SHS/qad
4
1
Fork 0
Code Issues 5 Pull Requests Releases Wiki Activity

moved to shstk

Browse Source
This commit is contained in:
Пелипенко Иван
2020-08-25 22:24:02 +03:00
parent d4f1c78a6e
commit b92a1fa558
904 changed files with 2448 additions and 36452 deletions
Download Patch File Download Diff File Expand all files Collapse all files

230
libs/qglview/shaders/FXAA.frag Normal file
View File

@@ -0,0 +1,230 @@
#version 130
in vec4 posPos;
uniform sampler2D tex0; // 0
//uniform float vx_offset;
uniform vec2 dt;
uniform float FXAA_SPAN_MAX = 8.;
uniform float FXAA_REDUCE_MUL = 1. / 8.;
#define FxaaInt2 ivec2
//#define vec2 vec2
vec3 FxaaPixelShader(vec4 posPos, // Output of FxaaVertexShader interpolated across screen.
sampler2D tex, // Input texture.
vec2 rcpFrame) { // Constant {1.0/frameWidth, 1.0/frameHeight}.
/*---------------------------------------------------------*/
// #define FXAA_REDUCE_MIN (1. / 128.)
#define FXAA_REDUCE_MIN (1. / 128.)
//#define FXAA_REDUCE_MUL (1.0/8.0)
//#define FXAA_SPAN_MAX 8.0
/*---------------------------------------------------------*/
vec3 rgbNW = texture2D(tex, posPos.zw).xyz;
vec3 rgbNE = textureOffset(tex, posPos.zw, ivec2(1, 0)).xyz;
vec3 rgbSW = textureOffset(tex, posPos.zw, ivec2(0, 1)).xyz;
vec3 rgbSE = textureOffset(tex, posPos.zw, ivec2(1, 1)).xyz;
vec3 rgbM = texture2D(tex, posPos.xy).xyz;
/*---------------------------------------------------------*/
vec3 luma = vec3(0.299, 0.587, 0.114);
float lumaNW = dot(rgbNW, luma);
float lumaNE = dot(rgbNE, luma);
float lumaSW = dot(rgbSW, luma);
float lumaSE = dot(rgbSE, luma);
float lumaM = dot(rgbM, luma);
/*---------------------------------------------------------*/
float lumaMin = min(lumaM, min(min(lumaNW, lumaNE), min(lumaSW, lumaSE)));
float lumaMax = max(lumaM, max(max(lumaNW, lumaNE), max(lumaSW, lumaSE)));
/*---------------------------------------------------------*/
vec2 dir;
dir.x = -((lumaNW + lumaNE) - (lumaSW + lumaSE));
dir.y = ((lumaNW + lumaSW) - (lumaNE + lumaSE));
/*---------------------------------------------------------*/
float dirReduce = max(
(lumaNW + lumaNE + lumaSW + lumaSE) * (0.25 * FXAA_REDUCE_MUL),
FXAA_REDUCE_MIN);
float rcpDirMin = 1. / (min(abs(dir.x), abs(dir.y)) + dirReduce);
dir = min(vec2( FXAA_SPAN_MAX, FXAA_SPAN_MAX),
max(vec2(-FXAA_SPAN_MAX, -FXAA_SPAN_MAX),
dir * rcpDirMin)) * rcpFrame.xy;
/*--------------------------------------------------------*/
vec3 rgbA = (1. / 2.) * (
texture2D(tex, posPos.xy + dir * (1. / 3. - 0.5)).xyz +
texture2D(tex, posPos.xy + dir * (2. / 3. - 0.5)).xyz);
vec3 rgbB = rgbA * (1. / 2.) + (1. / 4.) * (
texture2D(tex, posPos.xy + dir * (0. / 3. - 0.5)).xyz +
texture2D(tex, posPos.xy + dir * (3. / 3. - 0.5)).xyz);
float lumaB = dot(rgbB, luma);
if ((lumaB < lumaMin) || (lumaB > lumaMax)) return rgbA;
return rgbB;
}
vec3 Fxaa3PixelShader (
// {xy} = center of pixel
vec4 pos,
// {xyzw} = not used on FXAA3 Quality
//vec4 posPos,
// {rgb_} = color in linear or perceptual color space
// {__a} = luma in perceptual color space (not linear)
sampler2D tex,
// This must be from a constant/uniform.
// {x_} = 1.0/screenWidthInPixels
// {_y} = 1.0/screenHeightInPixels
vec2 rcpFrame
// {xyzw} = not used on FXAA3 Quality
//vec4 rcpFrameOpt
) {
/*--------------------------------------------------------------------------*/
//#if (FXAA_GATHER4_ALPHA == 1)
/*vec4 luma4A = FxaaTexOffAlpha4(tex, pos.xy, FxaaInt2(-1, -1), rcpFrame.xy);
#if (FXAA_DISCARD == 0)
vec4 rgbyM = texture2D(tex, pos.xy);
#endif
vec4 luma4B = FxaaTexAlpha4(tex, pos.xy, rcpFrame.xy);
float lumaNE = textureOffset(tex, pos.xy, ivec(1, -1)).w;
float lumaSW = textureOffset(tex, pos.xy, ivec(-1, 1)).w;
float lumaNW = luma4A.w;
float lumaN = luma4A.z;
float lumaW = luma4A.x;
float lumaM = luma4A.y;
float lumaE = luma4B.z;
float lumaS = luma4B.x;
float lumaSE = luma4B.y;*/
//#else
vec3 luma = vec3(0.299, 0.587, 0.114);
float lumaN = dot(textureLodOffset(tex, pos.xy, 0., ivec2(0, -1)).rgb, luma);
float lumaW = dot(textureLodOffset(tex, pos.xy, 0., ivec2(-1, 0)).rgb, luma);
vec4 rgbyM = texture2D(tex, pos.xy);
float lumaE = dot(textureLodOffset(tex, pos.xy, 0., ivec2( 1, 0)).rgb, luma);
float lumaS = dot(textureLodOffset(tex, pos.xy, 0., ivec2( 0, 1)).rgb, luma);
float lumaM = dot(rgbyM.rgb, luma);
//#endif
/*--------------------------------------------------------------------------*/
float rangeMin = min(lumaM, min(min(lumaN, lumaW), min(lumaS, lumaE)));
float rangeMax = max(lumaM, max(max(lumaN, lumaW), max(lumaS, lumaE)));
float range = rangeMax - rangeMin;
//return vec4(range);
/*--------------------------------------------------------------------------*/
#define FXAA_QUALITY_EDGE_THRESHOLD_MIN (1.0/12.0)
#define FXAA_QUALITY_EDGE_THRESHOLD (1.0/6.0)
if(range < max(FXAA_QUALITY_EDGE_THRESHOLD_MIN, rangeMax * FXAA_QUALITY_EDGE_THRESHOLD))
/*#if (FXAA_DISCARD == 1)
FxaaDiscard;
#else*/
return rgbyM.rgb;
//return vec3(0);
//#endif
/*--------------------------------------------------------------------------*/
//#if (FXAA_GATHER4_ALPHA == 0)
float lumaNW = dot(textureLodOffset(tex, pos.xy, 0., ivec2(-1,-1)).rgb, luma);
float lumaNE = dot(textureLodOffset(tex, pos.xy, 0., ivec2( 1,-1)).rgb, luma);
float lumaSW = dot(textureLodOffset(tex, pos.xy, 0., ivec2(-1, 1)).rgb, luma);
float lumaSE = dot(textureLodOffset(tex, pos.xy, 0., ivec2( 1, 1)).rgb, luma);
//#endif
/*--------------------------------------------------------------------------*/
#define FXAA_QUALITY_SUBPIX_CAP (3.0/4.0)
//#define FXAA_QUALITY_SUBPIX_CAP 0
#define FXAA_QUALITY_SUBPIX_TRIM (1.0/4.0)
#define FXAA_QUALITY_SUBPIX_TRIM_SCALE (1.0/(1.0 - FXAA_QUALITY_SUBPIX_TRIM))
/*--------------------------------------------------------------------------*/
float lumaL = (lumaN + lumaW + lumaE + lumaS) * 0.25;
float rangeL = abs(lumaL - lumaM);
float blendL = clamp((rangeL / range) - FXAA_QUALITY_SUBPIX_TRIM, 0., 1.) * FXAA_QUALITY_SUBPIX_TRIM_SCALE;
blendL = min(FXAA_QUALITY_SUBPIX_CAP, blendL);
/*--------------------------------------------------------------------------*/
float edgeVert =
abs(lumaNW + (-2.0 * lumaN) + lumaNE) +
10.0 * abs(lumaW + (-2.0 * lumaM) + lumaE ) +
abs(lumaSW + (-2.0 * lumaS) + lumaSE);
float edgeHorz =
abs(lumaNW + (-2.0 * lumaW) + lumaSW) +
10.0 * abs(lumaN + (-2.0 * lumaM) + lumaS ) +
abs(lumaNE + (-2.0 * lumaE) + lumaSE);
//return vec3(edgeHorz);
//float edgeVert = abs(lumaS - lumaN);
//float edgeHorz = abs(lumaE - lumaW);
bool horzSpan = edgeHorz >= edgeVert;
/*--------------------------------------------------------------------------*/
float lengthSign = horzSpan ? -rcpFrame.y : -rcpFrame.x;
//if (edgeHorz == edgeVert) ;//lengthSign = 0.;
if(!horzSpan) {
lumaN = lumaW;
lumaS = lumaE;
}
float gradientN = abs(lumaN - lumaM);
float gradientS = abs(lumaS - lumaM);
lumaN = (lumaN + lumaM) * 0.5;
lumaS = (lumaS + lumaM) * 0.5;
/*--------------------------------------------------------------------------*/
bool pairN = gradientN >= gradientS;
if(!pairN) {
lumaN = lumaS;
gradientN = gradientS;
lengthSign = -lengthSign;
}
vec2 posN;
posN = pos.xy + (horzSpan ? vec2(0.0, lengthSign * 0.5) : vec2(lengthSign * 0.5, 0.0));
//posN.x = pos.x + (horzSpan ? 0.0 : lengthSign * 0.5);
//posN.y = pos.y + (horzSpan ? lengthSign * 0.5 : 0.0);
/*--------------------------------------------------------------------------*/
#define FXAA_SEARCH_STEPS 8
#define FXAA_SEARCH_THRESHOLD (1.0/8.0)
/*--------------------------------------------------------------------------*/
gradientN *= FXAA_SEARCH_THRESHOLD;
/*--------------------------------------------------------------------------*/
vec2 posP = posN;
vec2 offNP = horzSpan ? vec2(rcpFrame.x, 0.0) : vec2(0.0, rcpFrame.y);
float lumaEndN = 0.;
float lumaEndP = 0.;
bool doneN = false;
bool doneP = false;
posN += offNP * (-1.5);
posP += offNP * ( 1.5);
for(int i = 0; i < FXAA_SEARCH_STEPS; i++) {
lumaEndN = dot(texture2DLod(tex, posN.xy, 0.).rgb, luma);
lumaEndP = dot(texture2DLod(tex, posP.xy, 0.).rgb, luma);
bool doneN2 = abs(lumaEndN - lumaN) >= gradientN;
bool doneP2 = abs(lumaEndP - lumaN) >= gradientN;
if(doneN2 && !doneN) posN += offNP;
if(doneP2 && !doneP) posP -= offNP;
if(doneN2 && doneP2) break;
doneN = doneN2;
doneP = doneP2;
if(!doneN) posN -= offNP * 2.0;
if(!doneP) posP += offNP * 2.0;
}
/*--------------------------------------------------------------------------*/
float dstN = horzSpan ? pos.x - posN.x : pos.y - posN.y;
float dstP = horzSpan ? posP.x - pos.x : posP.y - pos.y;
/*--------------------------------------------------------------------------*/
bool directionN = dstN < dstP;
lumaEndN = directionN ? lumaEndN : lumaEndP;
/*--------------------------------------------------------------------------*/
if(((lumaM - lumaN) < 0.0) == ((lumaEndN - lumaN) < 0.0))
lengthSign = 0.0;
/*--------------------------------------------------------------------------*/
float spanLength = (dstP + dstN);
dstN = directionN ? dstN : dstP;
float subPixelOffset = 0.5 + (dstN * (-1.0/spanLength));
subPixelOffset += blendL * (1.0/8.0);
subPixelOffset *= lengthSign;
vec3 rgbF = texture2DLod(tex, pos.xy + (horzSpan ? vec2(0., subPixelOffset) : vec2(subPixelOffset, 0.)), 0.).xyz;
/*--------------------------------------------------------------------------*/
/*#if (FXAA_LINEAR == 1)
lumaL *= lumaL;
#endif*/
float lumaF = dot(rgbF, vec3(0.299, 0.587, 0.114)) + (1.0/(65536.0*256.0));
float lumaB = mix(lumaF, lumaL, blendL);
float scale = min(4.0, lumaB/lumaF);
rgbF *= scale;
return vec3(rgbF);//, lumaM.rgb);
//, lumaM.rgb);
}
void main() {
gl_FragColor.rgb = Fxaa3PixelShader(posPos, tex0, dt);
}

