source: data/branches/Shader_HS18/programs/Cg/Example_Basic_sm4.cg

/*
  Basic ambient lighting vertex program
*/
void ambientOneTexture_vp(float4 position    : POSITION,
                                                  float3   normal    : NORMAL,
                                                  float2   uv        : TEXCOORD0,
                                                  float3   tangent   : TANGENT,                                           

                                                  
                                                  out float4 oPosition : SV_POSITION,
                                                  out float2 oUv           : TEXCOORD0,
                                                  out float4 colour    : COLOR,

                                                  uniform float4x4 worldViewProj,
                                                  uniform float4 ambient)
{
        oPosition = mul(worldViewProj, position);
        oUv = uv;
        colour = ambient;
}

/*
  Basic fragment program using texture and diffuse colour.
*/
void diffuseOneTexture_fp(float4 position          : SV_POSITION, 
                                                  float2 uv                : TEXCOORD0,
                                                  float4 diffuse           : COLOR,
                                                  out float4 colour        : COLOR,
                                                  uniform sampler2D texMap : register(s0))
{
        colour = tex2D(texMap,uv) * diffuse;
}
                          
/*
  Single-weight-per-vertex hardware skinning, 2 lights
  The trouble with vertex programs is they're not general purpose, but
  fixed function hardware skinning is very poorly supported
*/
void hardwareSkinningOneWeight_vp(
        float4 position : POSITION,
        float3 normal   : NORMAL,
        float2 uv       : TEXCOORD0,
        float  blendIdx : BLENDINDICES,
        

        out float4 oPosition : SV_POSITION,
        out float2 oUv       : TEXCOORD0,
        out float4 colour           : COLOR,
        // Support up to 24 bones of float3x4
        // vs_1_1 only supports 96 params so more than this is not feasible
        uniform float3x4   worldMatrix3x4Array[24],
        uniform float4x4 viewProjectionMatrix,
        uniform float4   lightPos[2],
        uniform float4   lightDiffuseColour[2],
        uniform float4   ambient)
{
        // transform by indexed matrix
        float4 blendPos = float4(mul(worldMatrix3x4Array[blendIdx], position).xyz, 1.0);
        // view / projection
        oPosition = mul(viewProjectionMatrix, blendPos);
        // transform normal
        float3 norm = mul((float3x3)worldMatrix3x4Array[blendIdx], normal);
        // Lighting - support point and directional
        float3 lightDir0 =      normalize(
                lightPos[0].xyz -  (blendPos.xyz * lightPos[0].w));
        float3 lightDir1 =      normalize(
                lightPos[1].xyz -  (blendPos.xyz * lightPos[1].w));

        oUv = uv;
        colour = ambient + 
                (saturate(dot(lightDir0, norm)) * lightDiffuseColour[0]) + 
                (saturate(dot(lightDir1, norm)) * lightDiffuseColour[1]);
        
}       

/*
  Single-weight-per-vertex hardware skinning, shadow-caster pass
*/
void hardwareSkinningOneWeightCaster_vp(
        float4 position : POSITION,
        float3 normal   : NORMAL,
        float  blendIdx : BLENDINDICES,
        

        out float4 oPosition : SV_POSITION,
        out float4 colour    : COLOR,
        // Support up to 24 bones of float3x4
        // vs_1_1 only supports 96 params so more than this is not feasible
        uniform float3x4   worldMatrix3x4Array[24],
        uniform float4x4 viewProjectionMatrix,
        uniform float4   ambient)
{
        // transform by indexed matrix
        float4 blendPos = float4(mul(worldMatrix3x4Array[blendIdx], position).xyz, 1.0);
        // view / projection
        oPosition = mul(viewProjectionMatrix, blendPos);
        
        colour = ambient;
        
}       

/*
  Two-weight-per-vertex hardware skinning, 2 lights
  The trouble with vertex programs is they're not general purpose, but
  fixed function hardware skinning is very poorly supported
*/
void hardwareSkinningTwoWeights_vp(
        float4 position : POSITION,
        float3 normal   : NORMAL,
        float2 uv       : TEXCOORD0,
        float4 blendIdx : BLENDINDICES,
        float4 blendWgt : BLENDWEIGHT,
        

        out float4 oPosition : SV_POSITION,
        out float2 oUv       : TEXCOORD0,
        out float4 colour           : COLOR,
        // Support up to 24 bones of float3x4
        // vs_1_1 only supports 96 params so more than this is not feasible
        uniform float3x4   worldMatrix3x4Array[24],
        uniform float4x4 viewProjectionMatrix,
        uniform float4   lightPos[2],
        uniform float4   lightDiffuseColour[2],
        uniform float4   ambient,
        uniform float4   diffuse)
{
        // transform by indexed matrix
        float4 blendPos = float4(0,0,0,0);
        int i;
        for (i = 0; i < 2; ++i)
        {
                blendPos += float4(mul(worldMatrix3x4Array[blendIdx[i]], position).xyz, 1.0) * blendWgt[i];
        }
        // view / projection
        oPosition = mul(viewProjectionMatrix, blendPos);
        // transform normal
        float3 norm = float3(0,0,0);
        for (i = 0; i < 2; ++i)
        {
                norm += mul((float3x3)worldMatrix3x4Array[blendIdx[i]], normal) * 
                blendWgt[i];
        }
        norm = normalize(norm);
        // Lighting - support point and directional
        float3 lightDir0 =      normalize(
                lightPos[0].xyz -  (blendPos.xyz * lightPos[0].w));
        float3 lightDir1 =      normalize(
                lightPos[1].xyz -  (blendPos.xyz * lightPos[1].w));

