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 X570 we are running using Windows 10 64-bit with the 1903 update as per our Ryzen 3000 CPU review.

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 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

110 Comments

View All Comments

  • shabby - Monday, August 12, 2019 - link

    I agree, the difference between $200 and $400 boards is slim. The extra power/vrm features aren't needed since all cpus hit a 4.3ghz wall, 10gbe should be standard here.
  • 1_rick - Monday, August 12, 2019 - link

    I bought one of these a couple days after launch and it came with a code for 20% off a custom cable order at CableMod.
  • funks - Monday, August 12, 2019 - link

    PCIE Bottlenecked out of the box.

    Target: Hypothetical 4K -> 8K Video Editing workstation station (using Davinci Resolve)..

    Wants:

    2 - x8 lanes PCIE 3.0 Video Cards - Primary and Secondary X16 slots

    x4 lanes NVME PCIE 4.0 (OS / Application Drive) - Primary M2 slot

    x4 lanes NVME PCIE 4.0 (Data / Scratch Drive) - Secondary M2 slot (hanging off chipset)

    x4 lanes PCIE 2.0 (10 Gigabit NIC) - Tertiary x16 slot (hanging off chipset)

    PCIE 4.0 NVME x4 drives already exist out in the wild, so if you plug one of those on the secondary M2 slot (Data Drive), and happen to plug in a 10 GB PCIE 2.0 x4 card on the third mechanical PCIEx16 slot - then you are bottle necking already as both are trying to go through the PCIE 4.0 x4 link between the chipset and the CPU. For 4K -> 8K Video Editing using a shared file server (connected via 10 Gigabit NIC) along with the DATA drive (secondary M2 running at PCIE 4.0 x4) as a scratch disk - there's a bottle neck. Davinci Resolve for example can use multiple video cards (so primary and secondary PCIEx16 slot will be at 8x each populated with a video card). Primary M2 slot can be used with PCIE 4.0 NVME for OS / Application Data.

    It's like buying a network switch without adequate switching capability for the number of ports exposed. I guess it's why TR4 ain't obsolete.
  • cygnus1 - Monday, August 12, 2019 - link

    I'd say it's fine. You're just building it wrong. I'd suggest putting the scratch disk on the x4 NVMe slot and your boot/app drive on the x2 slot. Scratch disk needs throughput a lot more than the app/boot disk. PCIe 4.0 x4 is overkill for a disk if it's just boot and apps, x2 is fine. The lesser number of channels does not reduce IOPs capabilities and that's more important than bandwidth on the boot/app disk.
  • funks - Monday, August 12, 2019 - link

    For the price you pay on these boards, shouldn't have to compromise.

    BTW, what's up with the dual LAN ports on these boards? People planning on setting up their machines as a router or something? Those two PCIE lanes (One for Realtek LAN - RTL8117 , and one for Intel LAN - I211-AT should have been connected to an Aquantia 10 Gigabit NIC instead.

    2 - PCIE 3.0 lanes have about 2 GB/sec of bandwidth, plenty for a 10 Gigabit ethernet
  • cygnus1 - Monday, August 12, 2019 - link

    So, realistically this has 1 real NIC. The RTL NIC is the remote management controller, aka a BMC. I myself really wouldn't put that on a network that gets exposed to the internet
  • kobblestown - Monday, August 12, 2019 - link

    I fail to see why would anyone choose this instead of a Threadripper board. I bought the Asrock X399 Professional Gaming (stupid name!) one year ago for 350 UK pounds and TR 1920X for the same price. The board has 10G ethernet + plus 2 1G intel ones (plus WiFi but who uses that for real work), 8 memory slots with ECC support, two 16x and 2 8x PCIe slots plus three M.2 slots. No compromises. It even has a serial port (so you can configure Linux with serial console support and log in over that from, say, an RPi). I don't miss anything I see here.
  • ibejohn818 - Monday, August 12, 2019 - link

    Really liked Asus x99 WS boards. However, this feels like a girl with a stuffed bra and fake id... you take her home and realize you can't go all-the-way :(.
    I hope they put together an x399 WS board for TR3 release and I'm looking forward to seeing the TR3 yields and if slim yields are going to raise the prices on the top of the line sku's
  • Lord of the Bored - Monday, August 12, 2019 - link

    But without the lights, how will you know it is working?
  • The_Assimilator - Tuesday, August 13, 2019 - link

    What utter trash. No front USB 3.2, no 10GbE, only 7 rear USB ports. "Workstation" used to mean "no frills and tons of features", Asus has changed that to "has no RGB and costs double the price of better-featured boards".

Log in

Don't have an account? Sign up now