Sign in to follow this  

DX11 Massive performance increase after migrating engine from DX10 to DX11.

This topic is 2547 days old which is more than the 365 day threshold we allow for new replies. Please post a new topic.

If you intended to correct an error in the post then please contact us.

Recommended Posts

... but... why?
I'm asking this mostly out of curiosity, why would this happen?

I've written my own little deferred renderer using SlimDX with DX10 some time ago, and I was having a good time with it.
It was working well, and faster than I anticipated (mostly thanks to all the wonderful performance suggestions on these forums, especially from MJP).
I recently decided to migrate my engine to DX11.
It wasn't as hard as I imagined, it was pretty much a one day job (at least to get the basics working, I disabled some things I'm not needing immediately.
I set it to use compatibility level 10_0 (I got dx10 gpu's).

After the first successful compile, I was surprised to say the least.
My game was running so much faster, even though, besides switching to dx11 I changed nothing whatsoever.
The first thing I noticed is that the dx11 version uses > 90% of my gpu, the dx10 version uses ~75%. This would explain the increase in speed.
The really interesting aspect that the dx11 version scales SO MUCH better when adding dynamic lights, and I have no idea why.

Example with 500 small dynamic point lights in small test scene:
DX10:
- GPU usage 35%
- FPS 52

DX11:
- GPU usage 92%
- FPS 220

Basically what happens is that the DX10 version suffers from using many dynamic light sources.
There's a bottleneck somewhere which causes the GPU usage to go down.
I've never been able to track it down unfortunately.
The DX11 version doesn't seem to have this bottleneck at all.

Same thing with SLI:
If I use 2 way AFR SLI the DX10 GPU usage drops from 75% to 55%.
With DX11 GPU usage drops from ~92% to ~90% (it basically stays the same and nearly halves frame times)

Now don't get me wrong, I'm loving this, but I'm still curious what could be causing this?
I mean... this is quite extreme, the DX11 version runs over 2000 dynamic point lights and still stays over 100fps easily, wheras the DX10 one begins struggling at "only" 300 point lights.
The scenes are exactly identical, so are the shaders and the code (I only changed everything DX10 related to DX11)

The only thing I can think of is that DX11 use a more efficient way of sending data to the GPU?

Cheers,
Hyu

Share this post


Link to post
Share on other sites
I've never heard anyone making this type of claim before, but perhaps your driver has better support for DX11? From the numbers you have mentioned, it clearly shows that the CPU is less of a bottleneck, which allows more GPU to be used. This would seem to indicate that the submission process is better supported in DX11.

DX11 does introduce multithreading, but you need to intentionally use it to gain the advantages from it. However, perhaps the required changes in driver allowed for some other optimizations at the same time??? Who knows, but congrats on the performance increase!

Share this post


Link to post
Share on other sites
Driver optimizations are certainly a possibility, I hadn't thought of that.
Ah well, I was just curios if it was something obvious.
I'm glad I got rid of my bottleneck, even if it was in a bit of a weird fashion.

Share this post


Link to post
Share on other sites
It's quite a lot of code unfortunately, I've been playing with this for nearly a year.
I basically just changed the using SlimDX.Direct3D10; statement to using SlimDX.Direct3D11;
I changed all device calls to use device.ImmediateContext and modified shader compilation so use effect profile fx_5_0 instead of fx_4_0.
The device&swapchain is created with FeatureLevel.Level_10_0.
Apart from that I just modified anything the compiler complained about (mostly renamed methods etc).

Share this post


Link to post
Share on other sites
I Think I finally know what happened, and it's something quite stupid really.
After doing a Build -> Clean on the DX10 project, it runs nearly as fast as the DX11 one...

I've changed the point light rendering routine recently so they are rendered using instanced bounding volumes, instead of using a draw call for each light.
I assume, even though the code was setup otherwise, the DX10 project was still using the drawing routine without instancing.
The Build -> Clean forced a complete recompile and fixed it. :/

Note to self: Do a full rebuild every now and then.

Share this post


Link to post
Share on other sites

This topic is 2547 days old which is more than the 365 day threshold we allow for new replies. Please post a new topic.

If you intended to correct an error in the post then please contact us.

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!

Register a new account

Sign in

Already have an account? Sign in here.

Sign In Now

Sign in to follow this  

  • Forum Statistics

    • Total Topics
      628730
    • Total Posts
      2984427
  • Similar Content

    • By GreenGodDiary
      Having some issues with a geometry shader in a very basic DX app.
      We have an assignment where we are supposed to render a rotating textured quad, and in the geometry shader duplicate this quad and offset it by its normal. Very basic stuff essentially.
      My issue is that the duplicated quad, when rendered in front of the original quad, seems to fail the Z test and thus the original quad is rendered on top of it.
      Whats even weirder is that this only happens for one of the triangles in the duplicated quad, against one of the original quads triangles.

