Low CPU utilization & Low FPS

[Dwarden 1124]

fred41 work and finding was used already to improve A3 in memory operations ... do I need add more ?

ofc the performance difference of actual default allocator, fred41 new allocator and Windows 8.1 allocator needs to be retested

as last serious tests were only w7 and I think some w2008/2012

I'm using the experimental fred41 allocator on some of my experimental servers and it does quite good job compared to ours new default

[fred41 42]

@Th4d, amazing? I wish it would be a bit more amazing :)

All numbers on arma client are measured, with Helos A3 benchmark (in a scientifically correct way) and in relation to BI's default allocator.

However, the thread related to the LP allocator is here:

http://forums.bistudio.com/showthread.php?163640-Arma3-and-the-LARGEADDRESSAWARE-flag-%28memory-allocation-gt-2GB%29

Greets,

Fred41

[Th4d 10]

fred41 work and finding was used already to improve A3 in memory operations ... do I need add more ?

Yeah that´s pretty vague and it´s hard to compare 2 unknown variables and it´s impact. But if you guys had tangible gains that we can expect to see in a future update, that´s great!

ofc the performance difference of actual default allocator, fred41 new allocator and Windows 8.1 allocator needs to be retested

as last serious tests were only w7 and I think some w2008/2012

I'm using the experimental fred41 allocator on some of my experimental servers and it does quite good job compared to ours new default

I agree, i think it would be great to see those, making statements like 9% clientsided gains under certain unknown circunstances is pretty easy, but i would love to see them in some replicatable tests. No doubt it would increase our praise for the effort.

@Th4d, amazing? I wish it would be a bit more amazing :)

All numbers on arma client are measured, with Helos A3 benchmark (in a scientifically correct way) and in relation to BI's default allocator.

However, the thread related to the LP allocator is here:

http://forums.bistudio.com/showthread.php?163640-Arma3-and-the-LARGEADDRESSAWARE-flag-%28memory-allocation-gt-2GB%29

Greets,

Fred41

Yeah i´ve been through that thread, lots of unreliable tests from users without specific parameters to be replicable, results could even be placebo with statements like "performance seems improved, client felt smooth" or "we tested it with single on server loaded = nothing in fps changed. Then a mate with low hardware tested clientside = nothing in fps changed." And tested it for myself with no real gains (i have 16gb), that´s why i expected a more reliable and standard test shown with real world results, since i consider that my perspective alone isn´t enough, after all it´s hard to account for all the variables.

9% fps gain is a big statement, so i would love to see those tests showing that, done in a scientific approach to back it up.

I´m not saying that there is no improvement in memory allocation, but i do question if this memory improvement has any influence in fps gains, and compared to what.

If you tell me how to test it to achieve those 9%, i will gladly do so. If you want me to continue this inquiry in the other thread, i shall.

Edited April 13, 2014 by Th4d

[jiltedjock 10]

6-9% more fps clientside? that´s amazing!, But now, compared to what exactly, the current default intel one, or windows 8 one? and using what tests? are they reliable and by that i mean do they vary between them? Can i see those tests? Because i would love to see 6-9% improvements on a controlled test. Because you know, without well made tests confirmed by third parties one could claim anything right?

Meanwhile, thanks for your hard work.

Wow. Just, wow.

[fred41 42]

If you want me to continue this inquiry in the other thread, i shall.

... i am really impressed, Th4d ... :rolleyes:

[windies 11]

25% more memory access speed can have very different effects to armas overall performance.

A arma client, for example, will have (dependend of used settings) probably other bottlenecks in the foreground, so that you just see maybe 6% more FPS.

With other settings (better adapted to your hardware) you can see 9% more FPS.

On arma server, the usage of large pages means most likely more increase, but it is very difficult to express the difference in numbers.

I think this is not negligible, considering it is free (not counting the hours i spend on it :) )

The reason, why i replied to your post in this thread, is that i basically hold dear the technically correctness of your posts,

and i got the impression, that the post i replied to, was an exception in respect thereof ;)

Greets,

Fred41

And that 6% increase is what I'm talking about. 6% of 30 fps is 1.8 fps which is a very very small increase, well within margin of error territory. Even 9% is 2.6 fps which again is still pretty minor. You're right in the sense it is free so it's not negligible, however my main issue with someone saying "Here use this memory allocator, you will go from 2 fps to 60 fps like magic!" still holds true.

