Jump to content

  • Log In with Google      Sign In   
  • Create Account

Steve_Segreto

Member Since 26 Jun 2009
Offline Last Active May 15 2016 08:58 AM

Posts I've Made

In Topic: Skeletal animation shader questions

04 January 2016 - 09:53 PM

Hi this is a great list of questions!

 

In my experience constants buffer are the best way in dx9, 10 and 11 to send the updated bone transforms to the shader for the vertex skinning. A buffer of about 50 or less 4x4 matrices should be able to handle most (> 90%) of the low to mid class game engine skinned actors in one draw call (I can confirm this for Dark Age of Camelot, Unreal Tournament, Mortal Kombat Armageddon, Zelda Twilight Princess and TitanQuest skinned actors).

 

As for the 4 bone weights per vertex limit, this does seem to be an arbitrary legacy based limit from shader model 2 and the fixed function before it when the blend indices were packed into 4 dwords. I think I saw some research paper that concluded for bipedal meshes 4 blend indices is sufficient for a certain fidelity of realistic motion, but I can't find the paper at hand to link to it.

 

As for the last question of whether you should always blend in 4 bone weights, I actually use another number to tell me how many of the 4 blend indices are needed. Here is some example shader model 2 code for skinning:

 

CRenderableMesh 0F7B78E8:
=================================================================================
Vertex Declaration: 0B98C860
=================================================================================
 8 Vertex Elements
{ Stream = 0, Offset = 0, Type = D3DDECLTYPE_FLOAT3, Method = D3DDECLMETHOD_DEFAULT, Usage = D3DDECLUSAGE_POSITION, UsageIndex = 0 },
{ Stream = 0, Offset = 12, Type = D3DDECLTYPE_FLOAT3, Method = D3DDECLMETHOD_DEFAULT, Usage = D3DDECLUSAGE_NORMAL, UsageIndex = 0 },
{ Stream = 0, Offset = 24, Type = D3DDECLTYPE_FLOAT3, Method = D3DDECLMETHOD_DEFAULT, Usage = D3DDECLUSAGE_BLENDWEIGHT, UsageIndex = 0 },
{ Stream = 0, Offset = 36, Type = D3DDECLTYPE_D3DCOLOR, Method = D3DDECLMETHOD_DEFAULT, Usage = D3DDECLUSAGE_BLENDINDICES, UsageIndex = 0 },
{ Stream = 0, Offset = 40, Type = D3DDECLTYPE_FLOAT4, Method = D3DDECLMETHOD_DEFAULT, Usage = D3DDECLUSAGE_TEXCOORD, UsageIndex = 0 },
{ Stream = 0, Offset = 56, Type = D3DDECLTYPE_FLOAT4, Method = D3DDECLMETHOD_DEFAULT, Usage = D3DDECLUSAGE_TEXCOORD, UsageIndex = 1 },
{ Stream = 0, Offset = 72, Type = D3DDECLTYPE_FLOAT4, Method = D3DDECLMETHOD_DEFAULT, Usage = D3DDECLUSAGE_TEXCOORD, UsageIndex = 2 },
{ Stream = 0, Offset = 88, Type = D3DDECLTYPE_FLOAT4, Method = D3DDECLMETHOD_DEFAULT, Usage = D3DDECLUSAGE_TEXCOORD, UsageIndex = 3 }
Vertex Shader 0FA01450:
=================================================================================
//--------------------------------------------------------------------------------------
// Automatically generated Vertex Shader.
//
// Copyright (c) Steve Segreto. All rights reserved.
// Shader Flags = 887f9
// Shader Type = Linear-Based Quaternion Skinning
// Shader Quality = PHONG_LIGHTING
//--------------------------------------------------------------------------------------
 
struct DirLight
{
    float4 ambient;
    float4 diffuse;
    float4 spec;
    float3 dirW;
    float4 fogColor;
    float3 lightPosW;
};
 
struct Mtrl
{
    float4 ambient;
    float4 diffuse;
    float4 spec;
    float  specPower;
    float4 emissive;
};
 
