AMD 3990X Against Prosumer CPUs

The first set of consumers that will be interested in this processor will be those looking to upgrade into the best consumer/prosumer HEDT package available on the market. The $3990 price is a high barrier to entry, but these users and individuals can likely amortize the cost of the processor over its lifetime. To that end, we’ve selected a number of standard HEDT processors that are near in terms of price/core count, as well as putting in the 8-core 5.0 GHz Core i9-9900KS and the 28-core unlocked Xeon W-3175X.

AMD 3990X Consumer Competition
AnandTech AMD
3990X
AMD
3970X
Intel
3175X
Intel i9-
10980XE
AMD
3950X
Intel
9900KS
SEP $3990 $1999 $2999 $979 $749 $513
Cores/T 64/128 32/64 28/56 18/36 16/32 8/16
Base Freq 2900 3700 3100 3000 3500 5000
Turbo Freq 4300 4500 4300 4800 4700 5000
PCIe 4.0 x64 4.0 x64 3.0 x48 3.0 x48 4.0 x24 3.0 x16
DDR 4x 3200 4x 3200 6x 2666 4x 2933 2x 3200 2x 2666
Max DDR 512 GB 512 GB 512 GB 256 GB 128 GB 128 GB
TDP 280 W 280 W 255 W 165 W 105 W 127 W

The 3990X is beyond anything in price at this level, and even at the highest consumer cost systems, $1000 could be the difference between getting two or three GPUs in a system. There has to be big upsides here moving from the 32 core to the 64 core.

Corona 1.3 Benchmark

Corona is a classic 'more threads means more performance' benchmark, and while the 3990X doesn't quite get perfect scaling over the 32 core, it is almost there.

Blender 2.79b bmw27_cpu Benchmark

The 3990X scores new records in our Blender test, with sizeable speed-ups against the other TR3 hardware.

Agisoft Photoscan 1.3.3, Complex Test

Photoscan is a variable threaded test, and the AMD CPUs still win here, although 24 core up to 64 core all perform within about a minute of each other in this 20 minute test. Intel's best consumer hardware is a few minutes behind.

y-Cruncher 0.7.6 Multi-Thread, 250m Digits

y-cruncher is an AVX-512 accelerated test, and so Intel's 28-core with AVX-512 wins here. Interestingly the 128 cores of the 3990X get in the way here, likely the spawn time of so many threads is adding to the overall time.

AppTimer: GIMP 2.10.4

GIMP is a single threaded test designed around opening the program, and Intel's 5.0 GHz chip is the best here. the 64 core hardware isn't that bad here, although the W10 Enterprise data has the better result.

3D Particle Movement v2.1

Without any hand tuned code, between 32 core and 64 core workloads on 3DPM, there's actually a slight deficit on 64 core.

3D Particle Movement v2.1 (with AVX)

But when we crank in the hand tuned code, the AVX-512 CPUs storm ahead by a considerable margin.

DigiCortex 1.20 (32k Neuron, 1.8B Synapse)

We covered Digicortex on the last page, but it seems that the different thread groups on W10 Pro is holidng the 3990X back a lot. With SMT disabled, we score nearer 3x here.

LuxMark v3.1 C++

Luxmark is an AVX2 accelerated program, and having more cores here helps. But we see little gain from 32C to 64C.

POV-Ray 3.7.1 Benchmark

As we saw on the last page, POV-Ray preferred having SMT off for the 3990X, otherwise there's no benefit over the 32-core CPU.

AES Encoding

AES gets a slight bump over the 32 core, however not as much as the 2x price difference would have you believe.

Handbrake 1.1.0 - 1080p60 HEVC 3500 kbps Fast

As we saw on the previous page, W10 Enterprise causes our Handbrake test to go way up, but on W10 Pro then the 3990X loses ground to the 3950X.

