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

[CAT-THE-FIFTH]

I'll do a test where i leave the cpu oc, primary timings and frequency in place but put all the secondary and tertiary timings on auto. Let's see how much impact the sub timings have on performance. Anyone want to guess?

Fallout 4 really likes RAM speed/latency - I expect the tighter sub-timings will make a difference!

3080 Ti but I doubt that test taxes any GPU, more likely be limited by Nvidias driver overhead at that res.

In the game AMD GPUs have more issues - Nvidia DX11 drivers implement a primitive form of multithreading, but the tables are turned in DX12/Vulkan.

Time for another leaderboad:

I included one of the results from the AT thread too:
https://forums.anandtech.com/thread...nce-in-fallout-4.2548618/page-4#post-40641600
That user, gamervivek, upgraded from a 5800X to 12700KF with the rest of the system staying the same.

Humbug uses a Ryzen 7 5800X.

 

[CAT-THE-FIFTH]

Copy & paste error! Let me fix it up there.

Can you add in your Core i5 results too and RX470 results too? Will be useful to put older CPUs and what type of GPU is used also into context.

I will try and see if I can get around to putting Windows on my Core i5 10400 system with a GTX960 and see how that fares!

 

[CAT-THE-FIFTH]

okay,

Just noticed the top score is on Windows 11 too!

 

[CAT-THE-FIFTH]

Same cpu oc, same primary timings and frequency but only put the subs on auto:

To me, that's a notable delta and well worth extracting the performance out of the system you already have.

It's why I tried tuning the subtimings on my system too. If you look at the Ryzen 5 3600 result with 3200CL16,my Ryzen 7 3700X was running about the same clockspeed but at 3600CL16 and they performance increase was noticeable. I also found Fallout 4 to be a good test of game stable RAM overclocks too.

Had a little go with my NAS which has a 4650G running stock which is about 4.3Ghz and has 64Gb CL22 ECC RAM @ 2933 and a 1080Ti just because I was testing GPU after a rebuild of air cooler, not stellar numbers as you might expect with less cache and slow RAM leading to poor latency ~48 and ~60 for the two scenarios

That is a noticeably drop in performance!

 

[CAT-THE-FIFTH]

To be fair have the board set in 35w mode, so it might be capped but didn't appear to be, the performance is not a million miles away from a 3600 in the table above and the 4650 is a 3600 with less cache and in my case running on slow server RAM.

The clockspeed is somewhat higher,and its mostly a lightly threaded test. But it could be the RAM,but the APUs have the memory controller on-die,so should help a bit in that regard. I suspect its a bit of the RAM and a bit of the cache.

 

[CAT-THE-FIFTH]

Here's my 9900k which is very dialed in as well:

Goes without saying, ADL absolutely crushes it with without timings tune. With tuned, it's a different level. Same mem kit btw. Just cfl has no "gears" and tops out higher.

CFL is still doing well considering its a few generations out of date now.

 

[CAT-THE-FIFTH]

@Robert896r1 Thanks again for all the effort you have been putting into testing.Fallout 4 is a game which tends to respond very well to memory tweaking.

 

[CAT-THE-FIFTH]

A lot of tests are not with older games based on un-updated engines. But based on a standard FPS test,a Core i7 6700K is slightly ahead than my Ryzen 7 3700X for example in the game.

Many are probably better optimised for Intel CPUs,but for me I wanted to see how much Zen3 improved over Zen2. In the Diamond City test which uses less drawcalls but also has more NPCs,the improvements over Zen2 are pretty decent,but Intel is better.

 

[CAT-THE-FIFTH]

I have a Core i5 10400F and a GTX960 but that box runs Linux,so could try and put Windows on it.

 

[CAT-THE-FIFTH]

Me and KompuKare really just wanted to see relative performance in this game,because its old,DX11 and never tested on newer CPUs and what sort of relative performance we would get from each option. The performance in this test is a best case scenario.I know very well a Core i7 6700K slightly outperforms my Ryzen 7 3700X in this.

This is not so much a discussion about what brand is best - both me and Kompukare have AMD CPUs when we knew Intel would be better. What we want to know is how much of an upgrade the newer CPUs are,and whether we should just wait for a new platform.

If you actually run it,especially with settlement building and the various mods,drawcalls can easily hit 20000,so the 11700 drawcall test is not too hard. It basically becomes a bit like Minecraft with an RPG/FPS bit. Mods like Sim Settlements 2 also change the game in massive ways,with its focus on settlements. My main Sanctuary Hills settlement with Sim Settlements 2 is hitting nearly 60 NPCs IIRC.

In one playthough I build a skyscraper settlement with 30 stories and 50+ NPCs. Fallout 4 and Skyrim still have a reasonable amount of players and the last reviews stopped at Zen+ and its only been the odd forum post after that.

