Sign in to follow this  
Alundra

DX11 Template shader, Bad practice ?

Recommended Posts

Alundra    2316

Hi all,

It's possible to do that to factor the shader code, code from intel sample :

// Templated shader factory utilities
namespace ShaderFactoryUtil
{
    template <typename T> LPCSTR GetShaderProfileString();
    template <typename T> T* CreateShader(ID3D11Device* d3dDevice, const void* shaderBytecode, size_t bytecodeLength);

    // Vertex shader
    template <> inline LPCSTR GetShaderProfileString<ID3D11VertexShader>() { return "vs_5_0"; }
    template <> inline 
    ID3D11VertexShader* CreateShader<ID3D11VertexShader>(ID3D11Device* d3dDevice, const void* shaderBytecode, size_t bytecodeLength)
    {
        ID3D11VertexShader *shader = 0;
        HRESULT hr = d3dDevice->CreateVertexShader(shaderBytecode, bytecodeLength, 0, &shader);
        if (FAILED(hr)) {
            // This shouldn't produce errors given proper bytecode, so a simple assert is fine
            assert(false);
        }
        return shader;
    }

    // Pixel shader
    template <> inline LPCSTR GetShaderProfileString<ID3D11PixelShader>() { return "ps_5_0"; }
    template <> inline 
    ID3D11PixelShader* CreateShader<ID3D11PixelShader>(ID3D11Device* d3dDevice, const void* shaderBytecode, size_t bytecodeLength)
    {
        ID3D11PixelShader *shader = 0;
        HRESULT hr = d3dDevice->CreatePixelShader(shaderBytecode, bytecodeLength, 0, &shader);
        if (FAILED(hr)) {
            // This shouldn't produce errors given proper bytecode, so a simple assert is fine
            assert(false);
        }
        return shader;
    }

    // Compute shader
    template <> inline LPCSTR GetShaderProfileString<ID3D11ComputeShader>() { return "cs_5_0"; }
    template <> inline 
    ID3D11ComputeShader* CreateShader<ID3D11ComputeShader>(ID3D11Device* d3dDevice, const void* shaderBytecode, size_t bytecodeLength)
    {
        ID3D11ComputeShader *shader = 0;
        HRESULT hr = d3dDevice->CreateComputeShader(shaderBytecode, bytecodeLength, 0, &shader);
        if (FAILED(hr)) {
            // This shouldn't produce errors given proper bytecode, so a simple assert is fine
            assert(false);
        }
        return shader;
    }
}

// Templated (on shader type) shader wrapper to wrap basic functionality
// TODO: Support optional lazy compile
template <typename T>
class Shader
{
public:
    Shader(ID3D11Device* d3dDevice, LPCTSTR srcFile, LPCSTR functionName, CONST D3D10_SHADER_MACRO *defines = 0)
    {
        // TODO: Support profile selection from the application? Probably not necessary as we don't
        // support down-level hardware at the moment anyways.
        LPCSTR profile = ShaderFactoryUtil::GetShaderProfileString<T>();
        UINT shaderFlags = D3D10_SHADER_ENABLE_STRICTNESS | D3D10_SHADER_PACK_MATRIX_ROW_MAJOR;
        ID3D10Blob *bytecode = 0;
        ID3D10Blob *errors = 0;
        HRESULT hr = D3DX11CompileFromFile(srcFile, defines, 0, functionName, profile, shaderFlags, 0, 0, &bytecode, &errors, 0);
        if (errors) {
            OutputDebugStringA(static_cast<const char *>(errors->GetBufferPointer()));
        }
        if (FAILED(hr)) {
            // TODO: Define exception type and improve this error string, but the ODS will do for now
            throw std::runtime_error("Error compiling shader");
        }
        mShader = ShaderFactoryUtil::CreateShader<T>(d3dDevice, bytecode->GetBufferPointer(), bytecode->GetBufferSize());
        bytecode->Release();
    }
    
    ~Shader() { mShader->Release(); }
    T* GetShader() { return mShader; }

private:
    // Not implemented
    Shader(const Shader&);
    Shader& operator=(const Shader&);

    T* mShader;
};

typedef Shader<ID3D11VertexShader> VertexShader;
typedef Shader<ID3D11PixelShader> PixelShader;
typedef Shader<ID3D11ComputeShader> ComputeShader;

Do you see that as a bad practice ?

