Puget Systems print logo
Read this article at https://www.pugetsystems.com/guides/1622
Article Thumbnail

Cinema 4D CPU Rendering Performance: Intel Core X-10000 vs AMD Threadripper 3rd Gen

Written on November 25, 2019 by William George


For years, choosing between Intel and AMD processors has been relatively straight forward. Intel held a strong lead in per-core performance, and combined with a moderate number of cores, that gave their processors an edge in lightly to moderately threaded applications. AMD excelled in pure core count, making them great for heavily threaded workloads, but with lower per-core performance and architectural design limitations that led to poor results in some situations. This changed quite a bit on the consumer side when AMD launched their 3rd gen Ryzen CPUs, but still held true when it came to the HEDT (High End Desktop) processors from both brands.

Now, both Intel and AMD are launching new HEDT processors that have the potential to shake things up dramatically!

On Intel's side, the new Core X-10000 series processors are only slightly faster than the previous generation - but Intel has cut their prices nearly in half. For example, while the MSRP of the Core i9 9980XE was $1,979 the new Core i9 10980XE is just $979.

On AMD's side, the new Threadripper 3rd Gen CPUs are actually a little more expensive than earlier models (by $100-200) but their raw performance is expected to be quite a bit better. The gains are not in core count, though, but rather in clock speed, performance per core, and architectural improvements that eliminate some bottlenecks that the first and second-generation Threadripper CPUs had.

Intel Core X-1000 series vs AMD Threadripper 3rd Gen in Cinebench R20

For this article we are taking a look at how these new processors compare against each other, the previous generation they are replacing, and their mainstream desktop counterparts. The focus is on CPU-based rendering performance in Cinema 4D, so we are using Maxon's free Cinebench R20 benchmark. More info about this tool and how we used it are available in the Benchmark Details.

If you would prefer to skip over our test setup and benchmark sections, feel free to jump straight to the Conclusion.

We also took a look at rendering in V-Ray Next in another article, for those who use that plug-in instead of the native C4D renderer.

Looking for a Cinema 4D Workstation?

Puget Systems offers a range of powerful and reliable systems that are tailor-made for your unique workflow.

Configure a System!

Labs Consultation Service

Our Labs team is available to provide in-depth hardware recommendations based on your workflow.

Find Out More!

Test Hardware

Here are the specifications of the different platforms we used for our testing:

AMD Ryzen Test Platform
CPU AMD Ryzen 9 3950X ($749)
AMD Ryzen 9 3900X ($499)
AMD Ryzen 7 3800X ($399)
CPU Cooler Noctua NH-U12S
Motherboard Gigabyte X570 AORUS ULTRA
RAM 4x DDR4-2933 16GB (64GB total)
Intel 9th Gen Test Platform
CPU Intel Core i9 9900K ($499)
Intel Core i7 9700K ($385)
CPU Cooler Noctua NH-U12S
Motherboard Gigabyte Z390 Designare
RAM 4x DDR4-2666 16GB (64GB total)
AMD Threadripper 2nd Gen Test Platform
CPU AMD TR 2990WX - DLM on ($1,799)
AMD TR 2970WX - DLM on ($1,299)
AMD TR 2950X ($899)
CPU Cooler Corsair Hydro Series H80i v2
Motherboard Gigabyte X399 AORUS Xtreme
RAM 4x DDR4-2666 16GB (64GB total)
Intel X-9000 Series Test Platform
CPU Intel Core i9 9980XE ($1,979)
Intel Core i9 9960X ($1,684)​​​​​​​
Intel Core i9 9940X ($1,387)​​​​​​​
Intel Core i9 9920X ($1,189)​​​​​​​
Intel Core i9 9900X ($989)​​​​​​​
CPU Cooler Noctua NH-U12DX i4
Motherboard Gigabyte X299 Designare EX
RAM 4x DDR4-2666 16GB (64GB total)
AMD Threadripper 3rd Gen Test Platform
CPU AMD TR 3970X ($1,999)
AMD TR 3960X ($1,399)
CPU Cooler Corsair Hydro Series H80i v2
Motherboard Gigabyte TRX40 AORUS Xtreme
RAM 4x DDR4-2933 16GB (64GB total)
Intel X-10000 Series Test Platform
CPU Intel Core i9 10980XE ($979)
Intel Core i9 10940X ($784)
Intel Core i9 10920X ($689)​​​​​​​​​​​​​​
Intel Core i9 10900X ($590)​​​​​​​​​​​​​​
CPU Cooler Noctua NH-U12DX i4
Motherboard Gigabyte X299 Designare EX
RAM 4x DDR4-2933 16GB (64GB total)
Shared Hardware/Software
Video Card NVIDIA GeForce RTX 2080 Ti 11GB
Hard Drive Samsung 960 Pro 1TB
Software Windows 10 Pro 64-bit (version 1903)
Cinebench R20

