Fallout 4 CPU benchmark thread(need some Zen3 and Zen4 results!)

CAT-THE-FIFTH · 25 Feb 2022 at 21:17

humbug said:
Insurgency an old game from New World Interactive, a tiny indy dev, their game scales infinitely better than this.

There are no excuses for this, its really bad and it shouldn't be blamed on DX11, there are a huge amount of DX11 games far more complex than this which don't choke the GPU on 10% CPU load.

You said it your self CAT this will not fly on consoles they will have to hire someone who knows how to code because using 10 - 20% of a consoles CPU before the performance chokes will not work, this game will not run on the PS5 or Xbox Series X at the required minimum 60Hz, not even close, be lucky to get more than 30.

Well the engine is based on Gamebryo from the late 90s and Creation Engine was first seen in the Elder Scrolls 3 and that version only used one or two cores. Basically the version of the engine in Fallout 4 actually has some degree of multi-threading added.

https://imgur.com/a/wfiYst1

Basically NPC logic is one thread,and one is a rendering thread. This benchmark is mostly measuring rendering(with some NPC load in the second test). Basically modern games use newer methods to try and reduce the amount of drawcalls. It's why in areas with tons of NPCs,and the userbuilt settlements it becomes very CPU limited as those threads can hit nearly 100% CPU limitation.

I have had the same sorts of dips at the same places in the game,at 1440p with a Xeon E3 1230 V2,Ryzen 5 2600 and Ryzen 7 3700X with a GTX960,RX470,GTX1080 and RTX3060TI!

Another game which was massively limited by its graphics rendering thread was WoW. At one point anything above a GTX1060 was apparently making the game CPU limited,but the engine has been updated to DX12 now.

humbug · 25 Feb 2022 at 21:24

I see, Makes a lot of sense, thanks CAT

CAT-THE-FIFTH · 16 Apr 2022 at 10:50

I managed to get hold of a Ryzen 7 5700X for around £185 so have now got around to testing it with the benchmark. Driver version,ENB version and RAM settings are the same as used here in results number 3:
https://forums.overclockers.co.uk/posts/35406797/

The SSD has changed from a 500GB WD SN700 to a 1.92TB Seagate Firecuda 520.

The results are an average of three runs as before. In terms of single core speeds - the Ryzen 7 3700X would hit about 4.15GHZ to 4.2GHZ at best,and the Ryzen 7 5700X is 4.65GHZ at best.

Both CPUs are in an NCase M1 with a low profile Noctua L12S CPU cooler,so probably not the best cooling either.

Corvega=69FPS(Drawcalls=11724)
Diamond City=87.67FPS(Drawcalls=8035)

Corvega is a 9.5% improvement over the Ryzen 7 3700X.
Diamond City is an 18.9% improvement over the Ryzen 7 3700X.

I will hopefully get around to reassembling my Core i5 10400F rig with a GTX960 and testing the game on that too.

KompuKare · 16 Apr 2022 at 16:16

Congrats on the 5700X at that price!
Here's the updated table with your new score:

Right behind Humbug now. On the Ryzen side, we are now just waiting for 5800X3D results, and maybe if someone has better timings than @sandys.

CAT-THE-FIFTH · 16 Apr 2022 at 18:21

KompuKare said:
Congrats on the 5700X at that price!
Here's the updated table with your new score:

Right behind Humbug now. On the Ryzen side, we are now just waiting for 5800X3D results, and maybe if someone has better timings than @sandys.

Thanks for the updated chart! The RAM is at 3600C16 like the previous highest Ryzen 7 3700X result. Any chance you can add in the Core i9 9900K results too? The Ryzen 7 5700X is at stock but a few cores seem to hold at 4.65GHZ - I did some direct time-runs of my modded Fallout 4 game and I seem to be getting similar improvements. I have yet to get all the results together.

KompuKare · 17 Apr 2022 at 16:35

Okay, another update to the leaderboard. Had to add the post# coloums as posts were getting hard to find:

LtMatt · 22 Apr 2022 at 09:16

I saw a couple of folks ask me to test this. Unfortunately I do not have this game, but hopefully someone else with a 5800X3D can test it for you.

fish · 23 Apr 2022 at 00:03

I have this game and thought i would try to add some numbers for this based on the post above

I'm not sure if this is correct, but I have followed all the instructions and have the following system

5800x3d stock
64gb 3200 cl16 ram
3080 FE undervolted to 0.875v and under clocked to 1915mhz

I got 123.4 for S2 (8064) and 94.5 for S1 (11735)

edit: enb 0.468, drivers 512.15 and win 11 64 bit

KompuKare · 23 Apr 2022 at 10:17

LtMatt said:
I saw a couple of folks ask me to test this. Unfortunately I do not have this game, but hopefully someone else with a 5800X3D can test it for you.

Thanks for posting here. While cdkeys have it for £3.50 or so, if you'd never play there's not much point!

fish said:
I have this game and thought i would try to add some numbers for this based on the post above

I'm not sure if this is correct, but I have followed all the instructions and have the following system

5800x3d stock
64gb 3200 cl16 ram
3080 FE undervolted to 0.875v and under clocked to 1915mhz

I got 123.4 for S2 (8064) and 94.5 for S1 (11735)

edit: enb 0.468, drivers 512.15 and win 11 64 bit

Right, so that puts you in position #3 just behind Rovert896r1's 12600K results (who uses those crazy memory clocks):

It also puts you way ahead of humbug's stock 5800X score:
S1: 94.5 vs 66.6, so over 141%
S2: 123.4 vs 91.0, so over 135%
Averages: 109.0 vs 78.8, so about an 138% improvement.
And 5800X3D's stock clocks (base/boost of 3.4/4.5) are a good bit below the plain old 5800X (3.8/4.7). So much so, that a stock 5700X (3.4/4.6) would probably the more accurate comparison.
Would be interesting if later someone is able to run a 5800X3D somewhat overclocked (FSP or the new AMD Curve Optimiser) and/or faster RAM speeds.

