Benchmarking Performance: CPU Rendering Tests

Rendering tests are a long-time favorite of reviewers and benchmarkers, as the code used by rendering packages is usually highly optimized to squeeze every little bit of performance out. Sometimes rendering programs end up being heavily memory dependent as well - when you have that many threads flying about with a ton of data, having low latency memory can be key to everything. Here we take a few of the usual rendering packages under Windows 10, as well as a few new interesting benchmarks.

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

Corona 1.3: link

Corona is a standalone package designed to assist software like 3ds Max and Maya with photorealism via ray tracing. It's simple - shoot rays, get pixels. OK, it's more complicated than that, but the benchmark renders a fixed scene six times and offers results in terms of time and rays per second. The official benchmark tables list user submitted results in terms of time, however I feel rays per second is a better metric (in general, scores where higher is better seem to be easier to explain anyway). Corona likes to pile on the threads, so the results end up being very staggered based on thread count.

Rendering: Corona Photorealism

Blender 2.78: link

For a render that has been around for what seems like ages, Blender is still a highly popular tool. We managed to wrap up a standard workload into the February 5 nightly build of Blender and measure the time it takes to render the first frame of the scene. Being one of the bigger open source tools out there, it means both AMD and Intel work actively to help improve the codebase, for better or for worse on their own/each other's microarchitecture.

Rendering: Blender 2.78

LuxMark v3.1: Link

As a synthetic, LuxMark might come across as somewhat arbitrary as a renderer, given that it's mainly used to test GPUs, but it does offer both an OpenCL and a standard C++ mode. In this instance, aside from seeing the comparison in each coding mode for cores and IPC, we also get to see the difference in performance moving from a C++ based code-stack to an OpenCL one with a CPU as the main host.

Rendering: LuxMark CPU C++Rendering: LuxMark CPU OpenCL

POV-Ray 3.7.1b4: link

Another regular benchmark in most suites, POV-Ray is another ray-tracer but has been around for many years. It just so happens that during the run up to AMD's Ryzen launch, the code base started to get active again with developers making changes to the code and pushing out updates. Our version and benchmarking started just before that was happening, but given time we will see where the POV-Ray code ends up and adjust in due course.

Rendering: POV-Ray 3.7

Cinebench R15: link

The latest version of CineBench has also become one of those 'used everywhere' benchmarks, particularly as an indicator of single thread performance. High IPC and high frequency gives performance in ST, whereas having good scaling and many cores is where the MT test wins out.

Rendering: CineBench 15 MultiThreaded

Rendering: CineBench 15 SingleThreaded

Conclusions on Rendering: It is clear from these graphs that most rendering tools require full cores, rather than multiple threads, to get best performance. The exception is Cinebench.

Benchmarking Performance: CPU System Tests Benchmarking Performance: CPU Web Tests
POST A COMMENT

177 Comments

View All Comments

  • Gideon - Monday, February 12, 2018 - link

    BTW Octane 2.0 is retired for Google (just check their github), and even they endorse using Mozillas Speedometer 2.0 (darn can't find the relevant blog post). Reply
  • Ian Cutress - Monday, February 12, 2018 - link

    I know; in the same way we have legacy benchmarks up, some people like to look at the data.

    Not directed to you in general, but don't worry if 100% of the benchmarks aren't important to you: If there's 40 you care about, and we have 80 that include those 40, don't worry that the other 40 aren't relevant for what you want. I find it surprising how many people want 100% of the tests to be relevant to them, even if it means fewer tests. Optane was easy to script up and a minor addition, just like CB11.5 is. As time marches on, we add more.
    Reply
  • kmmatney - Monday, February 12, 2018 - link

    In this case, a few 720p gaming benchmarks would have been useful, or even 1080p at medium or low settings. Reply
  • III-V - Tuesday, February 13, 2018 - link

    Who uses 720p and is in the market for this? Reply
  • PeachNCream - Tuesday, February 13, 2018 - link

    I'm happy with 1366x768 and I'm seriously considering the 2400G because it looks like it can handle max detail settings at that resolution. I'm not interested in playing at high resolutions, but I do like having all the other non-AA eye candy turned on. Reply
  • atatassault - Tuesday, February 13, 2018 - link

    People who buy sub $100 monitors. Reply
  • WorldWithoutMadness - Tuesday, February 13, 2018 - link

    Just google GDP per capita and you'll find huge market for 720p budget gaming pc. Reply
  • Sarah Terra - Wednesday, February 14, 2018 - link

    Wow, i just came here after not visiting in ages, really sad to see how far this site has fallen.

    Ian Cutress was the worst thing that ever happened to Anandtech.

    At one point AT was the defacto standard for tech news on the web, but now it has simply become irrelevant.

    Unless things change i see AT slowly but surely dying
    Reply
  • mikato - Thursday, February 15, 2018 - link

    Me. My TV is 720p and still kicking after many years. These CPUs would make for a perfect high end HTPC with some solid gaming ability. Awesome. Reply
  • nevcairiel - Tuesday, February 13, 2018 - link

    Some more realistic gaming settings might be nice. Noone is going to play on settings that result in ~20 fps, and the GPU/CPU scaling can tilt quite a bit if you reduce the settings.

    I can see why you might not like it, because it takes the focus away from the GPU a bit and makes comparisons against a dGPU harder (unless you run it on the exact same hardware, which might mean you have to re-run it every time), but this is a combined product, so testing both against other iGPU products would be useful info.
    Reply

Log in

Don't have an account? Sign up now