//--------------------------------------------------------------------------------------
// Macro defines
//--------------------------------------------------------------------------------------
#define MATRIX_PALETTE_SIZE (13)
 
//--------------------------------------------------------------------------------------
// Global variables
//--------------------------------------------------------------------------------------
uniform extern DirLight gLight;
uniform extern Mtrl gMtrl;
uniform extern float4x4 gWorld;
uniform extern float4x4 gWVP;
uniform extern float4x4 gInvWorld;
uniform extern float4x4 gView;
uniform extern float3 gEyePosW;
uniform extern float gFarClipDist;
uniform extern float gAlphaRef = 0.29f;
uniform extern float gFogRange = 250.0f;
uniform extern float gFogStart = 1.0f;
uniform extern matrix amPalette[ MATRIX_PALETTE_SIZE ];
uniform extern float gNumBones;
 
//----------------------------------------------------------------------------
// Shader body - VS_Skin
//----------------------------------------------------------------------------
 
//
// Define the inputs -- caller must fill this, usually right from the VB.
//
struct VS_SKIN_INPUT
{
    float4 vPos;
    float3 vNor;
    float3 vBlendWeights;
    float4 vBlendIndices;
};
 
//
// Return skinned position and normal
//
struct VS_SKIN_OUTPUT
{
    float4 vPos;
    float3 vNor;
};
 
//
// Call this function to skin VB position and normal.
//
VS_SKIN_OUTPUT VS_Skin( const VS_SKIN_INPUT vInput, int iNumBones )
{
    VS_SKIN_OUTPUT vOutput = (VS_SKIN_OUTPUT) 0;
 
    float fLastWeight = 1.0;
    float afBlendWeights[ 3 ] = (float[ 3 ]) vInput.vBlendWeights;
    int aiIndices[ 4 ]        = (int[ 4 ])   D3DCOLORtoUBYTE4( vInput.vBlendIndices );
 
    for( int iBone = 0; (iBone < 3) && (iBone < iNumBones - 1); ++ iBone )
    {
        float fWeight = afBlendWeights[ iBone ];
        fLastWeight -= fWeight;
        vOutput.vPos.xyz += mul( vInput.vPos, amPalette[ aiIndices[ iBone  ] ] ) * fWeight;
        vOutput.vNor     += mul( float4(vInput.vNor, 0.0f), amPalette[ aiIndices[ iBone  ] ] ) * fWeight;
    }
 
    vOutput.vPos.xyz += mul( vInput.vPos, amPalette[ aiIndices[ iNumBones - 1 ] ] ) * fLastWeight;
    vOutput.vNor     += mul( float4(vInput.vNor, 0.0f), amPalette[ aiIndices[ iNumBones - 1 ] ] ) * fLastWeight;
 
    return vOutput;
}
struct VS_in
{
    float3 posL         : POSITION0;
    float3 normalL      : NORMAL0;
    float3 BlendWeights : BLENDWEIGHT;
    float4 BlendIndices : BLENDINDICES;
    float4 tex0_tex1    : TEXCOORD0;
    float4 tex2_tex3    : TEXCOORD1;
    float4 tex4_tex5    : TEXCOORD2;
    float4 tex6_tex7    : TEXCOORD3;
};
 
struct VS_out
{
    float4 posH         : POSITION0;
    float4 tex0_tex1    : TEXCOORD0;
    float4 tex2_tex3    : TEXCOORD1;
    float4 tex4_tex5    : TEXCOORD2;
    float4 tex6_tex7    : TEXCOORD3;
    float3 normalW      : TEXCOORD4;
    float4 posVS        : TEXCOORD5;
    float4 color        : COLOR0;
    float  fogLerpParam : COLOR1;
};
 
VS_out VS_Scene( VS_in i )
{
    //
    // Zero out our output.
    //
    VS_out o = (VS_out)0;
 
    //
    // Skin VB inputs
    //
    VS_SKIN_INPUT  vsi = { float4( i.posL, 1.0f ), i.normalL, i.BlendWeights, i.BlendIndices };
    VS_SKIN_OUTPUT vso = VS_Skin( vsi, gNumBones );
    i.posL = vso.vPos.xyz;
    i.normalL = vso.vNor;
 