 

Share this post


Link to post
Share on other sites
Hodgman    51226

It certainly works fine biggrin.png
 
But I would probably prefer to follow the KISS rule and stick to something simpler like a switch statement instead of fancy templates here. 

namespace ShaderProfile { enum Type {
	Vertex, Pixel, Compute
}}
const char* s_shaderProfileStrings[] = { "vs_5_0", "ps_5_0", "cs_5_0" };
void* CreateShader(ID3D11Device* d3dDevice, const void* shaderBytecode, size_t bytecodeLength);
{
	HRESULT hr = 0;
	void* shader = 0;
	switch(type)
	{
	case ShaderProfile::Vertex:
	        hr = d3dDevice->CreatePixelShader(shaderBytecode, bytecodeLength, 0, (ID3D11PixelShader**)&shader); break;
	case ShaderProfile::Pixel:
	        hr = d3dDevice->CreateComputeShader(shaderBytecode, bytecodeLength, 0, (ID3D11VertexShader**)&shader); break;
	case ShaderProfile::Compute:
	        hr = d3dDevice->CreateVertexShader(shaderBytecode, bytecodeLength, 0, (ID3D11ComputeShader**)&shader); break;
	default: assert(false); return 0;
	}
	if (FAILED(hr))
		assert(false);
	return shader;
}


class Shader : NonCopyable
{
public:
    Shader(ShaderProfile::Type type, ID3D11Device* d3dDevice, LPCTSTR srcFile, LPCSTR functionName, CONST D3D10_SHADER_MACRO *defines = 0)
    {
        mType = type;
        //todo - this should be loading bytecode from disk instead of compiling at runtime
        const char* profile = s_shaderProfileStrings[type];
        UINT shaderFlags = D3D10_SHADER_ENABLE_STRICTNESS | D3D10_SHADER_PACK_MATRIX_ROW_MAJOR;
        ID3D10Blob *bytecode = 0;
        ID3D10Blob *errors = 0;
        HRESULT hr = D3DX11CompileFromFile(srcFile, defines, 0, functionName, profile, shaderFlags, 0, 0, &bytecode, &errors, 0);
        if (errors) {
            OutputDebugStringA(static_cast<const char *>(errors->GetBufferPointer()));
        }
        if (FAILED(hr)) assert(false && "Error compiling shader");
        mShader = ShaderFactoryUtil::CreateShader(type, d3dDevice, bytecode->GetBufferPointer(), bytecode->GetBufferSize());
        bytecode->Release();
    }
    
    ~Shader()
    {
	switch(mType)
	{
	case ShaderProfile::Vertex:
	        ((ID3D11VertexShader*)mShader)->Release();
	case ShaderProfile::Pixel:
	        ((ID3D11PixelShader*)mShader)->Release();
	case ShaderProfile::Compute:
	        ((ID3D11ComputeShader*)mShader)->Release();
	}
        
    }
    void* GetVertexShader()  const { assert(mType==ShaderProfile::Vertex) ; return (ID3D11VertexShader* )mShader; }
    void* GetPixelShader()   const { assert(mType==ShaderProfile::Pixel  ); return (ID3D11PixelShader*  )mShader; }
    void* GetComputeShader() const { assert(mType==ShaderProfile::Compute); return (ID3D11ComputeShader*)mShader; }

private:
    ShaderProfile::Type mType;
    void* mShader;
};