A quick note about memory specifications: the latest CPUs from AMD and Intel support varying speeds of RAM depending on how many modules are installed. In past articles we've sometimes tested at multiple speeds, but to help keep things more uniform going forward we are standardizing on the speed that each processor/platform supports when all memory slots are used (even if we aren't filling them completely for our testing). Along with using the same total RAM capacity, that should help to keep results fair and consistent.

Benchmark Details

As previously mentioned, we used Maxon's Cinebench R20 utility for this comparison. It renders a scene using Cinema 4D's built-in engine, fully utilizing all cores until the render is completed. Based on how long that takes, an artificial "CB score" is assigned - with higher scores being better, and representing shorter render times. There is also a single-core mode available, performing the same task with just one active thread, but that is not really indicative of real-world performance so we did not include it in our test runs.

Benchmark Results

There is a lot going on in the chart below, so before getting into it here is a reference key for the color scheme:

  • Light blue = Intel consumer CPUs (9th Gen Core series)
  • Dark blue = Intel HEDT CPUs (X-9000 series)
  • Dark blue with glow - NEW Intel HEDT CPUs (X-10000 series)
  • Light red = AMD consumer CPUs (Ryzen 3rd Gen)
  • Dark red = AMD HEDT CPUs (Threadripper 2nd Gen)
  • Dark red with glow - NEW AMD HEDT CPUs (Threadripper 3rd Gen)

AMD 3rd Gen Threadripper vs Intel Core X-10000 Series in Cinebench R20


Intel's new Core X processors range from 5 to 10% faster than the previous generation, while also being half the price.

That alone would be great news for Cinema 4D users, but because of the dual product launch happening it is overshadowed by AMD's new Threadripper. The new Threadripper processors are around 50% faster than their predecessors, and the top-end 3970X is almost twice the speed of Intel's top-end Core i9 10980XE. Its price is also twice that of the Intel chip, but that is when looking at the CPU alone; a whole system with the Threadripper would still cost more, but nowhere near double.

Is Intel X Series or AMD Threadripper 3rd Gen CPUs better for Cinema 4D?

For pure rendering, AMD's new 3rd Gen Threadripper processors are by far the better choice. A lot of work in Cinema 4D is modeling and animation, though, which are more lightly-threaded. We are still working on developing benchmarks to better test that aspect of performance, but based on other tests it looks like the latest Intel and AMD CPUs should be pretty similar for that workload.

Looking for a Cinema 4D Workstation?

Puget Systems offers a range of poweful and reliable systems that are tailor-made for your unique workflow.

Configure a System!

Labs Consultation Service

Our Labs team is available to provide in-depth hardware recommendations based on your workflow.

Find Out More!
Tags: Intel 9th Gen, Intel X-series, Intel vs AMD, AMD Ryzen 3rd Gen, AMD Threadripper 2nd Gen, Intel X-10000, AMD Threadripper 3rd Gen, Threadripper, CPU, Rendering, Cinebench, Cinema4D

"but based on other tests it looks like the latest Intel and AMD CPUs should be pretty similar for that workload."

Oh well. Time to give up on you, fellas...

Posted on 2019-11-25 21:20:28

Hmm? I'm not sure I understand what you are saying :/

For very, very lightly threaded performance (like 1-2 threads) AMD and Intel are pretty much on par now... which is great news, since up until Ryzen 3rd Gen this summer it had been Intel in a clear lead for years.

Now, you can get great single-threaded performance with both manufacturers - and better multi-threaded performance with AMD at most price points.

Posted on 2019-11-25 21:32:38

Please dont tell me that you have costumers looking at this bench and thinking
"hmmm..yes, i really need on of these 18-32 core monsters for my lightly threaded demands, thats what i m gonna use them for..
start one task using 1-2 cores and wait untill it has finished.."
Also, there is a thing called starting multiple instances of a task, how does the single-threaded performance be on par there?
Thats possible with Cinema4d, but not only, if i m not wrong.

Posted on 2019-11-25 23:27:15

I think it is mostly mixed-workloads where it matters, which is incredibly common. C4D is actually a prime example since you have the rendering side of things (which is highly threaded), and the modeling side (which is primarily single threaded). If the box is just going to be rendering 24/7 then single threaded performance is really only a factor when it comes to actually loading the scene data in preparation for the render, so it isn't a significant factor. But, at least as our customers go, most people want to use their system for multiple things so it needs to have some amount of versatility.

