Puget Systems print logo

https://www.pugetsystems.com

Read this article at https://www.pugetsystems.com/guides/1655
Article Thumbnail

Photoshop CPU performance: AMD Threadripper 3990X 64 Core

Written on February 7, 2020 by Matt Bach
Share:

Introduction

Before we get into the meat of this article, we want to make something very clear: Photoshop is not at all a target application for AMD's new Threadripper 3990X processor. This CPU is a wonder of technology with 64 cores (which is 3.5x more cores than Intel's current X-series CPUs), but there are very few tasks in Photoshop that can take effectively utilize this many cores. In general, there is little benefit to having more than 6-8 CPU cores for Photoshop, which leads to CPUs in the $500 price range being as fast (or faster) than CPUs that are considerably more expensive.

In fact, some applications can actually see a decrease in performance with more CPU cores, which is honestly the main reason why we are doing this testing. It is very unlikely that this processor will break any Photoshop performance records, but given how ubiquitous Photoshop is in a variety of industries, it will be valuable to know whether this processor may pose issues for people who use Photoshop in more of a secondary role.

AMD Threadripper 3990X 64 Core Photoshop Review

In this article, we will be examining the performance of the AMD Threadripper 3990X 64 Core CPU in Photoshop as compared to the latest AMD Threadripper, AMD Ryzen, Intel X-series, and Intel 9th Gen processors. If you are interested in how this CPU performs in other applications, we also have several other articles for Premiere Pro, After Effects, Lightroom Classic, DaVinci Resolve, and more available on our article listing page.

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

Looking for a Photoshop Workstation?

Puget Systems offers a range of workstations that are tailor-made for your unique workflow. Our goal is to provide the most effective and reliable system possible so you can concentrate on your work and not worry about your computer.

Configure a System!

Test Setup

Listed below are the specifications of the systems we will be using 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 3rd Gen Test Platform
CPU AMD TR 3990X ($3,990)
AMD TR 3970X ($1,999)
AMD TR 3960X ($1,399)
CPU Cooler Noctua NH-U12S TR4-SP3
Motherboard Gigabyte TRX40 AORUS PRO WIFI
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 1909)
Adobe Photoshop 2020 (Ver. 21.0.2)
PugetBench for Photoshop V0.8 BETA

*All the latest drivers, OS updates, BIOS, and firmware applied as of January 20th, 2019

A few notes regarding the hardware and software used in our testing:

First, since many of the platforms we are testing support different RAM speeds depending on how many sticks you use and even whether those sticks are single or dual rank, we have decided to standardize on using four 16GB sticks of whatever the "middle" supported RAM speed is (rounding up when applicable). This means that the latest Ryzen, Threadripper, and X-series platforms are using DDR4-2933 while the Intel 9th Gen is using DDR4-2666.

The second thing to note is that we are using Noctua air coolers on all of our test platforms. We are not certain yet if this cooler will have enough capacity to keep the 3990X cool when installed in our workstations (our product qualification team is still investigating that), but in our air-conditioned Labs environment on open-air testbeds, we did not encounter any significant performance degradation with this cooler versus a beefier liquid cooler.

Lastly, there are reported issues with this processor using Windows 10 Pro due to how Windows behaves after you have 64 threads. This likely won't affect Lightroom Classic performance since it can't effectively utilize anywhere near this many cores, but we have further testing using Windows 10 Pro for Workstations planned. If you want to learn more about this, Anandtech has a terrific writeup going over the issue and the problems it causes when doing head-to-head CPU performance comparisons like this.

Benchmark Results

While our benchmark presents various scores based on the performance of each test, we also like to provide the individual results for you to examine. If there is a specific task that is a hindrance to your workflow, examining the raw results for that task is going to be much more applicable than the scores that our benchmark calculated.

Feel free to skip to the next section for our analysis of these results to get a wider view of how each CPU performs in Photoshop.

AMD Threadripper 3990X Photoshop Benchmark Results

Photoshop Benchmark Analysis

A lot is going on in the chart below, so before getting into it we wanted to provide a key regarding the color scheme.

  • Light blue = Intel 9th Gen
  • Dark blue = Intel X-10000 series
  • Light red = AMD Ryzen 3rd Gen
  • Dark red = AMD Threadripper 3rd Gen

As we mentioned at the start of this post, Photoshop does not typically use more than a handful of CPU cores which means that the "per-core" performance (determined by the Turbo clocks) is typically what determines how well a CPU will perform. And since most modern CPUs have very similar "Max Turbo" speeds, all the CPUs we tested should perform very similarly.

If we wanted to nit-pick at the results, we could declare that the AMD Threadripper 3990X is not a good choice for Photoshop since it scored lower than almost every other CPU we tested. While this certainly means we would never recommend the 3990X (or any HEDT processor for that matter) to someone building a dedicated Photoshop workstation, it also isn't going to be significantly worse than other processor options. At most, the 3990X will be ~6% slower than the fastest CPU Photoshop, and while that may be important for some users, if you using Photoshop in more of a secondary role it is unlikely to be noticeable in the real world.