Share this post


Link to post
Share on other sites

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  

  • Similar Content

    • By Endurion
      I have a gaming framework with an renderer interface. Those support DX8, DX9 and latest, DX11. Both DX8 and DX9 use fixed function pipeline, while DX11 obviously uses shaders. I've got most of the parts working fine, as in I can switch renderers and notice almost no difference. The most advanced features are 2 directional lights with a single texture  
      My last problem is lighting; albeit there's documentation on the D3D lighting model I still can't get the behaviour right. My mistake shows most prominently in the dark side opposite the lights. I'm pretty sure the ambient calculation is off, but that one's supposed to be the most simple one and should be hard to get wrong.
      Interestingly I've been searching high and low, and have yet to find a resource that shows how to build a HLSL shader where diffuse, ambient and specular are used together with material properties. I've got various shaders for all the variations I'm supporting. I stepped through the shader with the graphics debugger, but the calculation seems to do what I want. I'm just not sure the formula is correct.
      This one should suffice though, it's doing two directional lights, texture modulated with vertex color and a normal. Maybe someone can spot one (or more mistakes). And yes, this is in the vertex shader and I'm aware lighting will be as "bad" as in fixed function; that's my goal currently.
      // A constant buffer that stores the three basic column-major matrices for composing geometry. cbuffer ModelViewProjectionConstantBuffer : register(b0) { matrix model; matrix view; matrix projection; matrix ortho2d; }; struct DirectionLight { float3 Direction; float PaddingL1; float4 Ambient; float4 Diffuse; float4 Specular; }; cbuffer LightsConstantBuffer : register( b1 ) { float4 Ambient; float3 EyePos; float PaddingLC1; DirectionLight Light[8]; }; struct Material { float4 MaterialEmissive; float4 MaterialAmbient; float4 MaterialDiffuse; float4 MaterialSpecular; float MaterialSpecularPower; float3 MaterialPadding; }; cbuffer MaterialConstantBuffer : register( b2 ) { Material _Material; }; // Per-vertex data used as input to the vertex shader. struct VertexShaderInput { float3 pos : POSITION; float3 normal : NORMAL; float4 color : COLOR0; float2 tex : TEXCOORD0; }; // Per-pixel color data passed through the pixel shader. struct PixelShaderInput { float4 pos : SV_POSITION; float2 tex : TEXCOORD0; float4 color : COLOR0; }; // Simple shader to do vertex processing on the GPU. PixelShaderInput main(VertexShaderInput input) { PixelShaderInput output; float4 pos = float4( input.pos, 1.0f ); // Transform the vertex position into projected space. pos = mul(pos, model); pos = mul(pos, view); pos = mul(pos, projection); output.pos = pos; // pass texture coords output.tex = input.tex; // Calculate the normal vector against the world matrix only. //set required lighting vectors for interpolation float3 normal = mul( input.normal, ( float3x3 )model ); normal = normalize( normal ); float4 ambientEffect = Ambient; float4 diffuseEffect = float4( 0, 0, 0, 0 ); float4 specularEffect = float4( 0, 0, 0, 0 ); for ( int i = 0; i < 2; ++i ) { // Invert the light direction for calculations. float3 lightDir = -Light[i].Direction; float lightFactor = max( dot( lightDir, input.normal ), 0 ); ambientEffect += Light[i].Ambient * _Material.MaterialAmbient; diffuseEffect += saturate( Light[i].Diffuse * dot( normal, lightDir ) );// * _Material.MaterialDiffuse; //specularEffect += Light[i].Specular * dot( normal, halfangletolight ) * _Material.MaterialSpecularPower; } specularEffect *= _Material.MaterialSpecular; //ambientEffect.w = 1.0; ambientEffect = normalize( ambientEffect ); /* Ambient effect: (L1.ambient + L2.ambient) * object ambient color Diffuse effect: (L1.diffuse * Dot(VertexNormal, Light1.Direction) + L2.diffuse * Dot(VertexNormal, Light2.Direction)) * object diffuse color Specular effect: (L1.specular * Dot(VertexNormal, HalfAngleToLight1) * Object specular reflection power + L2.specular * Dot(VertexNormal, HalfAngleToLight2) * Object specular reflection power ) * object specular color Resulting color = Ambient effect + diffuse effect + specular effect*/ float4 totalFactor = ambientEffect + diffuseEffect + specularEffect; totalFactor.w = 1.0; output.color = input.color * totalFactor; return output; }   Edit: This message editor is driving me nuts (Arrrr!) - I don't write code in Word.
    • By Mercesa
      Hey folks. So I'm having this problem in which if my camera is close to a surface, the SSAO pass suddenly spikes up to around taking 16 milliseconds.
      When still looking towards the same surface, but less close. The framerate resolves itself and becomes regular again.
      This happens with ANY surface of my model, I am a bit clueless in regards to what could cause this. Any ideas?
      In attached image: y axis is time in ms, x axis is current frame. The dips in SSAO milliseconds are when I moved away from the surface, the peaks happen when I am very close to the surface.