    //
    // Transform normal to world space and pass along
    // to be interpolated by rasterizer.
    //
    o.normalW = mul( gInvWorld, float4(i.normalL, 0) ).xyz;
 
    //
    // Pass along per-vertex color to be interpolated by rasterizer.
    //
    o.color = gMtrl.diffuse;
 
    //
    // Transform position to homogeneous clip space.
    //
    float4 vPositionVS = mul(float4(i.posL, 1.0f), mul(gWorld, gView));
    o.posH = mul(float4(i.posL, 1.0f), gWVP);
 
    //
    // This position will be used to output view space depth.
    //
    o.posVS = vPositionVS;
    o.posVS.z = max(o.posVS.z, 0.0f);
 
    //
    // Pass on texture coordinates to be interpolated in rasterization.
    //
    o.tex0_tex1.xy = i.tex0_tex1.xy;
    o.tex0_tex1.zw = i.tex0_tex1.zw;
    o.tex2_tex3.xy = i.tex2_tex3.xy;
    o.tex2_tex3.zw = i.tex2_tex3.zw;
    o.tex4_tex5.xy = i.tex4_tex5.xy;
    o.tex4_tex5.zw = i.tex4_tex5.zw;
    o.tex6_tex7.xy = i.tex6_tex7.xy;
    o.tex6_tex7.zw = i.tex6_tex7.zw;
 
    //
    // Compute vertex distance from camera in world
    // space for fog calculation.
    //
    float dist = distance(mul(float4(i.posL, 1.0f), gWorld).xyz, gEyePosW);
    o.fogLerpParam = saturate((dist - gFogStart) / gFogRange);
 
    //
    // Done--return the output.
    //
    return o;
}
Pixel Shader 0FA11C80:
=================================================================================
//--------------------------------------------------------------------------------------
// Automatically generated Pixel Shader.
//
// Copyright (c) Steve Segreto. All rights reserved.
// Shader Flags = 827e8
// Shader Type = Linear-Based Quaternion Skinning
// Shader Quality = PHONG_LIGHTING
//--------------------------------------------------------------------------------------
 
struct DirLight
{
    float4 ambient;
    float4 diffuse;
    float4 spec;
    float3 dirW;
    float4 fogColor;
    float3 lightPosW;
};
 
struct Mtrl
{
    float4 ambient;
    float4 diffuse;
    float4 spec;
    float  specPower;
    float4 emissive;
};
 
//--------------------------------------------------------------------------------------
// Macro defines
//--------------------------------------------------------------------------------------
 
//--------------------------------------------------------------------------------------
// Global variables
//--------------------------------------------------------------------------------------
uniform extern DirLight gLight;
uniform extern Mtrl gMtrl;
uniform extern float4x4 gInvWorld;
uniform extern float4x4 gView;
uniform extern float3 gEyePosW;
uniform extern float gFarClipDist;
uniform extern float gAlphaRef = 0.29f;
uniform extern float3 gFogColor;
uniform extern texture gTex0;
 
struct PS_in
{
    float4 tex0_tex1    : TEXCOORD0;
    float4 tex2_tex3    : TEXCOORD1;
    float4 tex4_tex5    : TEXCOORD2;
    float4 tex6_tex7    : TEXCOORD3;
    float3 normalW      : TEXCOORD4;
    float4 posVS        : TEXCOORD5;
    float4 color        : COLOR0;
    float  fogLerpParam : COLOR1;
};
 
struct PS_out
{
    float4 vMaterial    : COLOR0;
    float4 vWorldNrm    : COLOR1;
    float4 vEmittance   : COLOR2;
    float4 vDepth       : COLOR3;
};
 
sampler TexS0 = sampler_state
{
    Texture   = <gTex0>;
    MinFilter = Linear;
    MagFilter = Linear;
    MipFilter = Point;
    AddressU  = Wrap;
    AddressV  = Wrap;
};
 
PS_out PS_Scene( PS_in i )
{
    //
    // Zero out our output.
    //
    PS_out o = (PS_out)0;
 
    //
    // Interpolated normals can become unnormal.
    //
    i.normalW   = normalize(i.normalW);
 
