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

Intel's HEDT chips are quite good at Corona, but if we compare the 3900X to the 3950X, we still see some good scaling.

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

AMD is taking the lead in our blender test, with the 16-core chips easily going through Intel's latest 18-core hardware.

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.

In our test, we run the simple ‘Ball’ scene on both the C++ code path, 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++

Despite using Intel's Embree engine, again AMD's 16-cores easily win out against Intel's 18-core chips, at under half the cost.

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

POV-Ray ends up with AMD 16-core splitting the two Intel 18-core parts, which means we're likely to see the Intel Core i9-10980XE at the top here. It would have been interesting to see where an Intel 16-core Core-X on Cascade would end up for a direct comparison, but Intel has no new 16-core chip planned.

CPU Performance: System Tests CPU Performance: Encoding Tests


View All Comments

  • bigboxes - Friday, November 15, 2019 - link

    derp Reply
  • Alexvrb - Friday, November 15, 2019 - link

    As the review points out, it's also hard to measure burst frequency. The harder you try, the more you skew the result, too. The CPU could very well be hitting 4.7 briefly in variable workloads on the hot core... although maybe other samples hit it more often or for slightly longer periods of time. Reply
  • III-V - Thursday, November 14, 2019 - link

    For real. It's the performance that matters, not some number with zero real world meaning. Reply
  • Marlin1975 - Thursday, November 14, 2019 - link

    Wow thats a lot of CPU for not much when you compare it against the competition and how much others cost.

    I am surprised the dual channel memory does not hold it back more.
  • Foeketijn - Thursday, November 14, 2019 - link

    That's exactly what I was thinking. An incredable feat to score about double compaired with a 3700x, with twice the cores, twice the power envelope but the same memory bandwidth. What are those embedded Epyc chips (3000 series) doing with quad channel DDR4? Reply
  • brantron - Thursday, November 14, 2019 - link

    Zen 1 and Broadwell have higher memory bandwidth than Skylake-X at low thread counts.

    Broadwell D is still updated almost annually High memory bandwidth at low power is apparently somebody's thing.

  • Silma - Thursday, November 14, 2019 - link

    Based on you geomean chart, it looks like on 7nm, Intel chips would destroy AMD's, and there's a real possibility Intel's 10 nm chips will be competitive in price & superior in performance if Intel prices them to compete. Reply
  • Silma - Thursday, November 14, 2019 - link

    Anyway, congrats to AMD and thanks for heating the competition again. Reply
  • naxeem - Thursday, November 14, 2019 - link

    Intel can't really do much. They have nothing in the pipeline. Reply
  • Teckk - Thursday, November 14, 2019 - link

    Destroy is probably too strong? AMD will be on TSMCs 5 nm plus their new designs so they'll mostly be on par or in the same situation as today. Reply

Log in

Don't have an account? Sign up now