Some mysterious effects on gameplay

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.
iceboy
Posts: 22
Joined: 04 Oct 2020, 14:22

Some mysterious effects on gameplay

Post by iceboy » 29 Jan 2021, 20:16

I've learnt a lot in this forum and improved my gameplay by magnitudes. However there are things that I didn't see discussions about and hard to explain. They also improve gameplays by a lot - I wouldn't say input lag here because I don't have measurements, but it should be a mix of things including input lag.

Single channel memory: back in 2010 in the z67/z77 times with ddr3, once a good player told me that he improved gameplay a lot by pulling off one memory stick. I thought - how could that be - and ignored. Later I tried and it was real. At the moment I believe more in science and didn't continue to play with that configuration which I regret now. Now with z170 with ddr4, the same thing happened, with both default timings and extreme timings. For single and dual channels, AIDA64 and MLC shows same latency, dual channels doubles the bandwidth, but result in much worse gameplay. I also found the sweet spot for memory frequency on 6700K is ddr4-2400. Even if ddr4-3200 has lower latency, the gameplay is worse, things feel heavy; while ddr4-2133 will make things dull.

Speedstep: while it's common to think it's best to turn off every CPU power feature, I found it's actually better to turn on speedstep. Is this due to some TDP limit?

Prefetch: turning off hardware prefetcher and adjacent line prefetch will make gameplay better. Maybe it's due to more efficient usage of the little 8MB L3 cache.

FCLK: the default 800MHz is the best. 400MHz is slow and 1GHz will make gameplay unstable. Maybe Z170 is too old here.

NVidia Powermizer: turning off is better, to make GPU run at fixed clock, although in my game the GPU usage is 0%. The graphics memory frequency has a similar sweet spot as the main memory, higher is not always better.

NVidia Power Options (in the control panel and NVInspector): Adaptive is slow, Maximum performance is dull - the hidden value "prefer consistent performance" is the best.

I'm also waiting for the 11th gen to hope to get more clues.

deama
Posts: 368
Joined: 07 Aug 2019, 12:00

Re: Some mysterious effects on gameplay

Post by deama » 29 Jan 2021, 23:24

The single memory stick thing seems interesting, you're saying that gameplay feels better by just using 1 single-channel memory stick? What if you used a single dual-channel stick?

Phoenix
Posts: 4
Joined: 24 Jan 2021, 20:14

Re: Some mysterious effects on gameplay

Post by Phoenix » 31 Jan 2021, 11:51

I hope it won't be true in my case, as I'm looking forward to buying 2 more RAM sticks for a quad-channel to boost my ancient PC a little...

Could you provide latency results from Intel® Memory Latency Checker v3.9 (can't post links but you can find it easily on the Intel page) dual channel vs single channel?

_Red
Posts: 3
Joined: 31 Jan 2021, 21:22

Re: Some mysterious effects on gameplay

Post by _Red » 31 Jan 2021, 21:32

Single vs Dual channel won't make a difference on input delay.
Technically it would make it worse as framerates are lower.
3200Mhz is objectively better as it has a higher bandwidth which matters the most, sounds like it's unstable.
Speedstep: while it's common to think it's best to turn off every CPU power feature, I found it's actually better to turn on speedstep. Is this due to some TDP limit?
Turning off all C-States, Power savings things in the BIOS is objectively better for input delay and DPC latency. Performance will remain the same however.
Prefetch: turning off hardware prefetcher and adjacent line prefetch will make gameplay better. Maybe it's due to more efficient usage of the little 8MB L3 cache.
Leave it on.
NVidia Powermizer: turning off is better, to make GPU run at fixed clock, although in my game the GPU usage is 0%. The graphics memory frequency has a similar sweet spot as the main memory, higher is not always better.

NVidia Power Options (in the control panel and NVInspector): Adaptive is slow, Maximum performance is dull - the hidden value "prefer consistent performance" is the best.
Yes, prefer maximum performance is the best option. Even better if you enable K-Boost or manually tune it.

Sounds like you're messing around with too much and making things potentially worse. Some things here are good, some are bad.