[jiltedjock 10]

And that 6% increase is what I'm talking about. 6% of 30 fps is 1.8 fps which is a very very small increase, well within margin of error territory. Even 9% is 2.6 fps which again is still pretty minor. You're right in the sense it is free so it's not negligible, however my main issue with someone saying "Here use this memory allocator, you will go from 2 fps to 60 fps like magic!" still holds true.

Utter garbage. We all accept that changes to, say, graphics settings might mean a couple of FPS gained here, a couple gained there. They add up. What makes this less worthy of using? No one is saying you will get extraordinary gains with it. And somehow 9% is nothing just because in frame terms that is a small number? Frankly you should be embarrassed posting tosh like this in response to Fred who has actually contributed something.

[Th4d 10]

... i am really impressed, Th4d ... :rolleyes:

I wasn´t being sarcastic or ironic, i truly questioned the fps gains you claimed because i haven´t seen them, to me isn´t 6 or 9%, its zero. Being vague or outright ignoring when people are straightforward and ask both if there is detailed replicatable evidence and as to how one could achieve that claimed clientsided fps gain, barely answering while being sarcastic is pretty much what i would expect from someone that can´t back up those claims with unbiased information, you know, proof that it isn´t bullshit.

You pointed me to your topic but seems like everyone there tests in a completely different manner from each other, without any sort of standands. Not to mention they don´t even take into account graphic settings, viewrange, other applications in the background such as antivirus. A lot of things could affect performance, especially if one is using a hard disk drive. So no, no test mentioned there comes close to being done in a scientific manner. My bet is that you throw around this 9% fps gain because someone on that topic said so without providing any evidence for it, which to me is unbelievable.

Maybe i should simply add -maxmem 16000 or other placebos to pile up with it so i can feel the game being "smoother" ? /s

Somehow this discussion reminds me of this:

Edited April 14, 2014 by Th4d

[windies 11]

Utter garbage. We all accept that changes to, say, graphics settings might mean a couple of FPS gained here, a couple gained there. They add up. What makes this less worthy of using? No one is saying you will get extraordinary gains with it. And somehow 9% is nothing just because in frame terms that is a small number? Frankly you should be embarrassed posting tosh like this in response to Fred who has actually contributed something.

Did I say somewhere that what he is doing is fruitless or unimportant? I praised him for caring enough to even be doing it in the first place and basically said that is what we need to begin with both from BI as well as 3rd parties. Read what I said about people touting the one fix magic like it somehow completely fixes the game.

My main issue is with people touting one fix as a catch all for the plethora of problems plaguing the engine, like as Th4d pointed out silly things like setting -maxmem=16000 or other various placebo and voodoo tricks that do absolutely nothing, and then instigating against those who point out that it's either negligible at best by itself as a solution or it's complete BS and doesn't work period. A lot of the problems only BI can fix through architectural changes to the engine itself. Doesn't mean that I think a small fix here or there isn't important or do I think it means that small changes and performance improvements don't add up, but it doesn't mean that it saves BI from the work they need or should be doing to their engine to fix issue's or that people should enabling the behavior by stating such ridiculous and silly claims about "tweaks" when in reality they offer little to no advantage. In the case of Fred's memory allocator it offers a slight performance increase but by itself it's not a magical fix all by itself either.

[MavericK96 0]

Meanwhile, this discussion about memory allocation, while interesting and potentially relevant to performance gains, has little to do with CPU/GPU utilization I am guessing.

[TheBigOne_014 16]

Yeap,... it nothing related to GPU/CPU! I's more into HDD/SDD to RAM transfer, it caches files faster so you gain more FPS, little improvment but it's an improvment!

---------- Post added at 11:01 AM ---------- Previous post was at 10:37 AM ----------

by stating such ridiculous and silly claims about "tweaks" when in reality they offer little to no advantage. In the case of Fred's memory allocator it offers a slight performance increase but by itself it's not a magical fix all by itself either.

