Sign in to follow this  

DX11 [solved]My tessellation pipeline that draws nothing.

This topic is 1699 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

Ok, I believe that I am using the right blend state, and I believe that my ProjectionView matrix is ok, and I've eliminated relevant DX11 warnings and errors, but I still can't get anything to appear on screen. I'm greatly hampered by the fact that there is no way to debug my tessellation shaders with SharpDX and VS2012 express. This is my first stab at tessellation so I probably am doing something obviously wrong, so I would like to post my shaders to see if anything jumps out at anyone. What I am trying to do is draw instanced 3rd order bezier triangles. Besides the above, what other things might I check when nothing is drawn?

 

Here is the VS:

cbuffer PerFrameBuffer : register(b0)
{
	//float4x4 World; This is just the identity matrix, so not needed
	float4x4 ViewProjection;
	float4 vecEye; 
	float4 LightDirection;
	float4 LightColor; 
};

struct VertexInput
{
	//imediate data
	float3 PositionLocal		: POSITION0;
	int index					: BLENDINDICES;
	//instance data
	float3 Translation			: POSITION1;
	float Altitudes[4]			: PSIZE;
};

struct VertexOutput
{
	float3 PositionWorld	: POSITION;
	float2 MainTexCoord		: TEXCOORD;
};

VertexOutput VS(VertexInput vin)
{
	VertexOutput vout;

	//Add altitudes
	float3 transPos = vin.PositionLocal + vin.Translation;
	transPos.y += vin.Altitudes[vin.index];

	vout.MainTexCoord = transPos.xz;
	vout.PositionWorld = transPos;

	return vout;
}

 

 

Here is the pass thru Hull shader:


struct VertexOutput
{
	float3 PositionWorld	: POSITION;
	float2 MainTexCoord		: TEXCOORD;
};

struct PatchTess
{
	float EdgeTess[3]	: SV_TessFactor;
	float InsideTess	: SV_InsideTessFactor;
};

PatchTess PatchHS(InputPatch<VertexOutput,10> patch, uint patchID : SV_PrimitiveID)
{
	PatchTess pt;

	pt.EdgeTess[0] = 6;
	pt.EdgeTess[1] = 6;
	pt.EdgeTess[2] = 6;
	pt.InsideTess = 6;

	return pt;
}

struct HullOut
{
	float3 PositionWorld	: POSITION;
	float2 MainTexCoord		: TEXCOORD;
};

[domain("tri")]
[partitioning("fractional_even")]
[outputtopology("triangle_cw")]
[outputcontrolpoints(10)]
[patchconstantfunc("PatchHS")]
HullOut HS(InputPatch<VertexOutput,10> p, uint i : SV_OutputControlPointID, uint patchId : SV_PrimitiveID)
{
	HullOut hout;

	hout = p[i];

	return hout;
}

 

 

Here is the domain shader, where the meat of the intended operation is. The math here might be wrong, but should still produce visible geometry:

#define p300 0
#define p030 1
#define p003 2
#define p210 3
#define p201 4
#define p120 5
#define p021 6
#define p012 7
#define p102 8
#define p111 9

#define U bary.x
#define V bary.y
#define W bary.z

cbuffer PerFrameBuffer : register(b0)
{
	//float4x4 World; This is just the identity matrix, so not needed
	float4x4 ViewProjection;
	float4 vecEye; 
	float4 LightDirection;
	float4 LightColor; 
};

struct PatchTess
{
	float EdgeTess[3]	: SV_TessFactor;
	float InsideTess	: SV_InsideTessFactor;
};

struct HullOut
{
	float3 PositionWorld	: POSITION;
	float2 MainTexCoord		: TEXCOORD;
};

struct DomainOut
{
	float4 PositionH		: SV_Position;
	float3 Normal			: NORMAL0;
	float3 Tangent			: TANGENT0;
	float3 Bitangent		: BITANGENT0;
	float3 View				: NORMAL1;
	float2 MainTexCoord		: TEXCOORD0;
};

[domain("tri")]
DomainOut DS(PatchTess patchTess, float3 bary : SV_DomainLocation, const OutputPatch<HullOut,10> cp)
{
	DomainOut dout;

	float3 position =
		cp[p300].PositionWorld * pow(U,3) +
		cp[p030].PositionWorld * pow(V,3) +
		cp[p003].PositionWorld * pow(W,3) +
		cp[p210].PositionWorld * 3 * pow(U,2) * V +
		cp[p201].PositionWorld * 3 * pow(U,2) * W +
		cp[p120].PositionWorld * 3 * U * pow(V,2) +
		cp[p021].PositionWorld * 3 * pow(V,2) * W +
		cp[p012].PositionWorld * 3 * V * pow(W,2) +
		cp[p102].PositionWorld * 3 * U * pow(W,2) +
		cp[p111].PositionWorld * 6 * U * V * W;

	float3 tangent =
		cp[p300].PositionWorld * pow(U,2) +
		cp[p120].PositionWorld * pow(V,2) +
		cp[p102].PositionWorld * pow(W,2) +
		cp[p201].PositionWorld * 2 * U * W +
		cp[p210].PositionWorld * 2 * U * V +
		cp[p111].PositionWorld * 2 * V * W;

	float3 bitangent = 
		cp[p030].PositionWorld * pow(V,2) +
		cp[p012].PositionWorld * pow(W,2) +
		cp[p210].PositionWorld * pow(U,2) +
		cp[p120].PositionWorld * 2 * U * V +
		cp[p021].PositionWorld * 2 * V * W +
		cp[p111].PositionWorld * 2 * U * W;

	tangent = normalize(tangent);
	bitangent = normalize(bitangent);
	float3 normal = normalize(cross(tangent,bitangent));

	dout.View = vecEye.xyz - position.xyz;
	dout.PositionH = mul(float4(position,1.0f),ViewProjection);
	dout.Normal = normal;
	dout.Tangent = tangent;
	dout.Bitangent = bitangent;

	dout.MainTexCoord = cp[p300].MainTexCoord * U + cp[p030].MainTexCoord * V + cp[p003].MainTexCoord * W;

	return dout;
}

 

Last is the pixel shader, which has a simple shading algorithm that has been disabled to merely produce one color. I'm really hoping to see that color 'Reddish' but it's not happening:

cbuffer PerFrameBuffer : register(b0)
{
	//float4x4 World; This is just the identity matrix, so not needed
	float4x4 ViewProjection;
	float4 vecEye; 
	float4 LightDirection;
	float4 LightColor; 
};

struct DomainOut
{
	float4 PositionH		: SV_Position;
	float3 Normal			: NORMAL0;
	float3 Tangent			: TANGENT0;
	float3 Bitangent		: BITANGENT0;
	float3 View				: NORMAL1;
	float2 MainTexCoord		: TEXCOORD0;
};

float4 PS(DomainOut input) : SV_Target
{
    float4 Color = float4 (0, 0, 0, 1); 
	float4 Reddish = float4 (0.8,0.5,0.8,1.0);
	float4 specularColor = float4(1,1,1,1);

    float4 diffuse = {LightColor.rgb, 1.0f};   
    float4 ambient = { 0.03f, 0.03f, 0.03f, 1.0f};   
  
    float3 LightDir = normalize(LightDirection.xyz);   
    float3 ViewDir = normalize(input.View);    
       
    float4 diff = saturate(dot(input.Normal, LightDir)); // diffuse component   
  
    // R = 2 * (N.L) * N - L   
    float3 Reflect = normalize(2 * diff * input.Normal - LightDir);    
    float specular = pow(saturate(dot(Reflect, ViewDir)), 15); // R.V^n   
  
    // I = Acolor + Dcolor * N.L + (R.V)n   
    Color += ambient + diffuse  * diff + specular * (specularColor * LightColor);  

	float4 Final = Color * Reddish;
	Final.a = 1.0;

	//return Final;
	return Reddish;
       
}

 

 

Share this post


Link to post
Share on other sites

When I started out with tessellation, I found it helpful to really simplify things and then build up the complexity step by step.  I would suggest making your pixel shader just output a solid white color - then you can eliminate any shading errors or missing constant buffers from the pixel shader right off the bat.