However, for an install and forget CPU, that's a really good score especially since those tuned Alder Lake scores must use a lot more power too.

CAT-THE-FIFTH · 23 Apr 2022 at 12:44

LtMatt said:
I saw a couple of folks ask me to test this. Unfortunately I do not have this game, but hopefully someone else with a 5800X3D can test it for you.

It's only a few quid from CDKeys currently!

fish said:
I have this game and thought i would try to add some numbers for this based on the post above

I'm not sure if this is correct, but I have followed all the instructions and have the following system

5800x3d stock
64gb 3200 cl16 ram
3080 FE undervolted to 0.875v and under clocked to 1915mhz

I got 123.4 for S2 (8064) and 94.5 for S1 (11735)

edit: enb 0.468, drivers 512.15 and win 11 64 bit

Thanks for going to the trouble of running the benchmark - that is nearly a 40% improvement over my Ryzen 7 5700X which is running faster RAM!

@KompuKare My system has the memory running at 3600C16 not 2666MHZ!

Robert896r1 · 23 Apr 2022 at 12:46

I got a x3d coming so will test. Maybe I can beat my own scores and lock out the podium lol

CAT-THE-FIFTH · 23 Apr 2022 at 12:51

Robert896r1 said:
I got a x3d coming so will test. Maybe I can beat my own scores and lock out the podium lol

It will be great to see your results!

KompuKare · 23 Apr 2022 at 13:04

CAT-THE-FIFTH said:
@KompuKare My system has the memory running at 3600C16 not 2666MHZ!

Ah, fixed:

Might explain why your 5700X and normal 5800X are so close.
The image you posted on the 5800X3D review thread was the one before I corrected fish's CPU cell to be Ryzen orange which makes it a bit easier to tell apart; if you want to change it, the link is: https://i.imgur.com/dT09t1p.png

Robert896r1 said:
I got a x3d coming so will test. Maybe I can beat my own scores and lock out the podium lol

Now, I guess 4166CL15 is asking too much from the Ryzen IMC but it may even be that for this test your previous extreme memory timings matter a lot less because of the 96MB cache. Will be very interested how your results compare with fish's. The beauty of 5800X3D and fish's results is that stock is easy and even my mis-matched 2x32GB 3200CL16 stuff could work.

Robert896r1 · 23 Apr 2022 at 13:08

It'll be bdie sync'd to whatever i can max it out and timings fully tightened. Maybe some bclk if it's stable enough. The sooner you ask gibbo to send me a chip, the faster i can test!

CAT-THE-FIFTH · 23 Apr 2022 at 13:54

@KompuKare Fallout 4 loves memory bandwidth - I have not tried tweaking the RAM any further with the Ryzen 7 5700X,so its quite possible I could get better timings.

KompuKare · 23 Apr 2022 at 14:23

CAT-THE-FIFTH said:
@KompuKare Fallout 4 loves memory bandwidth - I have not tried tweaking the RAM any further with the Ryzen 7 5700X,so its quite possible I could get better timings.

Wonder if the two scenes can show this somehow, say IF one was more bandwidth demanding, and IF the other was more latency.
Guess not, but I added a S1/S2 ration column:

(conditional formatting ignores Tired9's results as they the drawcalls in their results were nowhere near 11,700 and 8,000).

Unsure whether that tells us anything though?

CAT-THE-FIFTH · 23 Apr 2022 at 15:06

KompuKare said:
Wonder if the two scenes can show this somehow, say IF one was more bandwidth demanding, and IF the other was more latency.
Guess not, but I added a S1/S2 ration column:

(conditional formatting ignores Tired9's results as they the drawcalls in their results were nowhere near 11,700 and 8,000).

Unsure whether that tells us anything though?

Corvega is very drawcall heavy because you are high up in a large built-up area so is more a rendering thread test IMHO. Diamond City has a much higher NPC density.

Having said that test 1 shows the least improvement from Zen2 to Zen3.

fish · 23 Apr 2022 at 16:29

I will have a look at a memory over clock but it’s difficult as I have 4x 16 gb sticks and have to clock down to cl18 ish.I did manage to get it working before on rdr2 and saw about 3-4 fps gains on a 5600x

zero989 · 25 Apr 2022 at 00:11

Was bored so I tried it on my laptop, 11900H (24MB L3 Cache).

~4800Mhz CPU 1.23v 4.4ghz cache
16GBx2 3200MHZ C16-17-17-33-1T 1.2v Gear 2
RTX 3080 16GB Laptop GPU

S1 11711 73 FPS
S2 7945 88.1 FPS

AVG 80.5 FPS

Windows 10 21H2. Can probably get slightly higher with a fresh install of win10 as that maxes out memory performance.

AMD users should be using BGS (Bank Group Swap) Alt Mode and should also disable GDM (Gear Down Mode) in addition to optimizing subtimings.

kindle12015 · 25 Apr 2022 at 00:51

12600KF (5.125GHz, 100.5BLCK x 51, x40 ECores, x43 Ring, 2x8GB DDR4 3920MHz 15-15-15-32 Gear 1 CR1 1.55V Samsung B-Die), RTX 3080, Win11
Save1 (Corvega): 11693 - 96.8 FPS
Save2 (City): 8029 - 123.4 FPS
AVG: 110.1 FPS

https://imgur.com/aX0c027
https://imgur.com/whkNc9o

I wonder what OCed 12700K and 12900K results will be like. They should be a lot faster cause of bigger cache.