SpiderPig Posted March 13 Share Posted March 13 I hate to say it, but I'm seeing it a lot slower overall. Actually, it seems 2.5x slower. These shots are in release. In 0.9.5 I've had to remove the skydome due to some shader errors, and the terrain due to it not texturing. The terrain was replaced with a single plane. So 0.9.5 is doing less work but is a lot slower and the grass don't look as good. Also in 0.9.5 I've seen the FPS fluctuate between 120 and 60 FPS like a seesaw even when the camera is still. Scene in 0.9.4: Same scene in 0.9.5: Quote Link to comment Share on other sites More sharing options...
Josh Posted March 13 Share Posted March 13 At the moment this isn't really actionable information. What is different about your demo and the performance benchmark apps? Are you constantly streaming geometry in? Quote My job is to make tools you love, with the features you want, and performance you can't live without. Link to comment Share on other sites More sharing options...
SpiderPig Posted March 13 Author Share Posted March 13 No geometry streaming. Everything is static with default shaders. Quote Link to comment Share on other sites More sharing options...
Josh Posted March 13 Share Posted March 13 I would also be looking at the rest of the render statistic values. Quote My job is to make tools you love, with the features you want, and performance you can't live without. Link to comment Share on other sites More sharing options...
SpiderPig Posted March 13 Author Share Posted March 13 Yeah I'll take a closer look at those and see what they say. Quote Link to comment Share on other sites More sharing options...
Josh Posted March 13 Share Posted March 13 Would also disable your directional light for testing. 1 Quote My job is to make tools you love, with the features you want, and performance you can't live without. Link to comment Share on other sites More sharing options...
Dreikblack Posted March 14 Share Posted March 14 My tetsts of Ultra benchmarks 2023 and compiled sources with beta 0.9.5 (RTX 4080): Old/new FPS Unique Geometry ~7500 / 6400-6800 Lighting 2500 / 2100 Instanced Geometry 1700-2100 / 3600 Animation 3000 / 3400 Quote Link to comment Share on other sites More sharing options...
SpiderPig Posted March 14 Author Share Posted March 14 Don't really see a problem with any of these stats. Besides the FPS that is. It gets down to 90 for a second or two then back up to about 200 for a bit. I wish I could use FRAPS to verify the FPS but it doesn't seem to work with ultra. It decided to work now. FRAPS confirms the FPS is correct. Quote Link to comment Share on other sites More sharing options...
SpiderPig Posted March 14 Author Share Posted March 14 Here's a short video on the unstable FPS I'm seeing. https://www.youtube.com/watch?v=Lm7dVy-pqHM Quote Link to comment Share on other sites More sharing options...
Josh Posted March 14 Share Posted March 14 Can't profile a video! Quote My job is to make tools you love, with the features you want, and performance you can't live without. Link to comment Share on other sites More sharing options...
CJO Games Posted March 14 Share Posted March 14 I can confirm that this is the case for me too (when I can even run the editor without continuous crashes to desktops) when it does run the editor is very much slower than it was before. The more assets that are added to the map/terrain then the more unstable the editor appears to become the more likely it is to crash the more likely it is that FPS count reduces etc. Quote Link to comment Share on other sites More sharing options...
Josh Posted March 14 Share Posted March 14 I tested on my GEForce 1080, and these are the numbers I got: 0.9.4 / 0.9.5 Instances: 1206 / 2320 Lighting: 863 / 810 Animation: 1067 / 1032 Batches: 5199 / 3300 So on Nvidia it's faster in one test, slower in the other, and about the same in the other two. When you are running at 1000+ frames per second, it's very easy for small things to have a disproportionate impact on the framerate. Adding something that takes 1/4 of a millisecond will drop 6000 FPS to 4000, so I don't think at that speed the results are very meaningful. Both the instances and batches tests could have been skewed by very small changes. Quote My job is to make tools you love, with the features you want, and performance you can't live without. Link to comment Share on other sites More sharing options...
Josh Posted March 14 Share Posted March 14 If you look at GPU utilization on the 1080, the numbers are like this: 0.9.4 / 0.9.5 Instances: 96% / 85% Lighting 96% / 96% Animation 96% / 93% Batches 76% / 67% Again, they are for practical purposes identical in lighting and animation. The batches test had lower GPU usage, which may be caused by small changes in the visibility list processing step, since this involves 1000+ separate batches that have to be iterated through and processed in the rendering thread. The GPU usage in the instances test is strange because 0.9.5 has lower GPU utilization but higher performance. This may be attributed to small changes in shader code, although I do not know what those changes would be. 0.9.5 does use one fewer vertex attribute, but I don't really see that doubling the framerate. All in all, it looks like OpenGL 4.6 gives AMD a major performance boost and runs about the same as Vulkan on Nvidia cards in these tests. Quote My job is to make tools you love, with the features you want, and performance you can't live without. Link to comment Share on other sites More sharing options...
SpiderPig Posted March 14 Author Share Posted March 14 3 hours ago, Josh said: Can't profile a video! I'm working on an example for you. Quote Link to comment Share on other sites More sharing options...
SpiderPig Posted March 14 Author Share Posted March 14 I'm slowly narrowing this down. I have conducted tests with the individual models and I am seeing 2x the performance I was in 0.9.4. Maybe 0.9.5 is showing up a bug in my code that wasn't noticeable before. Quote Link to comment Share on other sites More sharing options...
SpiderPig Posted March 15 Author Share Posted March 15 While putting together an example I have found something; When the trees trunks are white, the FPS is stable. When they are black, the FPS is a sine wave going from 90FPS to 280FPS and back and forth. It's hit and miss which one I get, obviously there are missing shaders and I think something it's not being set correctly by default upon engine load. It's interesting how the terrain is black also, I have not assigned any material to this terrain. Quote Link to comment Share on other sites More sharing options...
SpiderPig Posted March 15 Author Share Posted March 15 This appears to be identified and solved with this bug here. At lest in debug mode. Will test release mode soon. Quote Link to comment Share on other sites More sharing options...
Solution Josh Posted March 16 Solution Share Posted March 16 It actually makes sense why your colors were flipping back and forth. The bindless texture override in the shader family was not being taken into account in the sorting, so it was just random. So sometimes your trees were being rendered with the more expensive terrain shader. 1 Quote My job is to make tools you love, with the features you want, and performance you can't live without. Link to comment Share on other sites More sharing options...
Recommended Posts
Join the conversation
You can post now and register later. If you have an account, sign in now to post with your account.
Note: Your post will require moderator approval before it will be visible.