        
        oUv = uv;
        colour = diffuse * (ambient + 
                (saturate(dot(lightDir0, norm)) * lightDiffuseColour[0]) + 
                (saturate(dot(lightDir1, norm)) * lightDiffuseColour[1]));
        
}

/*
  Two-weight-per-vertex hardware skinning, shadow caster pass
*/
void hardwareSkinningTwoWeightsCaster_vp(
        float4 position : POSITION,
        float3 normal   : NORMAL,
        float2 uv       : TEXCOORD0,
        float4 blendIdx : BLENDINDICES,
        float4 blendWgt : BLENDWEIGHT,
        

        out float4 oPosition : SV_POSITION,
        out float4 colour           : COLOR,
        // Support up to 24 bones of float3x4
        // vs_1_1 only supports 96 params so more than this is not feasible
        uniform float3x4   worldMatrix3x4Array[24],
        uniform float4x4 viewProjectionMatrix,
        uniform float4   ambient)
{
        // transform by indexed matrix
        float4 blendPos = float4(0,0,0,0);
        int i;
        for (i = 0; i < 2; ++i)
        {
                blendPos += float4(mul(worldMatrix3x4Array[blendIdx[i]], position).xyz, 1.0) * blendWgt[i];
        }
        // view / projection
        oPosition = mul(viewProjectionMatrix, blendPos);
        

        colour = ambient;
}


/*
  Four-weight-per-vertex hardware skinning, 2 lights
  The trouble with vertex programs is they're not general purpose, but
  fixed function hardware skinning is very poorly supported
*/
void hardwareSkinningFourWeights_vp(
        float4 position : POSITION,
        float3 normal   : NORMAL,
        float2 uv       : TEXCOORD0,
        float4 blendIdx : BLENDINDICES,
        float4 blendWgt : BLENDWEIGHT,
        

        out float4 oPosition : SV_POSITION,
        out float2 oUv       : TEXCOORD0,
        out float4 colour           : COLOR,
        // Support up to 24 bones of float3x4
        // vs_1_1 only supports 96 params so more than this is not feasible
        uniform float3x4   worldMatrix3x4Array[24],
        uniform float4x4 viewProjectionMatrix,
        uniform float4   lightPos[2],
        uniform float4   lightDiffuseColour[2],
        uniform float4   ambient)
{
        // transform by indexed matrix
        float4 blendPos = float4(0,0,0,0);
        int i;
        for (i = 0; i < 4; ++i)
        {
                blendPos += float4(mul(worldMatrix3x4Array[blendIdx[i]], position).xyz, 1.0) * blendWgt[i];
        }
        // view / projection
        oPosition = mul(viewProjectionMatrix, blendPos);
        // transform normal
        float3 norm = float3(0,0,0);
        for (i = 0; i < 4; ++i)
        {
                float3x3 d = (float3x3)worldMatrix3x4Array[blendIdx[i]];
                norm += mul(d, normal) * 
                blendWgt[i];
        }
        norm = normalize(norm);
        // Lighting - support point and directional
        float3 lightDir0 =      normalize(
                lightPos[0].xyz -  (blendPos.xyz * lightPos[0].w));
        float3 lightDir1 =      normalize(
                lightPos[1].xyz -  (blendPos.xyz * lightPos[1].w));

        
        oUv = uv;
        colour = ambient + 
                (saturate(dot(lightDir0, norm)) * lightDiffuseColour[0]) + 
                (saturate(dot(lightDir1, norm)) * lightDiffuseColour[1]);
        
}

// hardware morph animation (no normals)
void hardwareMorphAnimation(float3 pos1 : POSITION,
                          float4 normal         : NORMAL,
                          float2 uv               : TEXCOORD0,
                          float3 pos2     : TEXCOORD1,
                                                  
                          out float4 oPosition : SV_POSITION,
                          out float2 oUv           : TEXCOORD0,
                          out float4 colour    : COLOR,

                          uniform float4x4 worldViewProj, 
                          uniform float4 anim_t)
{
        // interpolate
        float4 interp = float4(pos1 + anim_t.x*(pos2 - pos1), 1.0f);
        
        oPosition = mul(worldViewProj, interp);
        oUv = uv;
        colour = float4(1,0,0,1);
}

// hardware pose animation (no normals)
void hardwarePoseAnimation(float3 pos : POSITION,
                          float4 normal         : NORMAL,
                          float2 uv               : TEXCOORD0,
                          float3 pose1    : TEXCOORD1,
                          float3 pose2    : TEXCOORD2,
                                                  