 

Next I would actually eliminate the hull and domain shaders, and just pass your geometry from vertex shader to pixel shader.  Verify that your vertices are appearing in the location that you expect (this will likely require moving some transformation code from the DS to the VS, but you can move it back fairly easily later).  Instead of doing instanced rendering, try with just standard rendering instead (that will eliminate issues with your instance buffers). 

 

Only once you have the geometry input to the tessellation stages verified, and then that the output stages from the tessellation stages verified, would I try to debug the hull and domain shaders.  Have you been able to verify these things yet?  If so, then we can move a little deeper into the investigation - if we know it is a tessellation issue or not!

Share this post


Link to post
Share on other sites

Thanks Jason. That sounds like a good idea. It's time to start paring things down. One thing I forgot to mention above was the setup of the depth buffer, as if maybe it was always failing the depth test or something, I've got that set up how it should be, I had forgotten to set the DepthStencilState, but fixing that didn't help. I'll do what you suggest, although I'll have to change alot of stuff, because my inputs are just a series of control points. I'll have to decide how to turn them into triangles, or just draw points.

Share this post


Link to post
Share on other sites

About the control points - just output them as regular points, and ensure their positions are as expected.  Don't expend too much energy on the verification - you are just making sure it is set up the way you expect.  That should really only require the changes in the shaders, plus the primitive topology.

Share this post


Link to post
Share on other sites

As this is my first dx11 app, I do have a related question. Is there anything else I am supposed to do to turn on the different pipeline stages other than setting them in the immediate context? In SharpDX you would say  context.HullShader.Set(hexCornerHS).

 

 

For instance let's say I want to use tessellation on one drawn element, and then only a vertex/pixel shader on another drawn element. Would I then have to set the hull/domain shaders to 'null' in order to disable them? 

Share this post


Link to post
Share on other sites
1) Well for the tesselation you need hull and domain shader. Other than that: constant buffers, views etc for the correct stages.
2) Yes. Whenever you issue a draw call, everything that is currently set goes into it. It won't change until you change it.

Oh, and cephalo, I found something useful. With a pass-through geometry shader like this...
[maxvertexcount(3)]
void PassThroughTriangleGS(triangle DomainOut gin[3], inout TriangleStream<DomainOut> stream)
{
    for(int i = 0; i < 3; i++)
    {
        stream.Append(gin[i]);
    }
    stream.RestartStrip();
}
... you can actually force PIX to show what the tesselator spits out. It even highlights the whole patch biggrin.png
715781249054966.jpg
b98a4c249054972.jpg

Share this post


Link to post
Share on other sites

Ok, I tried unbird's trick, and kindof unfortunately I got almost the exact geometry I expected in the post GS window. However, I don't understand why the viewport shows a mere dot. In actual rendering, I don't see a dot even though my pixel shader currently puts out one color. 

[attachment=14875:PIXpic.png]

 

To see how this geometry looks right to me, here is a screenshot of the DirectX 9 version of this project: It's basically a hex terrain map.

[attachment=14876:HexMap.jpg]

Share this post


Link to post
Share on other sites

interesting tip unbird. I thought that I couldn't have a geometry shader when the tessellation stages were active.

There isn't any restriction like that.  You have to have a vertex shader and a pixel shader, but outside of that there is no hard rule except that the last stage before the rasterizer has to output the SV_Position semantic.

Share this post


Link to post
Share on other sites

The w-components of your post GS vertices is very large - that means that your geometry is very far away, and will appear small in your viewport.  Can you double check your view and projection matrices to make sure they are properly set?  Have you tried these matrices with a normal rendering setup (i.e. sans tessellation)?

Share this post


Link to post
Share on other sites

Hmm, I am starting to suspect the matrices. There is some confusion here because my camera class began with XNA, changed to SlimDX under DX9 and then to SharpDX under DX11, and I'm not sure if the methods with the same name are doing the same thing anymore. Here is the code to my update method in the camera.

 

        public override void Update()
        {
            Quaternion rot = Quaternion.RotationYawPitchRoll(input.Yaw,input.Pitch,input.Roll);
            avatarRotation = rot * avatarRotation;

            avatarPosition += Vector3.TransformCoordinate(new Vector3(0.0f, 0.0f, input.Velocity), Matrix.RotationQuaternion(avatarRotation));

            Matrix rotMatrix = Matrix.RotationQuaternion(avatarRotation);
            Vector3 transformedRef = Vector3.TransformCoordinate(thirdPersonRef, rotMatrix);

            cameraPosition = transformedRef + avatarPosition;
//            Vector4 upVector4 = rotMatrix.get_Rows(1);
            Vector4 upVector4 = rotMatrix.Row1;
            Vector3 upVector3 = new Vector3(upVector4.X, upVector4.Y, upVector4.Z);
            view = Matrix.LookAtRH(cameraPosition, avatarPosition, upVector3);
            projection = Matrix.PerspectiveFovRH(UsefulFunctions.ToRadians(45.0f),
                        aspectRatio, 0.1f, 500.0f);

            Matrix frustumMatrix = view * Matrix.PerspectiveFovRH(UsefulFunctions.ToRadians(50.0f),
                        aspectRatio, 0.1f, 500.0f);
            frustum.BuildViewFrustum(frustumMatrix);

            base.Update();
        }

Hmm, when I debug this code, I am getting a different View matrix from my DX9 version than with my DX11 version. The Projection matrix is the same in both versions. I'm not sure what's going on here. 

 

EDIT: I have another clue, when I move the camera at all with my controls, PIX showed no draw calls. I realized that my frustum checker was rejecting everything as being outside the frustum. That doesn't actually solve the problem, but it definately indicates that the matrices are wrong. I just need to know why I'm getting different matrices with the same code.

Edited by cephalo

Share this post


Link to post
Share on other sites

Ok, I found one mistake in my camera code. It turns out that SlimDX uses a zero base index on the row getter method, while SharpDX uses a one base index. You can see the commented out old SlimDX code above, instead of Row1, I needed Row2 to match the old Rows(1). Now that my initial up vector is (0,1,0) like it is supposed to be, all my matrices are the same between my DX9 version and my DX11 version. Unfortunately the problem still exists and I can't see anything. I'll have to test this again with my computer that allows PIX to run to see if my W values become sane. Although having the wrong up vector shouldn't make things invisible.

Edited by cephalo

Share this post


Link to post
Share on other sites

Ok, fixing that glich with the up vector gets rid of the weird W values. Now that I think about it, if you have an up vector that is nowhere close to perpendicular with your view direction, you're going to get skewed results. Here is my new screenshot:

 

[attachment=14883:PIXpic2.png]

 

Shot in the dark: Forgot to transpose the matrices ?

