Print

Please login or register.
1 Hour 1 Day 1 Week 1 Month Forever
Login with username, password and session length

[madk]

Am I the only one who doesn't have massive fps issues when playing my processor is 3.2 ghz like the op, but I never reached 20 fps even with 200 dwarfs on a 5x5 site(at 200 dwarfs its more like 40 fps). I still would like to see the code optimized so I can raise the population cap to 500.

I don't understand some of the drains on cpu people are talking about how can item count cause strain on the cpu aren't pcs basically designed to count things?

a 5x5 area is killer. I never embark on larger than a 3x3, usually a 2x2. This way, the FPS retains a very steady high speed.

[MaDeR Levap]

Answering to title: never.

Faster computers? Multithreading? Optimizations and other trulty esoteric tricks? Meh. 16x16 x 500z x 200 beards will rape any computer produced in next 50 years. And if even not, this is easily fixed by adding another 200 beards. Or 800. See? This is too easy.

In other words, this game will eat any cycle that you throw at it and then some more.

[UmbrageOfSnow]

I actually keep a fortress running until it gets to about 5 FPS (unless there is some other reason to quit, like boredom).  But I read while the fortress is running anyway, so I just check the announcements every so often, or wait until it pauses, or until I need to redesignate a bunch of tasks to get done.

[Gnoll Fortress]

Gnoll Fortress:

Interesting. There are a couple things that might possibly explain it. How much clutter do you have in your fort? What are your init options? How organized are you with the layout of your fort?

I agree that large item counts shouldn't have a big impact of framerate, as the program shouldn't have to do stuff with every single item on a frame-by-frame basis, but that doesn't mean that they won't have an impact. It could even be more subtle. If your program has more memory usage, it can lead to bad cache performance, which makes stuff slow. Speaking of which, how much RAM do you have?

Layout of the fort:
My fort has multiple passageways to make movement between places faster and booze hidden in every corner so that they never have to go far for it, a two up down stair cases make my main stairwell leading to the caverns, the workshops are on the top level with relevent stockpiles directly beneath them with more staircases so the haulers can go from workshop and step directly down and be at the stockpile.

As far as init options go I turn rent off and use cooz's tileset.

As for ram I have 4gb so that should be more than enough for anything.

Clutter? my fort is very cluttered I was interested to see if reducing it would help so I took my quantum stockpile of the years of junk my fort never needed and atom smashed it under a bridge I did go from 46 fps to 48 so there might be something to this. I have noticed from task manager that df uses 600 000kb of ram and increases as the fort gets larger, I noticed it went from 550 000kb to 600 000kb at one point while I was playing and I never understood why. It might have been due to my discovery of the first cavern.

[Niveras]

Ramps are extremely FPS friendly on the other hand. It's why the outside map, even with steep slopes and tons of ramps, doesn't cause lag. Design your fortresses with ramps instead of stairs and traffic zones and you'll see your FPS drastically improve.

Not sure what the logic is behind that proving anything. The only time the outside map is your only source of ramps or stairs is when you first embark, but a first embark is going to be fast if only because you have 7 dwarves. Not to mention no issues with caverns, manual waterfalls, stone/seeds, etc.

Edit: Grr, must learn to read entire threads before replying.

If I may be forgiven a personal plug, feel free to explore my Canyonlance map for an example of aesthetically pleasing and efficient ramp designs (link). With 7 years of history, 50 dwarves and close to 20,000 items I still get 100FPS.

Also, I'm not sure that a 3x3 with 50 dwarves running at 100 FPS is particularly noteworthy.

 I doubt I have 20,000 items (no idea how to check that besides manually tallying the lists in stocks), but my five year fort of 80 dwarves runs at 100 FPS, baring ambushes, despite my staircase stack hitting through to the first cavern layer. I even have temperature turned on and an active waterfall in my dining area (15x15 square with 4 3x3 "splash" areas); however, eventually dumps up into an aquifer, which I think is a lot more FPS-saving than my previous constructions pumping water through fortifications off the map. They also have minimal flow areas.