                          out float4 oPosition : SV_POSITION,
                          out float2 oUv           : TEXCOORD0,
                          out float4 colour    : COLOR,

                          uniform float4x4 worldViewProj, 
                          uniform float4 anim_t)
{
        // interpolate
        float4 interp = float4(pos + anim_t.x*pose1 + anim_t.y*pose2, 1.0f);
        
        oPosition = mul(worldViewProj, interp);
        oUv = uv;
        colour = float4(1,0,0,1);
}

// hardware morph animation (with normals)
void hardwareMorphAnimationWithNormals(float3 pos1 : POSITION,
                          float3 normal1  : NORMAL,
                          float2 uv               : TEXCOORD0,
                          float3 pos2     : TEXCOORD1,
                          float3 normal2  : TEXCOORD2,
                                                  
                          out float4 oPosition : SV_POSITION,
                          out float2 oUv           : TEXCOORD0,
                          out float4 colour    : COLOR,

                          uniform float4x4 worldViewProj, 
                          uniform float4 objSpaceLightPos,
                          uniform float4 ambient,
                          uniform float4 anim_t)
{
        // interpolate position
        float4 posinterp = float4(pos1 + anim_t.x*(pos2 - pos1), 1.0f);

        // nlerp normal
        float3 ninterp = normal1 + anim_t.x*(normal2 - normal1);
        ninterp = normalize(ninterp);
        
        oPosition = mul(worldViewProj, posinterp);
        oUv = uv;
        
        float3 lightDir = normalize(
                objSpaceLightPos.xyz -  (posinterp.xyz * objSpaceLightPos.w));

        // Colour it red to make it easy to identify
        float lit = saturate(dot(lightDir, ninterp));
        colour = float4((ambient.rgb + float3(lit,lit,lit)) * float3(1,0,0), 1);
}

// hardware pose animation (with normals)
void hardwarePoseAnimationWithNormals(float3 pos : POSITION,
                          float3 normal    : NORMAL,
                          float2 uv                : TEXCOORD0,
                          float3 pose1pos  : TEXCOORD1,
                          float3 pose1norm : TEXCOORD2,
                          float3 pose2pos  : TEXCOORD3,
                          float3 pose2norm : TEXCOORD4,
                                                  
                          out float4 oPosition : SV_POSITION,
                          out float2 oUv           : TEXCOORD0,
                          out float4 colour    : COLOR,

                          uniform float4x4 worldViewProj, 
                          uniform float4 objSpaceLightPos,
                          uniform float4 ambient,
                          uniform float4 anim_t)
{
        // interpolate
        float4 posinterp = float4(pos + anim_t.x*pose1pos + anim_t.y*pose2pos, 1.0f);
        
        // nlerp normal
        // First apply the pose normals (these are actual normals, not offsets)
        float3 ninterp = anim_t.x*pose1norm + anim_t.y*pose2norm;

        // Now add back any influence of the original normal
        // This depends on what the cumulative weighting left the normal at, if it's lacking or cancelled out
        //float remainder = 1.0 - min(anim_t.x + anim_t.y, 1.0);
        float remainder = 1.0 - min(length(ninterp), 1.0);
        ninterp = ninterp + (normal * remainder);
        ninterp = normalize(ninterp);

        oPosition = mul(worldViewProj, posinterp);
        oUv = uv;
        
        float3 lightDir = normalize(
                objSpaceLightPos.xyz -  (posinterp.xyz * objSpaceLightPos.w));

        // Colour it red to make it easy to identify
        float lit = saturate(dot(lightDir, ninterp));
        colour = float4((ambient.rgb + float3(lit,lit,lit)) * float3(1,0,0), 1);
}

void basicPassthroughTangent_v( float4   position  : POSITION,
                                                                float3   normal    : NORMAL,
                                                                float2   texcord   : TEXCOORD0,
                                                                float3   tangent   : TANGENT,                                             
                                                        out float4   oPosition : SV_POSITION,
                                                        out float3   oTangent  : TEXCOORD0,

                                                uniform float4x4 worldViewProj)
{
        oPosition = mul(worldViewProj, position);
        oTangent = tangent;
}
void basicPassthroughNormal_v(float4   position  : POSITION,
                                                          float3   normal    : NORMAL,
                                                          float2   texcord   : TEXCOORD0,
                                                          float3   tangent   : TANGENT,                                           
                                                  out float4   oPosition : SV_POSITION,
                                                  out float3   oNormal  : TEXCOORD0,
                                      uniform float4x4 worldViewProj)
{
        oPosition = mul(worldViewProj, position);
        oNormal = normal;
}
// Basic fragment program to display UV
float4 showuv_p (float4 position : SV_POSITION, float2 uv : TEXCOORD0, float4 colour    : COLOR) : COLOR
{
        // wrap values using frac
        return float4(frac(uv.x), frac(uv.y), 0, 1);
}
// Basic fragment program to display 3d uv
float4 showuvdir3d_p (float4 position : SV_POSITION, float3 uv : TEXCOORD0) : COLOR
{
        float3 n = normalize(uv);
        return float4(n.x, n.y, n.z, 1);
}