User avatar
n1zoo
Posts: 183
Joined: 04 Feb 2020, 06:26
Location: Lithuania

Re: Some mysterious effects on gameplay

Post by n1zoo » 01 Feb 2021, 10:11

shader cacher has some impact on hitreg. off feels better for me.
+ try to uncheck realtek ethernet in msi utility mode. feels like headshots landing more in cs

User avatar
nuggify
Posts: 116
Joined: 25 Jan 2020, 16:57

Re: Some mysterious effects on gameplay

Post by nuggify » 01 Feb 2021, 16:07

blackmagic wrote:
01 Feb 2021, 11:48

the question is only now...for how long it stays like that and when it degrades again ? xD

but that give me sadly no advantage in online gaming...all still same bad like before.
At least you are awake about the fact that it helps temporarily before it degrades. Tons of people go in circles, coming up with new tweaks everyday- insistent that it everyday they are "fixing their input lag". Its downright sad.

Eonds
Posts: 262
Joined: 29 Oct 2020, 10:34

Re: Some mysterious effects on gameplay

Post by Eonds » 02 Feb 2021, 07:19

Get better equipment
Last edited by Eonds on 31 May 2021, 21:56, edited 1 time in total.

User avatar
Chief Blur Buster
Site Admin
Posts: 11647
Joined: 05 Dec 2013, 15:44
Location: Toronto / Hamilton, Ontario, Canada
Contact:

Re: Some mysterious effects on gameplay

Post by Chief Blur Buster » 02 Feb 2021, 21:59

Eonds wrote:
02 Feb 2021, 07:19
I'm fucking malding that my reply didn't even post. Before you go switching
Can you please send me a PM to explain what happened?

The 1st and 2nd posts of all new forum members go in a Moderator Queue, for anti-spam protections. Once a new forum member has passed a few posts (usually approximately 5 posts) they are automatically able to post immediately.

Yes, we realize the Moderator Queue message is not easy to read -- we'll get that fixed so it's clearer. Apologies.
Head of Blur Busters - BlurBusters.com | TestUFO.com | Follow @BlurBusters on Twitter

Image
Forum Rules wrote:  1. Rule #1: Be Nice. This is published forum rule #1. Even To Newbies & People You Disagree With!
  2. Please report rule violations If you see a post that violates forum rules, then report the post.
  3. ALWAYS respect indie testers here. See how indies are bootstrapping Blur Busters research!

Eonds
Posts: 262
Joined: 29 Oct 2020, 10:34

Re: Some mysterious effects on gameplay

Post by Eonds » 02 Feb 2021, 23:37

It's all okay, the page redirected really fast and i couldn't read it. I now realize that the message has to get approved first. Thank you

iceboy
Posts: 22
Joined: 04 Oct 2020, 14:22

Re: Some mysterious effects on gameplay

Post by iceboy » 09 Apr 2021, 14:15

Update - tl;dr - I found out a big factor for difference between single vs dual memory is ... memory size

The memory kit is 2x8G and dual channel will have 16G total. I limited the memory size to 8G using "bcdedit /set truncatememory", and the gameplay starts to feel significantly snappier. This recalls me the fact that the game uses memory-mapped files to load its assets and with a large memory size there can be a lot of memory used for caching. I then limit the memory down to 4G and 2G and each step down brings a significant difference. It seems that limiting the memory to just enough can bring best performance. 2G is enough for me - this machine is only for playing this ancient game, I don't even run a web browser on it.

This also shows that memory is not free - using idle memory to cache data has a cost - it makes everything larger, page table, kernel memory pools, mm allocators, "working set", and it's not always a good idea. This can also partially explain why 32-bit system performed better (because the memory is capped at 3-4G) and enabling pagefile performed better (smaller working set). I've also seen people using ISLC to achieve similar goals and I'll try to dig down (e.g. play with RAMMap, CacheSet and tune kernel parameters) once I have time.

Edit: With memory limit to 2G, single and dual channel memory still has a difference and single channel still feels better as more precise, dual channel memory feels "bold, stronger" but tend to go out of control.

Intel 11th gen CPU is disappointing in core-to-core and memory latency.

Post Reply