Trying Out The New OpenGL Threaded Dispatch In Mesa 17.1

[gbil]

Please keep in mind that as already posted by myself and others, while fps count is lower in Feral ports, the experience is smoother. I confirmed that in Hitman and now that git fixed the crash with Tomb Raider also there. Down 50fps in the avg benchmark yet much smoother in actual gameplay.

[mitch074]

I didn't notice Tomb Raider to be smoother, but then my CPU is so much above the recommendations (any i5 recommended, mine is more than twice as fast as a 750) that it's coal to Newcastle. DE:MD seems bound somewhere, as downtown Prague is almost unplayable - except when, after having changed graphics settings several times something seems to 'unclog' and frame rate becomes much more acceptable; GL threading seems to help some, but still not as much as said 'unclogging'.

[agaman]

I have tried gl_thread using oibaf PPA.

With Deus EX and Dota activating gl_thread the performance is worse.
But with Civilization VI the performance it's better.

Seems to me that it's working as expected

http://openbenchmarking.org/result/1703197-RI-GLTHREAD226

[geearf]

Please keep in mind that as already posted by myself and others, while fps count is lower in Feral ports, the experience is smoother. I confirmed that in Hitman and now that git fixed the crash with Tomb Raider also there. Down 50fps in the avg benchmark yet much smoother in actual gameplay.

What do you think makes it smoother?
If min and avg fps are worse, I don't understand what could be better.

[mitch074]

What do you think makes it smoother?
If min and avg fps are worse, I don't understand what could be better.

A smoother gameplay usually comes from:
* much higher low fps (but one has to remove graph spikes and dips: if you get a tenth of a second of 10 fps for shaders to be loaded and then min fps is 30 fps, it's much better than getting 15 fps every 2 seconds)
* much less frame rate variance (see above for spikes)
* less micro-stuttering (frame time variance, they're usually so fast they don't appear on a graph but are very jarring during play)

The two latest Mesa improvements (shaders on-disk cache, GL thread) are major improvements towards smoother gameplay by reducing CPU spikes without the game's developer having to do much, if anything, to make use of them. Personally, I don't MIND max fps dropping as long as average remains pretty much the same but stuttering goes away.

[gbil]

At this point I truly believe that with the threaded dispatch on the reported fps is wrong since I can't believe that running at ~20fps gives a much smoother results than ~28fps just because the CPU spikes have been sorted out.

since I'm not an expert though just writing what I see/feel I would appreciate more input from an expert to sort this out.

[geearf]

A smoother gameplay usually comes from:
* much higher low fps (but one has to remove graph spikes and dips: if you get a tenth of a second of 10 fps for shaders to be loaded and then min fps is 30 fps, it's much better than getting 15 fps every 2 seconds)
* much less frame rate variance (see above for spikes)
* less micro-stuttering (frame time variance, they're usually so fast they don't appear on a graph but are very jarring during play)

The two latest Mesa improvements (shaders on-disk cache, GL thread) are major improvements towards smoother gameplay by reducing CPU spikes without the game's developer having to do much, if anything, to make use of them. Personally, I don't MIND max fps dropping as long as average remains pretty much the same but stuttering goes away.

Frame-rate variance is a good point, that would makes sense!

Thanks!

[geearf]

At this point I truly believe that with the threaded dispatch on the reported fps is wrong since I can't believe that running at ~20fps gives a much smoother results than ~28fps just because the CPU spikes have been sorted out.

since I'm not an expert though just writing what I see/feel I would appreciate more input from an expert to sort this out.

Here's an example of one of Mitch's case, that would explain it (it's just an example):

In the original case you have an average of 28 FPS. Since it's an average it doesn't represent the whole distribution by itself, so let's say you usually are between 6 FPS and 50 FPS (for simplicity's sake, we'll just say that 28 is not just the average but also the median).
In the threads case your average is 20 FPS, let's say that this time you are between 16 and 24 FPS. This case has a smaller step between the min and max, the lower FPS is also much higher in this case. This would probably look smoother.

[LinuxID10T]

Maybe I can buy that as an explanation. But then why does radv performance tank so bad. Vulkan is multi threaded by design.

Vulkan is by design. RADV isn't as of yet. Testing DOTA 2 I get twice the frame rate if I limit it to two cores as opposed to letting it use all 16 logical cores.

[gbil]

Here's an example of one of Mitch's case, that would explain it (it's just an example):

In the original case you have an average of 28 FPS. Since it's an average it doesn't represent the whole distribution by itself, so let's say you usually are between 6 FPS and 50 FPS (for simplicity's sake, we'll just say that 28 is not just the average but also the median).
In the threads case your average is 20 FPS, let's say that this time you are between 16 and 24 FPS. This case has a smaller step between the min and max, the lower FPS is also much higher in this case. This would probably look smoother.

But when you are talking about averages you are talking about benchmarking I guess, while I'm talking about realtime numbers while playing the game, or I understood wrong?