Also,another reason - Starfield is probably going to be the last game to use the Creation Engine,and the first single player game made on Creation Engine since Zen launched(and will be on consoles).It most likely will have a build system too. It will be interesting to benchmark that too and see if the engine has gotten some Zen optimisations and optimisations for RDNA2.

 

[CAT-THE-FIFTH]

Is Starfield uses this engine it will be another Elite Dangerous Odyssey flop given it is now the game cited as the next Star Citizen.

Star Citizen is what it is because of its engine complexity which enables it to function as a fully open world with out load screens or instancing on a massive scale, a scale way beyond anything ever seen before.

Because of that its very heavy even on 32 thread CPU's, Frontier Development tried to make a Star Citizen competitor in Odyssey without that complexity and it flopped, hard, this benchmark barely even registered on my CPU, it was idle.

PS: i am, was? looking forward to Starfield.

It's not going to be that type of game IMHO. I expect its more likely to something close to The Outer Worlds but on a larger scale. So an RPG in space,with certain exploration aspects,a degree of base building,etc.
Actually WRT to the engine I got it wrong. Starfield and The Elder Scrolls 6 are using Creation Engine 2. So it could be made from the ground up to run on AMD CPUs,because of the consoles. Fallout 4/Skyrim were mostly PC titles shoehorned onto consoles.

 

[CAT-THE-FIFTH]

@Tired9 @Robert896r1 @humbug As a request any chance you can make a new thread for the other games you want to test please? I will contribute quite happily to them and try and buy the games for them too.

There is hardly any information for this game past Zen+ and the this thread is to investigate how newer hardware performs with it. The more contributions the merrier as it can even out any outlier results.

We're back to that IPC word. Instructions-per-cycle. Nice but not in any way precise as what we really want is performance while running task X which is pretty different. Let's call it ipcX. Problem is that a CPU (or maybe we should say system as memory etc. plays a huge role) which is very good at ipcX may not be as good at ipcY (that is performance while running task Y), or ipcZ.

It may be mostly single-threaded as the Process Explorer shot I posted in #12 shows one thread being far more used than the others.For some reason, the engine used for Fallout 4 (and Skyrim etc.) doesn't do that well on certain processers.

At the end of the day, this benchmark measures one thing only: the performance you get when running Fallout 4 at those GPU low settings. So ipcFO4 or even ipcFO4low. And this may not even be the same as ipcSkyrim despite being based on the same engine.

I think people are missing this,but some of us seriously want to use this thread to get a rough ballpark of performance with a game which hasn't been tested for a few years.

Yes,a game which seriously is poorly optimised. ATM,most information is very anecdotal about it.

Also,TBF the Zen3 results are not that bad.



A tuned Ryzen 9 5950X with an RTX3080TI isn't that much slower than a similar clockspeed Core i5 12600K with the same memory and a marginally RTX3080 - about 12% slower overall. The Ryzen 9 5950X is 21% faster than my semi-tuned Ryzen 7 3700X. I pushed the RAM as much as I could - if anything I could get away with better memory settings but Fallout 4 would throw up errors.

@humbug Also comments about the Core i9 9900K. It's also close to the lower of the two Alderlake results at 92FPS and 113FPS,because of the extreme tuned memory at 4400MHZ and a 5.2GHZ overclock. That is a huge increase in memory performance there.

Then the performance going down to 77FPS and 101FPS when the memory is dialed back to 3600CL14,which is below the top Zen3 result(with a 5.2GHZ overclock). At least comparing to the top Zen3 result,it is running at a higher clockspeeds,so if you want to use "IPC" Zen3 is better than CFL.

It's also showing how memory dependent this game is which itself is useful. My Ryzen 7 3700X is running 3600MHZ RAM at CL16-19-20-38-60 1T timings. KompuKare has a Ryzen 5 3600 running only about 100~200MHZ slower than my Ryzen 7 3700X,and the game really only uses 6 cores AFAIK,so that difference is down to the RAM timings IMHO.

It sort of confirms some information which Techspot showed a while back,but it does show tuning memory is a way to extract extra performance in games.

 

[CAT-THE-FIFTH]

Zen 3 @ 4.85Ghz, 3800MT/s CL16: 86 FPS (100%)
ADL @ 5.0Ghz, 3800MT/s CL16: 96 FPS (111%)
ADL @ 5.3Ghz, 4166MT/s CL15: 113 FPS (131%)

That suggests whatever this game is doing it is limited by your memory speed.