13
libs/qglview/shaders/FXAA.vert Normal file
View File

@@ -0,0 +1,13 @@
#version 130
out vec4 posPos;
uniform float FXAA_SUBPIX_SHIFT = 1. / 4.;
uniform vec2 dt;
void main(void) {
posPos.xy = gl_MultiTexCoord0.xy;
posPos.zw = gl_MultiTexCoord0.xy - (dt * (0.5 + FXAA_SUBPIX_SHIFT));
gl_TexCoord[0] = gl_MultiTexCoord0;
gl_Position = ftransform();
}

8
libs/qglview/shaders/bloom_0.frag Normal file
View File

@@ -0,0 +1,8 @@
#version 120
uniform sampler2D t0;
uniform float clum;
void main(void) {
gl_FragColor = max((texture2D(t0, gl_TexCoord[0].xy) / clum - 0.8) * 5., vec4(0.));
}

30
libs/qglview/shaders/bloom_1.frag Normal file
View File

@@ -0,0 +1,30 @@
#version 130
uniform sampler2D t0;
uniform vec2 vsize;
void main(void) {
vec2 tc = gl_TexCoord[0].xy, dt = 2. / vsize, dt2 = dt + dt;
gl_FragColor = (texture2D(t0, tc) * 3. +
textureOffset(t0, tc, ivec2(1, 0)) * 2. +
textureOffset(t0, tc, ivec2(0, 1)) * 2. +
textureOffset(t0, tc, ivec2(-1, 0)) * 2. +
textureOffset(t0, tc, ivec2(0, -1)) * 2. +
textureOffset(t0, tc, ivec2(1, 1)) * 1.5 +
textureOffset(t0, tc, ivec2(1, -1)) * 1.5 +
textureOffset(t0, tc, ivec2(-1, -1)) * 1.5 +
textureOffset(t0, tc, ivec2(-1, 1)) * 1.5 +
textureOffset(t0, tc, ivec2(2, 0)) +
textureOffset(t0, tc, ivec2(0, 2)) +
textureOffset(t0, tc, ivec2(-2, 0)) +
textureOffset(t0, tc, ivec2(0, -2)) +
textureOffset(t0, tc, ivec2(2, 1)) +
textureOffset(t0, tc, ivec2(2, -1)) +
textureOffset(t0, tc, ivec2(-2, -1)) +
textureOffset(t0, tc, ivec2(-2, 1)) +
textureOffset(t0, tc, ivec2(1, 2)) +
textureOffset(t0, tc, ivec2(1, -2)) +
textureOffset(t0, tc, ivec2(-1, -2)) +
textureOffset(t0, tc, ivec2(-1, 2))) / 29.;
//gl_FragColor = texture2D(t0, tc);
}

8
libs/qglview/shaders/bloom_pass_0.frag Normal file
View File

@@ -0,0 +1,8 @@
#version 150
uniform sampler2D t0;
uniform float factor = 1., threshold = 0.8;
void main(void) {
qgl_FragData[0].rgb = max(texelFetch(t0, ivec2(gl_FragCoord.xy), 0).rgb - vec3(threshold), vec3(0.)) * factor;
}

6
libs/qglview/shaders/bloom_pass_0.vert Normal file
View File

@@ -0,0 +1,6 @@
#version 150
void main(void) {
qgl_FragTexture = qgl_Texture;
gl_Position = vec4(qgl_Vertex,1);
}