Don't take this as a personal atack (it isn't) but is it me or are you contradicting yourself? If it improves performance then it's a TWEAK! ;)

The maxMem parameter it's not a placebo! If used with Fred41 memory allocator it further improves it! maxMem tell's arma to use 2047Mb of ram, if the parameter it's no inserted it will only vaues between 512-1536 MB. In terms of real world performance the gain is low, but there is a gain.

The other parameter that may help is the exThread, whith this you make sure arma is using all threads available by the OS, probably it ALLEADY does the same without the parameter, and then you don't have any gain in performance.

The problem is that the majority of the info lauched on the web about this parameter is a complete mess and missleading, and has you have seen before, guys saying to put ridiculous values on maxmem and another i saw on youtube it was about the exThreads = to extra cpu's, lol. Players were complaining because the game crashed at start,... lol. This makes player not belive in the real use and gains of this parameters.

[jiltedjock 10]

I wasn´t being sarcastic or ironic, i truly questioned the fps gains you claimed because i haven´t seen them, to me isn´t 6 or 9%, its zero.

What test did you do? Outline it in detail then we can all try it and report back.

[windies 11]

Yeap,... it nothing related to GPU/CPU! I's more into HDD/SDD to RAM transfer, it caches files faster so you gain more FPS, little improvment but it's an improvment!

---------- Post added at 11:01 AM ---------- Previous post was at 10:37 AM ----------

Don't take this as a personal atack (it isn't) but is it me or are you contradicting yourself? If it improves performance then it's a TWEAK! ;)

The maxMem parameter it's not a placebo! If used with Fred41 memory allocator it further improves it! maxMem tell's arma to use 2047Mb of ram, if the parameter it's no inserted it will only vaues between 512-1536 MB. In terms of real world performance the gain is low, but there is a gain.

The other parameter that may help is the exThread, whith this you make sure arma is using all threads available by the OS, probably it ALLEADY does the same without the parameter, and then you don't have any gain in performance.

The problem is that the majority of the info lauched on the web about this parameter is a complete mess and missleading, and has you have seen before, guys saying to put ridiculous values on maxmem and another i saw on youtube it was about the exThreads = to extra cpu's, lol. Players were complaining because the game crashed at start,... lol. This makes player not belive in the real use and gains of this parameters.

If you wanna cherry pick statements and literally have to bold out elements of a sentence to make your point while discarding the real point behind them, you've pretty much failed really. I guess it's a case of reading what you want to see instead of what's actually there.

I have also tried Fred's memory allocator before and got almost no performance increase and actually saw a decrease in performance under certain scenario's with lots of changing objects coupled with AI in combat ironically. YMMV I guess.

[jiltedjock 10]

If you wanna cherry pick statements and literally have to bold out elements of a sentence to make your point while discarding the real point behind them, you've pretty much failed really. I guess it's a case of reading what you want to see instead of what's actually there.

I have also tried Fred's memory allocator before and got almost no performance increase and actually saw a decrease in performance under certain scenario's with lots of changing objects coupled with AI in combat ironically. YMMV I guess.

Whereas you put statements in your posts like "Here use this memory allocator, you will go from 2 fps to 60 fps like magic!". In quotes. As if someone has said it. And then you, in your eyes, thoroughly demolish this post that no-one has ever made with your "well reasoned" arguments such as 9% of 30FPS being worth less than 9% of some other FPS, because it is a smaller number.

Total waste of space, in all senses.

[TheBigOne_014 16]

@ windies

Sorry,... that doesn't work with me! I "bolded the elements" so you could see what you wrote and when you realized the mistake you made you try to excuse yourself by attacking the way i exposed your line of thinking! And even more you got so unsure what you wrote that you bury yourself even more. And i quote (not bolding this time):

In the case of Fred's memory allocator it offers a slight performance increase but by itself it's not a magical fix all by itself either.

And then you state:

I have also tried Fred's memory allocator before and got almost no performance increase and actually saw a decrease in performance under certain scenario's with lots of changing objects coupled with AI in combat ironically. YMMV I guess.

The complete oposite in every way! ;)

[Th4d 10]

What test did you do? Outline it in detail then we can all try it and report back.