I still don't know why you only got 66FPS in the first test on your Ryzen 7 5800X,but the second test was around 25% better than my Ryzen 7 3700X. I suspect if you fiddled about with your Ryzen 7 5800X you could get better scores. The slightly higher clockspeed and slightly higher IPC of ADL,is probably contributing towards that 11% extra performance,but memory tuning does help in the game.

@CAT-THE-FIFTH Memory tuning, properly, has always lead to a performance bump in games. If you just oc your cores and cache, the moment the pipeline has to wait on memory, you're going to have a performance bottleneck. The whole point of tuning mem is to speed it up and limit the waiting the cpu has to do. Unfortunately, it takes a lot of time and built up knowledge to tune mem to it's maximum potential but it's notable performance people leave at the table while often focusing in the wrong areas.

I agree - but Fallout 4 seems quite sensitive to it,why I tried my best to tune it on my Ryzen 7 3700X,but sadly I didn't end up with the best kit and I am stuck on a B450 motherboard(and I have a SFF system too). I could test better tuned settings but it was always this game which would bug out!

 

[CAT-THE-FIFTH]

https://kingfaris.co.uk/blog/intel-ram-oc-impact/summary my buddy did mem scaling testing a while back on cml. You can see the summary results here. Depending on the game and where the bottlenecks are, you can gain a lot but even on games where the bump in avg fps isn't as big, min fps still shows a notable gain. Games such as CS:GO, F1 2019 which can mainly run in cache naturally see the least gained.

That is a really interesting set of results. I wonder if the Ryzen 7 5800X3D with its 192MB cache will be a monster in some games,then?

@CAT-THE-FIFTH

It was a cheap 32GB kit, £90 and its not been tested by my MB vendor so XMP is running in a safe mode, normally its 18-21-21 on the main timings, i have set those to 16-18-18 (which is what XMP should be) i have not gone in to sub timings which no doubt are also excessively lose.

I can't be #### to tune it, altho i probably should, normally i don't think it makes much difference, i do play high FPS games as most of the games i play tend to be older and with a 2070 Super the frame rates blow out to many 100's and don't seem to bottleneck the GPU, those frame rates are also a lot higher than they were with the 3600.

I have also tested it against other Zen 3 CPU's and while mine is not the fastest Zen 3 its also not lagging much behind, so again i don't feel like my crap memory matters much.

I tuned mine specifically because of prior experience with the game,but took a bet on getting B-die,but got Hynix CJR instead. My results are also for a SFF system running a Noctua L12S cooler in an NCase M1,so probably the CPU is running a bit hotter than it should.

I personally think Starfield should be better optimised though!

 

[CAT-THE-FIFTH]

Yes, in 2022 or 2024 or when ever Starfiled is due out a game being so heavily bottlenecked by a modern high performance CPU loaded at 10% would be a joke, you just can't get away with pretending its 1997 anymore.

It actually shows scaling to six cores,but just loads one or two a huge amount. Being a DX9/DX11 engine is no wonder. What the game needs is more effective load balancing which I suspect only DX12 or Vulkan has. It also ties into why some of the AMD dGPU results are not as good as Nvidia dGPUs,because of Nvidia trying to make their DX11 drivers more multi-threaded.

For cache bound games or those on the edge of being able to live in cache only, yes. For “bigger more intense” games which need mem access, not really.

If you think of mem as L4 cache it starts to make more sense of these things are related.

It will be interesting to see what games benefit the most from! I suspect it will be those of the type you describe.

To me this game has the hallmarks of an X87 instruction, an ancient and for many many years obsolete (Direct to Memory Operand) compiler.

It used to a decade ago,until they moved to SSE type instructions with the newer versions of the engine. If you think performance is not great now,it was even worse a decade ago!

Having said that the Phenom II X4 980 was the fastest AMD CPU in Skyrim for years. An FX8350 could barely match it.

 

[CAT-THE-FIFTH]

Some modders did that first, and that made such a big difference that eventually for FO4 and Skyrim SE Bethesda were embarrassed into to supporting it too!
Okay, it might have been a bit more than hitting a compiler flag but x87 instructions even when Skyrim came out was already antiquated. You'd hope for the next time they re-use this old engine they make it scale better.

GPU scaling and NPC scaling are of course not necessarily the same thing. Scaling well to many threads to get great draw call performance is one thing, scaling the AI to many threads is another.

Still disappointed that the consoles didn't come with any neural net, NPU, in their SoC designs. After all, almost all phones have some. An NPU plus a good AI framework should really be in the next gen consoles.

Skyboost! Yeah,having some network would be fantastic for running NPCs AI.

 

[CAT-THE-FIFTH]

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.

Spoiler

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.

 

[CAT-THE-FIFTH]

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.

 

[CAT-THE-FIFTH]

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.

 

[CAT-THE-FIFTH]

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!

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!