The AMD Ryzen Threadripper 1950X and 1920X Review: CPUs on Steroids
by Ian Cutress on August 10, 2017 9:00 AM ESTCPU 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.
Corona loves threads.
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.
Blender loves threads and memory bandwidth.
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.
Like Blender, LuxMark is all about the thread count. Ray tracing is very nearly a textbook case for easy multi-threaded scaling. Though it's interesting just how close the 10-core Core i9-7900X gets in the CPU (C++) test despite a significant core count disadvantage, likely due to a combination of higher IPC and clockspeeds.
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.
Similar to LuxMark, POV-Ray also wins on account of threads.
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.
Intel recently announced that its new 18-core chip scores 3200 on Cinebench R15. That would be an extra 6.7% performance over the Threadripper 1950X for 2x the cost.
Facebook
Twitter
RSS
347 Comments
View All Comments
Pekish79 - Friday, August 11, 2017 - link
Vraybench 1.0.5SanX - Friday, August 11, 2017 - link
*** AMD, make 2-chip mobos for upcoming multicore wars, you will double your profit from this at no cost for you +++vicbee - Friday, August 11, 2017 - link
Off subject: Having just read the article about nVidia's meteoric rise in profits, some of which directly attributed to high end "gamers" video cards purchased expressly for coin mining, I wonder if it and AMD are going to manufacture CPU's and GPU's specifically for that purpose and how that will affect the price of said parts...Avro Arrow - Friday, August 11, 2017 - link
Hi Ian, thanks for doing this article. It's important to see all possible outcomes because in the real world, anything is possible. I do have one question that has be puzzled. Why do you say that Threadripper only has 64 PCI-Express 3.0 lanes when it's been reported several times by everyone, including official AMD releases (and also including by you) that it has 64? I thought it might be just a typo but you state it in several places and in all of your specs. This is not a new thing so is there something about Threadripper that we don't know?HotJob - Friday, August 11, 2017 - link
Could someone explain to me what a "2P" system is from the competition section of the article?coolhardware - Saturday, August 12, 2017 - link
"2P" system = two processor system, i.e. a system with two physical CPU sockets and two CPUs installed.In the past a 2P (or 4P) system was really handy to get more cores especially back when 1 core, 2 core, and eventually 4 core CPUs were high end. In the consumer realm, way back, the Pentium II was the first 2P system I ever built and people even did it with Celerons as well:
http://www.cpu-central.com/dualceleron/
the Opterons were also fun for dual or quad processor systems including some SFF options like the ZMAX-DP socket 940 system.
https://www.newegg.com/Product/Product.aspx?Item=N...
Now fast forward with ThreadRipper already available at Amazon and NewEgg
http://amzn.to/2wDqgWw (URL shortened)
https://www.newegg.com/Product/Product.aspx?Item=N...
I do not think I will ever be building a 2P or 4P system again!!!
:-)
rvborgh - Friday, August 11, 2017 - link
hi Ian,i think the Cinebench 11.5 benchmarks are incorrect for both ThreadRippers. ThreadRipper is almost equivalent to my Quad Opteron (48 core) system which scores 3229cb on R15... and 39.04 on Cinebench 11.5. if i downclock all cores to approximately 2.9 GHz i end up with around 3000cb in R15 and in the 36 range point range for 11.5.
The fact that you are only scoring in the 18 range makes me wonder if you had the Threadripper set in some mode where it was only using 8 out of the 16 cores. Can you verify this... please? Thanks :) i would think you should see scores in the 36 range with 11.5.
Other than this minor detail... great article.
PS: i've had the same issues with software not liking NUMA on my quad opteron system as well... Cinebench especially does not like it.
Tchamber - Saturday, August 12, 2017 - link
Hi, Ian. Thanks for the review. As usual it was in depth and informative. I'm in the middle of building a 1700x system now based on your review. I wanted to say you handle all the nay-Sayers, gloomy Gusses and negative Nacies with aplomb! I think most people's own slant colors how they see your reviews. I appreciate the consistency of what you do here. I took a look over at Ars, and they could be called AMD shills for all the positive things they say... Keep it up!Tchamber - Saturday, August 12, 2017 - link
P.S.I loved your Kessel Run reference, it tied in nicely with your Yoda quote.
B3an - Saturday, August 12, 2017 - link
Too many plebs complaining about a lack of 3D rendering benches. The fact is a 16 core CPU is still much slower than GPU's at rendering. I'll be getting a 1950X but it wont even be used for rendering when i know for a fact that my two GPUs will still be much faster with things like Blender. Even a single high-end GPU will still easily beat the 1950X at these tasks.Seems like immature moron fanboys are crying over this stuff because they just want to see AMD at the top of the charts.