This isn't even taking into account the fact that things like launching Windows, starting applications, and a ton of the "random" stuff you do while using your computer is either single or lightly threaded. We actually had a number of customers return 2nd Gen Threadripper systems because even though the performance for big jobs like rendering was terrific, many of the more "active" things they uses the system for wasn't as good as the alternatives.

We also sold a ton of Threadripper 2nd Gen that people loved because it was being used for a more dedicated task that Threadripper excelled it. It all comes down to individual needs and workflows - but what is great with these new Threadrippers is that you no longer even need to choose between single and multi-threaded workloads. They are just awesome for both.

Posted on 2019-11-25 23:34:57
Mr. Trickster

Result intel cpu looks like it was overclocked and fix in this frequency. Did frequency of mesh be high up to? And this time we aren’t know about work conditions thredripper. I mean we don’t know does amd cpu work in stock condition or it is overclocked.
In review text you wrote a few words about ram memory works, but in cinebench test ram frequency don’t influence at result. Also Very interesting to see at temperature and power consumed by all cpu. (Sorry, if my English is awful.)

Posted on 2019-11-26 03:43:31

All of the CPUs were run at stock BIOS settings. The only significant customizations made in the BIOS were in regard to the memory: on CPUs that support it (the newer AMD and Core X models) we set the RAM speed to 2933 with CL21 timings.

I didn't track power consumption or temperatures, as the focus here was on performance. When our product team tests and qualifies hardware components for use in our workstations they pay attention to details like that, but up here in our Labs department we just make sure that cooling is sufficient for the parts to run at maximum performance :)

Posted on 2019-11-26 17:09:54
Mr. Trickster

Thank you for your attention William!

Posted on 2019-11-26 17:23:27
John Lindsay

Very concerned over your crippling of AMD ram speed in these tests. 4x 16GB Dual Rank is rated to 3200mhz on AMD ; so by artificially limiting the speed down to Intel, which is no fault of AMD, you are limiting performance of Thread Ripper and Ryzen based cpu`s. A significant problem with your testing methodology.

Posted on 2019-11-29 13:40:30

In this particular application, it doesn't look like RAM speed makes a big difference. When the Ryzen 9 3950X came out I did test with both 2666 and 3200MHz memory, but the results were only a fraction of a percent apart:


So I don't think testing with 3200MHz instead of the 2933 we used in this article would have made any difference in the charts or conclusion. Moreover, as noted in the Test Hardware section, I wanted to use the speed of memory that would allow for maxing out the RAM slots on the board (even though I wasn't planning on doing that on the Threadripper platform, in order to keep the amount of memory the same on each system). And further, 4 x Dual Rank memory is actually only rated for 2666MHz on Ryzen, or 2933MHz for 4 x Single Rank. With all the craziness about different supported speeds based on the CPU and memory configuration, I opted to just go with the middle-of-the-road 2933MHz and avoid the mess and time of testing with multiple RAM speeds :)

Posted on 2019-11-29 19:52:16
Petar J Petrovic

Out of curiosity, what would be the render time difference or generally speed increase between 10900x and 3900x. I may be old fashioned but I'm having a hard time understanding benchmarks that are not based in real world measurements. I think V-ray also went from time units to somethingsomethig/ per second (also seemingly meaning nothing in practical terms) :) There's about 1300 + points increase for R9, but...how big of a difference is that actually?

Posted on 2019-12-08 11:38:01

I generally prefer real-world performance measurements as well (either seconds to process something or else the amount of processing that can happen per second - which is what V-Ray Next's benchmark uses). I'm not 100% certain about the scoring system Cinebench uses, but I am under the impression that the increase from 5627 -> 7471 (the scores of those two processors, rounded to the nearest whole number) represents a ~33% increase in performance... or to look at it another way, a ~25% reduction in render times.

Not massive, it is true, but if your budget allows there are now CPUs which can cut render times by over ~67% compared to the 10900X (I am referring to the top-end TR 3970X). That should easily make rendering that previously took overnight happen within the space of a workday :)

Posted on 2019-12-09 18:04:12
Petar J Petrovic

Thanks, that helps. I was planning on going GPU rendering route because of price performace ratio. I figured no TR can catch up with 2x 2070 super cards (or 3) in that price range. Wanted to see if I should go for one more PCIe slot (4 for Intel) or faster CPU (amd, but only 3 gpu slots).