55
libs/qglview/shaders/bloom_pass_1.frag Normal file
View File

@@ -0,0 +1,55 @@
#version 150
uniform sampler2D t0;
uniform int radius = 2;
uniform vec2 dt;
void main(void) {
vec2 tc = qgl_FragTexture.xy;
float r = float(radius);
int o = radius, o2 = radius * 2;
vec3 scol = (texture(t0, tc).rgb * 3. +
texture(t0, tc + dt * vec2( o, 0 )).rgb * 2. +
texture(t0, tc + dt * vec2( 0, o )).rgb * 2. +
texture(t0, tc + dt * vec2( -o, 0 )).rgb * 2. +
texture(t0, tc + dt * vec2( 0, -o)).rgb * 2. +
texture(t0, tc + dt * vec2( o, o )).rgb * 1.5 +
texture(t0, tc + dt * vec2( o, -o)).rgb * 1.5 +
texture(t0, tc + dt * vec2( -o, -o )).rgb * 1.5 +
texture(t0, tc + dt * vec2( -o, o )).rgb * 1.5 +
texture(t0, tc + dt * vec2( o2, 0 )).rgb +
texture(t0, tc + dt * vec2( 0, o2)).rgb +
texture(t0, tc + dt * vec2(-o2, 0 )).rgb +
texture(t0, tc + dt * vec2( 0, -o2)).rgb +
texture(t0, tc + dt * vec2( o2, o )).rgb +
texture(t0, tc + dt * vec2( o2, -o)).rgb +
texture(t0, tc + dt * vec2(-o2, -o )).rgb +
texture(t0, tc + dt * vec2(-o2, o )).rgb +
texture(t0, tc + dt * vec2( o, o2)).rgb +
texture(t0, tc + dt * vec2( o, -o2)).rgb +
texture(t0, tc + dt * vec2( -o, -o2)).rgb +
texture(t0, tc + dt * vec2( -o, o2)).rgb) / 29.;
/*vec3 scol = (texelFetch(t0, tc, 0).rgb * 3. +
texelFetch(t0, tc + ivec2( o, 0 ), 0).rgb * 2. +
texelFetch(t0, tc + ivec2( 0, o ), 0).rgb * 2. +
texelFetch(t0, tc + ivec2( -o, 0 ), 0).rgb * 2. +
texelFetch(t0, tc + ivec2( 0, -o), 0).rgb * 2. +
texelFetch(t0, tc + ivec2( o, o ), 0).rgb * 1.5 +
texelFetch(t0, tc + ivec2( o, -o), 0).rgb * 1.5 +
texelFetch(t0, tc + ivec2( -o, -o ), 0).rgb * 1.5 +
texelFetch(t0, tc + ivec2( -o, o ), 0).rgb * 1.5 +
texelFetch(t0, tc + ivec2( o2, 0 ), 0).rgb +
texelFetch(t0, tc + ivec2( 0, o2), 0).rgb +
texelFetch(t0, tc + ivec2(-o2, 0 ), 0).rgb +
texelFetch(t0, tc + ivec2( 0, -o2), 0).rgb +
texelFetch(t0, tc + ivec2( o2, o ), 0).rgb +
texelFetch(t0, tc + ivec2( o2, -o), 0).rgb +
texelFetch(t0, tc + ivec2(-o2, -o ), 0).rgb +
texelFetch(t0, tc + ivec2(-o2, o ), 0).rgb +
texelFetch(t0, tc + ivec2( o, o2), 0).rgb +
texelFetch(t0, tc + ivec2( o, -o2), 0).rgb +
texelFetch(t0, tc + ivec2( -o, -o2), 0).rgb +
texelFetch(t0, tc + ivec2( -o, o2), 0).rgb) / 29.;*/
qgl_FragData[0].rgb = scol;
//qgl_FragData[0].rgb = vec3(r/10.);
}

6
libs/qglview/shaders/bloom_pass_1.vert Normal file
View File

@@ -0,0 +1,6 @@
#version 150
void main(void) {
qgl_FragTexture = qgl_Texture;
gl_Position = vec4(qgl_Vertex,1);
}

47
libs/qglview/shaders/dof.frag Normal file
View File

@@ -0,0 +1,47 @@
#version 150
uniform float z_near, z_far;
uniform sampler2D t0, td;
uniform vec2 dt;
uniform float radius, focus, diaphragm;
float w, sum;
const float _pe = 2.4e-7;
vec4 getTexel(vec2 c, float coeff) {
vec4 ret = texture(t0, c);
float cw = texture(td, c).r;
cw = clamp(1. - abs(cw - w) * 1000, 0., 1.) * coeff;
sum += cw;
return ret * cw;
}
void main(void) {
vec2 tc = qgl_FragTexture.xy;
vec4 scol = texture(t0, tc);
w = texture(td, tc).r;
float z = w + w - 1;
z = ((_pe - 2.) * z_near) / (z + _pe - 1.); // infinite depth
z = 1./(z + 1);
float cf = 1./(focus + 1);
float factor = clamp(abs(z - cf) * diaphragm, 0, 100);
factor = 1. - 1. / (factor + 1.);
factor *= factor;
factor *= factor;
//factor *= factor;
factor *= radius;
vec2 cdt = factor * dt;
sum = 1.;
scol += getTexel(tc + (cdt * 1), 2.5);
scol += getTexel(tc + (cdt * 2), 2.0);
scol += getTexel(tc + (cdt * 3), 1.5);
scol += getTexel(tc + (cdt * 4), 1.0);
scol += getTexel(tc + (cdt * 5), 0.5);
scol += getTexel(tc + (cdt * -1), 2.5);
scol += getTexel(tc + (cdt * -2), 2.0);
scol += getTexel(tc + (cdt * -3), 1.5);
scol += getTexel(tc + (cdt * -4), 1.0);
scol += getTexel(tc + (cdt * -5), 0.5);
scol /= sum;
qgl_FragData[0].rgba = scol;
}

6
libs/qglview/shaders/dof.vert Normal file
View File

@@ -0,0 +1,6 @@
#version 150
void main(void) {
qgl_FragTexture = qgl_Texture;
gl_Position = vec4(qgl_Vertex,1);
}

7
libs/qglview/shaders/downscale.frag Normal file
View File

@@ -0,0 +1,7 @@
#version 150
uniform sampler2D t0;
void main(void) {
qgl_FragData[0].rgb = textureLod(t0, qgl_FragTexture.xy, 3).rgb;
}

6
libs/qglview/shaders/downscale.vert Normal file
View File

@@ -0,0 +1,6 @@
#version 150
void main(void) {
qgl_FragTexture = qgl_Texture;
gl_Position = qgl_ftransform();
}

67
libs/qglview/shaders/dsl_pass_0.frag Normal file
View File

@@ -0,0 +1,67 @@
#version 150
//#extension GL_ARB_conservative_depth: enable
//layout(depth_less) out float gl_FragDepth;
in vec3 src_normal, normal, binormal;//, et;
in vec4 pos, ppos;
in float fogCoord, FC, C;
in mat3 TBN;
uniform bool acc_fog;
uniform vec2 dt;
uniform float z_far, z_near;
const vec3 luma = vec3(0.299, 0.587, 0.114);
void main(void) {
//float z = pos.w;//((z_near / (z_near-z_far)) * z_far) / (pos.w - (z_far / (z_far-z_near)));
//float logz = log(pos.w * C + 1.) * FC;
vec4 dc = qgl_FragColor;
vec2 tc = qgl_FragTexture.xy;
float hei = dot(texture(qgl_Material.map_relief.map, tc * qgl_Material.map_relief.scale).rgb, luma) * qgl_Material.map_relief.amount + qgl_Material.map_relief.offset;
vec3 n, dn, bn;
dn = texture(qgl_Material.map_normal.map, tc * qgl_Material.map_normal.scale).rgb - vec3(0.5, 0.5, 1.);
dn = dn * qgl_Material.map_normal.amount + qgl_Material.map_normal.offset;
dn.y = -dn.y;
dn = TBN * dn;
//dn.z = 0;
n = normalize(qgl_NormalMatrix * (normal + dn));
bn = normalize(qgl_NormalMatrix * binormal);
//n = dn;
dc *= texture(qgl_Material.map_diffuse.map, tc * qgl_Material.map_diffuse.scale) * qgl_Material.map_diffuse.amount + qgl_Material.map_diffuse.offset;
vec4 spec = texture(qgl_Material.map_specular.map, tc * qgl_Material.map_specular.scale) * qgl_Material.map_specular.amount + qgl_Material.map_specular.offset;
spec *= qgl_Material.color_specular;
float specularity = dot(texture(qgl_Material.map_specularity.map, tc * qgl_Material.map_specularity.scale).rgb, luma) * qgl_Material.map_specularity.amount + qgl_Material.map_specularity.offset;
specularity = clamp(specularity, 0.05, 0.99);
float reflectivity = qgl_Material.reflectivity;//dot(texture(qgl_Material.map_specularity.map, tc).rgb, luma) * qgl_Material.map_specularity.amount + qgl_Material.map_specularity.offset;
reflectivity = clamp(reflectivity, 0., 1.);
vec4 self = texture(qgl_Material.map_self_illumination.map, tc * qgl_Material.map_self_illumination.scale) * qgl_Material.map_self_illumination.amount + qgl_Material.map_self_illumination.offset;
self *= qgl_Material.color_self_illumination;
vec3 speed = pos.xyz/pos.w - ppos.xyz/ppos.w;
//speed /= abs(pos.z);
//gl_FragDepth = logz;
qgl_FragData[0] = vec4(dc.rgb, 0.);
qgl_FragData[1] = vec4(n.xyz, specularity + round(reflectivity * 100));
qgl_FragData[2] = vec4(spec.rgb, hei);
qgl_FragData[3] = vec4(self.rgb, bn.x);
qgl_FragData[4] = vec4(speed.xy, bn.yz);
//gl_FragData[0] = vec4(et.xyz, pos.w);
//gl_FragDepth = gl_FragCoord.z - clamp(hei / pos.z / pos.z / (abs(n.z) + 1), -0.01, 0.01);
/*vec4 dp = pos;
dp.x = floor(dp.w / 255.) / 255.;
dp.w -= dp.x * 65025;
dp.y = floor(dp.w) / 255.;
dp.w -= dp.y * 255.;
dp.z = fract(dp.w);*/
//dp.x = dp.w;
//dp.w = (gl_FrontMaterial.specular.r + gl_FrontMaterial.specular.g + gl_FrontMaterial.specular.b) / 3. / 25.5;
//gl_FragData[2] = dp;
//gl_FragData[3] = vec4(light_model / 255., 0, 0, 0);
}