    //
    // VERT_MODE_SRC_IGNORE
    //
    float3 matAmbient  = gMtrl.ambient.rgb;
    float4 matDiffuse  = gMtrl.diffuse;
    float3 matEmissive = gMtrl.emissive.rgb;
 
    //
    // Incoming colors.
    //
    float3 color_stage0 = saturate((matAmbient * gLight.ambient) + matDiffuse + matEmissive);
    o.vEmittance.y = gMtrl.spec.r;
    o.vEmittance.z = gMtrl.specPower;
    float  alpha_stage0 = matDiffuse.a;
 
    //
    // Sample textures.
    //
    float4 color0 = tex2D(TexS0, i.tex0_tex1.xy);
 
    //
    // Apply texturing stages
    //
 
    //
    // Diffuse map.
    //
    float3 color_stage1  = color_stage0 * color0.rgb;
 
    //
    // Final (pre-fog) color.
    //
    float4 texColor = float4( color_stage1.rgb, alpha_stage0 );
 
    //
    // Add fog
    //
    o.vMaterial = texColor;
    o.vEmittance.w = i.fogLerpParam;
    // convert normal to texture space [-1;+1] -> [0;1]
    o.vWorldNrm.xyz = i.normalW * 0.5 + 0.5;
 
    // post-perspective z/w depth
    o.vDepth = i.posVS.z / gFarClipDist;
 
    //
    // Done--return the output.
    //
    return o;
}

In Topic: Memory Leaks on shutdown of QT application

03 January 2016 - 10:42 AM

That's the funny thing about chasing heap leaks, when you examine the code everything looks like its being cleaned up correctly. You need to enlist the help of tools like the CRT debug heap or gflags debug heap to help you understand which allocations are being made without being freed, because this can provoke new thought and cause you to see what you are missing. I just caught a heap leak in my own source code last night that resulted from some scene graph nodes not being parented as I would have expected so even though the de-allocation code was rock solid and correct, there was still a heap leak because for a certain class of model a certain group of scene graph nodes were created as orphans without parents and thus a top-down de-allocation algorithm couldn't find them.


In Topic: Memory Leaks on shutdown of QT application

02 January 2016 - 12:37 PM

Hi! If you have memory leaks that you are concerned about (e.g. that actually leak memory in response to application activities besides simply exiting the application), then you will need to clear away the application exit memory leaks as well so that you can more clearly see the other memory leaks to remove them.

 

At the basic level, you have allocated memory and have not freed it before your application exits. This can also stem from incrementing a ref count to a COM object (often unknowingly through an API call) and thus preventing the program from freeing the memory for the COM object. You could also be re-allocating memory to a pointer without first freeing it (this would be a dangerous heap leak).

 

A first suggestion is to enable debug heap at the beginning of your program and then run the application in Visual Studio in debug mode and scrub through the unfreed allocations.

 

if the below doesn't work, try gflags from application verifier and enable their debug heap, but I have run out of memory on moderately sized and larger programs doing that (debug heaps are expensive on memory budgets!) Good luck, please post more information for us to help you!!!

    // Enable run-time memory check for debug builds.
#if defined(DEBUG) | defined(_DEBUG)
    _CrtSetDbgFlag( _CRTDBG_ALLOC_MEM_DF | _CRTDBG_LEAK_CHECK_DF );
#endif

In Topic: good approach to randomly generate the contents of a dungeon or room

31 December 2015 - 01:54 PM

Here's a graph based approach that usually forces the player to explore most of your randomly created dungeon, which is the equivalent of "fun" right? :)

 

http://www.roguebasin.com/index.php?title=Creating_Measurably_%22Fun%22_Maps


In Topic: OpenTissue 64-bit version prebuilt wanted.

31 December 2015 - 01:52 PM

Thanks for teaching me about the existence of OpenTissue it looks fun!

 

You may have to setup the CMAKE environment required by OpenTissue and modify it to perform a 64-bit build. I don't have any pre-built 64-bit versions of it sorry. Maybe you could post the operator overload compiler errors and we could help you with that?


PARTNERS