       
      Edit: So I've done some more in-depth profiling with Nvidia nsight. So these are the facts from my results
      Count of command buffers goes from 4 (far away from surface) to ~20(close to surface).
      The command buffer duration in % goes from around ~30% to ~99%
      Sometimes the CPU duration takes up to 0.03 to 0.016 milliseconds per frame while comparatively usually it takes around 0.002 milliseconds.
      I am using a vertex shader which generates my full-screen quad and afterwards I do my SSAO calculations in my pixel shader, could this be a GPU driver bug? I'm a bit lost myself. It seems there could be a CPU/GPU resource stall. But why would the amount of command buffers be variable depending on distance from a surface?
       
       
      Edit n2: Any resolution above 720p starts to have this issue, and I am fairly certain my SSAO is not that performance heavy it would crap itself at a bit higher resolutions.
       
    • By turanszkij
      In DirectX 11 we have a 24 bit integer depth + 8bit stencil format for depth-stencil resources ( DXGI_FORMAT_D24_UNORM_S8_UINT ). However, in an AMD GPU documentation for consoles I have seen they mentioned, that internally this format is implemented as a 64 bit resource with 32 bits for depth (but just truncated for 24 bits) and 32 bits for stencil (truncated to 8 bits). AMD recommends using a 32 bit floating point depth buffer instead with 8 bit stencil which is this format: DXGI_FORMAT_D32_FLOAT_S8X24_UINT.
      Does anyone know why this is? What is the usual way of doing this, just follow the recommendation and use a 64 bit depthstencil? Are there performance considerations or is it just recommended to not waste memory? What about Nvidia and Intel, is using a 24 bit depthbuffer relevant on their hardware?
      Cheers!
       
    • By gsc
      Hi! I am trying to implement simple SSAO postprocess. The main source of my knowledge on this topic is that awesome tutorial.
      But unfortunately something doesn't work... And after a few long hours I need some help. Here is my hlsl shader:
      float3 randVec = _noise * 2.0f - 1.0f; // noise: vec: {[0;1], [0;1], 0} float3 tangent = normalize(randVec - normalVS * dot(randVec, normalVS)); float3 bitangent = cross(tangent, normalVS); float3x3 TBN = float3x3(tangent, bitangent, normalVS); float occlusion = 0.0; for (int i = 0; i < kernelSize; ++i) { float3 samplePos = samples[i].xyz; // samples: {[-1;1], [-1;1], [0;1]} samplePos = mul(samplePos, TBN); samplePos = positionVS.xyz + samplePos * ssaoRadius; float4 offset = float4(samplePos, 1.0f); offset = mul(offset, projectionMatrix); offset.xy /= offset.w; offset.y = -offset.y; offset.xy = offset.xy * 0.5f + 0.5f; float sampleDepth = tex_4.Sample(textureSampler, offset.xy).a; sampleDepth = vsPosFromDepth(sampleDepth, offset.xy).z; const float threshold = 0.025f; float rangeCheck = abs(positionVS.z - sampleDepth) < ssaoRadius ? 1.0 : 0.0; occlusion += (sampleDepth <= samplePos.z + threshold ? 1.0 : 0.0) * rangeCheck; } occlusion = saturate(1 - (occlusion / kernelSize)); And current result: http://imgur.com/UX2X1fc
      I will really appreciate for any advice!
    • By isu diss
       I'm trying to code Rayleigh part of Nishita's model (Display Method of the Sky Color Taking into Account Multiple Scattering). I get black screen no colors. Can anyone find the issue for me?
       
