The AMD 2nd Gen Ryzen Deep Dive: The 2700X, 2700, 2600X, and 2600 Tested
by Ian Cutress on April 19, 2018 9:00 AM ESTCPU System Tests
Our first set of tests is our general system tests. These set of tests are meant to emulate more about what people usually do on a system, like opening large files or processing small stacks of data. This is a bit different to our office testing, which uses more industry standard benchmarks, and a few of the benchmarks here are relatively new and different.
All of our benchmark results can also be found in our benchmark engine, Bench.
FCAT Processing: link
One of the more interesting workloads that has crossed our desks in recent quarters is FCAT - the tool we use to measure stuttering in gaming due to dropped or runt frames. The FCAT process requires enabling a color-based overlay onto a game, recording the gameplay, and then parsing the video file through the analysis software. The software is mostly single-threaded, however because the video is basically in a raw format, the file size is large and requires moving a lot of data around. For our test, we take a 90-second clip of the Rise of the Tomb Raider benchmark running on a GTX 980 Ti at 1440p, which comes in around 21 GB, and measure the time it takes to process through the visual analysis tool.
FCAT is a purely single threaded task, and it takes benefits from the top frequency parts and high IPC from Intel. On the AMD front, the Ryzen 5 parts are scoring better than the Ryzen 7 parts, but are within an error margin.
Dolphin Benchmark: link
Many emulators are often bound by single thread CPU performance, and general reports tended to suggest that Haswell provided a significant boost to emulator performance. This benchmark runs a Wii program that ray traces a complex 3D scene inside the Dolphin Wii emulator. Performance on this benchmark is a good proxy of the speed of Dolphin CPU emulation, which is an intensive single core task using most aspects of a CPU. Results are given in minutes, where the Wii itself scores 17.53 minutes (1052 seconds).
Dolphin is also a single threaded test, and has historically had benefits on Intel CPUs. The new Ryzen-2000 series, with extra IPC and frequency, are pushing ahead of Intel's Skylake parts.
3D Movement Algorithm Test v2.1: link
This is the latest version of the self-penned 3DPM benchmark. The goal of 3DPM is to simulate semi-optimized scientific algorithms taken directly from my doctorate thesis. Version 2.1 improves over 2.0 by passing the main particle structs by reference rather than by value, and decreasing the amount of double->float->double recasts the compiler was adding in. It affords a ~25% speed-up over v2.0, which means new data.
For this multi-threaded test, the new 8-core Ryzen 7 2700X pulls further head of Intel's 8-core Skylake-X compared to the 1800X. At six cores however, the Coffee Lake i7-8700K is sandwiched between the Ryzen 5 2600X and Ryzen 5 2600.
Agisoft Photoscan 1.3: link
Photoscan stays in our benchmark suite from the previous version, however now we are running on Windows 10 so features such as Speed Shift on the latest processors come into play. The concept of Photoscan is translating many 2D images into a 3D model - so the more detailed the images, and the more you have, the better the model. The algorithm has four stages, some single threaded and some multi-threaded, along with some cache/memory dependency in there as well. For some of the more variable threaded workload, features such as Speed Shift and XFR will be able to take advantage of CPU stalls or downtime, giving sizeable speedups on newer microarchitectures.
Photoscan is a variable threaded test, and time improvement from the 1800X to the 2700X shows the extra TDP and Precision Boost 2 can literally shave minutes from a test. Intel's slower mesh architecture of Skylake-X on the 8-core 7820X compared to the ring architecture of the Coffee Lake 8700K means that the two fewer cores on the 8700K allows them to draw level, but they are still four minutes or so behind the Ryzen 7 2700X. The big 18-core Intel CPU, the i9-7980XE, is needed to win here.
Civilization6 AI Test
Our Civilization AI test uses the steam version of Civilization 6 and runs the in-game AI test to process 25 rounds of an example end-game. We run the benchmark on our GTX 1080 at 1080p Medium to ensure that rendering is not a limiting factor, and the results are given as the geometric mean of the 25 rounds in the test, to give the average time to process one round of AI.
Parts of the AI test can use multiple threads, however the extra single core performance on Intel does push those parts into the lead.