      Here's a video to show you what happens: Video (ignore the stretched textures)

      Here's my GS: (VS is simple passthrough shader and PS is just as basic)
      struct VS_OUT { float4 Pos : SV_POSITION; float2 UV : TEXCOORD; }; struct VS_IN { float4 Pos : POSITION; float2 UV : TEXCOORD; }; cbuffer cbPerObject : register(b0) { float4x4 WVP; }; [maxvertexcount(6)] void main( triangle VS_IN input[3], inout TriangleStream< VS_OUT > output ) { //Calculate normal float4 faceEdgeA = input[1].Pos - input[0].Pos; float4 faceEdgeB = input[2].Pos - input[0].Pos; float3 faceNormal = normalize(cross(faceEdgeA.xyz, faceEdgeB.xyz)); //Input triangle, transformed for (uint i = 0; i < 3; i++) { VS_OUT element; VS_IN vert = input[i]; element.Pos = mul(vert.Pos, WVP); element.UV = vert.UV; output.Append(element); } output.RestartStrip(); for (uint j = 0; j < 3; j++) { VS_OUT element; VS_IN vert = input[j]; element.Pos = mul(vert.Pos + float4(faceNormal, 0.0f), WVP); element.Pos.xyz; element.UV = vert.UV; output.Append(element); } }  
      I havent used geometry shaders much so im not 100% on what happens behind the scenes.
      Any tips appreciated! 
    • By mister345
      Hi, I'm building a game engine using DirectX11 in c++.
      I need a basic physics engine to handle collisions and motion, and no time to write my own.
      What is the easiest solution for this? Bullet and PhysX both seem too complicated and would still require writing my own wrapper classes, it seems. 
      I found this thing called PAL - physics abstraction layer that can support bullet, physx, etc, but it's so old and no info on how to download or install it.
      The simpler the better. Please let me know, thanks!
    • By Hexaa
      I try to draw lines with different thicknesses using the geometry shader approach from here:
      https://forum.libcinder.org/topic/smooth-thick-lines-using-geometry-shader
      It seems to work great on my development machine (some Intel HD). However, if I try it on my target (Nvidia NVS 300, yes it's old) I get different results. See the attached images. There
      seem to be gaps in my sine signal that the NVS 300 device creates, the intel does what I want and expect in the other picture.
      It's a shame, because I just can't figure out why. I expect it to be the same. I get no Error in the debug output, with enabled native debugging. I disabled culling with CullMode.None. Could it be some z-fighting? I have little clue about it but I tested to play around with the RasterizerStateDescription and DepthBias properties with no success, no change at all. Maybe I miss something there?
      I develop the application with SharpDX btw.
      Any clues or help is very welcome
       


    • By Beny Benz
      Hi,
      I'm currently trying to write a shader which shoud compute a fast fourier transform of some data, manipulating the transformed data, do an inverse FFT an then displaying the result as vertex offset and color. I use Unity3d and HLSL as shader language. One of the main problems is that the data should not be passed from CPU to GPU for every frame if possible. My original plan was to use a vertex shader and do the fft there, but I fail to find out how to store changing data betwen shader calls/passes. I found a technique called ping-ponging which seems to be based on writing and exchangeing render targets, but I couldn't find an example for HLSL as a vertex shader yet.
      I found https://social.msdn.microsoft.com/Forums/en-US/c79a3701-d028-41d9-ad74-a2b3b3958383/how-to-render-to-multiple-render-targets-in-hlsl?forum=xnaframework
      which seem to use COLOR0 and COLOR1 as such render targets.
      Is it even possible to do such calculations on the gpu only? (/in this shader stage?, because I need the result of the calculation to modify the vertex offsets there)
      I also saw the use of compute shaders in simmilar projects (ocean wave simulation), do they realy copy data between CPU / GPU for every frame?
      How does this ping-ponging / rendertarget switching technique work in HLSL?
      Have you seen an example of usage?
      Any answer would be helpfull.
      Thank you
      appswert
    • By ADDMX
      Hi
      Just a simple question about compute shaders (CS5, DX11).
      Do the atomic operations (InterlockedAdd in my case) should work without any issues on RWByteAddressBuffer and be globaly coherent ?
      I'v come back from CUDA world and commited fairly simple kernel that does some job, the pseudo-code is as follows:
      (both kernels use that same RWByteAddressBuffer)
      first kernel does some job and sets Result[0] = 0;
      (using Result.Store(0, 0))
      I'v checked with debugger, and indeed the value stored at dword 0 is 0
      now my second kernel
      RWByteAddressBuffer Result;  [numthreads(8, 8, 8)] void main() {     for (int i = 0; i < 5; i++)     {         uint4 v0 = DoSomeCalculations1();         uint4 v1 = DoSomeCalculations2();         uint4 v2 = DoSomeCalculations3();                  if (v0.w == 0 && v1.w == 0 && v2.w)             continue;         //    increment counter by 3, and get it previous value         // this should basically allocate space for 3 uint4 values in buffer         uint prev;         Result.InterlockedAdd(0, 3, prev);                  // this fills the buffer with 3 uint4 values (+1 is here as the first 16 bytes is occupied by DrawInstancedIndirect data)         Result.Store4((prev+0+1)*16, v0);         Result.Store4((prev+1+1)*16, v1);         Result.Store4((prev+2+1)*16, v2);     } } Now I invoke it with Dispatch(4,4,4)
      Now I use DrawInstancedIndirect to draw the buffer, but ocassionaly there is missed triangle here and there for a frame, as if the atomic counter does not work as expected
      do I need any additional synchronization there ?
      I'v tried 'AllMemoryBarrierWithGroupSync' at the end of kernel, but without effect.
      If I do not use atomic counter, and istead just output empty vertices (that will transform into degenerated triangles) the all is OK - as if I'm missing some form of synchronization, but I do not see such a thing in DX11.
      I'v tested on both old and new nvidia hardware (680M and 1080, the behaviour is that same).
       
  • Popular Now