I tried starting a couple of single player campaign missions (signal lost and common enemy) at certain spots comparing my fps between freds one and the -system which i simply got used to using for a long time, since i´ve read about windows 7 one being "state of the art" by that guy i posted earlier, and also creating a server with a small tdm one with a friend, making sure videosettings werent too high to make sure the video wouldn´t be the bottleneck. I know it´s somewhat vague and that´s why i asked for the replicatable reliable method he used to claim those gains, but upon going through that entire topic i saw some guy saying he had 9% fps gains and now i´m pretty sure that´s where fred got his number.

[MavericK96 0]

Actually now that I think about it, I think I've been using fred's memory allocator for awhile now. Haven't noticed any major performance gains with it, though I'd have to go back to the default allocator to be sure.

[windies 11]

@ windies

Sorry,... that doesn't work with me! I "bolded the elements" so you could see what you wrote and when you realized the mistake you made you try to excuse yourself by attacking the way i exposed your line of thinking! And even more you got so unsure what you wrote that you bury yourself even more. And i quote (not bolding this time):

And then you state:

The complete oposite in every way! ;)

I'm accepting that some people "see" a performance increase and I'm not disputing it, simply stating from my personal experience I haven't noticed any increase. Like I said, YMMV. Quit looking for some excuse to keep trying to argue and accept that it's not some "god fix" for everything and everyone should just stop bitching or complaining about their issue's. :rolleyes:

[TheBigOne_014 16]

I'll try to make a video with some benchmarks! ;) The cotton proof! ;)

[bullhorn 18]

Having the same issue here.

4-core CPU usually caps around 50% on average, the GPU won't go above 30%. :|

[jumpinghubert 48]

I'm accepting....bla bla

please.....s...u....

[windies 11]

please.....s...u....

*sigh*

Edited April 16, 2014 by Windies

[gamerpaddy 11]

Hello, i have (like many others) FPS problems. if i ask someone, how do i fix it, the common answer is: get a better pc...

Ok, now ive tried some settings.

Background informations:

im using tbbmalloc allocator (you can find by google tbbmalloc)

im running an AMD phenom 1100T @ 6x3.3ghz with watercooling to keep below 45°C,

GTX 670 (no oc),

4x4gb ddr3 1333 rams,

steam and arma on secondary SSD,

windows on primary SSD

Settings:

<depending on test, it could change>

1920x1080 (at primary montor) 60hz

arma3.cfg maxframesahead 1 and detectframesahead 1

VSync is DISABLED (even in nvidia control panel, global setting and ingame)

Turbo Core (AMD turbo stuff) is disabled

Launch parameters:

-cpuCount=6 -exThreads=7 -maxMem=8192 -maxVram=2048 -noBenchmark -noLogs -noPause -noSplash -malloc=tbbmalloc

The game is running at 30fps in singleplayer (if im not running an gamemode like Joes sandbox)

At multiplayer, its depending on how many players there are.

I got at 5-10 players 23-30fps

10-20 i got 18-23fps

above 20 its between 9 and 18fps

Ok, first i thought my pc is too slow (like everyone without clue say)

i switched the settings to LOW (it was everything on HIGH), after that the fps did not change, but the graphics was terrible.

Hmm, what about ULTRA. OK so now i switched everything to Ultra (viewdistance 3500, objects 2000), same fps as before.

Now i overclocked my CPU from 6x3.3 to 6x4ghz. the game was actually playable (25fps on 40player server), but after some time i got an bluescreen over and over again.

Back to default clock (after trying 3.8, 3.6 and 3.5ghz)

Weird, ok lets have some fun and activate Nvidia sorround, so i can play on 3 monitors.

The result was:

5760x1080@60hz vsync on, everythign on ultra, 12km viewdistance 5km object, 200m shadow. AA 8x, SMAA ultra, HDAO ultra, caustics activate blah.

Then the surprise: 20player server: 26fps WAT?

i heard that my PC is actually doing something now, CPU load was 90%, RAM was 78% and graphics 98% and the fans was audible even with headset on.

Fine, but its hard to play on that resolution, and 26fps is not the solution. its still too low.