46
libs/qglview/shaders/dsl_pass_0.vert Normal file
View File

@@ -0,0 +1,46 @@
#version 150
out vec3 src_normal, normal, binormal;//, et;
out vec4 pos, ppos;
out float fogCoord, FC, C;
out mat3 TBN;
uniform bool acc_fog;
uniform vec2 dt;
uniform vec3 eye;
uniform mat4 prev_ModelViewProjectioMatrix;
uniform float z_near, z_far;
void main(void) {
normal = qgl_Normal;//(qgl_NormalMatrix * qgl_Normal);
binormal = qgl_Bitangent;//(qgl_NormalMatrix * qgl_Normal);
pos = qgl_ftransform();
TBN = mat3(qgl_Tangent, qgl_Bitangent, qgl_Normal);
/*if (acc_fog) {
fogCoord = (gl_Fog.end - length(pos.xyz) * 0.85) / (gl_Fog.end - gl_Fog.start);
fogCoord = 1. - clamp(fogCoord, 0., 1.);
}*/
//gl_TexCoord[0] = gl_MultiTexCoord0;
//gl_TexCoord[1] = gl_MultiTexCoord1;
src_normal = normalize(vec3(pos.xy * dt * 2., 0));
qgl_FragTexture = qgl_Texture;
qgl_FragColor = qgl_Color;
//tp /= tp.w;
ppos = prev_ModelViewProjectioMatrix * vec4(qgl_Vertex.xyz, 1);
//pos.w = pos.w;
//speed = tp - ppos;
//speed /= (abs(speed) + 1.);
//speed.xyz *= speed.w;
//pos *= pos.w;
//logz = gl_Position.w*C + 1; //version with fragment code
C = 0.01;
FC = 1. / log(z_far * C + 1.);
//pos.z = (logz + logz - 1) * pos.w;
gl_Position = pos;
}

167
libs/qglview/shaders/dsl_pass_1.frag Normal file
View File

@@ -0,0 +1,167 @@
#version 150
//#extension GL_EXT_gpu_shader4 : enable
in vec3 view_dir;
in vec4 view_pos;
uniform vec3 ambient;
uniform sampler2D t0, t1, t2, t3, t4, t_pp;
uniform sampler2D td;
uniform int gid, lightsCount, shadow_on;
uniform float z_near, z_far;
uniform bool firstPass;
uniform vec2 dt;
uniform vec4 back_color;
uniform mat4 mat_proji, mat_view, mat_viewi, mat_viewproji;
float light_diffuse(int model, vec3 l, vec3 n) {return max(0., dot(l, n));}
float light_specular(int model, vec3 l, vec3 n, vec3 h, vec3 v, float shininess) {return max(0., pow(dot(n, h), shininess));}
vec4 pos, lpos, shp;
vec3 li, si, ldir, halfV, bn, bn2, lwdir;
vec3 vds, vds2;
float sh_pow, sh_mul, dist, NdotL, NdotH, spot, ldist, diff, sdist, shadow;
float getShadow(int light, vec3 view_pos, vec3 dpos) {
shp = qgl_Light[light].shadowMatrix * vec4(view_pos + dpos, 1);
shp.z -= z_near / 20.;
return textureProj(qgl_Light[light].shadow, shp);
}
void calcLight(in int index, in vec3 n, in vec3 v, in vec4 v2) {
lpos = qgl_Light[index].position;
ldir = lpos.xyz - (pos.xyz * lpos.w);
ldist = length(ldir);
ldir = normalize(ldir);
halfV = normalize(ldir + v);
NdotL = max(dot(n, ldir), 0.0001);
NdotH = max(dot(n, halfV), 0.0001);
spot = step(0., NdotL) * qgl_Light[index].intensity;
if (qgl_Light[index].endAngle <= 90.) {
float scos = max(dot(-ldir, qgl_Light[index].direction.xyz), 0.);
spot *= scos * step(qgl_Light[index].endAngleCos, scos);
spot *= smoothstep(qgl_Light[index].endAngleCos, qgl_Light[index].startAngleCos, scos);
//lwdir = mat3(mat_viewi) * qgl_Light[index].direction.xyz;
//bn = normalize(cross(lwdir, vec3(1, 0, 0)));
//bn2 = normalize(cross(lwdir, bn));
float ds = ldist/200.;//max(abs(sdist) / 5000, 0.02);
//spot *= clamp(1. - sdist, 0, 1);
vds = ds * bn.xyz;
vds2 = ds * bn2.xyz;
float shadow = getShadow(index, pos.xyz, vec3(0)) * 3.;
shadow += getShadow(index, pos.xyz, vds ) * 2.;
shadow += getShadow(index, pos.xyz, - vds ) * 2.;
shadow += getShadow(index, pos.xyz, - vds2 ) * 2.;
shadow += getShadow(index, pos.xyz, + vds2 ) * 2.;
/*shadow += getShadow(index, pos.xyz, vds - vds2 ) * 1.5;
shadow += getShadow(index, pos.xyz, vds + vds2 ) * 1.5;
shadow += getShadow(index, pos.xyz, - vds - vds2 ) * 1.5;
shadow += getShadow(index, pos.xyz, - vds + vds2 ) * 1.5;
shadow += getShadow(index, pos.xyz, vds + vds );
shadow += getShadow(index, pos.xyz, - vds - vds );
shadow += getShadow(index, pos.xyz, - vds2 - vds2);
shadow += getShadow(index, pos.xyz, + vds2 + vds2);
shadow += getShadow(index, pos.xyz, vds + vds - vds2 );
shadow += getShadow(index, pos.xyz, - vds - vds - vds2 );
shadow += getShadow(index, pos.xyz, vds + vds + vds2 );
shadow += getShadow(index, pos.xyz, - vds - vds + vds2 );
shadow += getShadow(index, pos.xyz, vds - vds2 - vds2);
shadow += getShadow(index, pos.xyz, vds + vds2 + vds2);
shadow += getShadow(index, pos.xyz, - vds - vds2 - vds2);
shadow += getShadow(index, pos.xyz, - vds + vds2 + vds2);*/
//shadow += shadow += getShadow(index, pos.xyz, vds+vds2)*10;
spot *= mix(1., shadow / 11., shadow_on);
}
spot /= (qgl_Light[index].constantAttenuation + ldist * (qgl_Light[index].linearAttenuation + ldist * qgl_Light[index].quadraticAttenuation));
///li += spot * gl_LightSource[index].diffuse.rgb * light_diffuse(0, ldir, n);
//si += spot * qgl_Light[index].color.rgb * sh_mul * light_specular(0, ldir, n, halfV, v, sh_pow);
float NdotLs = NdotL*NdotL;
float NdotHs = NdotH*NdotH;
float ndlc = (1. - NdotLs) / NdotLs;
float der = NdotLs * (sh_mul + ndlc);
diff = 2. / (1. + sqrt(1. + (1. - sh_mul) * ndlc));
li += spot * qgl_Light[index].color.rgb * diff;// * light_diffuse(0, ldir, n);
ndlc = (1. - NdotHs) / NdotHs;
der = NdotHs * (sh_mul + ndlc);
si += spot * qgl_Light[index].color.rgb * (sh_mul / (der*der) / 3.1416);
}
const float _pe = 2.4e-7;
void main(void) {
//if (d == 1.) discard;
ivec2 tc = ivec2(gl_FragCoord.xy);
float z = texelFetch(td, tc, 0).r;
if (z == 1.) {
qgl_FragData[0] = back_color;
return;
}
vec4 v0 = texelFetch(t0, tc, 0),
v1 = texelFetch(t1, tc, 0),
v2 = texelFetch(t2, tc, 0),
v3 = texelFetch(t3, tc, 0),
v4 = texelFetch(t4, tc, 0);
z = z + z - 1;
z = ((_pe - 2.) * z_near) / (z + _pe - 1.); // infinite depth
vec2 sp = gl_FragCoord.xy * dt * 2 - vec2(1, 1);
vec3 dc = v0.rgb, n = v1.xyz;
bn = normalize(vec3(v3.w, v4.zw));
bn2 = normalize(cross(n, bn));
float height = v2.w;
li = qgl_AmbientLight.color.rgb * qgl_AmbientLight.intensity;
si = vec3(0.);
/*float posz = z_near * z_far / (texelFetch(td, tc, 0).r * (z_far - z_near) - z_far);
pos = vec4(sp, 0., 1) * mat_proji;
pos.xy *= v0.z;
pos.z = posz;*/
pos.w = 1;
pos.xyz = view_dir * z;
//pos.z = -pos.z;
//pos.z = posz;
//pos.xyz += n * height;
//pos.xyz = v3.xyz;
//pos = v3;
//pos = vec4(sp, 0, 1.) * mat_proji;
//pos *= v0.w;
//pos.z += 1;
//pos.xy *= 10.;
//pos.z = v0.w;
vec3 v = normalize(-pos.xyz);
float reflectivity = 0.;
float specularity = modf(v1.w, reflectivity);
sh_pow = 1. / max((1. - specularity), 0.0001);
sh_mul = max(1. - specularity, 0.0001);
for (int i = 0; i < 8; ++i)
calcLight(i, n, v, v2);
// calcLight(0, n, v, v2);
qgl_FragData[0] = vec4(max(vec3(0), li * dc + si * v2.rgb + v3.rgb + texelFetch(t_pp, tc, 0).rgb), v0.w);
//qgl_FragData[0].rgb = vec3(length(view_pos.xyz - qgl_Light[1].position.xyz)/3);
//qgl_FragData[0].rgb = vec3(view_pos.xyz);
//shd = shd - shp.w;
/*vec3 fp = pos.xyz;// * lpos.w;
vec3 _dlp = fp - qgl_Light[0].position.xyz;
vec3 _ld = qgl_Light[0].direction.xyz;
float lz = dot(_ld, _dlp);
vec3 _lt = normalize(cross(_ld, _dlp));
vec3 _lt2 = normalize(cross(_lt, _dlp));
float ly = dot(qgl_Light[0].shadowDir0.xyz, normalize(_dlp));
float lx = dot(qgl_Light[0].shadowDir1.xyz, normalize(_dlp));
vec3 dd = mat3(mat_viewi)*(normalize(_dlp) - _ld);
//qgl_FragData[0].rgb = vec3(abs(shp.xy/shp.w)/1,0);
float Y = dot(_dlp, qgl_Light[0].shadowDir0.xyz) / length(qgl_Light[0].shadowDir0.xyz);
float X = dot(_dlp, qgl_Light[0].shadowDir1.xyz) / length(qgl_Light[0].shadowDir1.xyz);
qgl_FragData[0].rgb = vec3(abs((mat3(mat_viewi)*_dlp).x)/100);*/
//qgl_FragData[0].rgb = vec3(abs(mat3(mat_viewi)* qgl_Light[0].direction.xyz));
//qgl_FragData[0].rgb = vec3(texture(qgl_Light[0].shadow,shp.xyz/shp.w)/2);
//qgl_FragData[0].a = 0.;
}