How do you update your constant buffers ?

 

I used to know what that means... but I forget now. Transpose them where? Since this is a terrain map of sorts, it actually defines world space in a way. The world matrix for this data would be the identity matrix, so I left it out of my calculations. Tell me if I'm mistaken, but m * identity == m correct?

 

The constant buffer is something I had doubts about, according to PIX it appears that it is being updated, but it's hard to tell if it's being done correctly. My code for creating and updating is as follows:

 

            perFrameBuffer = new Buffer(Game.GraphicsDevice, new BufferDescription { 
                Usage = ResourceUsage.Dynamic, 
                SizeInBytes = PerFrameBuffer.SizeOf, 
                BindFlags = SharpDX.Direct3D11.BindFlags.ConstantBuffer,
                CpuAccessFlags = CpuAccessFlags.Write
            });

            //Take a snapshot of the camera properties so that they don't change in mid draw
            Vector2 cameraPos = new Vector2(camera.Position.X, camera.Position.Z);
            Matrix viewMatrix = camera.View;
            Matrix projectionMatrix = camera.Projection;
            Vector3 vecEye = camera.Position;

            DataBox box = Game.GraphicsDevice.ImmediateContext.MapSubresource(perFrameBuffer, 0, MapMode.WriteDiscard, SharpDX.Direct3D11.MapFlags.None);
            var cb = new PerFrameBuffer();
            cb.ProjectionView = Matrix.Multiply(viewMatrix,projectionMatrix);
            cb.VecEye = new Vector4(vecEye,1);
            cb.LightDirection = new Vector4(0.0f, 0.6f, -0.9f, 1);
            cb.LightColor = new Vector4(1.0f, 1.0f, 1.0f, 1.0f);

            Utilities.Write(box.DataPointer, ref cb);
            Game.GraphicsDevice.ImmediateContext.UnmapSubresource(perFrameBuffer, 0);

 

Share this post


Link to post
Share on other sites
Bullseye!
 
cb.ProjectionView = Matrix.Multiply(viewMatrix,projectionMatrix);
 
Should (usually) be
 
cb.ProjectionView = Matrix.Transpose(Matrix.Multiply(viewMatrix,projectionMatrix));
EDIT Ooops. put an invert first, sorry. Corrected

Explanation: Shaders default to column-major packing in constant buffers, unless you compile with a flag telling otherwise. There are also corresponding HLSL keywords. So, you have to transpose your matrices this way (The effect framework took care of that automatically).

Tell me if I'm mistaken, but m * identity == m correct?

Yup, thats fine. Identity is "the 1", the matrix multiplications neutral element. Edited by unbird

Share this post


Link to post
Share on other sites

Dang. I was really hoping that would fix it, but I still am not seeing anything. I'm away from my PIX computer at the moment unfortunately so I can't check to see if the viewport geometry has changed.

 

Interesting, I had no idea that the effect framework did that automatically. There's probably a lot of stuff that I have no concept to even check.

 

I have one question about the PIX windows.

 

The Post-GS window in the above example is almost exactly what I was hoping to see in my viewport. The triangle shaped gaps are there because I do the hex field in two passes, first with the triangle pointing up(uh..north) and then a pass pointing down, and the displayed geometry is only the first draw call out of two needed for a block of hexes.

 

Since the final screen positioning is all handled in the domain shader, before the geometry shader, why is the Post-GS window correct and the viewport window so messed up? What could be changing between the GS and the output if the GS is just a pass thru?

Share this post


Link to post
Share on other sites
Two things:
  • Conversion from homogenous to cartesian coordinates aka perspective divide (x/w,y/w,z/w)
  • Viewport transformation (denormalizing to fit to your render target)
Note: PIX does sort of a "zoom to extent" for every view except the last, so even if your vertices are in a very big or very small scale, you will see them all.

If your matrices are fine and the viewport too, you should now see something more sensible. But maybe you have still other bugs.

Share this post


Link to post
Share on other sites

Ooh! I'm getting closer. Check out the PIX. The viewport is now exactly right.

 

[attachment=14884:PIXpic3.png]

 

I still am not seeing anything on screen. Just in case the triangle windings are backwards, (I'm using clockwise) I tried to move the camera downward to look up at the terrain, but I was unable to do that. It's hard to know what the camera is doing when you can't see anything.

 

This is what happens when you code for 3 months straight without debugging, which I did because I didn't really know how to debug in this new environment. You have to debunk 50 unfounded theories one... at... a... time. Thanks everyone for sticking with me, I don't think I could have persevered without your help.

 

So the geometry appears correct. Period. What else could be the problem?

Share this post


Link to post
Share on other sites

Did you try to set all your shaders to null after your drawing is done?

I remember having a problem with my GShader sometime ago where i didnt set it to null.

This ended up that another call to a different vertex/pixel shader was using the GS Stage too displayed wierd stuff on the screen.

 

For testing i would set all the stages you are using for your tesselation to null after your are done with drawing.

And disable all other drawing you are doing beside your terrain rendering.

Edited by dxdude

Share this post


Link to post
Share on other sites

Can you do a PIX pixel history to see where the pixels generated from that geometry get dumped?  Typically you should be looking for something like a viewport not set (which appears not to be the case now) rasterizer state not correct (i.e. backface culling), scissor rect not set correctly (but the default state is neutral, so unless you set one it can't be the problem), and then depth test, stencil test, and blending.

 

Can you show us the rasterizer state and output merger state that are being used for your tessellation draw call?

Share this post


Link to post
Share on other sites

dxdude, I have turned off any other draw calls for now such as skybox etc. so what you mentioned should not be an issue.

 

Jason, I have a blend state, and a depthstencil state. I didn't know about the rasterizer state or the output merger state! So those are in some default condition. I'll have to look into that. As for pixel history, the only thing that shows up on the render window is the background color, so I'm not sure which pixel to click on. I'll try a few when I get a chance.

 

EDIT: Ok, I've now set this rasterizer state, but I still get no drawing:

            RasterizerStateDescription renderStateDesc = new RasterizerStateDescription();
            renderStateDesc.CullMode = CullMode.None;
            renderStateDesc.IsFrontCounterClockwise = false;
            renderStateDesc.FillMode = FillMode.Solid;
            RasterizerState rasterState = new RasterizerState(Game.GraphicsDevice, renderStateDesc);
            Game.GraphicsDevice.ImmediateContext.Rasterizer.State = rasterState;
         
 

 

As for the output merger state, I can't find that exact terminology in SharpDX. Does it go by another name?

 

EDIT2: also, I am clearing the depthstencil buffer with this command for every frame:

       public static void Render()
        {
            elapsedTime += GameTime.ElapsedTimeLastUpdate;
            if (maxFrameRate > 0 && ticksPerFrame > elapsedTime.Ticks)
                return;
            context.ClearDepthStencilView(depthView, DepthStencilClearFlags.Depth, 1.0f, 0);
            context.ClearRenderTargetView(renderTarget, new Color4(0.25f, 0.5f, 1.0f, 1.0f));
            //device.Clear(ClearFlags.Target | ClearFlags.ZBuffer, Color.CornflowerBlue, 1.0f, 0);
            //device.BeginScene();

            foreach (DrawableGameComponent comp in drawableGameComponents)
            {
                if(comp.Enabled)
                    comp.Render();
            }

            //device.EndScene();
            swapChain.Present(0, PresentFlags.None);

            elapsedTime = TimeSpan.Zero;

        }

 

 

 

I'm not sure if these values are carried over from DX9, and that maybe they are not valid anymore.

