Sign in to follow this  

DX11 dx 11 and multicore cpu

This topic is 2574 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

Hello.
I read some documentation on intel tbb.
From what I understand the generation of the tasks and their execution with the task sheduler is very useful for application logic (in my case a game).
I was wondering if you can use the tasks and sheduler for rendering operations in dx 11.
Somewhere (I seem to recall an example of the last directx 11 right in the SDK) there is an example that explain how speed up the rendering with multicore.
Where i can find some documentation ?
In google there are a lot of articles but not tecnical articles in c++ and dx11
thanks.

Share this post


Link to post
Share on other sites
I suppose any tutorial on multithreading will do.

That's about what we get with advancement on core number and simultaneous thread execution.
It's not a DX11 thing really, AFAIK DX11 doesn't care whether your cpu is qualcomm or intel, single or multipcore - Pleas correct me if i'm wrong.

If you want totorials of how to split up repeating DX processes, I think you can look at about anything related to graphics and multithreading. Check the graphics card pipeline and get a feeling of what things are thread safe and not.

For instance, having a geometry generator or texture loader could easily take place in a seperate thread without crashing a DX application.

But I'm rambling. Maybe that's not really what you wanted to know.

[Edited by - SuperVGA on November 30, 2010 6:57:23 AM]

Share this post


Link to post
Share on other sites
Direct3D 11 natively supports multithreading, and allows for multithreaded resource creation as well as multithreaded command list creation. The latter point is more interesting for performance, and could significantly reduce the amount of CPU overhead involved with submitting all of the API calls.

There is a sample in the DXSDK that shows how to implement the multithreaded command list generation. The Hieroglyph 3 engine also implements multithreading, so you can take a look at that too.

Share this post


Link to post
Share on other sites
Any insight into when using multithreaded command list generation is beneficial? When I run the SDK sample, it takes a few extra milliseconds when using the multithreaded paths, despite taking extra CPU time (which i suppose means its actually multithreaded at least haha)

I assume it must have something to do with the length of the command lists..

Share this post


Link to post
Share on other sites
Any insight into when using multithreaded command list generation is beneficial? When I run the SDK sample, it takes a few extra milliseconds when using the multithreaded paths, despite taking extra CPU time (which i suppose means its actually multithreaded at least haha)

I assume it must have something to do with the length of the command lists..

Share this post


Link to post
Share on other sites
It does indeed have to do with the size of the command lists, and it also depends on how many cores you have on your machine. If you run it on a single or dual core machine, then it may not help at all (and may actually decrease performance as well).

If your app is CPU bound though, it could be quite beneficial to parallelize the CPU submission calls. I don't have any hard numbers, but I have been developing some stress tests to see if I can find where it starts to benefit from having the multiple cores. Hopefully within the next couple weeks I will be able to add the stress test to my engine distribution...

Share this post


Link to post
Share on other sites
The main "problem" right now is that while drivers support multi-threaded resource creation they (when I last checked) didn't natively support multi-threaded command list creation.

So, the runtime and driver kind of 'fake' it right now (effectively storing everything up and then submitting as normal); although I think we are getting closer to native support for this functionality.

The main point being that, atm, any stress test won't give an accurate view of how things will work in the future [smile]

Share this post


Link to post
Share on other sites
The 'Driver Command Lists' ability reported by the runtime is based on the driver's ability to simultaneously create command lists from multiple threads. However, the benefit from multithreading can still be had depending on how much work is done to generate a rendering sequence. For example, if the transformation matrix concatenation is performed on each thread for independent rendering passes, then the net result is to divide the number of transforms needed to perform by the number of cores on the machine (neglecting memory access pattern effects). This will still have a positive effect on performance, regardless of if the command list is created in parallel or in sequential operation.

Share this post


Link to post
Share on other sites
Out of curiosity, I just ran the multithreaded rendering sample from the SDK on both my laptop and my desktop. Here are the configurations and the results:

Laptop: Core 2 Duo 1.6 GHz, 2 GB, Vista, 8600M GT - Single threaded ~5-6 FPS, Multi-threaded ~8-9 FPS
Desktop: Phenom II X4 3.2 GHz, 4 GB, Win7, 5700 series Radeon - Single threaded ~22-24 FPS, Multi-threaded ~44-45 FPS

So in both cases I see a significant speedup with the MT activated. Also interesting is the fact that the laptop GPU is a DX10 part, meaning that the CPU savings are implemented with a DX10 driver for the DX11 runtime. I suspect that if you see degraded performance in this sample, you are probably GPU bound meaning that the parallelism can't help you anyways...

Share this post


Link to post
Share on other sites
Hmm interesting. I updated my GPU drivers just now and it has improved performance of the multithreaded path. Immediate mode appears to be the fastest, so like you said I must be GPU bound

Desktop: i7 3.4 GHz, 64-bit win7, HD5750

Immidiate ~65 fps
ST Def/Scene ~39 fps
MT Def/Scene ~54 fps
ST Def/Chunk ~50 fps
MT Def/Chunk ~55 fps

Share this post


Link to post
Share on other sites

This topic is 2574 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
      628740
    • Total Posts
      2984472
  • 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