16
libs/qglview/shaders/dsl_pass_1.vert Normal file
View File

@@ -0,0 +1,16 @@
#version 150
in vec3 view_corner;
out vec3 view_dir;
out vec4 view_pos;
void main(void) {
//view_dir = vec3(0.8);
view_pos = vec4(qgl_ModelViewMatrix * vec4(qgl_Vertex.xy, 1, 1));
view_pos /= view_pos.w;
view_dir = vec3(view_corner.xyz);// / view_corner.z;
qgl_FragTexture = qgl_Texture;
qgl_FragColor = qgl_Color;
gl_Position = qgl_ftransform();
//gl_Position = vec4(qgl_Vertex,1);
}

13
libs/qglview/shaders/dsl_pass_2.frag Normal file
View File

@@ -0,0 +1,13 @@
#version 120
uniform sampler2D t0, depth;
uniform vec3 backColor;
void main(void) {
//gl_FragColor.rgb=vec3(1,1,1);
if (texture2D(depth, gl_TexCoord[0].xy).x == 1.) {
gl_FragColor.rgb = backColor;
return;
}
gl_FragColor.rgb = texture2D(t0, gl_TexCoord[0].xy).rgb;
}

6
libs/qglview/shaders/dsl_pass_2.vert Normal file
View File

@@ -0,0 +1,6 @@
#version 120
void main(void) {
gl_TexCoord[0] = gl_MultiTexCoord0;
gl_Position = ftransform();
}

7
libs/qglview/shaders/fbo_add.frag Normal file
View File

@@ -0,0 +1,7 @@
#version 150
uniform sampler2D t0, t1;
void main(void) {
qgl_FragData[0].rgb = texelFetch(t0, ivec2(gl_FragCoord.xy), 0).rgb + texelFetch(t1, ivec2(gl_FragCoord.xy), 0).rgb;
}

6
libs/qglview/shaders/fbo_add.vert Normal file
View File

@@ -0,0 +1,6 @@
#version 150
void main(void) {
qgl_FragTexture = qgl_Texture;
gl_Position = qgl_ftransform();
}

