2017 CPU Benchmarking

For our review, we are implementing our fresh CPU testing benchmark suite, using new scripts developed specifically for this testing. This means that with a fresh OS install, we can configure the OS to be more consistent, install the new benchmarks, maintain version consistency without random updates and start running the tests in under 5 minutes. After that it's a one button press to start an 8-10hr test (with a high-performance core) with nearly 100 relevant data points in the benchmarks given below. The tests cover a wide range of segments, some of which will be familiar but some of the tests are new to benchmarking in general, but still highly relevant for the markets they come from.

Our new CPU tests go through six main areas. We cover the Web (we've got an un-updateable version of Chrome 56), general system tests (opening tricky PDFs, emulation, brain simulation, AI, 2D image to 3D model conversion), rendering (ray tracing, modeling), encoding (compression, AES, h264 and HEVC), office based tests (PCMark and others), and our legacy tests, throwbacks from another generation of bad code but interesting to compare.

Our graphs typically list CPUs with microarchitecture, SKU name, cost and power. The cost will be one of two numbers, either the 1k unit price 'tray price' for when a business customer purchases 1000 CPUs, or the MSRP likely to be found at retail. The problem here is that neither Intel nor AMD are consistent: Intel has a tray price for every CPU, but an MSRP only for parts sold at retail. AMD typically quotes MSRP for CPUs at retail, tray prices for enterprise CPUs, and doesn't say much about OEM only parts. We try to find a balance here, so prices may be $10-$20 from what you might expect.

A side note on OS preparation. As we're using Windows 10, there's a large opportunity for something to come in and disrupt our testing. So our default strategy is multiple: disable the ability to update as much as possible, disable Windows Defender, uninstall OneDrive, disable Cortana as much as possible, implement the high performance mode in the power options, and disable the internal platform clock which can drift away from being accurate if the base frequency drifts (and thus the timing ends up inaccurate).

Web Tests on Chrome 56

Sunspider 1.0.2
Mozilla Kraken 1.1
Google Octane 2.0

System Tests

PDF Opening
3DPM v2.1
Dolphin v5.0
DigiCortex v1.20
Agisoft PhotoScan v1.0

Rendering Tests

Corona 1.3
Blender 2.78
LuxMark CPU C++
LuxMark CPU OpenCL
POV-Ray 3.7.1b4
Cinebench R15 ST
Cinebench R15 MT

Encoding Tests

7-Zip 9.2
WinRAR 5.40
AES Encoding (TrueCrypt 7.2)
HandBrake v1.0.2 x264 LQ
HandBrake v1.0.2 x264-HQ
HandBrake v1.0.2 HEVC-4K

Office / Professional

Chromium Compile (v56)
SYSmark 2014 SE

Legacy Tests

3DPM v1 ST / MT
x264 HD 3 Pass 1, Pass 2
Cinebench R11.5 ST / MT
Cinebench R10 ST / MT

A side note - a couple of benchmarks (LuxMark) weren't fully 100% giving good data during testing. Need to go back and re-work this part of our testing.

2017 CPU Gaming Tests

For our new set of GPU tests, we wanted to think big. There are a lot of users in the ecosystem that prioritize gaming above all else, especially when it comes to choosing the correct CPU. If there's a chance to save $50 and get a better graphics card for no loss in performance, then this is the route that gamers would prefer to tread. The angle here though is tough - lots of games have different requirements and cause different stresses on a system, with various graphics cards having different reactions to the code flow of a game. Then users also have different resolutions and different perceptions of what feels 'normal'. This all amounts to more degrees of freedom than we could hope to test in a lifetime, only for the data to become irrelevant in a few months when a new game or new GPU comes into the mix. Just for good measure, let us add in DirectX 12 titles that make it easier to use more CPU cores in a game to enhance fidelity.

Our original list of nine games planned in February quickly became six, due to the lack of professional-grade controls on Ubisoft titles. If you want to see For Honor, Steep or Ghost Recon: Wildlands benchmarked on AnandTech, point Ubisoft Annecy or Ubisoft Montreal in my direction. While these games have in-game benchmarks worth using, unfortunately they do not provide enough frame-by-frame detail to the end user, despite using it internally to produce the data the user eventually sees (and it typically ends up obfuscated by another layer as well). I would instead perhaps choose to automate these benchmarks via inputs, however the extremely variable loading time is a strong barrier to this.

So we have the following benchmarks as part of our 4/2 script, automated to the point of a one-button run and out pops the results four hours later, per GPU. Also listed are the resolutions and settings used.

