[Answered] ArmA 2 - Multicore-CPU support flawed? (only 50% CPU usage on quadcore)

[ahmedjbh 0]

Do you get the same amount of CPu usage regardless of Ai being on the map or not?

[xav 0]

I'll do some more tests when I'm back from work, will be interesting to see how big the difference between 2 and 4 cores actually is.

Have you done your tests yet?

[bluesteel 0]

Have you done your tests yet?

The test results are posted in this thread:

http://forums.bistudio.com/showthread.php?t=73663

[=Spetsnaz= 0]

can anyone tell me how well the dual core amd windsor 6000+ runs? mines OCed to 3.29ghz? some people are saying the game runs very well and others saying it runs the game like crap??

[Masterfragg 10]

If it does not need more than those 50%, why would my fps drop then? Besides, with a proper resolution (1680x1050) I get only 25-30fps in that campaign mission; even if I get around 40-50fps when I just stand around at the same spot in an empty map.

What is even more weird btw, I tried disabling 2 cores (changing affinity to only 2 cores) and that yielded extremely much lower fps (went from 50 to 30 in that case) and the CPU usage was down to 25-35%.

To sum this up, when the game has 2 cores availabe, it uses only 50-75% of those two cores. But if it gets 4 cores, it uses only 50% of all 4. Something is seriously wrong with this picture.

Truth is that Arma2 is much like Cryostatis, it is not multi-core optimized.

If you see your game using 50% of a dual core cpu and 25% of each core on a quad core then you are looking at a non-optimized game.

It really is that simple otherwise you'd see a variable rate more often.

People WILL disagree and probably flame a little but thats how simple it is. Like it or lump it, and check out a few other optimized games and you'll see.

[Yapab 10]

Have to agree.... yesterday I went from a Core2Duo E6420 @ 3.4ghz.... to a Core2Quad Q9550 @ 4ghz.

I was expecting the performance improvement to be large, after all I have:

1) 600mhz more per core x4

2) 2 extra cores

3) 8MB extra CPU cache (4 vs 12)

4) Newer Yorkfield architecture which is about 10% faster clock for clock

After testing 5 recent games I saw improvements of 60% for multi-core optimised games (more than 2 cores) and 30% for games which are dual core optimised, but do not use more than 2 cores.

With ARMA2 I saw an increase of 8%.... probably related to the 600mhz core increase.

This was quite disappointing as ARMA2 was one reason I decided to upgrade, it is the worst performing game which i want to keep playing.

So yeh... very disappointed and ARMA2 engine sure does not use more than 2 cores, it maxes one core out while the 2nd core has to wait for it.

Yapa

[Bulldogs 10]

Make sure you're starting the game with -cpucount=4 or it won't properly utilise each core.

[Yapab 10]

Make sure you're starting the game with -cpucount=4 or it won't properly utilise each core.

Yep tested with and without, no difference.

[-=seany=- 5]

-cpucount=# is only useful for emulating behaviour of less cores than you have. If you have 4 cores, the game already uses all of them automatically.

[Bulldogs 10]

-cpucount=# is only useful for emulating behaviour of less cores than you have. If you have 4 cores, the game already uses all of them automatically.

Technically that should be correct, but many people have noticed Arma 2 using 2-3 cores when running a quadcore without -cpucount=4. I'm not sure what causes the bug but it's best to try avoid it.

As a side note on performance. I get better performance with -cpucount=4 (haven't checked core usage yet) but get lower performance when I set -maxmem=2048

[Yapab 10]

The game does not use Quad core efficiently, because one core is still maxed out and the others have to wait for it.... any benefits seen from Quad core are related to your sound/graphics drivers offloading the load onto the other "free" cores.

My friend with an E8400 @ 4ghz gets the same fps that I do with a Q9550 @ 4ghz.... and he has two 8800GT in SLI, i have two GTX275 in SLI....

Yapa

[kklownboy 43]

with my setup, I get in Real game play(not the benchmarks1,2) all cores(i7,HT off) up to 96%, and when loading, or having the map up/doing some 2D interaction menu, they will drop down to 60%~ with usualy one core holding the Fort at 80%( core 3). This may be do to my GPUs( 4 of them).

[Leon86 13]

The game does not use Quad core efficiently, because one core is still maxed out and the others have to wait for it.... any benefits seen from Quad core are related to your sound/graphics drivers offloading the load onto the other "free" cores.

My friend with an E8400 @ 4ghz gets the same fps that I do with a Q9550 @ 4ghz.... and he has two 8800GT in SLI, i have two GTX275 in SLI....

Yapa

did you force v-sync off? if you went from 55 fps to 60 that doesn't say anything.

Also, I read somewhere that arma increases scene complexity if it thinks it has the rescources. so maybe you now have way more objects on screen.

If you're gonna benchmark the cpu performance for arma at least put the resolution very low and put the vsync off so your framerate is not limited at all by the videocards, I know my 8800gtx has trouble with some red trees, on 1920x1200 it slows down performance from 100+ to 30- fps regardless of any setting in video options.

I went from an e6750 @ 400x8=3200 ghz to a q6600 @ 400x7=2800 ghz and performance in cities has improved dramaticly. (stutters have almost completely gone, fps is now more or less constant, albeit maybe (3200-2800)/3200=12.5% lower, who cares, no more stutter

also, when I run benchmark mission 2, cpu use goes up to 80%.

Edited January 27, 2010 by Leon86

[SWAT_BigBear 0]

Benchmark #2, as you can see when the game is not minimized, it is in fact using all four cores close to even.

Edited January 27, 2010 by SWAT_BigBear

[Yapab 10]

Yes ofcourse I have vsync off, I have been benching and playing games since the early 90's....

@SWAT_bigbear, that is called Windows Vista/7 Load balancing, not proper quad core usage.

[Bamoon 10]

Hi guys... found out a trick today if your the owner of a quad core cpu.

Normaly we can only use half of our quad core cpu power, yes thats true, but i found out that if i made a deaticated server on my own cpu and played through that my cpu usaged was 78% instead of the 50% and it was running nice in-game with a lot more units.. Offcasue u have to ha a good quad core and som ram... but it is worth a try.. worked out for me... dont know if you guys know that but i thought i would are my discovery

Me system is:

cpu: qaud core q9650 3gh 12mb.

ram: ddr2 6gb

graphic: Nvidea g460(oc) 1gb goes like hell edition.

Edited May 1, 2011 by Bamoon

[Dwarden 1125]

already explained in http://forums.bistudio.com/showthread.php?t=100519

http://forums.bistudio.com/showpost.php?p=1797139&postcount=35

by our lead coder

ArmA 2 can use up to 31 cores in theory, but experiments have shown that with most scenes the gain above 4 cores is small and above 8 cores unmeasurable.

The explanation is Amdahl's law - only parts of the application is using all cores. See Real Virtuality Going Multicore blog.

---------- Post added at 13:58 ---------- Previous post was at 13:54 ----------

In build 76122 and newer the default for dualcores will be changed to -exThreads=3 based on user feedback.

We have also changed the cpu core detection, therefore depending on how many logical cpus are present, default -cpuCount values will be as follows:

1 1

...

6 6

7 7

8 4

9 4

10 5

11 5

12 6

13 6

14 7

....

Some day hopefully we will find a time to provide a proper HT detection, but until then I think the above provides quite reasonable default settings.

there are more details in rest of the thread