Will a gtx1080ti make much perf. difference over a 1070?

Discuss anything ZDoom-related that doesn't fall into one of the other categories.

Re: Will a gtx1080ti make much perf. difference over a 1070?

Postby Jerry.C » Mon Feb 12, 2018 1:02 pm

Hypersonic wrote:I was comparing vid_maxfps 60 and vid_maxfps 200 on a 60hz display, and noticed that with vid_maxfps 60 there were subtle but noticeable stutters



For me it is the other way around: With vsync on everything is smooth as butter, as long as the map does not overtax the engine, but with uncapped frame rate it fluctuates strongly enough that it can be perceived as some slight stuttering.
Jerry.C
 
Joined: 06 Jan 2018

Re: Will a gtx1080ti make much perf. difference over a 1070?

Postby Graf Zahl » Mon Feb 12, 2018 3:08 pm

For me as well. It sounds a bit odd that a supposedly steady frame rate causes stuttering. That's normally the sign of something not working right.
User avatar
Graf Zahl
Lead GZDoom Developer
 
Joined: 19 Jul 2003
Location: Germany

Re: Will a gtx1080ti make much perf. difference over a 1070?

Postby Hypersonic » Mon Feb 12, 2018 5:17 pm

Perhaps stutter is a wrong word. It's like every few frames it 'holds then skips'. For example, say you log the travel distance at regular time intervals and you're traveling in a straight line with constant speed.
Something like 1 2 3 4 4 6 7 8 9 9 11
The velocity averages out properly, but it like stays in one spot for 2 frames, then the third frame jumps forward to make up for the hold in place. My guess is that when a new frame isn't ready it just shows the old frame again, but I have vsync off in game.

I can see this when I set vid_maxfps 60 and on Heretic in the start of e2m5 looking straight up at the high pillars while walking forward. However totally smooth with the default vid_maxfps 200.
Hypersonic
 
Joined: 14 Aug 2017

Re: Will a gtx1080ti make much perf. difference over a 1070?

Postby dpJudas » Mon Feb 12, 2018 5:39 pm

vid_maxfps 60 doesn't lock the update to the vertical sync of the monitor. If you want it to run at the monitor refresh rate, use vid_vsync 1 together with either vid_maxfps 200 or vid_maxfps 0.

You didn't mention if you run it fullscreen or windowed. If it is windowed, even with vsync off, the vsync is actually still on in Windows. The DWM presents a "screenshot" of the desktop every vsync. This image consists of the latest finished frame at the time the DWM does its composition.

If you're running it fullscreen it should be smooth with vid_maxfps 60 (only if vid_vsync is 0), but there might be CPU speed stepping in play here that makes it speed the CPU up and down between frames due to a low workload. You can try go to the power settings in Windows and force it to performance, if you want to check if that's what is happening.
dpJudas
 
 
 
Joined: 28 May 2016

Re: Will a gtx1080ti make much perf. difference over a 1070?

Postby Hypersonic » Mon Feb 12, 2018 6:02 pm

Same thing with full screen, vid_maxfps 60, vid_vsync 0. I even set minimum processor state to 100%, but it didn't change it. It's not a problem though, just setting vid_maxfps 200 solves it.

I wonder, are physics fps and input polling tied to video fps?
Hypersonic
 
Joined: 14 Aug 2017

Re: Will a gtx1080ti make much perf. difference over a 1070?

Postby Medicris » Tue Feb 13, 2018 3:01 pm

In my experience, it's a lot better to set the max FPS to something that's not exactly 60 to avoid that odd hitching you're speaking of. Try 61, 62, 59, or what I ended up using for games, 70. It helps that 70 is double 35, as explained below.

70 seems to be the best compromise between how visible the tearing is. It's a lot worse and when it's in roughly the same spot or the tear slowly and visibly moves downward, like with max 61 or 62.

The physics simulation actually runs at ~35fps at all times, but the engine interpolates these as a part of its unlocked framerate feature. Input polling is still technically 35fps in the "physics" simulation, but it accepts and displays all input inbetween those frames. As a result, whether capped or uncapped, your mouse input will feel responsive.

Edward wrote a more technical post on this, visible here: viewtopic.php?f=4&t=47296&start=15#p874957
User avatar
Medicris
 
Joined: 05 Oct 2013
Location: British Columbia

Re: Will a gtx1080ti make much perf. difference over a 1070?

Postby Hypersonic » Tue Feb 13, 2018 7:41 pm

This is strange, I can no longer reproduce it, it is now smooth at vid_maxfps 60 with vid_vsync 1 (but still jumpy with vid_vsync 0.) Even in windowed mode. Perhaps earlier another process was interfering.
Hypersonic
 
Joined: 14 Aug 2017

Re: Will a gtx1080ti make much perf. difference over a 1070?

Postby invictius » Tue Feb 20, 2018 4:39 pm

I take it that restricting the pci-e bus to 4x won't make any difference at all?
invictius
 
Joined: 03 Aug 2012

Re: Will a gtx1080ti make much perf. difference over a 1070?

Postby Rachael » Tue Feb 20, 2018 11:41 pm

As has been repeatedly stated - as long as GZDoom remains CPU-locked, it will not make a difference. It might make a difference with texture and vector point transfers when the CPU and GPU are actually communicating, but otherwise no. The card is going to be fiddling around waiting for the CPU most of the time.
User avatar
Rachael
QZDoom + Webmaster
 
Joined: 13 Jan 2004

Previous

Return to General

Who is online

Users browsing this forum: Vostyok and 1 guest