What's worse?: External FPS limiter or GPU at 100%

Everything about latency. Tips, testing methods, mouse lag, display lag, game engine lag, network lag, whole input lag chain, VSYNC OFF vs VSYNC ON, and more! Input Lag Articles on Blur Busters.
Post Reply
Leot
Posts: 5
Joined: 23 Sep 2022, 22:44

What's worse?: External FPS limiter or GPU at 100%

Post by Leot » 18 Mar 2023, 02:36

I'll start out by saying I'm aware that it's better to use an in-game FPS limiter rather than an external one in terms of input lag. I also realize that having your GPU at 100% usage also introduces input lag.

Now, let's say a game doesn't have an in-game FPS limiter nor NVidia Reflex. Which option is worse for overall input lag: Using an external FPS limiter to prevent high GPU usage, or using no FPS limiter and letting the game run at 100% GPU usage?

User avatar
jorimt
Posts: 2481
Joined: 04 Nov 2016, 10:44
Location: USA

Re: What's worse?: External FPS limiter or GPU at 100%

Post by jorimt » 18 Mar 2023, 10:57

Leot wrote:
18 Mar 2023, 02:36
A framerate limited solely by maxed GPU usage has higher latency than a framerate limited by an external FPS limiter that is preventing maxed GPU usage.
(jorimt: /jor-uhm-tee/)
Author: Blur Busters "G-SYNC 101" Series

Displays: ASUS PG27AQN, LG 48CX VR: Beyond, Quest 3, Reverb G2, Index OS: Windows 11 Pro Case: Fractal Design Torrent PSU: Seasonic PRIME TX-1000 MB: ASUS Z790 Hero CPU: Intel i9-13900k w/Noctua NH-U12A GPU: GIGABYTE RTX 4090 GAMING OC RAM: 32GB G.SKILL Trident Z5 DDR5 6400MHz CL32 SSDs: 2TB WD_BLACK SN850 (OS), 4TB WD_BLACK SN850X (Games) Keyboards: Wooting 60HE, Logitech G915 TKL Mice: Razer Viper Mini SE, Razer Viper 8kHz Sound: Creative Sound Blaster Katana V2 (speakers/amp/DAC), AFUL Performer 8 (IEMs)

masneb
Posts: 239
Joined: 15 Apr 2019, 03:04

Re: What's worse?: External FPS limiter or GPU at 100%

Post by masneb » 19 Mar 2023, 23:09

Leot wrote:
18 Mar 2023, 02:36
I'll start out by saying I'm aware that it's better to use an in-game FPS limiter rather than an external one in terms of input lag. I also realize that having your GPU at 100% usage also introduces input lag.

Now, let's say a game doesn't have an in-game FPS limiter nor NVidia Reflex. Which option is worse for overall input lag: Using an external FPS limiter to prevent high GPU usage, or using no FPS limiter and letting the game run at 100% GPU usage?
Depends on the game, most people have come to the conclusion that 100% usage is bad based on the Battlenonsense video from years ago particularly relating to Overwatch. That doesn't necessarily carry over to other games.

Also external FPS limiters are better then the one with the game, usually. Ingame > NVCPL > RTSS. And even RTSS depending on which flavor of limiter you're using will change the feel of your input.

Input lag is not the end all, be all, of consistent input. It JUST tracks the end to end delay, not what is being sent, the error in what is being sent, the validity of what is being sent, or how the game uses or chooses to interpret what is being sent. It's a very crude instrument, but it's pretty much all we have to work with right now.

FPSMaster
Posts: 185
Joined: 04 Jun 2021, 20:39

Re: What's worse?: External FPS limiter or GPU at 100%

Post by FPSMaster » 22 Mar 2023, 07:45

Most external FPS Limiters like RTSS or Driver FPS Limiters like the Nvidia Control Panel Frame Limiter don't actually Reduce the Frame Buffer Queue.
Even when the Overlay shows your GPU is below 97% Usage, the Game will still Buffer Frames which will Cause Input Lag.

IMPORTANT: Only In-Game Frame Limiters which are Built Into the Game Engine have the Abbility to Reduce the Frame Buffer-Queue in the most Efficient Way. This will Reduce your Overall System Latency.

Now Coming back to your Original Question. Your only Benefit from using a External Frame Rate Limiter would be the Flat Frame Times. This means you will get less Stutters and Smoother Gameplay.
Only Negative Effect: You will get higher Delay due to Higher Frametimes.
For Example if you get 100FPS which has 10ms of Lag. But you cap it to 60 FPS which has 16.6ms of Lag.
So, you will have 6.6ms more Lag but Smooth Gameplay, by Capping your FPS from 100 to 60.