Here are some screenshots and "screen shots"

i cant post URL's for informations like dxdiag, screenshots. so i have to use a bug to post it:

Ingame:

http://s1.directupload.net/images/140417/c9edi2y6.jpg

Outgame (captured with an camera):

http://s7.directupload.net/images/140417/vqu3xc8o.jpg

http://s14.directupload.net/images/140417/ef7culay.jpg

Well, will this be fixed soon?

Ive planned to get a i5 4670k.

but if this is going to be fixed someday, i will keep 1100T until there is a 400% better one for same price.

P.S. if someone needs more informations about my system, heres the dxdiag (x64)

http://pastebin.com/HpmzWzTc

(redirect to pastebin )

Edited April 17, 2014 by gamerpaddy

[LSD_Timewarp82 21]

Answer: not a single system can run Arma3 in this way how you dream or imagine it. It´s the engine of the game. You can buy 4 GTX Titans or whatever, the disappointing face is for free then.

[ratszo 17]

Hello, i have (like many others) FPS problems. if i ask someone, how do i fix it, the common answer is: get a better pc...

Ok, now ive tried some settings.

Background informations:

im using tbbmalloc allocator (you can find by google tbbmalloc)

im running an AMD phenom 1100T @ 6x3.3ghz with watercooling to keep below 45°C,

GTX 670 (no oc),

4x4gb ddr3 1333 rams,

steam and arma on secondary SSD,

windows on primary SSD

Settings:

<depending on test, it could change>

1920x1080 (at primary montor) 60hz

arma3.cfg maxframesahead 1 and detectframesahead 1

VSync is DISABLED (even in nvidia control panel, global setting and ingame)

Turbo Core (AMD turbo stuff) is disabled

Launch parameters:

-cpuCount=6 -exThreads=7 -maxMem=8192 -maxVram=2048 -noBenchmark -noLogs -noPause -noSplash -malloc=tbbmalloc

The game is running at 30fps in singleplayer (if im not running an gamemode like Joes sandbox)

At multiplayer, its depending on how many players there are.

I got at 5-10 players 23-30fps

10-20 i got 18-23fps

above 20 its between 9 and 18fps

Ok, first i thought my pc is too slow (like everyone without clue say)

i switched the settings to LOW (it was everything on HIGH), after that the fps did not change, but the graphics was terrible.

Hmm, what about ULTRA. OK so now i switched everything to Ultra (viewdistance 3500, objects 2000), same fps as before.

Now i overclocked my CPU from 6x3.3 to 6x4ghz. the game was actually playable (25fps on 40player server), but after some time i got an bluescreen over and over again.

Back to default clock (after trying 3.8, 3.6 and 3.5ghz)

Weird, ok lets have some fun and activate Nvidia sorround, so i can play on 3 monitors.

The result was:

5760x1080@60hz vsync on, everythign on ultra, 12km viewdistance 5km object, 200m shadow. AA 8x, SMAA ultra, HDAO ultra, caustics activate blah.

Then the surprise: 20player server: 26fps WAT?

i heard that my PC is actually doing something now, CPU load was 90%, RAM was 78% and graphics 98% and the fans was audible even with headset on.

Fine, but its hard to play on that resolution, and 26fps is not the solution. its still too low.

Here are some screenshots and "screen shots"

i cant post URL's for informations like dxdiag, screenshots. so i have to use a bug to post it:

Ingame:

http://s1.directupload.net/images/140417/c9edi2y6.jpg

Outgame (captured with an camera):

http://s7.directupload.net/images/140417/vqu3xc8o.jpg

http://s14.directupload.net/images/140417/ef7culay.jpg

Well, will this be fixed soon?

Ive planned to get a i5 4670k.

but if this is going to be fixed someday, i will keep 1100T until there is a 400% better one for same price.

P.S. if someone needs more informations about my system, heres the dxdiag (x64)

http://pastebin.com/HpmzWzTc

(redirect to pastebin )

Like you to repost this over at:

http://forums.bistudio.com/showthread.php?147391-Will-my-PC-run-Arma3-What-CPU-GPU-to-get-What-settings-What-System-Specifications/page202

This thread is for posts like,

"Answer: not a single system can run Arma3 in this way how you dream or imagine it. It´s the engine of the game. You can buy 4 GTX Titans or whatever, the disappointing face is for free then."

--a cesspool of nihilism.