  • Civilization 6 (1080p Ultra, 4K Ultra)
  • Ashes of the Singularity: Escalation* (1080p Extreme, 4K Extreme)
  • Shadow of Mordor (1080p Ultra, 4K Ultra)
  • Rise of the Tomb Raider #1 - GeoValley (1080p High, 4K Medium)
  • Rise of the Tomb Raider #2 - Prophets (1080p High, 4K Medium)
  • Rise of the Tomb Raider #3 - Mountain (1080p High, 4K Medium)
  • Rocket League (1080p Ultra, 4K Ultra)
  • Grand Theft Auto V (1080p Very High, 4K High)

For each of the GPUs in our testing, these games (at each resolution/setting combination) are run four times each, with outliers discarded. Average frame rates, 99th percentiles and 'Time Under x FPS' data is sorted, and the raw data is archived.

The four GPUs we've managed to obtain for these tests are:

  • MSI GTX 1080 Gaming X 8G
  • ASUS GTX 1060 Strix 6G
  • Sapphire Nitro R9 Fury 4GB
  • Sapphire Nitro RX 480 8GB

In our testing script, we save a couple of special things for the GTX 1080 here. The following tests are also added:

  • Civilization 6 (8K Ultra, 16K Lowest)

This benchmark, with a little coercion, are able to be run beyond the specifications of the monitor being used, allowing for 'future' testing of GPUs at 8K and 16K with some amusing results. We are only running these tests on the GTX 1080, because there's no point watching a slideshow more than once.

Test Bed and Setup Benchmarking Performance: CPU System Tests


View All Comments

  • Spoelie - Monday, July 24, 2017 - link

    On the first page, I assume the green highlight in the processor charts signifies an advantage for that side. Why are the cores/threads rows in the Ryzen side not highlighted? Or is 8/16 not better than 4/8? Reply
  • Ian Cutress - Monday, July 24, 2017 - link

    Derp. Fixed. Reply
  • Gothmoth - Monday, July 24, 2017 - link

    intel must really push money into anandtech. :) so many interesting things to report about and they spend time on a niche product..... Reply
  • Ian Cutress - Monday, July 24, 2017 - link

    This has been in the works for a while because our CPU failed. I work on the CPU stuff - other editors work on other things ;) If you've got an idea, reach out to us. I can never guarantee anything (I've got 10+ ideas that I don't have time to do) but if it's interesting we'll see what we can do. Plus it helps us direct what other content we should be doing. Reply
  • halcyon - Monday, July 24, 2017 - link

    This is an amazing amount of benchmarking with many options. thank you. Must have been a lot of work :-)
    The obvious idea is this:

    Gaming (modern CPU limited and most played games) & Productive work (rendering, encoding, 4K video work, R/statistics/Matlab)

    Test those under 4c/8t and 8c/16t CPUs both from AMD and Intel - all at most common non-esoteric overlock levels (+/-10%).

    This is what many of your readers want:

    How much does c. 5Ghz 4c/8t do vs 4.x Ghz 8c/16t when taken to it's everyday stable extreme, in modern games / productivity.

    The web is already full of benchmarks at stock speed. Or overclocked Ryzen R 7 against stock Intel, or OC intel against overclocked Ryzen - and the game/app selections are not very varied.

    The result is a simple graph that plots the (assumed) linear trend in performance/price and shows any deviations below/above the linear trend.

    Of course, if you already have the Coffee lake 6c/12t sample, just skip the 4c/8t and go with 6c/12t vs 8c/16 comparision.

    Thanks for all the hard work throughout all these years!
  • Ryan Smith - Monday, July 24, 2017 - link

    "so many interesting things to report about and they spend time on a niche product....."

    What can we say? CPUs have been our favorite subject for the last 20 years.=)
  • user_5447 - Monday, July 24, 2017 - link

    "For 2017, Intel is steering the ship in a slightly different direction, and launching the latest microarchitecture on the HEDT platform."

    Skylake-S, Kaby Lake-S and Kaby Lake-X share the same microarchitecture, right?
    Then Skylake-X is newer microarchitecture than Kaby Lake-X (changes to L2 and L3 caches, AVX-512).
  • Ian Cutress - Monday, July 24, 2017 - link

    Correct me if I'm wrong: SKL-SP cores are derived from SKL-S, and 14nm. KBL-S/X are 14+, and shares most of its design with SKL-S, and the main changes are power related. Underneath there's no real performance (except Speed Shift v2), but Intel classifies Kaby Lake as its latest non-AVX512 IPC microarchitecture. Reply
  • user_5447 - Monday, July 24, 2017 - link

    Kaby Lake-S has some errata fixes compared to Skylake-S. AFAIK, this is the only change to the CPU core (besides the Speed Shift v2, if it even involved hardware changes).
    David Kanter says Skylake-X/EP is 14+ nm http://www.realworldtech.com/forum/?threadid=16889...
  • extide - Wednesday, July 26, 2017 - link

    I have a buddy who works in the fabs -- SKL-X is still on plain 14nm Reply

Log in

Don't have an account? Sign up now