If you don't Cap your FPS you will get more Stutters, but less Lag due to Lower Frame Times.
You have to decide whats better for you. Less Lag or Smooth Gameplay.

Now, if you Play a Game that has a Built-in Frame Limiter, you have the Abbility to cut off Minimum 20ms Lag, by decreasing FPS until you don't reach 97%-100% GPU Usage anymore. That Way you get Smooth Gameplay and Less Lag.

User avatar
jorimt
Posts: 2481
Joined: 04 Nov 2016, 10:44
Location: USA

Re: What's worse?: External FPS limiter or GPU at 100%

Post by jorimt » 22 Mar 2023, 11:32

FPSMaster wrote:
22 Mar 2023, 07:45
Most external FPS Limiters like RTSS or Driver FPS Limiters like the Nvidia Control Panel Frame Limiter don't actually Reduce the Frame Buffer Queue.
Even when the Overlay shows your GPU is below 97% Usage, the Game will still Buffer Frames which will Cause Input Lag.

IMPORTANT: Only In-Game Frame Limiters which are Built Into the Game Engine have the Abbility to Reduce the Frame Buffer-Queue in the most Efficient Way. This will Reduce your Overall System Latency.
Sources or logic behind your claim? Because this does not track with my personal experience and testing...

I.E. extra pre-rendered frame generation in GPU-bound scenarios can be prevented by both in-game and external limiters, it just that most modern external limiters will typically have 1/2 to 1 frame more latency than a typical in-game limiter in the same scenario due to not being at the engine-level, but will still have lower overall latency than uncapped at the same framerate.

In other words, reduction of pre-rendered frames in the render queue due to maxed GPU usage only requires maxed GPU usage is prevented, regardless of whether an in-game or external limiter is being used to do so, since the cause of the extra pre-rendered frames, and thus extra latency in this scenario, is solely because the CPU is being forced to wait on the GPU.

So while an in-game limiter may be at least 2 frames lower latency than uncapped in an otherwise GPU-limited scenario, an external limiter will still be at least 1 frame lower latency than uncapped in the same scenario.
(jorimt: /jor-uhm-tee/)
Author: Blur Busters "G-SYNC 101" Series

Displays: ASUS PG27AQN, LG 48CX VR: Beyond, Quest 3, Reverb G2, Index OS: Windows 11 Pro Case: Fractal Design Torrent PSU: Seasonic PRIME TX-1000 MB: ASUS Z790 Hero CPU: Intel i9-13900k w/Noctua NH-U12A GPU: GIGABYTE RTX 4090 GAMING OC RAM: 32GB G.SKILL Trident Z5 DDR5 6400MHz CL32 SSDs: 2TB WD_BLACK SN850 (OS), 4TB WD_BLACK SN850X (Games) Keyboards: Wooting 60HE, Logitech G915 TKL Mice: Razer Viper Mini SE, Razer Viper 8kHz Sound: Creative Sound Blaster Katana V2 (speakers/amp/DAC), AFUL Performer 8 (IEMs)

Traveler
Posts: 75
Joined: 20 Jan 2023, 22:06

Re: What's worse?: External FPS limiter or GPU at 100%

Post by Traveler » 24 Mar 2023, 15:36

FPSMaster wrote:
22 Mar 2023, 07:45
Now Coming back to your Original Question. Your only Benefit from using a External Frame Rate Limiter would be the Flat Frame Times. This means you will get less Stutters and Smoother Gameplay.
Only Negative Effect: You will get higher Delay due to Higher Frametimes.
For Example if you get 100FPS which has 10ms of Lag. But you cap it to 60 FPS which has 16.6ms of Lag.
So, you will have 6.6ms more Lag but Smooth Gameplay, by Capping your FPS from 100 to 60.

If you don't Cap your FPS you will get more Stutters, but less Lag due to Lower Frame Times.
You have to decide whats better for you. Less Lag or Smooth Gameplay.

Now, if you Play a Game that has a Built-in Frame Limiter, you have the Abbility to cut off Minimum 20ms Lag, by decreasing FPS until you don't reach 97%-100% GPU Usage anymore. That Way you get Smooth Gameplay and Less Lag.
I think this is the type of answer I was looking for when my uneducated ass made this thread - viewtopic.php?f=10&t=11490

Post Reply