Edited by cephalo

Share this post


Link to post
Share on other sites
There are a couple of differences, sometimes more, sometimes less options (no alpha test anymore, and of course no fixed function stuff). But the main difference is that the states come now in whole blocks, are - more logically - set to the corresponding pipeline stage and you can't change single values atomically. But IMO most of it is quite similar.
 
There's no output merger state. There are two states: blend state and depth stencil state. Jason probably meant that.
 
Hmmm, ah yeah. I think I found something. Please allow a little detour first.

The parameterless constructor for c# structs will set everything to default ("zero", depending on type to 0, 0.0f, 0.0, null, "none" for flags and enums, etc.).
And: There's no way to change that - you have to know !

This is where object initializers and intellisense come in handy.
Example:
var renderTargetBlendDescription = new RenderTargetBlendDescription()
{
	BlendEnable = true,
	BlendOperation = BlendOperation.Add,
	x                                       // <- cursor position, type any letter here
};
Intellisense will then list all properties you haven't used so far. This way you won't miss any.

Long story short: If you're still using that blendstate here, you got a problem: It has a RenderTargetWriteMask of "None", meaning you don't write anything at all. You probably want ColorWriteMaskFlags.All.

Check your other state creations too.


PS: Grrrr, I'm so close to kill that forum editor, it even changes non-WISIWIG previews

Share this post


Link to post
Share on other sites

Wow that's good to know. I assumed that stuff I didn't set would have some sensible default value. The problem here is that there are tons of parameters, and I only know what a few of them are for. I did my best guess on what to put in there, and I still see nothing. Here are the new state creations, the first is in my initialization method and the second two are in my draw call:

 

            RasterizerStateDescription renderStateDesc = new RasterizerStateDescription 
            { 
                CullMode = CullMode.None,
                DepthBias = 0,
                DepthBiasClamp = 0,
                FillMode = FillMode.Solid,
                IsAntialiasedLineEnabled = false,
                IsDepthClipEnabled = true,
                IsFrontCounterClockwise = false,
                IsMultisampleEnabled = true,
                IsScissorEnabled = false,
                SlopeScaledDepthBias = 0
            };
            RasterizerState rasterState = new RasterizerState(Game.GraphicsDevice, renderStateDesc);
            Game.GraphicsDevice.ImmediateContext.Rasterizer.State = rasterState;

...

            RenderTargetBlendDescription rendBlendDesc = new RenderTargetBlendDescription
            {
                AlphaBlendOperation = BlendOperation.Add,
                BlendOperation = BlendOperation.Add,
                DestinationAlphaBlend = BlendOption.Zero,
                DestinationBlend = BlendOption.Zero,
                IsBlendEnabled = true,
                RenderTargetWriteMask = ColorWriteMaskFlags.All,
                SourceAlphaBlend = BlendOption.One,
                SourceBlend = BlendOption.One
            };
            BlendStateDescription blendDesc = new BlendStateDescription
            {
                AlphaToCoverageEnable = false,
                IndependentBlendEnable = false
            };
            blendDesc.RenderTarget[0] = rendBlendDesc;
            BlendState blendState = new BlendState(Game.GraphicsDevice, blendDesc);
            Game.GraphicsDevice.ImmediateContext.OutputMerger.SetBlendState(blendState);

            DepthStencilStateDescription depthDesc = new DepthStencilStateDescription
            {
                BackFace = new DepthStencilOperationDescription
                {
                    Comparison = Comparison.Less,
                    DepthFailOperation = StencilOperation.Keep,
                    FailOperation = StencilOperation.Keep,
                    PassOperation = StencilOperation.Keep
                },
                DepthComparison = Comparison.Less,
                DepthWriteMask = DepthWriteMask.All,
                FrontFace = new DepthStencilOperationDescription
                {
                    Comparison = Comparison.Less,
                    DepthFailOperation = StencilOperation.Keep,
                    FailOperation = StencilOperation.Keep,
                    PassOperation = StencilOperation.Keep
                },
                IsDepthEnabled = true,
                IsStencilEnabled = true,
                StencilReadMask = 0xff,
                StencilWriteMask = 0xff
            };
            DepthStencilState depthState = new DepthStencilState(Game.GraphicsDevice, depthDesc);
            Game.GraphicsDevice.ImmediateContext.OutputMerger.SetDepthStencilState(depthState);

Share this post


Link to post
Share on other sites

Unbird is right - I meant the depth/stencil state and blend state combined when I referred to the output merger state.  Sorry for the confusion.

 

Regarding the default parameters, you can take a look at the description pages for each of the states, and they list the true defaults that should be sensible.  For example, here is the blend state description.  Once you get those initialized, it should be fairly easy to proceed with the debugging.

Share this post


Link to post
Share on other sites
One thing: Disable stencil.

IsStencilEnabled = false,
Also, try setting all states to null for once, maybe the default states will give you at least something. One at a time. Then all.

Edit: Sort of ninja'ed wink.png Edited by unbird

Share this post


Link to post
Share on other sites

This topic is 1699 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
      628651
    • Total Posts
      2984043
  • Similar Content

    • 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).
       
    • By Doggolainen
      Hello, 
      I am, like many others before me, making a displacement map tesselator. I want render some terrain using a quad, a texture containing heightdata and the geometryshader/tesselator.
      So far, Ive managed the utilize the texture on the pixelshader (I return different colors depending on the height). I have also managed to tesselate my surface, i.e. subdivided my quad into lots of triangles .
       
      What doesnt work however is the sampling step on the domain shader. I want to offset the vertices using the heightmap.
      I tried calling the same function "textureMap.Sample(textureSampler, texcoord)" as on the pixelshader but got compiling errors. Instead I am now using the "SampleLevel" function to use the 0 mipmap version of the input texture.
      But yeah non of this seem to be working. I wont get anything except [0, 0, 0, 0] from my sampler.
      Below is some code: The working pixelshader, the broken domain shader where I want to sample, and the instanciations of the samplerstates on the CPU side.
      Been stuck on this for a while! Any help would be much appreciated!
       
