The AnandTech Coffee Lake Review: Initial Numbers on the Core i7-8700K and Core i5-8400
by Ian Cutress on October 5, 2017 9:00 AM EST- Posted in
- CPUs
- Intel
- Core i5
- Core i7
- Core i3
- 14nm
- Coffee Lake
- 14++
- Hex-Core
- Hyperthreading
Benchmarking Performance: CPU Legacy Tests
Our legacy tests represent benchmarks that were once at the height of their time. Some of these are industry standard synthetics, and we have data going back over 10 years. All of the data here has been rerun on Windows 10, and we plan to go back several generations of components to see how performance has evolved.
All of our benchmark results can also be found in our benchmark engine, Bench.
3D Particle Movement v1
3DPM is a self-penned benchmark, taking basic 3D movement algorithms used in Brownian Motion simulations and testing them for speed. High floating point performance, MHz and IPC wins in the single thread version, whereas the multithread version has to handle the threads and loves more cores. This is the original version, written in the style of a typical non-computer science student coding up an algorithm for their theoretical problem, and comes without any non-obvious optimizations not already performed by the compiler, such as false sharing.
CineBench 11.5 and 10
Cinebench is a widely known benchmarking tool for measuring performance relative to MAXON's animation software Cinema 4D. Cinebench has been optimized over a decade and focuses on purely CPU horsepower, meaning if there is a discrepancy in pure throughput characteristics, Cinebench is likely to show that discrepancy. Arguably other software doesn't make use of all the tools available, so the real world relevance might purely be academic, but given our large database of data for Cinebench it seems difficult to ignore a small five minute test. We run the modern version 15 in this test, as well as the older 11.5 and 10 due to our back data.
x264 HD 3.0
Similarly, the x264 HD 3.0 package we use here is also kept for historic regressional data. The latest version is 5.0.1, and encodes a 1080p video clip into a high quality x264 file. Version 3.0 only performs the same test on a 720p file, and in most circumstances the software performance hits its limit on high end processors, but still works well for mainstream and low-end. Also, this version only takes a few minutes, whereas the latest can take over 90 minutes to run.
Facebook
Twitter
RSS
222 Comments
View All Comments
watzupken - Saturday, October 7, 2017 - link
There are pros and cons of having integrated graphics. It sure takes up a lot of die space, but it is something that allows Intel to sell a lot of chips. Amongst enthusiasts, this is unnecessary, but this group may only represent a small percentage vs corporates that need only decent CPU and no need for fancy graphics. To be honest, Intel could likely have created a 8 core processor easily since the die size is still fairly small for Coffee Lake, but they chose not to. I don't think it is a matter of the graphic that is holding them back.James5mith - Friday, October 6, 2017 - link
Now to wait for the generation of Intel CPU's with native Thunderbolt3 on-die like Intel announced earlier this year.Zingam - Saturday, October 7, 2017 - link
Why is that a good thing?ReeZun - Friday, October 6, 2017 - link
"The difference between the Ryzen 5 1500X and the Core i3-8350K would be interesting, given the extreme thread deficit (12 threads vs 4) between the two."The 1500X houses 8 threads (not 12).
watzupken - Saturday, October 7, 2017 - link
The difference between the R5 1500X and i3 8350K goes beyond just the number of threads. The cache is also 2x more on the Ryzen chip. However, the i3 chip have the advantage of being able to reach higher clockspeed. I do agree that this will be an interesting comparison.sweeper765 - Friday, October 6, 2017 - link
I'm not up to date with current bios versions.Is multi-core enhancement still present in z370 motherboards? That would get rid of all those differences in turbo speeds. I know it is technically overclocking but i bet it's a pretty safe procedure without increasing the voltages.
Also, what's the deal with the 8700? Is it just as good as 8700k (minus 100mhz) if one decides not to overclock? Just trying to gather as many practical facts as i can before formulating an upgrade plan (sandy bridge user hehe )
This cpu family looks good on specs and benches (maybe the first worthy successor to sandy bridge) but it's not perfect. I hate that Intel decided not to solder, i expect temperatures to soar in the high 80's. Also the current motherboards are somewhat lacking in ports (usb, lan, sata).
I love my sandy bridge setup though.
6 1/2 years old and still going strong. Overclocked, cool, stable, silent. With current cpu's you don't get all these points.
Even if i upgrade i'm not going to touch it.
Ian Cutress - Saturday, October 7, 2017 - link
Is multi-core enhancement still present in z370 motherboards?As an option, yes.
As default? Will vary board to board. You can disable it.
However we had trouble with one of our boards: disabling MCT/MCE and then enabling XMP caused the CPU to sit at 4.3 GHz all day. Related to a BIOS bug which the vendor updated in a hurry.
Jodiuh - Friday, October 6, 2017 - link
What’s up with those rise of Tomb Raider benchmarks? Am I too seriously believ the i5 7400 is more capable than the 8700K...did I miss the overclocking part?Tech reports review much better with results that make sense.
peevee - Friday, October 6, 2017 - link
"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"+10%? Count again.
boeush - Friday, October 6, 2017 - link
Regarding most normal/gaming scenarios, I'm wondering with the 8700/k whether one couldn't get an even better performance by disabling hyperthreading in the UEFI.That would still yield 6 threads, but now ostensibly with a full 2 MB of L3 per thread. Plus, lower power per core (due to lower resource utilization) might mean more thermal headroom and higher overall sustained frequencies.
So you'd get maximum-possible single-thread performance while still being able to run 6-wide SMT (which, under most normal usage, isn't even a constraint worth noting...)
Amirite?