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 SingleThreadedRendering: CineBench 15 MultiThreaded

Benchmarking Performance: CPU System Tests Benchmarking Performance: CPU Web Tests
Comments Locked

140 Comments

View All Comments

  • Ian Cutress - Thursday, July 27, 2017 - link

    So one, overclocking is for a later review. Can't pass judgement on something that's not been tested. Other sites have certainly had more time (I get my chips 3-4 days after the US sites do, as I'm not in the US). This review was being written as the deadline passed, and is still being tested. It's not written it weeks in advance, with time to tooth comb and perfect every sentence. I've pulled an all-nighter to get to where it is now, even with some of the missing tests which are still being run. So when you say 'does not tell the full story', well not everything has been tested. I've made that abundantly clear several times in the review.

    Two, these chips are filling in volume at the lower end, especially in B2B where nothing is overclocked. You want me to sing the praises of a feature that we haven't had time to test for a product that's going to fill a market that won't use that feature, even though some in a different market might? If/when we get around to a pt2, I'll focus more on the enthusiast perspective. If you've read most of our CPU reviews over the past two years, most of the emphasis usually goes on out-of-the-box performance anyway.

    Third, on the very first page, in black and white, it states 'The big upswing for AMD here is going to be overclocking, and potentially push the Ryzen 3 CPUs through to compete with the next one up the stack depending on stock performance.'
  • vanilla_gorilla - Thursday, July 27, 2017 - link

    Ian, first off, great review as always and thank you. Second, you should just write up a large FAQ/disclaimer for your reviews that you can just link in the article and in comment replies. The same questions and complaints come up over and over, you've got to be tired of addressing them.
  • DrKlahn - Thursday, July 27, 2017 - link

    As I said, I understand it is for a later review. I also understand that a lot of these chips will never be overclocked. I don't want you to sing the praises of anything. I want a caveat in the conclusion that this potential exists and it impacts the value proposition. History has shown us (think the initial Radeon 290 reviews) that the first impression sticks with the reader regardless of how a product fares in the future. I have zero issues with your conclusion as an out of the box evaluation and appreciate your efforts. However your conclusion should have a caveat attached to it to call attention to everything the chip offers.
  • mikato - Thursday, July 27, 2017 - link

    I think that's fair. Here's another vote.
  • Gothmoth - Thursday, July 27, 2017 - link

    just saw your reply.... and i count on that. :-)
  • Gothmoth - Thursday, July 27, 2017 - link

    i hope anandtech will test the overcloked ryzen against the locked intels.
    but then... is amd paying enough fot advertising on anandtech..... :)
  • willis936 - Thursday, July 27, 2017 - link

    There is an R7 review and now an R3 review but nothing on the most interesting segment: R5. I've seen multiple other sites say that the R5 segment is where AMD is the clear winner for all workloads. Go up or down $50 and Intel makes more sense for gaming.
  • MrCommunistGen - Thursday, July 27, 2017 - link

    http://www.anandtech.com/show/11244/the-amd-ryzen-...
  • willis936 - Thursday, July 27, 2017 - link

    I wonder why that doesn't show up when using anandtech's search feature.

    http://www.anandtech.com/SearchResults?q=R5
  • MrCommunistGen - Thursday, July 27, 2017 - link

    This article doesn't show up when you search R3, and the 1800X article doesn't show up if you search R7.

    AMD isn't actually using R3, R5, and R7 as part of their branding for Ryzen, though I guess at least some are using that shorthand. The R3/5/7 are being used for GPU branding for some generations of discrete cards and APUs.

    If you look at the top of the article underneath the author's name, you'll see what tags the article has (and thus search terms) that you could use to find it in the future. Looks like "Ryzen" or "Ryzen 3" "Ryzen 5" and "Ryzen 7" are good terms.

    On the other hand, I found the link I posted above by going to Google and typing:
    anandtech 1600x review

Log in

Don't have an account? Sign up now