       
      Texture2D textureMap: register(t0); SamplerState textureSampler : register(s0); //Pixel shader float4 PS(PS_IN input) : SV_TARGET {     float4 textureColor = textureMap.Sample(textureSampler, input.texcoord);     return textureColor; } GS_IN DS(HS_CONSTANT_DATA input, float3 uvwCoord : SV_DomainLocation, const OutputPatch<DS_IN, 3> patch) {     GS_IN output;     float2 texcoord = uvwCoord.x * patch[0].texcoord.xy + uvwCoord.y * patch[1].texcoord.xy + uvwCoord.z *                    patch[2].texcoord.xy;     float4 textureColor = textureMap.SampleLevel(textureSampler, texcoord.xy, 0);      //fill  and return output....  }             //Sampler             SharpDX.Direct3D11.SamplerStateDescription samplerDescription;             samplerDescription = SharpDX.Direct3D11.SamplerStateDescription.Default();             samplerDescription.Filter = SharpDX.Direct3D11.Filter.MinMagMipLinear;             samplerDescription.AddressU = SharpDX.Direct3D11.TextureAddressMode.Wrap;             samplerDescription.AddressV = SharpDX.Direct3D11.TextureAddressMode.Wrap;             this.samplerStateTextures = new SharpDX.Direct3D11.SamplerState(d3dDevice, samplerDescription);             d3dDeviceContext.PixelShader.SetSampler(0, samplerStateTextures);             d3dDeviceContext.VertexShader.SetSampler(0, samplerStateTextures);             d3dDeviceContext.HullShader.SetSampler(0, samplerStateTextures);             d3dDeviceContext.DomainShader.SetSampler(0, samplerStateTextures);             d3dDeviceContext.GeometryShader.SetSampler(0, samplerStateTextures);  
    • By noodleBowl
      I just finished up my 1st iteration of my sprite renderer and I'm sort of questioning its performance.
      Currently, I am trying to render 10K worth of 64x64 textured sprites in a 800x600 window. These sprites all using the same texture, vertex shader, and pixel shader. There is basically no state changes. The sprite renderer itself is dynamic using the D3D11_MAP_WRITE_NO_OVERWRITE then D3D11_MAP_WRITE_DISCARD when the vertex buffer is full. The buffer is large enough to hold all 10K sprites and execute them in a single draw call. Cutting the buffer size down to only being able to fit 1000 sprites before a draw call is executed does not seem to matter / improve performance.  When I clock the time it takes to complete the render method for my sprite renderer (the only renderer that is running) I'm getting about 40ms. Aside from trying to adjust the size of the vertex buffer, I have tried using 1x1 texture and making the window smaller (640x480) as quick and dirty check to see if the GPU was the bottleneck, but I still get 40ms with both of those cases. 

      I'm kind of at a loss. What are some of the ways that I could figure out where my bottleneck is?
      I feel like only being able to render 10K sprites is really low, but I'm not sure. I'm not sure if I coded a poor renderer and there is a bottleneck somewhere or I'm being limited by my hardware