Facebook
Twitter
RSS
545 Comments
View All Comments
danjw - Friday, April 20, 2018 - link
They Anandtech used the rated speeds that the processors were stated to support by the manufactures. Anandtech, is using everything at stock. Anandtech ran all the processors through fully patched systems (both bios and OS). Not every website other tests to these same methodology. So, there will be differences in their results. None the less, Anandtech, is auditing their results to double check them. I really don't think they are going to see anything wrong. Toms, ran their Intel parts without the latest bios updates. Others overclocked their systems.Most users do not overclock their systems. Sure, a lot of us readers do, but not everyone. I overclock my systems, but, my two brothers who are both just as technical as I am, do not. It is a choice some make and others do not. The majority of users do not overclock. So, Anandtech does not overclock in their most reviews. They have at times in the past and may in the future include overclocking results in reviews, but they have are always broken out the overclocking results in a separate section and/or labeled the overclocked results to differentiate them from the standard clocked results. These are editorial choices that Anandtech makes, I don't see any problem with that.
Luckz - Monday, April 23, 2018 - link
Intel for some reason have 4 memory sticks. Weird idea.werpu - Friday, April 20, 2018 - link
Well the main difference is they tested against fully meltdown and specte patched systems, which in fact is the norm, while all other reviewers simply tested against bare metal. It is known that Intel took a pretty serious hit especially with Meltdown and a more serious hit with Spectre compared to AMD which did not have meltdown at all and to a lesser degree Spectre than Intel did.I would say Anandtechs tests are spot on.
And this reflects the sad state of nowadays performance testing which seems to be done to 99.9% by incompetent idiots or fanboys (especially the youtubers are the worst)
However in extreme situations Intel again wins since the 8700k can be oced by decapping and good cooling to 5GHz while the OC capabilities of the 2700x are basically non existent. It really depends, which is better. But the performance gap is closing and in non OCed system it is not existent anymore. It will be interesting next year when AMD has moved to 7nm while Intel still will be stuck at 10nm which they currently try to pull it but not have yet managed. Then the game might be entirely reversed.
Alphasoldier - Friday, April 20, 2018 - link
Unfortunatelly, you are the only idiot and fanboy here. Pretty much everyone stated in their reviews, the system were fully patched, all cpus were reused and everything was retested, because AMD fanboys were screaming Meltdown here, Spectre there.Now, the internet is full of this garbage review, it spreads like cancer, because AMD fanboys have nothing better to do, once again they are disappointed that 6 cores from Intel outperformed 8 cores from AMD and they are now like the Liverpool fans repeating "The next year will be ours"
But at least they got some fancy RBG cooler.
Fallen Kell - Friday, April 20, 2018 - link
Alphasoldier, I've been reading the reviews, and while many have stated they have applied the software (OS) patches, very few have stated they applied both the software and BIOS patches for the Spectre variant 2. Thew few places that I have seen which have stated both the software and BIOS patches were applied all seem to be showing much more similar results as the AT article.In anycase, Ryan stated they are looking into it, and I am certain we will see an update within the next few days. And don't come saying that I am a AMD fanboi, I havn't purchased a AMD CPU since the Thunderbird (i.e. a slot A CPU).
mapesdhs - Saturday, April 21, 2018 - link
werpu, oc an 8700K to 5GHz? Makes me laugh that a 300MHz bump over a CPU's max single core turbo is even called an oc these days. Sheesh, it's a far cry from the days of SB, oc hardly seems worth bothering with now.mkaibear - Thursday, April 19, 2018 - link
It's here, it's here!Dr. Swag - Thursday, April 19, 2018 - link
What is with the gaming benchmarks? On your tests the whole ryzen 2 series is a step above everything else, but all other reviews show it between ryzen and coffee lake...fallaha56 - Thursday, April 19, 2018 - link
This is the Spectre2 patch effectNot looking great for Intel and HFR gaming
Ryan Smith - Thursday, April 19, 2018 - link
"What is with the gaming benchmarks?"We're looking into it right now. Some of these results weren't in until very recently, so we're going back and doing some additional validation and logging to see if we can get to the bottom of this.