In fact, one of the most interesting aspects of these results is how similar the performance lines up with the "Maximum Turbo Boost" frequency for each CPU. You can't compare raw frequency between AMD and Intel (or even between different model lines within the same brand), but the Threadripper 3990X ended up scoring about 5% lower than the 3960X/3970X, which almost exactly lines up with its 5% lower Max Turbo frequency (4.6GHz vs 4.5GHz). This also applies on the Intel side where the Core i9 10900X (which has about a 2% lower Turbo Boost 3.0 frequency than the other X-series models), performed about 2% slower than the other X-series CPUs.

Is the AMD Threadripper 3990X good for Photoshop?

While the AMD Threadripper 3990X performs just fine in Photoshop, in most cases it is not going to be an optimal choice for a Photoshop workstation. Most users will be better off with a far less expensive (yet slightly faster) CPU like the Intel Core i9 9900K or AMD Ryzen 9 3900X and spending the cost difference on more RAM, faster storage, or other upgrades that will make their system even faster. Photoshop has few ways to leverage more than a few CPU cores for most tasks, which simply means that a massive CPU like the 64-core 3990X is complete overkill.

However, that isn't to say that the 3990X won't work for Photoshop, or that it will even be noticeably slower since the performance delta between the fastest and slowest CPU we tested was only about 8%. There may be no reason to spend the money on a 3990X for Photoshop alone, but if Photoshop is just one of many applications you use (and those other applications can benefit from having 64 cores), you can at least be confident that the Threadripper 3990X will get the job done.

Keep in mind that the benchmark results in this article are strictly for Photoshop and that performance will vary widely in different applications. If your workflow includes other software packages (we have similar articles for Lightroom Classic, Premiere Pro, After Effects, DaVinci Resolve, and many others), you need to consider how the processor will perform in all those applications. Be sure to check our list of Hardware Articles to keep up to date on how all of these software packages perform with the latest CPUs.

Looking for a Photoshop Workstation?

Puget Systems offers a range of workstations that are tailor-made for your unique workflow. Our goal is to provide the most effective and reliable system possible so you can concentrate on your work and not worry about your computer.

Configure a System!

Tags: Intel 9th Gen, Intel X-series, Intel vs AMD, AMD Ryzen 3rd Gen, AMD Threadripper 2nd Gen, Intel X-10000, Photoshop, Threadripper 3990X
Neo Morpheus

CPU like the Intel Core i9 9900K or AMD Ryzen 9 3900X

Lol, as expected. Intel first.

Posted on 2020-02-07 17:28:57

Actually, according to research on the serial position effect, the items at the end of a list (although in this case it is only two items) are typically stronger for things like sales. So if anything, listing AMD second means that we are favoring AMD.

You can read about this at https://cxl.com/blog/serial... or by Googling "Serial Position Effect", but to quote a few things from that article:

“I use this effect to add at the end of the list (so bottom of the list) the main attractive item (ex. North European who prefer the South of France) because I know that the users will go to the last item and I know that they will read the first too.”

"If the decision is made right away, place the most important item last on the list (this has to do with the time of exposure part of the Serial Position Effect)"

Now, I am no psychologist, so I can't speak to the accuracy of this research, but from what I have found it either doesn't matter in context like this, or the second item is stronger for sales purposes. I'm happy to discuss this further if you want, I think things like this are really interesting!

Posted on 2020-02-07 18:10:44
Iyu

Any hope that you'll benchmark brush/painting performance in Photoshop?

A possible way to do it would be to create a complex work path and have different tools (smudge-tool, a large soft brush, a few Kyle's Brushes etc.) trace it using the "stroke path" function.
If the pah is complex and the brush and file big enough the time it takes to stroke the path will end up long enough to create a well measurable difference in performance between systems.

Posted on 2020-02-10 03:01:34

Brush performance has long been on our wish list, but we haven't come up with a way to test it. Your idea is very interesting though, and on the surface, definitely seems like it should work. I've added it to our list of improvements to try for the next version of the benchmark! Thank you for the suggestion!

Posted on 2020-02-10 17:40:43
DinoRoss

this is probably the most important metric if anyone can find a way to test it, since it is the only thing that affects realtime human performance, like ping in an online game, or frames in an first person shooter. where as all the other metrics are like running ogame constructions, and doesn't really affect the user's performance or frustration. i get really frustrated when i see my brush drags because it's either too big or the brush is too complex/dense. where as auto-render allows me to take break and drink water/use bathroom.

Posted on 2020-04-24 01:36:15
digitiliad

I strongly agree. I can wait for anything in Photoshop, except for my brush to do what it's told.

Posted on 2020-04-30 12:20:38