      Just some other info:
      Dev PC specs: GPU: Intel HD Graphics 4600 / Nvidia GTX 850M (Nvidia is set to be the preferred GPU in the Nvida control panel. Vsync is set to off) CPU: Intel Core i7-4710HQ @ 2.5GHz Renderer:
      //The renderer has a working depth buffer //Sprites have matrices that are precomputed. These pretransformed vertices are placed into the buffer Matrix4 model = sprite->getModelMatrix(); verts[0].position = model * verts[0].position; verts[1].position = model * verts[1].position; verts[2].position = model * verts[2].position; verts[3].position = model * verts[3].position; verts[4].position = model * verts[4].position; verts[5].position = model * verts[5].position; //Vertex buffer is flaged for dynamic use vertexBuffer = BufferModule::createVertexBuffer(D3D11_USAGE_DYNAMIC, D3D11_CPU_ACCESS_WRITE, sizeof(SpriteVertex) * MAX_VERTEX_COUNT_FOR_BUFFER); //The vertex buffer is mapped to when adding a sprite to the buffer //vertexBufferMapType could be D3D11_MAP_WRITE_NO_OVERWRITE or D3D11_MAP_WRITE_DISCARD depending on the data already in the vertex buffer D3D11_MAPPED_SUBRESOURCE resource = vertexBuffer->map(vertexBufferMapType); memcpy(((SpriteVertex*)resource.pData) + vertexCountInBuffer, verts, BYTES_PER_SPRITE); vertexBuffer->unmap(); //The constant buffer used for the MVP matrix is updated once per draw call D3D11_MAPPED_SUBRESOURCE resource = mvpConstBuffer->map(D3D11_MAP_WRITE_DISCARD); memcpy(resource.pData, projectionMatrix.getData(), sizeof(Matrix4)); mvpConstBuffer->unmap(); Vertex / Pixel Shader:
      cbuffer mvpBuffer : register(b0) { matrix mvp; } struct VertexInput { float4 position : POSITION; float2 texCoords : TEXCOORD0; float4 color : COLOR; }; struct PixelInput { float4 position : SV_POSITION; float2 texCoords : TEXCOORD0; float4 color : COLOR; }; PixelInput VSMain(VertexInput input) { input.position.w = 1.0f; PixelInput output; output.position = mul(mvp, input.position); output.texCoords = input.texCoords; output.color = input.color; return output; } Texture2D shaderTexture; SamplerState samplerType; float4 PSMain(PixelInput input) : SV_TARGET { float4 textureColor = shaderTexture.Sample(samplerType, input.texCoords); return textureColor; }  
      If anymore info is needed feel free to ask, I would really like to know how I can improve this assuming I'm not hardware limited
    • By DiligentDev
      This article uses material originally posted on Diligent Graphics web site.
      Introduction
      Graphics APIs have come a long way from small set of basic commands allowing limited control of configurable stages of early 3D accelerators to very low-level programming interfaces exposing almost every aspect of the underlying graphics hardware. Next-generation APIs, Direct3D12 by Microsoft and Vulkan by Khronos are relatively new and have only started getting widespread adoption and support from hardware vendors, while Direct3D11 and OpenGL are still considered industry standard. New APIs can provide substantial performance and functional improvements, but may not be supported by older hardware. An application targeting wide range of platforms needs to support Direct3D11 and OpenGL. New APIs will not give any advantage when used with old paradigms. It is totally possible to add Direct3D12 support to an existing renderer by implementing Direct3D11 interface through Direct3D12, but this will give zero benefits. Instead, new approaches and rendering architectures that leverage flexibility provided by the next-generation APIs are expected to be developed.
      There are at least four APIs (Direct3D11, Direct3D12, OpenGL/GLES, Vulkan, plus Apple's Metal for iOS and osX platforms) that a cross-platform 3D application may need to support. Writing separate code paths for all APIs is clearly not an option for any real-world application and the need for a cross-platform graphics abstraction layer is evident. The following is the list of requirements that I believe such layer needs to satisfy:
      Lightweight abstractions: the API should be as close to the underlying native APIs as possible to allow an application leverage all available low-level functionality. In many cases this requirement is difficult to achieve because specific features exposed by different APIs may vary considerably. Low performance overhead: the abstraction layer needs to be efficient from performance point of view. If it introduces considerable amount of overhead, there is no point in using it. Convenience: the API needs to be convenient to use. It needs to assist developers in achieving their goals not limiting their control of the graphics hardware. Multithreading: ability to efficiently parallelize work is in the core of Direct3D12 and Vulkan and one of the main selling points of the new APIs. Support for multithreading in a cross-platform layer is a must. Extensibility: no matter how well the API is designed, it still introduces some level of abstraction. In some cases the most efficient way to implement certain functionality is to directly use native API. The abstraction layer needs to provide seamless interoperability with the underlying native APIs to provide a way for the app to add features that may be missing. Diligent Engine is designed to solve these problems. Its main goal is to take advantages of the next-generation APIs such as Direct3D12 and Vulkan, but at the same time provide support for older platforms via Direct3D11, OpenGL and OpenGLES. Diligent Engine exposes common C++ front-end for all supported platforms and provides interoperability with underlying native APIs. It also supports integration with Unity and is designed to be used as graphics subsystem in a standalone game engine, Unity native plugin or any other 3D application. Full source code is available for download at GitHub and is free to use.
      Overview
      Diligent Engine API takes some features from Direct3D11 and Direct3D12 as well as introduces new concepts to hide certain platform-specific details and make the system easy to use. It contains the following main components:
      Render device (IRenderDevice  interface) is responsible for creating all other objects (textures, buffers, shaders, pipeline states, etc.).
      Device context (IDeviceContext interface) is the main interface for recording rendering commands. Similar to Direct3D11, there are immediate context and deferred contexts (which in Direct3D11 implementation map directly to the corresponding context types). Immediate context combines command queue and command list recording functionality. It records commands and submits the command list for execution when it contains sufficient number of commands. Deferred contexts are designed to only record command lists that can be submitted for execution through the immediate context.
      An alternative way to design the API would be to expose command queue and command lists directly. This approach however does not map well to Direct3D11 and OpenGL. Besides, some functionality (such as dynamic descriptor allocation) can be much more efficiently implemented when it is known that a command list is recorded by a certain deferred context from some thread.
      The approach taken in the engine does not limit scalability as the application is expected to create one deferred context per thread, and internally every deferred context records a command list in lock-free fashion. At the same time this approach maps well to older APIs.
      In current implementation, only one immediate context that uses default graphics command queue is created. To support multiple GPUs or multiple command queue types (compute, copy, etc.), it is natural to have one immediate contexts per queue. Cross-context synchronization utilities will be necessary.
      Swap Chain (ISwapChain interface). Swap chain interface represents a chain of back buffers and is responsible for showing the final rendered image on the screen.
      Render device, device contexts and swap chain are created during the engine initialization.
      Resources (ITexture and IBuffer interfaces). There are two types of resources - textures and buffers. There are many different texture types (2D textures, 3D textures, texture array, cubmepas, etc.) that can all be represented by ITexture interface.
      Resources Views (ITextureView and IBufferView interfaces). While textures and buffers are mere data containers, texture views and buffer views describe how the data should be interpreted. For instance, a 2D texture can be used as a render target for rendering commands or as a shader resource.
      Pipeline State (IPipelineState interface). GPU pipeline contains many configurable stages (depth-stencil, rasterizer and blend states, different shader stage, etc.). Direct3D11 uses coarse-grain objects to set all stage parameters at once (for instance, a rasterizer object encompasses all rasterizer attributes), while OpenGL contains myriad functions to fine-grain control every individual attribute of every stage. Both methods do not map very well to modern graphics hardware that combines all states into one monolithic state under the hood. Direct3D12 directly exposes pipeline state object in the API, and Diligent Engine uses the same approach.
      Shader Resource Binding (IShaderResourceBinding interface). Shaders are programs that run on the GPU. Shaders may access various resources (textures and buffers), and setting correspondence between shader variables and actual resources is called resource binding. Resource binding implementation varies considerably between different API. Diligent Engine introduces a new object called shader resource binding that encompasses all resources needed by all shaders in a certain pipeline state.
      API Basics
      Creating Resources
      Device resources are created by the render device. The two main resource types are buffers, which represent linear memory, and textures, which use memory layouts optimized for fast filtering. Graphics APIs usually have a native object that represents linear buffer. Diligent Engine uses IBuffer interface as an abstraction for a native buffer. To create a buffer, one needs to populate BufferDesc structure and call IRenderDevice::CreateBuffer() method as in the following example:
      BufferDesc BuffDesc; BufferDesc.Name = "Uniform buffer"; BuffDesc.BindFlags = BIND_UNIFORM_BUFFER; BuffDesc.Usage = USAGE_DYNAMIC; BuffDesc.uiSizeInBytes = sizeof(ShaderConstants); BuffDesc.CPUAccessFlags = CPU_ACCESS_WRITE; m_pDevice->CreateBuffer( BuffDesc, BufferData(), &m_pConstantBuffer ); While there is usually just one buffer object, different APIs use very different approaches to represent textures. For instance, in Direct3D11, there are ID3D11Texture1D, ID3D11Texture2D, and ID3D11Texture3D objects. In OpenGL, there is individual object for every texture dimension (1D, 2D, 3D, Cube), which may be a texture array, which may also be multisampled (i.e. GL_TEXTURE_2D_MULTISAMPLE_ARRAY). As a result there are nine different GL texture types that Diligent Engine may create under the hood. In Direct3D12, there is only one resource interface. Diligent Engine hides all these details in ITexture interface. There is only one  IRenderDevice::CreateTexture() method that is capable of creating all texture types. Dimension, format, array size and all other parameters are specified by the members of the TextureDesc structure:
      TextureDesc TexDesc; TexDesc.Name = "My texture 2D"; TexDesc.Type = TEXTURE_TYPE_2D; TexDesc.Width = 1024; TexDesc.Height = 1024; TexDesc.Format = TEX_FORMAT_RGBA8_UNORM; TexDesc.Usage = USAGE_DEFAULT; TexDesc.BindFlags = BIND_SHADER_RESOURCE | BIND_RENDER_TARGET | BIND_UNORDERED_ACCESS; TexDesc.Name = "Sample 2D Texture"; m_pRenderDevice->CreateTexture( TexDesc, TextureData(), &m_pTestTex ); If native API supports multithreaded resource creation, textures and buffers can be created by multiple threads simultaneously.
      Interoperability with native API provides access to the native buffer/texture objects and also allows creating Diligent Engine objects from native handles. It allows applications seamlessly integrate native API-specific code with Diligent Engine.
      Next-generation APIs allow fine level-control over how resources are allocated. Diligent Engine does not currently expose this functionality, but it can be added by implementing IResourceAllocator interface that encapsulates specifics of resource allocation and providing this interface to CreateBuffer() or CreateTexture() methods. If null is provided, default allocator should be used.
      Initializing the Pipeline State
      As it was mentioned earlier, Diligent Engine follows next-gen APIs to configure the graphics/compute pipeline. One big Pipelines State Object (PSO) encompasses all required states (all shader stages, input layout description, depth stencil, rasterizer and blend state descriptions etc.). This approach maps directly to Direct3D12/Vulkan, but is also beneficial for older APIs as it eliminates pipeline misconfiguration errors. With many individual calls tweaking various GPU pipeline settings it is very easy to forget to set one of the states or assume the stage is already properly configured when in fact it is not. Using pipeline state object helps avoid these problems as all stages are configured at once.
      Creating Shaders
      While in earlier APIs shaders were bound separately, in the next-generation APIs as well as in Diligent Engine shaders are part of the pipeline state object. The biggest challenge when authoring shaders is that Direct3D and OpenGL/Vulkan use different shader languages (while Apple uses yet another language in their Metal API). Maintaining two versions of every shader is not an option for real applications and Diligent Engine implements shader source code converter that allows shaders authored in HLSL to be translated to GLSL. To create a shader, one needs to populate ShaderCreationAttribs structure. SourceLanguage member of this structure tells the system which language the shader is authored in:
