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

Being fully multithreaded, we see the order here follow core counts. That is except for the 32-core 2990WX sitting behind the 24-core 3960X, which goes to show how much extra performance is in the new TR generation.

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

We have new Threadripper records, with the 3970X almost getting to a minute to compute. Intel's nearest takes almost as long, but does only cost half as much. Again, the 3960X puts the 2990WX in its place.

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. 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++

Our LuxMark test again pushes both TR3 processors out in the lead.

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

More rendering, more wins for AMD. More losses for the 2990WX, even though on these tests it still beats the 10980XE quite easily.

Test Bed and Setup CPU Performance: System Tests
Comments Locked

245 Comments

View All Comments

  • csutcliff - Monday, November 25, 2019 - link

    RIP Intel
  • NikosD - Monday, November 25, 2019 - link

    It's a bloodpath.
    Threadrippers destroy even the Xeon W-3175X of 3000$.

    Intel is having hard times, no doubt about it.
    They look so incompetent nowadays.
  • melgross - Monday, November 25, 2019 - link

    You guys are really funny. Intel had its best year yet, and will have an even better one next year.

    While you can hope that AMD will take the industry over, it’s never going to happen. We’ve seen that predicted in the past, and it isn’t any truer now.
  • Xyler94 - Monday, November 25, 2019 - link

    The difference though, I don't think Intel can weasel their way through this storm as they did with the Athlon days.

    They didn't stay in the lead because people didn't want to buy AMD, they stayed because DELL and them were bribbed not to sell AMD, so your average consumer knew nothing about how much better the AMD platforms were.

    Intel still holds the performance crown for laptops, which is arguably the bigger segment of the consumer market, but if they don't do something soon, AMD has the performance crown in HEDT and Servers now, both high margin areas, which Intel is super worried about.
  • Santoval - Monday, November 25, 2019 - link

    Next year we will see Comet & Ice Lake based laptops compete with Zen 2 (+ Navi?) based laptops. Zen 2 based laptops will certainly surpass both in CPU performance, so the question is only if they'll be able to surpass the performance of the (Gen11) iGPU of Ice Lake. By that I mean only the parts with the 64 EUs of course, the Gen11 iGPUs with 24 and 48 EUs stand on chance.

    In any case, it appears that Comet Lake-U/Y will power the largest bulk of Intel's machines, machines with Ice Lake-U/Y will be released in low volume, and Ice Lake-U machines with 64 EU iGPUs will almost certainly be rarer than francium and more expensive than their weight in gold.
  • Santoval - Monday, November 25, 2019 - link

    edit : "stand *no* chance".
  • jabber - Tuesday, November 26, 2019 - link

    Guys, some of you may not remember but we've been in this situation before.

    There was a time that Intel was king and could do no wrong. then about 16 years ago they could not do a thing right and everyone was AMD/SKT939 till the day they died. Ho ho ho!

    Then AMD screwed up, Intel got it's act together and AMD was 'so over' etc. etc.

    No doubt AMD will screw up again in a couple of years and Intel will get it together again...

    Rinse and repeat. Just enjoy the ride.
  • xrror - Tuesday, November 26, 2019 - link

    What really sucked was seeing AMD management at the time just sit there like a sitting duck. People playing with overclocking Pentium M on desktop boards demonstrated nearly a year before Conroe launched that if Intel developed their mobile design into a desktop chip that it would be a monster chip against A64.

    And Intel did just that.

    That said, this time around... Sunny Cove had better start to scale clock wise, else it won't matter that it's 20% faster per clock if it can't actually reach 4Ghz.

    It's going to be interesting.
  • DaBones - Wednesday, November 27, 2019 - link

    A quick difference between then and now is that both companies are doing good things. Neither is releasing a dumpster fire of a product, this time around. That's just really cool, and whoever gets shiny, metal hats, I still have some pretty good hardware options!.
  • arcamdomain - Tuesday, December 17, 2019 - link

    AMD have never been this ruthless, zen has been a massive turning for all of the market, bringing the prices down and increasing performance from both sides, unfortunately for intel, AMD have the bigger arms in this arms race, TSMC and AMD are already talking about 5nm and 3nm respectively, at which point does this become a ant vs boot scenario.

Log in

Don't have an account? Sign up now