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
Koenig168 - Friday, October 6, 2017 - link
Hmm ... rather disappointing that Anandtech did not include Ryzen 1600/X until called out by astute readers.mkaibear - Friday, October 6, 2017 - link
...apart from including all the data in their benchmark tool, which they make freely available, you mean? They put in the CPUs they felt that were most relevant. The readership disagreed, so they changed it from their benchmark database. That level of service is almost unheard of in the industry and all you can do is complain. Bravo.Koenig168 - Friday, October 6, 2017 - link
Irrelevant. While I agree with most of what you said, that does not change the fact that Anandtech did not include Ryzen 1600/X until called out by astute readers. To make things a little clearer for you, the i7-8700 is a 6C/12T processor. The Ryzen 1600 is a 6C/12T processor. Therefore, a comparison with the Ryzen 1600 is relevant.You should have addressed the point I made. Instead all you can do is complain about my post. Bravo. (In case this goes over your head again, that last bit is added just to illustrate how pointless such comments are.)
mkaibear - Saturday, October 7, 2017 - link
So your point is, in essence, "they didn't do what I wanted them to do so they're damned for all time".They put up the comparison they felt was relevant, then someone asked them to include something different - so they did it. They listened to their readers and made changes to an article to fix it.
Should they have put the R5 in the original comparison? Possibly. I can see arguments either way but if pushed I'd have said they should have done - but since even the 1600X gets beaten by the 8400 in virtually every benchmark on their list (as per https://www.anandtech.com/bench/product/2018?vs=20... they would then have been accused by the lurking AMD fanboys of having picked comparisons to make AMD look bad (like on every other article where AMD gets beaten in performance).
So what are you actually upset about? That they made an editorial decision you disagree with? You can't accuse them of hiding data since they make it publicly accessible. You can't accuse them of not listening to the readers because they made the change when asked to. Where's the issue here?
mkaibear - Saturday, October 7, 2017 - link
OK on further reading it's not "virtually every" benchmark on the list, just more than half. It's 50% i5 win, 37% R5 win, 12% tied. So not exactly a resounding triumph for the Ryzen but not as bad as I made it out to be.In the UK the price differential is about £12 in favour of the i5, although the motherboard is about £30 more expensive (though of course Z370 is a lot more fully featured than B650) so I think pricing wise it's probably a wash - but if you want gaming performance on anything except Civ VI then you'd be better off getting the i5.
...oh and if you don't want gaming performance then you'll need to buy a discrete graphics card with the R5 which probably means the platform costs are skewed in favour of Intel a bit (£25 for a GF210, £32 for a R5 230...)
watzupken - Saturday, October 7, 2017 - link
As mentioned when I first called out this omission, I would think comparing a 6 vs 4 core irrelevant. This is what AnandTech recommended to lookout for on page 4 "Core Wars": Core i5-8400 vs Ryzen 5 1500X.You be the judge if this makes sense when there is a far better competition/ comparison between the i5 8400 vs R5 1600. Only when you go reading around and you realized that hey, the i5 8400 seems to be losing in some areas to the 1600. I give AnandTech the benefit of the doubt, so I am done debating what is relevant or not.
KAlmquist - Friday, October 6, 2017 - link
The Anandtech benchmark tool confirms what Ryan indicated in the introduction: the i7-8700k wins against the 1600X across the board, due faster clocks and better IPC. The comparison to the i5-8400 is more interesting. It either beats the 1600X by a hair, or loses rather badly. I think the issue is the lack of hyperthreading on the i5-8400 makes the 1600X the better all-around performer. But if you mostly run software that can't take advantage of more than 6 threads, then the i5-8400 looks very good.Personally, I wouldn't buy i5-8400 just because of the socket issue. Coffee Lake is basically just a port of Skylake to a new process, but Intel still came out with a new socket for it. Since I don't want to dump my motherboard in a landfill every time I upgrade my CPU, Intel needs a significantly superior processor (like they had when they were competing against AMD's bulldozer derivatives) to convince me to buy from them.
GreenMeters - Friday, October 6, 2017 - link
So Intel still isn't getting their head out of their rear and offering the option of a CPU that trades all the integrated GPU space for additional cores? Moronic.mkaibear - Friday, October 6, 2017 - link
Integrated graphics make up more than 70% of the desktop market. It's even greater than that for laptops. Why would they sacrifice their huge share of that 70% in order to gain a small share of the 30%? *that* would be moronic.In the meantime you can know that if you buy a desktop CPU from Intel it will have an integrated GPU which works even with no discrete graphics card, and if you need one without the integrated graphics you can go HEDT.
Besides, the limit for Intel isn't remotely "additional space", they've got more than enough space for 8/10/12 CPU cores - it's thermal. Having an integrated GPU which is unused doesn't affect that at all - or arguably it gives more of a thermal sink but I suspect in truth that's a wash.
Zingam - Saturday, October 7, 2017 - link
We need a completely new PC architecture - you need more CPU cores - add more CPU cores, you need more GPU cores add more GPU cores, all of them connected via some sort of Infinity fabric like bus and sharing a single RAM. That should be possible to implement. Instead of innovating Intel is stuck in the current 80s architecture introduced by IBM.