      SHADER_SOURCE_LANGUAGE_DEFAULT - The shader source language matches the underlying graphics API: HLSL for Direct3D11/Direct3D12 mode, and GLSL for OpenGL and OpenGLES modes. SHADER_SOURCE_LANGUAGE_HLSL - The shader source is in HLSL. For OpenGL and OpenGLES modes, the source code will be converted to GLSL. SHADER_SOURCE_LANGUAGE_GLSL - The shader source is in GLSL. There is currently no GLSL to HLSL converter, so this value should only be used for OpenGL and OpenGLES modes. There are two ways to provide the shader source code. The first way is to use Source member. The second way is to provide a file path in FilePath member. Since the engine is entirely decoupled from the platform and the host file system is platform-dependent, the structure exposes pShaderSourceStreamFactory member that is intended to provide the engine access to the file system. If FilePath is provided, shader source factory must also be provided. If the shader source contains any #include directives, the source stream factory will also be used to load these files. The engine provides default implementation for every supported platform that should be sufficient in most cases. Custom implementation can be provided when needed.
      When sampling a texture in a shader, the texture sampler was traditionally specified as separate object that was bound to the pipeline at run time or set as part of the texture object itself. However, in most cases it is known beforehand what kind of sampler will be used in the shader. Next-generation APIs expose new type of sampler called static sampler that can be initialized directly in the pipeline state. Diligent Engine exposes this functionality: when creating a shader, textures can be assigned static samplers. If static sampler is assigned, it will always be used instead of the one initialized in the texture shader resource view. To initialize static samplers, prepare an array of StaticSamplerDesc structures and initialize StaticSamplers and NumStaticSamplers members. Static samplers are more efficient and it is highly recommended to use them whenever possible. On older APIs, static samplers are emulated via generic sampler objects.
      The following is an example of shader initialization:
      ShaderCreationAttribs Attrs; Attrs.Desc.Name = "MyPixelShader"; Attrs.FilePath = "MyShaderFile.fx"; Attrs.SearchDirectories = "shaders;shaders\\inc;"; Attrs.EntryPoint = "MyPixelShader"; Attrs.Desc.ShaderType = SHADER_TYPE_PIXEL; Attrs.SourceLanguage = SHADER_SOURCE_LANGUAGE_HLSL; BasicShaderSourceStreamFactory BasicSSSFactory(Attrs.SearchDirectories); Attrs.pShaderSourceStreamFactory = &BasicSSSFactory; ShaderVariableDesc ShaderVars[] = {     {"g_StaticTexture", SHADER_VARIABLE_TYPE_STATIC},     {"g_MutableTexture", SHADER_VARIABLE_TYPE_MUTABLE},     {"g_DynamicTexture", SHADER_VARIABLE_TYPE_DYNAMIC} }; Attrs.Desc.VariableDesc = ShaderVars; Attrs.Desc.NumVariables = _countof(ShaderVars); Attrs.Desc.DefaultVariableType = SHADER_VARIABLE_TYPE_STATIC; StaticSamplerDesc StaticSampler; StaticSampler.Desc.MinFilter = FILTER_TYPE_LINEAR; StaticSampler.Desc.MagFilter = FILTER_TYPE_LINEAR; StaticSampler.Desc.MipFilter = FILTER_TYPE_LINEAR; StaticSampler.TextureName = "g_MutableTexture"; Attrs.Desc.NumStaticSamplers = 1; Attrs.Desc.StaticSamplers = &StaticSampler; ShaderMacroHelper Macros; Macros.AddShaderMacro("USE_SHADOWS", 1); Macros.AddShaderMacro("NUM_SHADOW_SAMPLES", 4); Macros.Finalize(); Attrs.Macros = Macros; RefCntAutoPtr<IShader> pShader; m_pDevice->CreateShader( Attrs, &pShader );
      Creating the Pipeline State Object
      After all required shaders are created, the rest of the fields of the PipelineStateDesc structure provide depth-stencil, rasterizer, and blend state descriptions, the number and format of render targets, input layout format, etc. For instance, rasterizer state can be described as follows:
      PipelineStateDesc PSODesc; RasterizerStateDesc &RasterizerDesc = PSODesc.GraphicsPipeline.RasterizerDesc; RasterizerDesc.FillMode = FILL_MODE_SOLID; RasterizerDesc.CullMode = CULL_MODE_NONE; RasterizerDesc.FrontCounterClockwise = True; RasterizerDesc.ScissorEnable = True; RasterizerDesc.AntialiasedLineEnable = False; Depth-stencil and blend states are defined in a similar fashion.
      Another important thing that pipeline state object encompasses is the input layout description that defines how inputs to the vertex shader, which is the very first shader stage, should be read from the memory. Input layout may define several vertex streams that contain values of different formats and sizes:
      // Define input layout InputLayoutDesc &Layout = PSODesc.GraphicsPipeline.InputLayout; LayoutElement TextLayoutElems[] = {     LayoutElement( 0, 0, 3, VT_FLOAT32, False ),     LayoutElement( 1, 0, 4, VT_UINT8, True ),     LayoutElement( 2, 0, 2, VT_FLOAT32, False ), }; Layout.LayoutElements = TextLayoutElems; Layout.NumElements = _countof( TextLayoutElems ); Finally, pipeline state defines primitive topology type. When all required members are initialized, a pipeline state object can be created by IRenderDevice::CreatePipelineState() method:
      // Define shader and primitive topology PSODesc.GraphicsPipeline.PrimitiveTopologyType = PRIMITIVE_TOPOLOGY_TYPE_TRIANGLE; PSODesc.GraphicsPipeline.pVS = pVertexShader; PSODesc.GraphicsPipeline.pPS = pPixelShader; PSODesc.Name = "My pipeline state"; m_pDev->CreatePipelineState(PSODesc, &m_pPSO); When PSO object is bound to the pipeline, the engine invokes all API-specific commands to set all states specified by the object. In case of Direct3D12 this maps directly to setting the D3D12 PSO object. In case of Direct3D11, this involves setting individual state objects (such as rasterizer and blend states), shaders, input layout etc. In case of OpenGL, this requires a number of fine-grain state tweaking calls. Diligent Engine keeps track of currently bound states and only calls functions to update these states that have actually changed.
      Binding Shader Resources
      Direct3D11 and OpenGL utilize fine-grain resource binding models, where an application binds individual buffers and textures to certain shader or program resource binding slots. Direct3D12 uses a very different approach, where resource descriptors are grouped into tables, and an application can bind all resources in the table at once by setting the table in the command list. Resource binding model in Diligent Engine is designed to leverage this new method. It introduces a new object called shader resource binding that encapsulates all resource bindings required for all shaders in a certain pipeline state. It also introduces the classification of shader variables based on the frequency of expected change that helps the engine group them into tables under the hood:
      Static variables (SHADER_VARIABLE_TYPE_STATIC) are variables that are expected to be set only once. They may not be changed once a resource is bound to the variable. Such variables are intended to hold global constants such as camera attributes or global light attributes constant buffers. Mutable variables (SHADER_VARIABLE_TYPE_MUTABLE) define resources that are expected to change on a per-material frequency. Examples may include diffuse textures, normal maps etc. Dynamic variables (SHADER_VARIABLE_TYPE_DYNAMIC) are expected to change frequently and randomly. Shader variable type must be specified during shader creation by populating an array of ShaderVariableDesc structures and initializing ShaderCreationAttribs::Desc::VariableDesc and ShaderCreationAttribs::Desc::NumVariables members (see example of shader creation above).
      Static variables cannot be changed once a resource is bound to the variable. They are bound directly to the shader object. For instance, a shadow map texture is not expected to change after it is created, so it can be bound directly to the shader:
      PixelShader->GetShaderVariable( "g_tex2DShadowMap" )->Set( pShadowMapSRV ); Mutable and dynamic variables are bound via a new Shader Resource Binding object (SRB) that is created by the pipeline state (IPipelineState::CreateShaderResourceBinding()):
      m_pPSO->CreateShaderResourceBinding(&m_pSRB); Note that an SRB is only compatible with the pipeline state it was created from. SRB object inherits all static bindings from shaders in the pipeline, but is not allowed to change them.
      Mutable resources can only be set once for every instance of a shader resource binding. Such resources are intended to define specific material properties. For instance, a diffuse texture for a specific material is not expected to change once the material is defined and can be set right after the SRB object has been created:
      m_pSRB->GetVariable(SHADER_TYPE_PIXEL, "tex2DDiffuse")->Set(pDiffuseTexSRV); In some cases it is necessary to bind a new resource to a variable every time a draw command is invoked. Such variables should be labeled as dynamic, which will allow setting them multiple times through the same SRB object:
      m_pSRB->GetVariable(SHADER_TYPE_VERTEX, "cbRandomAttribs")->Set(pRandomAttrsCB); Under the hood, the engine pre-allocates descriptor tables for static and mutable resources when an SRB objcet is created. Space for dynamic resources is dynamically allocated at run time. Static and mutable resources are thus more efficient and should be used whenever possible.
      As you can see, Diligent Engine does not expose low-level details of how resources are bound to shader variables. One reason for this is that these details are very different for various APIs. The other reason is that using low-level binding methods is extremely error-prone: it is very easy to forget to bind some resource, or bind incorrect resource such as bind a buffer to the variable that is in fact a texture, especially during shader development when everything changes fast. Diligent Engine instead relies on shader reflection system to automatically query the list of all shader variables. Grouping variables based on three types mentioned above allows the engine to create optimized layout and take heavy lifting of matching resources to API-specific resource location, register or descriptor in the table.
      This post gives more details about the resource binding model in Diligent Engine.
      Setting the Pipeline State and Committing Shader Resources
      Before any draw or compute command can be invoked, the pipeline state needs to be bound to the context:
      m_pContext->SetPipelineState(m_pPSO); Under the hood, the engine sets the internal PSO object in the command list or calls all the required native API functions to properly configure all pipeline stages.
      The next step is to bind all required shader resources to the GPU pipeline, which is accomplished by IDeviceContext::CommitShaderResources() method:
      m_pContext->CommitShaderResources(m_pSRB, COMMIT_SHADER_RESOURCES_FLAG_TRANSITION_RESOURCES); The method takes a pointer to the shader resource binding object and makes all resources the object holds available for the shaders. In the case of D3D12, this only requires setting appropriate descriptor tables in the command list. For older APIs, this typically requires setting all resources individually.
      Next-generation APIs require the application to track the state of every resource and explicitly inform the system about all state transitions. For instance, if a texture was used as render target before, while the next draw command is going to use it as shader resource, a transition barrier needs to be executed. Diligent Engine does the heavy lifting of state tracking.  When CommitShaderResources() method is called with COMMIT_SHADER_RESOURCES_FLAG_TRANSITION_RESOURCES flag, the engine commits and transitions resources to correct states at the same time. Note that transitioning resources does introduce some overhead. The engine tracks state of every resource and it will not issue the barrier if the state is already correct. But checking resource state is an overhead that can sometimes be avoided. The engine provides IDeviceContext::TransitionShaderResources() method that only transitions resources:
      m_pContext->TransitionShaderResources(m_pPSO, m_pSRB); In some scenarios it is more efficient to transition resources once and then only commit them.
      Invoking Draw Command
      The final step is to set states that are not part of the PSO, such as render targets, vertex and index buffers. Diligent Engine uses Direct3D11-syle API that is translated to other native API calls under the hood:
      ITextureView *pRTVs[] = {m_pRTV}; m_pContext->SetRenderTargets(_countof( pRTVs ), pRTVs, m_pDSV); // Clear render target and depth buffer const float zero[4] = {0, 0, 0, 0}; m_pContext->ClearRenderTarget(nullptr, zero); m_pContext->ClearDepthStencil(nullptr, CLEAR_DEPTH_FLAG, 1.f); // Set vertex and index buffers IBuffer *buffer[] = {m_pVertexBuffer}; Uint32 offsets[] = {0}; Uint32 strides[] = {sizeof(MyVertex)}; m_pContext->SetVertexBuffers(0, 1, buffer, strides, offsets, SET_VERTEX_BUFFERS_FLAG_RESET); m_pContext->SetIndexBuffer(m_pIndexBuffer, 0); Different native APIs use various set of function to execute draw commands depending on command details (if the command is indexed, instanced or both, what offsets in the source buffers are used etc.). For instance, there are 5 draw commands in Direct3D11 and more than 9 commands in OpenGL with something like glDrawElementsInstancedBaseVertexBaseInstance not uncommon. Diligent Engine hides all details with single IDeviceContext::Draw() method that takes takes DrawAttribs structure as an argument. The structure members define all attributes required to perform the command (primitive topology, number of vertices or indices, if draw call is indexed or not, if draw call is instanced or not, if draw call is indirect or not, etc.). For example:
      DrawAttribs attrs; attrs.IsIndexed = true; attrs.IndexType = VT_UINT16; attrs.NumIndices = 36; attrs.Topology = PRIMITIVE_TOPOLOGY_TRIANGLE_LIST; pContext->Draw(attrs); For compute commands, there is IDeviceContext::DispatchCompute() method that takes DispatchComputeAttribs structure that defines compute grid dimension.
      Source Code
      Full engine source code is available on GitHub and is free to use. The repository contains two samples, asteroids performance benchmark and example Unity project that uses Diligent Engine in native plugin.
      AntTweakBar sample is Diligent Engine’s “Hello World” example.