GTX 1080: World of Tanks enCore, Average FPS

And how about a simple game test - we know 64 cores is overkill for games, so here's a CPU bount test. There's not a lot in it between the 3990X and the 3970X, but Intel's high frequency CPUs are the best here.

Verdict

There are a lot of situations where the jump from AMD's 32-core $1999 CPU, the 3970X, up to the 64-core $3990 CPU only gives the smallest tangible gain. That doesn't bode well. The benchmarks that do get the biggest gains however can get near perfect scaling, making the 3990X a fantastic upgrade. However those tests are few and far between. If these were the options, the smart money is on the 3970X, unless you can be absolutely clear that the software you run can benefit from the extra cores.

The Windows and Multithreading Problem (A Must Read) AMD 3990X Against $20k Enterprise CPUs
Comments Locked

279 Comments

View All Comments

  • tuxRoller - Saturday, February 15, 2020 - link

    Funny.

    "WINDOWS 10 ENTERPRISE for this renderer was also performing much better than WINDOWS 10 PROFESSIONAL up until hitting 128 threads."

    My question is why didn't you at least click on the link?
  • Korguz - Saturday, February 15, 2020 - link

    then something has changed, as farther up, another poster made a post, and posted the SAME link as you did, and at the time, it looks like Mr Larabel didnt use anything other then win 10pro, as Sandtitz posted in reply to another that posted the SAME link then :
    Well, that's where the Win10 Pro Enterprise/Workstations comes to play.

    Had you read this Anandtech article you'd see how much faster it is than the plain Win10Pro.

    Mr. Larabel didn't use the Enterprise version for testing. This is quite understandable since Microsoft doesn't make it clear that there is a tremendous performance boost.

    as i had read the link when jospoortvliet posted it, it didnt state that the review used anything other then win 10 pro.

    so maybe the original review was updated since then.
  • tuxRoller - Monday, February 17, 2020 - link

    I don't believe anything changed. The earlier poster linked to an older article (https://www.anandtech.com/comments/15483/amd-threa... linked to https://www.phoronix.com/scan.php?page=article&... )
  • tuxRoller - Monday, February 17, 2020 - link

    Eek, sorry, I prematurely posted:)

    The link texts are pretty much identical save "3990x" vs "2990wx".

    The last thing I wanted to mention was that Enterprise didn't perform significantly better than pro (this might be due to it having been patched).
  • tuxRoller - Monday, February 17, 2020 - link

    https://www.phoronix.com/scan.php?page=article&...

    This article was just posted and compares W10 pro & Enterprise vs a number of different distros. Again W10P ≈W10E
  • Thanny - Saturday, February 8, 2020 - link

    You don't need to reboot a Linux server to patch it.

    It's a consequence of how the file systems work. In Linux, the name and location of the file are distinct from its contents. You can unlike an open file from the directory, create a new one with the same name, and the open file will continue functioning until it's closed. You can update everything in Linux outside the kernel without rebooting (and even that with a bit of prep work).

    So you're using a weakness of Windows as an excuse for the inferior stability of Windows mattering less.
  • PeachNCream - Monday, February 10, 2020 - link

    There is some argument for an occasional restart in the case of long-lived processes that retain older, unpatched binaries in memory due to in-flight workloads. A periodic restart will address that, but in general it is absolutely true that Linux does not really require reboots in order for patches to take effect.
  • clsmithj - Thursday, February 13, 2020 - link

    Linux IS more stable and it runs my Ryzen Threadripper 2990wx much better than Windows 10 Pro for Workstation I have it dual booting to with Fedora 31.
  • baka_toroi - Friday, February 7, 2020 - link

    If you get out of your bubble you'd realize most of them. What a useless comment.
  • rrinker - Friday, February 7, 2020 - link

    Oh I dunno, our not very large consulting firm has thousands of clients who all run Windows infrastructure.... Though the #1 use of servers with > 32 cores is running VMWare hypervisor with Windows servers as guests on top of that.

Log in

Don't have an account? Sign up now