      #define InnerRadius 6320000 #define OutterRadius 6420000 #define PI 3.141592653 #define Isteps 20 #define Ksteps 10 static float3 RayleighCoeffs = float3(6.55e-6, 1.73e-5, 2.30e-5); RWTexture2D<float4> SkyColors : register (u0); cbuffer CSCONSTANTBUF : register( b0 ) { float fHeight; float3 vSunDir; } float Density(float Height) { return exp(-Height/8340); } float RaySphereIntersection(float3 RayOrigin, float3 RayDirection, float3 SphereOrigin, float Radius) { float t1, t0; float3 L = SphereOrigin - RayOrigin; float tCA = dot(L, RayDirection); if (tCA < 0) return -1; float lenL = length(L); float D2 = (lenL*lenL) - (tCA*tCA); float Radius2 = (Radius*Radius); if (D2<=Radius2) { float tHC = sqrt(Radius2 - D2); t0 = tCA-tHC; t1 = tCA+tHC; } else return -1; return t1; } float RayleighPhaseFunction(float cosTheta) { return ((3/(16*PI))*(1+cosTheta*cosTheta)); } float OpticalDepth(float3 StartPosition, float3 EndPosition) { float3 Direction = normalize(EndPosition - StartPosition); float RayLength = RaySphereIntersection(StartPosition, Direction, float3(0, 0, 0), OutterRadius); float SampleLength = RayLength / Isteps; float3 tmpPos = StartPosition + 0.5 * SampleLength * Direction; float tmp; for (int i=0; i<Isteps; i++) { tmp += Density(length(tmpPos)-InnerRadius); tmpPos += SampleLength * Direction; } return tmp*SampleLength; } static float fExposure = -2; float3 HDR( float3 LDR) { return 1.0f - exp( fExposure * LDR ); } [numthreads(32, 32, 1)] //disptach 8, 8, 1 it's 256 by 256 image void ComputeSky(uint3 DTID : SV_DispatchThreadID) { float X = ((2 * DTID.x) / 255) - 1; float Y = 1 - ((2 * DTID.y) / 255); float r = sqrt(((X*X)+(Y*Y))); float Theta = r * (PI); float Phi = atan2(Y, X); static float3 Eye = float3(0, 10, 0); float ViewOD = 0, SunOD = 0, tmpDensity = 0; float3 Attenuation = 0, tmp = 0, Irgb = 0; //if (r<=1) { float3 ViewDir = normalize(float3(sin(Theta)*cos(Phi), cos(Theta),sin(Theta)*sin(Phi) )); float ViewRayLength = RaySphereIntersection(Eye, ViewDir, float3(0, 0, 0), OutterRadius); float SampleLength = ViewRayLength / Ksteps; //vSunDir = normalize(vSunDir); float cosTheta = dot(normalize(vSunDir), ViewDir); float3 tmpPos = Eye + 0.5 * SampleLength * ViewDir; for(int k=0; k<Ksteps; k++) { float SunRayLength = RaySphereIntersection(tmpPos, vSunDir, float3(0, 0, 0), OutterRadius); float3 TopAtmosphere = tmpPos + SunRayLength*vSunDir; ViewOD = OpticalDepth(Eye, tmpPos); SunOD = OpticalDepth(tmpPos, TopAtmosphere); tmpDensity = Density(length(tmpPos)-InnerRadius); Attenuation = exp(-RayleighCoeffs*(ViewOD+SunOD)); tmp += tmpDensity*Attenuation; tmpPos += SampleLength * ViewDir; } Irgb = RayleighCoeffs*RayleighPhaseFunction(cosTheta)*tmp*SampleLength; SkyColors[DTID.xy] = float4(Irgb, 1); } }  
  • Popular Now