CPU Performance, Short Form

For our motherboard reviews, we use our short form testing method. These tests usually focus on if a motherboard is using MultiCore Turbo (the feature used to have maximum turbo on at all times, giving a frequency advantage), or if there are slight gains to be had from tweaking the firmware. We put the memory settings at the CPU manufacturers suggested frequency, making it very easy to see which motherboards have MCT enabled by default.

For B550 we are running using Windows 10 64-bit with the 1909 update.

Rendering - Blender 2.7b: 3D Creation Suite - link

A high profile rendering tool, Blender is open-source allowing for massive amounts of configurability, and is used by a number of high-profile animation studios worldwide. The organization recently released a Blender benchmark package, a couple of weeks after we had narrowed our Blender test for our new suite, however their test can take over an hour. For our results, we run one of the sub-tests in that suite through the command line - a standard ‘bmw27’ scene in CPU only mode, and measure the time to complete the render.

Rendering: Blender 2.79b

Streaming and Archival Video Transcoding - Handbrake 1.1.0

A popular open source tool, Handbrake is the anything-to-anything video conversion software that a number of people use as a reference point. The danger is always on version numbers and optimization, for example the latest versions of the software can take advantage of AVX-512 and OpenCL to accelerate certain types of transcoding and algorithms. The version we use here is a pure CPU play, with common transcoding variations.

We have split Handbrake up into several tests, using a Logitech C920 1080p60 native webcam recording (essentially a streamer recording), and convert them into two types of streaming formats and one for archival. The output settings used are:

  • 720p60 at 6000 kbps constant bit rate, fast setting, high profile
  • 1080p60 at 3500 kbps constant bit rate, faster setting, main profile
  • 1080p60 HEVC at 3500 kbps variable bit rate, fast setting, main profile

Handbrake 1.1.0 - 720p60 x264 6000 kbps FastHandbrake 1.1.0 - 1080p60 x264 3500 kbps FasterHandbrake 1.1.0 - 1080p60 HEVC 3500 kbps Fast

Rendering – POV-Ray 3.7.1: Ray Tracing - link

The Persistence of Vision Ray Tracer, or POV-Ray, is a freeware package for as the name suggests, ray tracing. It is a pure renderer, rather than modeling software, but the latest beta version contains a handy benchmark for stressing all processing threads on a platform. We have been using this test in motherboard reviews to test memory stability at various CPU speeds to good effect – if it passes the test, the IMC in the CPU is stable for a given CPU speed. As a CPU test, it runs for approximately 1-2 minutes on high-end platforms.

Rendering: POV-Ray 3.7.1 Benchmark

Compression – WinRAR 5.60b3: link

Our WinRAR test from 2013 is updated to the latest version of WinRAR at the start of 2014. We compress a set of 2867 files across 320 folders totaling 1.52 GB in size – 95% of these files are small typical website files, and the rest (90% of the size) are small 30-second 720p videos.

Encoding: WinRAR 5.60b3

Synthetic – 7-Zip v1805: link

Out of our compression/decompression tool tests, 7-zip is the most requested and comes with a built-in benchmark. For our test suite, we’ve pulled the latest version of the software and we run the benchmark from the command line, reporting the compression, decompression, and a combined score.

It is noted in this benchmark that the latest multi-die processors have very bi-modal performance between compression and decompression, performing well in one and badly in the other. There are also discussions around how the Windows Scheduler is implementing every thread. As we get more results, it will be interesting to see how this plays out.

Encoding: 7-Zip 1805 CompressionEncoding: 7-Zip 1805 DecompressionEncoding: 7-Zip 1805 Combined

Point Calculations – 3D Movement Algorithm Test: link

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 win in the single thread version, whereas the multithread version has to handle the threads and loves more cores. For a brief explanation of the platform agnostic coding behind this benchmark, see my forum post here.

System: 3D Particle Movement v2.1

Neuron Simulation - DigiCortex v1.20: link

The newest benchmark in our suite is DigiCortex, a simulation of biologically plausible neural network circuits, and simulates activity of neurons and synapses. DigiCortex relies heavily on a mix of DRAM speed and computational throughput, indicating that systems which apply memory profiles properly should benefit and those that play fast and loose with overclocking settings might get some extra speed up. Results are taken during the steady-state period in a 32k neuron simulation and represented as a function of the ability to simulate in real time (1.000x equals real-time).

System: DigiCortex 1.20 (32k Neuron, 1.8B Synapse)

System Performance Gaming Performance
Comments Locked

61 Comments

View All Comments

  • Irata - Saturday, August 22, 2020 - link

    You also have x4 PCIe 4.0 plus several USB ports connected directly to the CPU with Ryzen. There is an Aorus board that allows the x8 plus three times x4 for nVME connection all directly from the CPU.

    If the Ampere and RDNA2 only need the bandwidth provider by 8x PCIe 4 / 16x PCIe 3, you can run the GPU and three nVME at full speed that way, plus USB devices connected to the CPU *and* still have the x4 PCIe 3 lanes for the chipset to CPU connection for everything else on B550.

    I'd say this is where Ryzen 2 and 3 shine vs the competition that is much more limited with PCIe 3 and four fewer lanes from the CPU.
  • Death666Angel - Saturday, August 22, 2020 - link

    I'm curious, what would be your use case for two x8 slots? Multi GPU is dead and are there any peripheral cards that need an x8 slot from the CPU? :)
  • MrVibrato - Sunday, August 23, 2020 - link

    There are x8 HBAs / RAID controllers.So, if one wants to use a GPU and such a HBA / RAID controller, two available x8 slots can make sense...
  • sandtitz - Friday, August 21, 2020 - link

    "...and the slightly older Intel AX200 [vs AX201]"

    According to Intel ARK, they're both the same product, released at the same time. Only the system connectivity differs.

    No reason to prefer either.
  • invinciblegod - Friday, August 21, 2020 - link

    What does system connectivity mean?
  • dotes12 - Friday, August 21, 2020 - link

    I think that Intel's AX200 does Wi-Fi through PCI-E and Bluetooth through USB, while Intel's AX201 uses CNVi for both in one CNVio link. I might have the 200/201 numbers reversed, but that's the idea as far as I understand it.
  • Hyoyeon - Friday, August 21, 2020 - link

    CNVi (intel proprietary) modules are often soldered, so I prefer the AX200.
  • jabber - Saturday, August 22, 2020 - link

    I must admit for me the PCIe slot setup I'd prefer is

    1 x 16
    4 x 4

    More practical for my use. Boards come with way too many 16 and 1 slots for my liking. The x4 slot is underappreciated.
  • Gigaplex - Saturday, August 22, 2020 - link

    x4 cards fit in an x16 slot. There's not really much benefit in putting a physical x4 slot on the board - may as well just put an x16 slot and have it share lanes with some of the other slots, dropping down to x4 active.
  • jabber - Monday, August 24, 2020 - link

    Ahhh well you see I want to just have SET slots. I don't want that "if X is in Y then V is x4 or disabled and if Y is in V then C is X16 and if X is in V then its x8 but if you have NVMe in Slot B its disabled" nonsense.

Log in

Don't have an account? Sign up now