       
      Atmospheric scattering sample is a more advanced example. It demonstrates how Diligent Engine can be used to implement various rendering tasks: loading textures from files, using complex shaders, rendering to multiple render targets, using compute shaders and unordered access views, etc.

      Asteroids performance benchmark is based on this demo developed by Intel. It renders 50,000 unique textured asteroids and allows comparing performance of Direct3D11 and Direct3D12 implementations. Every asteroid is a combination of one of 1000 unique meshes and one of 10 unique textures.

      Finally, there is an example project that shows how Diligent Engine can be integrated with Unity.

      Future Work
      The engine is under active development. It currently supports Windows desktop, Universal Windows and Android platforms. Direct3D11, Direct3D12, OpenGL/GLES backends are now feature complete. Vulkan backend is coming next, and support for more platforms is planned.
    • By noodleBowl
      I am currently working on my first iteration of my sprite renderer and I'm trying to draw 2 sprites. They both use the same texture and are placed into the same buffer, but unfortunately only the second sprite is shown on the the screen. I assume I messed something up when I place them into the buffer and that I am overwriting the data of the first sprite.

      So how should I be mapping my buffer with an offset?
      /* Code that sets up the sprite vertices and etc */ D3D11_MAPPED_SUBRESOURCE resource = vertexBuffer->map(vertexBufferMapType); memcpy(resource.pData, verts, sizeof(SpriteVertex) * VERTEX_PER_QUAD); vertexBuffer->unmap(); vertexCount += VERTEX_PER_QUAD; I feel like I should be doing something like:
      /* Code that sets up the sprite vertices and etc */ D3D11_MAPPED_SUBRESOURCE resource = vertexBuffer->map(vertexBufferMapType); //Place the sprite vertex data into the pData using the current vertex count as offset //The code resource.pData[vertexCount] is syntatically wrong though :( Not sure how it should look since pData is void pointer memcpy(resource.pData[vertexCount], verts, sizeof(SpriteVertex) * VERTEX_PER_QUAD); vertexBuffer->unmap(); vertexCount += VERTEX_PER_QUAD;  
      Also speaking of offsets can someone give an example of when the pOffsets param for the IASetVertexBuffers call would not be 0
       
  • Popular Now