CPU Performance: Rendering Tests

Rendering is often a key target for processor workloads, lending itself to a professional environment. It comes in different formats as well, from 3D rendering through rasterization, such as games, or by ray tracing, and invokes the ability of the software to manage meshes, textures, collisions, aliasing, physics (in animations), and discarding unnecessary work. Most renderers offer CPU code paths, while a few use GPUs and select environments use FPGAs or dedicated ASICs. For big studios however, CPUs are still the hardware of choice.

All of our benchmark results can also be found in our benchmark engine, Bench.

Corona 1.3: Performance Render

An advanced performance based renderer for software such as 3ds Max and Cinema 4D, the Corona benchmark renders a generated scene as a standard under its 1.3 software version. Normally the GUI implementation of the benchmark shows the scene being built, and allows the user to upload the result as a ‘time to complete’.

We got in contact with the developer who gave us a command line version of the benchmark that does a direct output of results. Rather than reporting time, we report the average number of rays per second across six runs, as the performance scaling of a result per unit time is typically visually easier to understand.

The Corona benchmark website can be found at https://corona-renderer.com/benchmark

Corona 1.3 Benchmark

A raw multithreaded test, the eight thread CPUs here score above the quad cores without SMT. The 2500X with four cores and eight threads is on par with a six-core Intel CPU here.

Blender 2.79b: 3D Creation Suite

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.

Blender can be downloaded at https://www.blender.org/download/

Blender 2.79b bmw27_cpu Benchmark

Bender is a variable threaded test, tackling lots of parts of the system. The move from a 4C/4T AMD chip to the 4C/8T AMD chip gets a good speedup, with the jump up in threads really helping. Our results are very clearly delineated on core count then thread count.

LuxMark v3.1: LuxRender via Different Code Paths

As stated at the top, there are many different ways to process rendering data: CPU, GPU, Accelerator, and others. On top of that, there are many frameworks and APIs in which to program, depending on how the software will be used. LuxMark, a benchmark developed using the LuxRender engine, offers several different scenes and APIs.


Taken from the Linux Version of LuxMark

In our test, we run the simple ‘Ball’ scene on both the C++ and OpenCL code paths, but in CPU mode. This scene starts with a rough render and slowly improves the quality over two minutes, giving a final result in what is essentially an average ‘kilorays per second’.

LuxMark v3.1 C++LuxMark v3.1 OpenCL

POV-Ray 3.7.1: Ray Tracing

The Persistence of Vision ray tracing engine is another well-known benchmarking tool, which was in a state of relative hibernation until AMD released its Zen processors, to which suddenly both Intel and AMD were submitting code to the main branch of the open source project. For our test, we use the built-in benchmark for all-cores, called from the command line.

POV-Ray can be downloaded from http://www.povray.org/

POV-Ray 3.7.1 Benchmark

For POV-Ray, the better AVX2 performance of the Core i3 shows as it almost matches the 2500X.

CPU Performance: System Tests CPU Performance: Office Tests
POST A COMMENT

65 Comments

View All Comments

  • Smell This - Tuesday, February 12, 2019 - link

    Thanks, Yall!

    "Where possible, we will extend out testing to include faster memory modules either at the same time as the review or a later date."
    ____ _____ _____ _____ _______

    It would be sweet with some OC action, too.

    Most impressive is the jump between the AMD Ryzen 2500X/1500X and Ryzen 3 2300X/1300X --- roughly 10% +/-. Good work, AMD.

    I guess this is the difference between Zen and Zen+. With 7nm Zen ++ arriving soon, and Zen+++ next year, the CPU times they are a changin' ...
    Reply
  • mr_yogi - Tuesday, February 12, 2019 - link

    Love the inclusion of the i5 2500K, great job. Reply
  • Valantar - Tuesday, February 12, 2019 - link

    These are both available from Norwegian retailers, though prices are ... not good. The 2500X costs as much as the 2600X, and the 2300X is barely cheaper than the 2600 (though admittedly the 2600 is _really_ cheap). Reply
  • urbanman2004 - Tuesday, February 12, 2019 - link

    Reviewing CPU's that'll never reach the mainstream open market. Smart idea Anandtech 😉 Reply
  • mikato - Thursday, April 4, 2019 - link

    Are you saying it doesn't count if they are sold in prebuilt systems? Reply
  • tygrus - Tuesday, February 12, 2019 - link

    AMD APUs (2400G & 2300G) try to keep atleast 50% of the power budget for GPU so the CPU load graph doesn't show the whole picture. It shows the power used for all chips for CPU load not CPU+GPU load. While having a mixture of CPU-only & CPU+GPU chips present means you want to focus on the CPU the reader needs to be reminded that the CPU+GPU load will be higher.

    I wish AMD had option for 95w TDP APU to compete with Intel models. With more CPU cores/headroom and 25% more GPU to use that 95w+ peak.
    Reply
  • azrael- - Wednesday, February 13, 2019 - link

    One reason to favor the 2300X and 2500X over the 'G' series CPUs is that Pinnacle Ridge supports ECC whereas Raven Ridge does not. Reply
  • Icehawk - Wednesday, February 13, 2019 - link

    I'm begging here - can you please, please, please show us your config settings for the HEVC encoding? You get rates that are 6x+ faster than I can achieve - my O/C'd 8700k gets ~45fps with 1080 Fast 3500 settings using all else as default in Handbrake. I'd really love to hit the #s you get with just an i5. Help! Reply
  • Ian Cutress - Friday, February 15, 2019 - link

    Check page 3?

    https://www.anandtech.com/show/13945/the-amd-ryzen...
    Reply
  • xrror - Wednesday, February 13, 2019 - link

    One additional savings for OEMs - they won't need to populate the motherboard components for integrated video on systems shipped with these.

    No need for displayport/HDMI/VGA connectors and associated filtering bits, so that saves a bit more on total BOM for the OEM.
    Reply

Log in

Don't have an account? Sign up now