However, I will say I like the empty central pillar format, with quadrants being designated for the appropriate industries. Might be a little less inefficient than staircase stacks in terms of steps taken by dwarves to get around, but probably a lot easier to design than my ~16x16 cubes of industry. Will also work for caravans once wagons are back in.

[Jimmy]

My reasoning around ramp vs stairs is taken from testing I've conducted in 40d. Specifically digging a 10x10 shaft of up/down stairs 10 z levels resulted in a dramatic drop in FPS, however mining out the stairs to leave an empty space instead resolves the drop. It's fairly conclusive evidence that stacked stairs drain FPS. I've never experienced such issues with ramps however, which is logical considering they're much more restrictive than stairs for movement purposes.

[Rafal99]

It is that nearby walkable tiles result in drop not just stairs. Empty space is not walkable so it doesn't decrease FPS. It is because the pathfinder has to check these 10x10x10 = 1000 tiles for possible path when any dwarf moves nearby.

[Snap]

Empty space KILLS FPS.

I had a map that started with an empty volcano all the way down to the magma sea. Every time that the empty volcano was visible on screen my FPS would drop from ~100 to ~30 move the screen so it was no longer visible and the FPS went back up to 100. Building a floor over the entire empty space of the volcano would only stop the FPS drop for the Z-level that was floored over even though there was no access to that space (the volcano went through a cavern, but there was no access to the cavern as I also floored over the very top z-level of the volcano).

So why would having this empty volcano shaft on-screen make the FPS drop?

[Kay12]

<open source wihne>

I think releasing the source would fix most of the FPS issues quickly.

</open source wihne>

[Thief^]

This is an accurate 8-directions (+Z) distance cost function:
Min(Abs(X),Abs(Y))*diagcost + Abs(Abs(X)-Abs(Y))*linearcost + Z*Zcost
The crazy Abs(Abs(X)-Abs(Y)) term can also be expressed as (Max(Abs(X),Abs(Y)) - Min(Abs(X),Abs(Y))) if you find that easier to understand.

[Jimmy]

<open source wihne>

I think releasing the source would fix most of the FPS issues quickly.

</open source wihne>

You're not alone in this dream, my friend. Still, I'm hoping that since improved pathfinding is number 3 in the Eternal Suggestions, we'll see marked improvements once that's addressed.

[fanatic]

<open source wihne>

I think releasing the source would fix most of the FPS issues quickly.

</open source wihne>

Seconded. But who cares?

I'm hoping that since improved pathfinding is number 3 in the Eternal Suggestions, we'll see marked improvements once that's addressed.

Hope - is a stupid feeling

[Jimmy]

<open source wihne>

I think releasing the source would fix most of the FPS issues quickly.

</open source wihne>

Seconded. But who cares?

I'm hoping that since improved pathfinding is number 3 in the Eternal Suggestions, we'll see marked improvements once that's addressed.

Hope - is a stupid feeling

Regarding the two of the top ten ESV items not specifically addressed on the new page, sped-up pathfinding and graphics support, the idea with the first is an upcoming date with the linux profiler now that we've got DF running over there to address the low-hanging fruit on the main grievance behind the suggestion (large, slow forts).

Ha!

[Dorten]

I didn't read the  thread, so may repeat someone else.

As computers will raise in power, DF will raise in complexity. And quantum computers of 50-years-in-the-future will melt calculating chemical reactions in meat being marinaded for some *meat roast*. That's my opinion.

[Kay12]

I didn't read the  thread, so may repeat someone else.

As computers will raise in power, DF will raise in complexity. And quantum computers of 50-years-in-the-future will melt calculating chemical reactions in meat being marinaded for some *meat roast*. That's my opinion.

This is unlikely, because according to Moore's law, computers become exponentially better, but there always will be a small number of people involved in the development (and increasing the complexity while at it) unless the source is released or the devteam starts growning otherwise.