1

我正在尝试将 Screen Space Ambient Occlusion 示例从 XNA 3.1 转换为 XNA 4.0。我已经修复了源代码中的所有问题，除了着色器文件中的这个奇怪问题。按照 Shawn Hargreaves 的博客的指导，我已经解决并修复了着色器的所有明显问题，但是当它编译时它使用了 620 个指令槽，这远远超过了 512 个指令槽的限制。这怎么可能在 XNA 3.1 中起作用，但在 XNA 4.0 中却不行？

3.1 文件副本的更改非常小，仅包括重命名几个函数。下面是当前形式的完整着色器源。对于减少编译到的指令槽数量的任何帮助，我将不胜感激。

float sampleRadius;
float distanceScale;
float4x4 Projection;

float3 cornerFustrum;

struct VS_OUTPUT
{
    float4 pos              : POSITION;
    float2 TexCoord         : TEXCOORD0;
    float3 viewDirection    : TEXCOORD1;
}; 

VS_OUTPUT VertexShaderFunction(
    float4 Position : POSITION, float2 TexCoord : TEXCOORD0)
{
    VS_OUTPUT Out = (VS_OUTPUT)0;

    Out.pos = Position;
    Position.xy = sign(Position.xy);
    Out.TexCoord = (float2(Position.x, -Position.y) + float2( 1.0f, 1.0f ) ) * 0.5f;
    float3 corner = float3(-cornerFustrum.x * Position.x,
            cornerFustrum.y * Position.y, cornerFustrum.z);
    Out.viewDirection =  corner;

    return Out;
}


texture depthTexture;
texture randomTexture;

sampler2D depthSampler = sampler_state
{
    Texture = <depthTexture>;
    ADDRESSU = CLAMP;
    ADDRESSV = CLAMP;
    MAGFILTER = LINEAR;
    MINFILTER = LINEAR;
};

sampler2D RandNormal = sampler_state
{
    Texture = <randomTexture>;
    ADDRESSU = WRAP;
    ADDRESSV = WRAP;
    MAGFILTER = LINEAR;
    MINFILTER = LINEAR;
};

float4 PixelShaderFunction(VS_OUTPUT IN) : COLOR0
{
    float4 samples[16] =
    {
        float4(0.355512,    -0.709318,  -0.102371,  0.0 ),
        float4(0.534186,    0.71511,    -0.115167,  0.0 ),
        float4(-0.87866,    0.157139,   -0.115167,  0.0 ),
        float4(0.140679,    -0.475516,  -0.0639818, 0.0 ),
        float4(-0.0796121,  0.158842,   -0.677075,  0.0 ),
        float4(-0.0759516,  -0.101676,  -0.483625,  0.0 ),
        float4(0.12493,     -0.0223423, -0.483625,  0.0 ),
        float4(-0.0720074,  0.243395,   -0.967251,  0.0 ),
        float4(-0.207641,   0.414286,   0.187755,   0.0 ),
        float4(-0.277332,   -0.371262,  0.187755,   0.0 ),
        float4(0.63864,     -0.114214,  0.262857,   0.0 ),
        float4(-0.184051,   0.622119,   0.262857,   0.0 ),
            float4(0.110007,    -0.219486,  0.435574,   0.0 ),
        float4(0.235085,    0.314707,   0.696918,   0.0 ),
        float4(-0.290012,   0.0518654,  0.522688,   0.0 ),
        float4(0.0975089,   -0.329594,  0.609803,   0.0 )
    };

    IN.TexCoord.x += 1.0/1600.0;
    IN.TexCoord.y += 1.0/1200.0;

    normalize (IN.viewDirection);
    float depth = tex2D(depthSampler, IN.TexCoord).a;
    float3 se = depth * IN.viewDirection;

    float3 randNormal = tex2D( RandNormal, IN.TexCoord * 200.0 ).rgb;

    float3 normal = tex2D(depthSampler, IN.TexCoord).rgb;
    float finalColor = 0.0f;

    for (int i = 0; i < 16; i++)
    {
        float3 ray = reflect(samples[i].xyz,randNormal) * sampleRadius;

        //if (dot(ray, normal) < 0)
        //  ray += normal * sampleRadius;

        float4 sample = float4(se + ray, 1.0f);
        float4 ss = mul(sample, Projection);

        float2 sampleTexCoord = 0.5f * ss.xy/ss.w + float2(0.5f, 0.5f);

        sampleTexCoord.x += 1.0/1600.0;
        sampleTexCoord.y += 1.0/1200.0;
        float sampleDepth = tex2D(depthSampler, sampleTexCoord).a;

        if (sampleDepth == 1.0)
        {
            finalColor ++;
        }
        else
        {       
            float occlusion = distanceScale* max(sampleDepth - depth, 0.0f);
            finalColor += 1.0f / (1.0f + occlusion * occlusion * 0.1);
        }
    }

    return float4(finalColor/16, finalColor/16, finalColor/16, 1.0f);
}


technique SSAO
{
    pass P0
    {          
        VertexShader = compile vs_3_0 VertexShaderFunction();
        PixelShader  = compile ps_3_0 PixelShaderFunction();
    }
}
4

3 回答 3

2

XNA 4.0 强制执行 512 条指令限制（xbox360 具有，HiDef 配置文件强制执行最低限度），而 XNA3.1 没有。

从好的方面来说，任何可以运行 XNA HiDef 配置文件的图形卡都不应该倒下，因为 XNA 允许任意数量的指令，它可能已经完成了。

由于您的代码中有一个循环，因此您可以尝试强制编译器使用循环指令，如果它当前正在展开它（我自己对此并不熟悉）。

于 2011-03-30T11:36:03.843 回答
1

如果您正在寻找具有开源的 XNA 4 SSAO，请查看此链接：使用 SSAO 法线进行延迟渲染

于 2011-03-30T12:53:01.353 回答
0

将着色器中的样本数从 16 减少到 8

于 2011-04-08T04:59:26.563 回答