2048
libs/qglview/shaders/fxaa_v3.h Normal file
View File

@@ -0,0 +1,2048 @@
/*============================================================================
NVIDIA FXAA 3.11 by TIMOTHY LOTTES
------------------------------------------------------------------------------
COPYRIGHT (C) 2010, 2011 NVIDIA CORPORATION. ALL RIGHTS RESERVED.
------------------------------------------------------------------------------
TO THE MAXIMUM EXTENT PERMITTED BY APPLICABLE LAW, THIS SOFTWARE IS PROVIDED
*AS IS* AND NVIDIA AND ITS SUPPLIERS DISCLAIM ALL WARRANTIES, EITHER EXPRESS
OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, IMPLIED WARRANTIES OF
MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. IN NO EVENT SHALL NVIDIA
OR ITS SUPPLIERS BE LIABLE FOR ANY SPECIAL, INCIDENTAL, INDIRECT, OR
CONSEQUENTIAL DAMAGES WHATSOEVER (INCLUDING, WITHOUT LIMITATION, DAMAGES FOR
LOSS OF BUSINESS PROFITS, BUSINESS INTERRUPTION, LOSS OF BUSINESS INFORMATION,
OR ANY OTHER PECUNIARY LOSS) ARISING OUT OF THE USE OF OR INABILITY TO USE
THIS SOFTWARE, EVEN IF NVIDIA HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH
DAMAGES.
------------------------------------------------------------------------------
INTEGRATION CHECKLIST
------------------------------------------------------------------------------
(1.)
In the shader source, setup defines for the desired configuration.
When providing multiple shaders (for different presets),
simply setup the defines differently in multiple files.
Example,
#define FXAA_PC 1
#define FXAA_HLSL_5 1
#define FXAA_QUALITY__PRESET 12
Or,
#define FXAA_360 1
Or,
#define FXAA_PS3 1
Etc.
(2.)
Then include this file,
#include "Fxaa3_11.h"
(3.)
Then call the FXAA pixel shader from within your desired shader.
Look at the FXAA Quality FxaaPixelShader() for docs on inputs.
As for FXAA 3.11 all inputs for all shaders are the same
to enable easy porting between platforms.
return FxaaPixelShader(...);
(4.)
Insure pass prior to FXAA outputs RGBL (see next section).
Or use,
#define FXAA_GREEN_AS_LUMA 1
(5.)
Setup engine to provide the following constants
which are used in the FxaaPixelShader() inputs,
FxaaFloat2 fxaaQualityRcpFrame,
FxaaFloat4 fxaaConsoleRcpFrameOpt,
FxaaFloat4 fxaaConsoleRcpFrameOpt2,
FxaaFloat4 fxaaConsole360RcpFrameOpt2,
FxaaFloat fxaaQualitySubpix,
FxaaFloat fxaaQualityEdgeThreshold,
FxaaFloat fxaaQualityEdgeThresholdMin,
FxaaFloat fxaaConsoleEdgeSharpness,
FxaaFloat fxaaConsoleEdgeThreshold,
FxaaFloat fxaaConsoleEdgeThresholdMin,
FxaaFloat4 fxaaConsole360ConstDir
Look at the FXAA Quality FxaaPixelShader() for docs on inputs.
(6.)
Have FXAA vertex shader run as a full screen triangle,
and output "pos" and "fxaaConsolePosPos"
such that inputs in the pixel shader provide,
// {xy} = center of pixel
FxaaFloat2 pos,
// {xy__} = upper left of pixel
// {__zw} = lower right of pixel
FxaaFloat4 fxaaConsolePosPos,
(7.)
Insure the texture sampler(s) used by FXAA are set to bilinear filtering.
------------------------------------------------------------------------------
INTEGRATION - RGBL AND COLORSPACE
------------------------------------------------------------------------------
FXAA3 requires RGBL as input unless the following is set,
#define FXAA_GREEN_AS_LUMA 1
In which case the engine uses green in place of luma,
and requires RGB input is in a non-linear colorspace.
RGB should be LDR (low dynamic range).
Specifically do FXAA after tonemapping.
RGB data as returned by a texture fetch can be non-linear,
or linear when FXAA_GREEN_AS_LUMA is not set.
Note an "sRGB format" texture counts as linear,
because the result of a texture fetch is linear data.
Regular "RGBA8" textures in the sRGB colorspace are non-linear.
If FXAA_GREEN_AS_LUMA is not set,
luma must be stored in the alpha channel prior to running FXAA.
This luma should be in a perceptual space (could be gamma 2.0).
Example pass before FXAA where output is gamma 2.0 encoded,
color.rgb = ToneMap(color.rgb); // linear color output
color.rgb = sqrt(color.rgb); // gamma 2.0 color output
return color;
To use FXAA,
color.rgb = ToneMap(color.rgb); // linear color output
color.rgb = sqrt(color.rgb); // gamma 2.0 color output
color.a = dot(color.rgb, FxaaFloat3(0.299, 0.587, 0.114)); // compute luma
return color;
Another example where output is linear encoded,
say for instance writing to an sRGB formated render target,
where the render target does the conversion back to sRGB after blending,
color.rgb = ToneMap(color.rgb); // linear color output
return color;
To use FXAA,
color.rgb = ToneMap(color.rgb); // linear color output
color.a = sqrt(dot(color.rgb, FxaaFloat3(0.299, 0.587, 0.114))); // compute luma
return color;
Getting luma correct is required for the algorithm to work correctly.
------------------------------------------------------------------------------
BEING LINEARLY CORRECT?
------------------------------------------------------------------------------
Applying FXAA to a framebuffer with linear RGB color will look worse.
This is very counter intuitive, but happends to be true in this case.
The reason is because dithering artifacts will be more visiable
in a linear colorspace.
------------------------------------------------------------------------------
COMPLEX INTEGRATION
------------------------------------------------------------------------------
Q. What if the engine is blending into RGB before wanting to run FXAA?
A. In the last opaque pass prior to FXAA,
have the pass write out luma into alpha.
Then blend into RGB only.
FXAA should be able to run ok
assuming the blending pass did not any add aliasing.
This should be the common case for particles and common blending passes.
A. Or use FXAA_GREEN_AS_LUMA.
============================================================================*/
/*============================================================================
INTEGRATION KNOBS
============================================================================*/
//
// FXAA_PS3 and FXAA_360 choose the console algorithm (FXAA3 CONSOLE).
// FXAA_360_OPT is a prototype for the new optimized 360 version.
//
// 1 = Use API.
// 0 = Don't use API.
//
/*--------------------------------------------------------------------------*/
#ifndef FXAA_PS3
#define FXAA_PS3 0
#endif
/*--------------------------------------------------------------------------*/
#ifndef FXAA_360
#define FXAA_360 0
#endif
/*--------------------------------------------------------------------------*/
#ifndef FXAA_360_OPT
#define FXAA_360_OPT 0
#endif
/*==========================================================================*/
#ifndef FXAA_PC
//
// FXAA Quality
// The high quality PC algorithm.
//
#define FXAA_PC 0
#endif
/*--------------------------------------------------------------------------*/
#ifndef FXAA_PC_CONSOLE
//
// The console algorithm for PC is included
// for developers targeting really low spec machines.
// Likely better to just run FXAA_PC, and use a really low preset.
//
#define FXAA_PC_CONSOLE 0
#endif
/*--------------------------------------------------------------------------*/
#ifndef FXAA_GLSL_120
#define FXAA_GLSL_120 0
#endif
/*--------------------------------------------------------------------------*/
#ifndef FXAA_GLSL_130
#define FXAA_GLSL_130 0
#endif
/*--------------------------------------------------------------------------*/
#ifndef FXAA_HLSL_3
#define FXAA_HLSL_3 0
#endif
/*--------------------------------------------------------------------------*/
#ifndef FXAA_HLSL_4
#define FXAA_HLSL_4 0
#endif
/*--------------------------------------------------------------------------*/
#ifndef FXAA_HLSL_5
#define FXAA_HLSL_5 0
#endif
/*==========================================================================*/
#ifndef FXAA_GREEN_AS_LUMA
//
// For those using non-linear color,
// and either not able to get luma in alpha, or not wanting to,
// this enables FXAA to run using green as a proxy for luma.
// So with this enabled, no need to pack luma in alpha.
//
// This will turn off AA on anything which lacks some amount of green.
// Pure red and blue or combination of only R and B, will get no AA.
//
// Might want to lower the settings for both,