Posted on 2019-12-09 19:06:25
Ra Le

Would it be wise to invest in X299? I am thinking of going with a 10940x and a X299 board for 6900 local currency. With intent to overclock. However for 9100 local currency I can get a 3960x plus a TRX40 board. I am already stretching my budget but wondering if long term the 2200 difference (30%) would suit me better.

I don't really need all the cores the 3960x puts on the table, but I would benefit most from single thread performance for 4 to 8 cores.

A final word of advice or a different way of looking at things would be highly appreciated.

Posted on 2020-02-25 14:15:18

My answer to that would depend on how much time you spend rendering. If you are not doing much or any rendering, then the 10940X is going to give you great modeling performance for a lower price... but there may be other options that would be just as good, and even less expensive - like the 9900K.

However, if you ever find yourself waiting on rendering (via the normal Cinema 4D engine) then the Threadripper - even just the 3960X! - is going to be almost twice as fast as the 10940X. Something like a 90% increase in rendering speed for only a 30% increase in price seems like a great deal :)

Posted on 2020-02-25 17:44:02

Hi William, I would like to come back to the post from Ra Le. I am also in the decision whether 3960X or 10940X. Although I only do GPU-Rendering, you said that the new Threadrippers are now equivalent even in single thread performance. My i7 8700K manages about 492 pt in the C4D SingleCoreBench (not so bad), but overall I don't feel the performance is outstanding. And because I want to use 4 GPUs and 256 Gig Ram, the Z370 platform is out of question. So for these reasons alone, I have to upgrade my system. I don't just do modeling with C4D. My daily work also includes simulations, animations, Mograh, XParticles, SimCashing etc. Furthermore After Effects, ZBrush, Photoshop, MP4 Conversation, Zippen etc.
Isn't the AMD sTR40 platform with PCIe 4 ultimately the more modern and therefore (somewhat) more future-proof platform? Or would you really recommend Intel 10 ... X under these conditions?

Posted on 2020-07-07 10:54:31

If you want four GPUs (which is a bit of a different goal than Ra Le had, as I understood it) then Intel's Core X is out... and even with AMD's Threadripper, you'll be pretty limited on motherboard and chassis selection to fit that many video cards. Normally, we actually recommend going over to one of the Xeon platforms when folks want that many GPUs - as you can see if you look at our recommended systems for GPU-based rendering engines (Octane and Redshift, for example).

AMD's platform is a bit more modern than what Intel is currently offering for Xeons, and of course offers higher core count processors if you are using applications which are well threaded (a couple of those things you mentioned might be, to varying degrees, but I'm not sure). The advantage with Xeons is support for ECC Registered memory and a bit more in the way of motherboard options for quad GPU setups. I could see either of those being viable for your workload, if you are building the system for yourself and are very careful about selecting components that will give you the space you need :)

Posted on 2020-07-07 16:57:38
mike miohn

Hi William, you're right, thats there are not many mainboard-options for 4 GPU-Setups. For AMD f.e. there is the Gigabyte TR40 Aorus Xtreme (not the cheapest) or the ASRock TR40 Creator. For Intel X there are also 2 I guess. But both platforms seam to have enough PCI-Lanes (72 vers 48) Isnt't this enough for 4 GPUs? And what I don't understand, is ECC Ram really such important? What are the benefits of ECC?

Posted on 2020-07-08 10:03:57

Hmm, I guess you can get four PCI-E slots at x8 or higher speed even with the Core X processors these days... so yeah, if you can find a motherboard for that platform which has the right slot layout, then it could work. I am not familiar with any off the top of my head, but it sounds like maybe you found a couple?

As for ECC Registered memory, there are two benefits: increased reliability (thanks to the ECC side) and higher memory module capacity (thanks to the Registered aspect). If you want to go over 256GB then ECC Reg memory is pretty much a requirement right now (until non-Registered 64GB modules become widely available)... but again, since you said 256GB is where you want to be then that is doable on TR and Core X now :)

Posted on 2020-07-10 01:01:44

omg ppl are so anoying... Puget makes their test FREE and avaliable for us. I´m from Brazil and for that matter alone I can´t buy Puget machines, but over the years they have helped me so much with my multiple systems upgrade because of their FREE articles Tests and that is definetly awesome. Thanks guys, and please do not care about those butthurt haters that keep saying "this test is fixed cause blablabla" they don´t have to fix tests, they are seeling their machines with both amd and intel, grow up ppl

Posted on 2020-04-29 20:25:03