 8th Generation CPUs: The Ones To Watch

Intel also sampled us the Core i5-8400, showing that six-core processors can cost less than $200. This processor, along with the Core i3-8100, will form the new backbone of general computing when using Intel components: the Core i3-8100 replaces old Core i5 processors for around $120, and enthusiasts who simply want a little more oomph can go with the Core i5-8400 at $190 at retail. It almost comes across as adding 50% cost for adding 50% performance. Personally I think the Core i3-8100, if made widely available, will be a top-selling processor for casual desktop users and gamers who were previously looking for a good performance-per-dollar part.

There is one other comparison to note: the Core i5-8600K and the Core i7-8700. These two parts are $50 apart, however the Core i7-8700 has double the threads, +10% raw frequency, 33% more L3 cache, and 1/3 lower TDP. The Core i5-8600K has overclocking, however going up to the i7 ensures stability, and should offer more raw performance. It will be interesting to get these two in to test, and especially to see if the TDP rating makes a significant performance difference.

Today’s Review Takeaway

We finally have six-core processors on Intel’s mainstream platform, which has driven up the core counts (and frequencies) of the company's low and mid-range processors. For anyone looking at building a system in the last 6-12 months, they should be able to build an equivalent with the latest-generation processor for $50-$100 less. Or spend the same and get a few more cores to play with. The last time we had this situation was a decade ago, and hopefully it won’t take another decade to happen again.

Dedicated reviews for the processors (with more gaming tests) are on the cards. Stay tuned!

CPU Gaming Performance: Grand Theft Auto
Comments Locked

222 Comments

View All Comments

  • mapesdhs - Friday, October 6, 2017 - link

    Any idea what that optimisation is? Seems odd that adding extra pure cores would harm performance, as opposed to adding HT which some games don't play nice with. Otherwise, are you saying that for this test, if it was present, the i3 8100 would come out on top? Blimey.
  • Ian Cutress - Saturday, October 7, 2017 - link

    They're either doing something to align certain CPU tasks for AVX, or it's bypassing code. You'd have to ask the developers on that.
  • mapesdhs - Monday, October 9, 2017 - link

    I doubt they'd explain what's happening, might be proprietory code or something.
  • WickedMONK3Y - Thursday, October 5, 2017 - link

    You have the spec of the i7 8700K slightly wrong. It has a base frequency of 3.7GHz not 3.8GHz.
    https://ark.intel.com/products/126684/Intel-Core-i...
  • Ian Cutress - Thursday, October 5, 2017 - link

    Mistake on our part. I was using our previous news post as my source and that had a Typo. This review (and that news) should be updated now.
  • Slomo4shO - Thursday, October 5, 2017 - link

    Ian, this is probably your worst review to date. Lackluster choice of CPUs, mid-grade GPU, and lack of direct competition in the product stack... Why would you not use a GTX 1080 Ti or Titan XP?
  • Ian Cutress - Thursday, October 5, 2017 - link

    All the CPUs we've ever tested are in Bench. Plenty of other data in there: the goal was to not put 30+ CPUs into every graph.

    Our benchmark database includes over 40 CPUs tested on the GTX 1080, which is the most powerful GPU I could get a set of so I can do parallel testing across several systems. If that wasn't enough (a full test per CPU takes 5 hours per GPU), the minute I get better GPUs I would have to start retesting every CPU. At the exclusion of other content. Our benchmark suite was updated in early Q2, and we're sticking with that set of GPUs (GTX 1080/1060/R9 Fury/RX 480) for a good while for that reason.

    Note I had three days to do this review.
  • crimson117 - Thursday, October 5, 2017 - link

    Good job! More people need to know about the bench...
  • Slomo4shO - Thursday, October 5, 2017 - link

    To be fair the R5 1600 was added to the benches after the fact. In addition, your othwr reviews tend to be much more detailed and data driven with relevant products and multiple GPUs.

    Why would I read your review if you expect me to dig through your benchmark to obtain relivant data?

    I can understand and appreciate the time crunch but it is a poor excuse for some of the decisions made in this review.

    Take it with a grain of salt, this was not your best work.
  • mapesdhs - Friday, October 6, 2017 - link

    Ooohhh the effort of examing the data in Bench! :D First world problems. Sheesh...

    Run your own tests then, see how you get on with having a life. It's insanely time consuming.

Log in

Don't have an account? Sign up now