// fxaaConsoleEdgeThresholdMin
// fxaaQualityEdgeThresholdMin
// In order to insure AA does not get turned off on colors
// which contain a minor amount of green.
//
// 1 = On.
// 0 = Off.
//
#define FXAA_GREEN_AS_LUMA 0
#endif
/*--------------------------------------------------------------------------*/
#ifndef FXAA_EARLY_EXIT
//
// Controls algorithm's early exit path.
// On PS3 turning this ON adds 2 cycles to the shader.
// On 360 turning this OFF adds 10ths of a millisecond to the shader.
// Turning this off on console will result in a more blurry image.
// So this defaults to on.
//
// 1 = On.
// 0 = Off.
//
#define FXAA_EARLY_EXIT 1
#endif
/*--------------------------------------------------------------------------*/
#ifndef FXAA_DISCARD
//
// Only valid for PC OpenGL currently.
// Probably will not work when FXAA_GREEN_AS_LUMA = 1.
//
// 1 = Use discard on pixels which don't need AA.
// For APIs which enable concurrent TEX+ROP from same surface.
// 0 = Return unchanged color on pixels which don't need AA.
//
#define FXAA_DISCARD 0
#endif
/*--------------------------------------------------------------------------*/
#ifndef FXAA_FAST_PIXEL_OFFSET
//
// Used for GLSL 120 only.
//
// 1 = GL API supports fast pixel offsets
// 0 = do not use fast pixel offsets
//
#ifdef GL_EXT_gpu_shader4
#define FXAA_FAST_PIXEL_OFFSET 1
#endif
#ifdef GL_NV_gpu_shader5
#define FXAA_FAST_PIXEL_OFFSET 1
#endif
#ifdef GL_ARB_gpu_shader5
#define FXAA_FAST_PIXEL_OFFSET 1
#endif
#ifndef FXAA_FAST_PIXEL_OFFSET
#define FXAA_FAST_PIXEL_OFFSET 0
#endif
#endif
/*--------------------------------------------------------------------------*/
#ifndef FXAA_GATHER4_ALPHA
//
// 1 = API supports gather4 on alpha channel.
// 0 = API does not support gather4 on alpha channel.
//
#if (FXAA_HLSL_5 == 1)
#define FXAA_GATHER4_ALPHA 1
#endif
#ifdef GL_ARB_gpu_shader5
#define FXAA_GATHER4_ALPHA 1
#endif
#ifdef GL_NV_gpu_shader5
#define FXAA_GATHER4_ALPHA 1
#endif
#ifndef FXAA_GATHER4_ALPHA
#define FXAA_GATHER4_ALPHA 0
#endif
#endif
/*============================================================================
FXAA CONSOLE PS3 - TUNING KNOBS
============================================================================*/
#ifndef FXAA_CONSOLE__PS3_EDGE_SHARPNESS
//
// Consoles the sharpness of edges on PS3 only.
// Non-PS3 tuning is done with shader input.
//
// Due to the PS3 being ALU bound,
// there are only two safe values here: 4 and 8.
// These options use the shaders ability to a free *|/ by 2|4|8.
//
// 8.0 is sharper
// 4.0 is softer
// 2.0 is really soft (good for vector graphics inputs)
//
#if 1
#define FXAA_CONSOLE__PS3_EDGE_SHARPNESS 8.0
#endif
#if 0
#define FXAA_CONSOLE__PS3_EDGE_SHARPNESS 4.0
#endif
#if 0
#define FXAA_CONSOLE__PS3_EDGE_SHARPNESS 2.0
#endif
#endif
/*--------------------------------------------------------------------------*/
#ifndef FXAA_CONSOLE__PS3_EDGE_THRESHOLD
//
// Only effects PS3.
// Non-PS3 tuning is done with shader input.
//
// The minimum amount of local contrast required to apply algorithm.
// The console setting has a different mapping than the quality setting.
//
// This only applies when FXAA_EARLY_EXIT is 1.
//
// Due to the PS3 being ALU bound,
// there are only two safe values here: 0.25 and 0.125.
// These options use the shaders ability to a free *|/ by 2|4|8.
//
// 0.125 leaves less aliasing, but is softer
// 0.25 leaves more aliasing, and is sharper
//
#if 1
#define FXAA_CONSOLE__PS3_EDGE_THRESHOLD 0.125
#else
#define FXAA_CONSOLE__PS3_EDGE_THRESHOLD 0.25
#endif
#endif
/*============================================================================
FXAA QUALITY - TUNING KNOBS
------------------------------------------------------------------------------
NOTE the other tuning knobs are now in the shader function inputs!
============================================================================*/
#ifndef FXAA_QUALITY__PRESET
//
// Choose the quality preset.
// This needs to be compiled into the shader as it effects code.
// Best option to include multiple presets is to
// in each shader define the preset, then include this file.
//
// OPTIONS
// -----------------------------------------------------------------------
// 10 to 15 - default medium dither (10=fastest, 15=highest quality)
// 20 to 29 - less dither, more expensive (20=fastest, 29=highest quality)
// 39 - no dither, very expensive
//
// NOTES
// -----------------------------------------------------------------------
// 12 = slightly faster then FXAA 3.9 and higher edge quality (default)
// 13 = about same speed as FXAA 3.9 and better than 12
// 23 = closest to FXAA 3.9 visually and performance wise
// _ = the lowest digit is directly related to performance
// _ = the highest digit is directly related to style
//
#define FXAA_QUALITY__PRESET 12
#endif
/*============================================================================
FXAA QUALITY - PRESETS
============================================================================*/
/*============================================================================
FXAA QUALITY - MEDIUM DITHER PRESETS
============================================================================*/
#if (FXAA_QUALITY__PRESET == 10)
#define FXAA_QUALITY__PS 3
#define FXAA_QUALITY__P0 1.5
#define FXAA_QUALITY__P1 3.0
#define FXAA_QUALITY__P2 12.0
#endif
/*--------------------------------------------------------------------------*/
#if (FXAA_QUALITY__PRESET == 11)
#define FXAA_QUALITY__PS 4
#define FXAA_QUALITY__P0 1.0
#define FXAA_QUALITY__P1 1.5
#define FXAA_QUALITY__P2 3.0
#define FXAA_QUALITY__P3 12.0
#endif
/*--------------------------------------------------------------------------*/
#if (FXAA_QUALITY__PRESET == 12)
#define FXAA_QUALITY__PS 5
#define FXAA_QUALITY__P0 1.0
#define FXAA_QUALITY__P1 1.5
#define FXAA_QUALITY__P2 2.0
#define FXAA_QUALITY__P3 4.0
#define FXAA_QUALITY__P4 12.0
#endif
/*--------------------------------------------------------------------------*/
#if (FXAA_QUALITY__PRESET == 13)
#define FXAA_QUALITY__PS 6
#define FXAA_QUALITY__P0 1.0
#define FXAA_QUALITY__P1 1.5
#define FXAA_QUALITY__P2 2.0
#define FXAA_QUALITY__P3 2.0
#define FXAA_QUALITY__P4 4.0
#define FXAA_QUALITY__P5 12.0
#endif
/*--------------------------------------------------------------------------*/
#if (FXAA_QUALITY__PRESET == 14)
#define FXAA_QUALITY__PS 7
#define FXAA_QUALITY__P0 1.0
#define FXAA_QUALITY__P1 1.5
#define FXAA_QUALITY__P2 2.0
#define FXAA_QUALITY__P3 2.0
#define FXAA_QUALITY__P4 2.0
#define FXAA_QUALITY__P5 4.0
#define FXAA_QUALITY__P6 12.0
#endif
/*--------------------------------------------------------------------------*/
#if (FXAA_QUALITY__PRESET == 15)
#define FXAA_QUALITY__PS 8
#define FXAA_QUALITY__P0 1.0
#define FXAA_QUALITY__P1 1.5
#define FXAA_QUALITY__P2 2.0
#define FXAA_QUALITY__P3 2.0
#define FXAA_QUALITY__P4 2.0
#define FXAA_QUALITY__P5 2.0
#define FXAA_QUALITY__P6 4.0
#define FXAA_QUALITY__P7 12.0
#endif
/*============================================================================
FXAA QUALITY - LOW DITHER PRESETS
============================================================================*/
#if (FXAA_QUALITY__PRESET == 20)
#define FXAA_QUALITY__PS 3
#define FXAA_QUALITY__P0 1.5
#define FXAA_QUALITY__P1 2.0
#define FXAA_QUALITY__P2 8.0
#endif
/*--------------------------------------------------------------------------*/
#if (FXAA_QUALITY__PRESET == 21)
#define FXAA_QUALITY__PS 4
#define FXAA_QUALITY__P0 1.0
#define FXAA_QUALITY__P1 1.5
#define FXAA_QUALITY__P2 2.0
#define FXAA_QUALITY__P3 8.0
#endif
/*--------------------------------------------------------------------------*/
#if (FXAA_QUALITY__PRESET == 22)
#define FXAA_QUALITY__PS 5
#define FXAA_QUALITY__P0 1.0
#define FXAA_QUALITY__P1 1.5
#define FXAA_QUALITY__P2 2.0
#define FXAA_QUALITY__P3 2.0
#define FXAA_QUALITY__P4 8.0
#endif
/*--------------------------------------------------------------------------*/
#if (FXAA_QUALITY__PRESET == 23)
#define FXAA_QUALITY__PS 6
#define FXAA_QUALITY__P0 1.0
#define FXAA_QUALITY__P1 1.5
#define FXAA_QUALITY__P2 2.0
#define FXAA_QUALITY__P3 2.0
#define FXAA_QUALITY__P4 2.0
#define FXAA_QUALITY__P5 8.0
#endif
/*--------------------------------------------------------------------------*/
#if (FXAA_QUALITY__PRESET == 24)
#define FXAA_QUALITY__PS 7
#define FXAA_QUALITY__P0 1.0
#define FXAA_QUALITY__P1 1.5
#define FXAA_QUALITY__P2 2.0
#define FXAA_QUALITY__P3 2.0
#define FXAA_QUALITY__P4 2.0
#define FXAA_QUALITY__P5 3.0
#define FXAA_QUALITY__P6 8.0
#endif
/*--------------------------------------------------------------------------*/
#if (FXAA_QUALITY__PRESET == 25)
#define FXAA_QUALITY__PS 8
#define FXAA_QUALITY__P0 1.0
#define FXAA_QUALITY__P1 1.5
#define FXAA_QUALITY__P2 2.0
#define FXAA_QUALITY__P3 2.0
#define FXAA_QUALITY__P4 2.0
#define FXAA_QUALITY__P5 2.0
#define FXAA_QUALITY__P6 4.0
#define FXAA_QUALITY__P7 8.0
#endif
/*--------------------------------------------------------------------------*/
#if (FXAA_QUALITY__PRESET == 26)
#define FXAA_QUALITY__PS 9
#define FXAA_QUALITY__P0 1.0
#define FXAA_QUALITY__P1 1.5
#define FXAA_QUALITY__P2 2.0
#define FXAA_QUALITY__P3 2.0
#define FXAA_QUALITY__P4 2.0
#define FXAA_QUALITY__P5 2.0
#define FXAA_QUALITY__P6 2.0
#define FXAA_QUALITY__P7 4.0
#define FXAA_QUALITY__P8 8.0
#endif
/*--------------------------------------------------------------------------*/
#if (FXAA_QUALITY__PRESET == 27)
#define FXAA_QUALITY__PS 10
#define FXAA_QUALITY__P0 1.0
#define FXAA_QUALITY__P1 1.5
#define FXAA_QUALITY__P2 2.0
#define FXAA_QUALITY__P3 2.0
#define FXAA_QUALITY__P4 2.0
#define FXAA_QUALITY__P5 2.0
#define FXAA_QUALITY__P6 2.0
#define FXAA_QUALITY__P7 2.0
#define FXAA_QUALITY__P8 4.0
#define FXAA_QUALITY__P9 8.0
#endif
/*--------------------------------------------------------------------------*/
#if (FXAA_QUALITY__PRESET == 28)
#define FXAA_QUALITY__PS 11
#define FXAA_QUALITY__P0 1.0
#define FXAA_QUALITY__P1 1.5
#define FXAA_QUALITY__P2 2.0
#define FXAA_QUALITY__P3 2.0
#define FXAA_QUALITY__P4 2.0
#define FXAA_QUALITY__P5 2.0
#define FXAA_QUALITY__P6 2.0
#define FXAA_QUALITY__P7 2.0
#define FXAA_QUALITY__P8 2.0
#define FXAA_QUALITY__P9 4.0
#define FXAA_QUALITY__P10 8.0
#endif
/*--------------------------------------------------------------------------*/
#if (FXAA_QUALITY__PRESET == 29)
#define FXAA_QUALITY__PS 12
#define FXAA_QUALITY__P0 1.0
#define FXAA_QUALITY__P1 1.5
#define FXAA_QUALITY__P2 2.0
#define FXAA_QUALITY__P3 2.0
#define FXAA_QUALITY__P4 2.0
#define FXAA_QUALITY__P5 2.0
#define FXAA_QUALITY__P6 2.0
#define FXAA_QUALITY__P7 2.0
#define FXAA_QUALITY__P8 2.0
#define FXAA_QUALITY__P9 2.0
#define FXAA_QUALITY__P10 4.0
#define FXAA_QUALITY__P11 8.0
#endif
/*============================================================================
FXAA QUALITY - EXTREME QUALITY
============================================================================*/
#if (FXAA_QUALITY__PRESET == 39)
#define FXAA_QUALITY__PS 12
#define FXAA_QUALITY__P0 1.0
#define FXAA_QUALITY__P1 1.0
#define FXAA_QUALITY__P2 1.0
#define FXAA_QUALITY__P3 1.0
#define FXAA_QUALITY__P4 1.0
#define FXAA_QUALITY__P5 1.5
#define FXAA_QUALITY__P6 2.0
#define FXAA_QUALITY__P7 2.0
#define FXAA_QUALITY__P8 2.0
#define FXAA_QUALITY__P9 2.0
#define FXAA_QUALITY__P10 4.0
#define FXAA_QUALITY__P11 8.0
#endif
/*============================================================================
API PORTING
============================================================================*/
#if (FXAA_GLSL_120 == 1) || (FXAA_GLSL_130 == 1)
#define FxaaBool bool
#define FxaaDiscard discard
#define FxaaFloat float
#define FxaaFloat2 vec2
#define FxaaFloat3 vec3
#define FxaaFloat4 vec4
#define FxaaHalf float
#define FxaaHalf2 vec2
#define FxaaHalf3 vec3
#define FxaaHalf4 vec4
#define FxaaInt2 ivec2
#define FxaaSat(x) clamp(x, 0.0, 1.0)
#define FxaaTex sampler2D
#else
#define FxaaBool bool
#define FxaaDiscard clip(-1)
#define FxaaFloat float
#define FxaaFloat2 float2
#define FxaaFloat3 float3
#define FxaaFloat4 float4
#define FxaaHalf half
#define FxaaHalf2 half2
#define FxaaHalf3 half3
#define FxaaHalf4 half4
#define FxaaSat(x) saturate(x)
#endif
/*--------------------------------------------------------------------------*/
#if (FXAA_GLSL_120 == 1)
// Requires,
// #version 120
// And at least,
// #extension GL_EXT_gpu_shader4 : enable
// (or set FXAA_FAST_PIXEL_OFFSET 1 to work like DX9)
#define FxaaTexTop(t, p) texture2DLod(t, p, 0.0)
#if (FXAA_FAST_PIXEL_OFFSET == 1)
#define FxaaTexOff(t, p, o, r) texture2DLodOffset(t, p, 0.0, o)
#else
#define FxaaTexOff(t, p, o, r) texture2DLod(t, p + (o * r), 0.0)
#endif
#if (FXAA_GATHER4_ALPHA == 1)
// use #extension GL_ARB_gpu_shader5 : enable
#define FxaaTexAlpha4(t, p) textureGather(t, p, 3)
#define FxaaTexOffAlpha4(t, p, o) textureGatherOffset(t, p, o, 3)
#define FxaaTexGreen4(t, p) textureGather(t, p, 1)
#define FxaaTexOffGreen4(t, p, o) textureGatherOffset(t, p, o, 1)
#endif
#endif
/*--------------------------------------------------------------------------*/
#if (FXAA_GLSL_130 == 1)
// Requires "#version 130" or better
#define FxaaTexTop(t, p) textureLod(t, p, 0.0)
#define FxaaTexOff(t, p, o, r) textureLodOffset(t, p, 0.0, o)
#if (FXAA_GATHER4_ALPHA == 1)
// use #extension GL_ARB_gpu_shader5 : enable
#define FxaaTexAlpha4(t, p) textureGather(t, p, 3)
#define FxaaTexOffAlpha4(t, p, o) textureGatherOffset(t, p, o, 3)
#define FxaaTexGreen4(t, p) textureGather(t, p, 1)
#define FxaaTexOffGreen4(t, p, o) textureGatherOffset(t, p, o, 1)
#endif
#endif
/*--------------------------------------------------------------------------*/
#if (FXAA_HLSL_3 == 1) || (FXAA_360 == 1) || (FXAA_PS3 == 1)
#define FxaaInt2 float2
#define FxaaTex sampler2D
#define FxaaTexTop(t, p) tex2Dlod(t, float4(p, 0.0, 0.0))
#define FxaaTexOff(t, p, o, r) tex2Dlod(t, float4(p + (o * r), 0, 0))
#endif
/*--------------------------------------------------------------------------*/
#if (FXAA_HLSL_4 == 1)
#define FxaaInt2 int2
struct FxaaTex { SamplerState smpl; Texture2D tex; };
#define FxaaTexTop(t, p) t.tex.SampleLevel(t.smpl, p, 0.0)
#define FxaaTexOff(t, p, o, r) t.tex.SampleLevel(t.smpl, p, 0.0, o)
#endif
/*--------------------------------------------------------------------------*/
#if (FXAA_HLSL_5 == 1)
#define FxaaInt2 int2
struct FxaaTex { SamplerState smpl; Texture2D tex; };
#define FxaaTexTop(t, p) t.tex.SampleLevel(t.smpl, p, 0.0)
#define FxaaTexOff(t, p, o, r) t.tex.SampleLevel(t.smpl, p, 0.0, o)
#define FxaaTexAlpha4(t, p) t.tex.GatherAlpha(t.smpl, p)
#define FxaaTexOffAlpha4(t, p, o) t.tex.GatherAlpha(t.smpl, p, o)
#define FxaaTexGreen4(t, p) t.tex.GatherGreen(t.smpl, p)
#define FxaaTexOffGreen4(t, p, o) t.tex.GatherGreen(t.smpl, p, o)
#endif
/*============================================================================
GREEN AS LUMA OPTION SUPPORT FUNCTION
============================================================================*/
#if (FXAA_GREEN_AS_LUMA == 0)
//FxaaFloat FxaaLuma(FxaaFloat4 rgba) { return rgba.w; }
FxaaFloat FxaaLuma(FxaaFloat4 rgba) { return dot(rgba.rgb, FxaaFloat3(0.299, 0.587, 0.114)); }
#else
FxaaFloat FxaaLuma(FxaaFloat4 rgba) { return rgba.y; }
#endif
/*============================================================================
FXAA3 QUALITY - PC
============================================================================*/
#if (FXAA_PC == 1)
/*--------------------------------------------------------------------------*/
FxaaFloat4 FxaaPixelShader(
//
// Use noperspective interpolation here (turn off perspective interpolation).
// {xy} = center of pixel
FxaaFloat2 pos,
//
// Used only for FXAA Console, and not used on the 360 version.
// Use noperspective interpolation here (turn off perspective interpolation).
// {xy__} = upper left of pixel
// {__zw} = lower right of pixel
FxaaFloat4 fxaaConsolePosPos,
//
// Input color texture.
// {rgb_} = color in linear or perceptual color space
// if (FXAA_GREEN_AS_LUMA == 0)
// {___a} = luma in perceptual color space (not linear)
FxaaTex tex,
//
// Only used on the optimized 360 version of FXAA Console.
// For everything but 360, just use the same input here as for "tex".
// For 360, same texture, just alias with a 2nd sampler.
// This sampler needs to have an exponent bias of -1.
FxaaTex fxaaConsole360TexExpBiasNegOne,
//
// Only used on the optimized 360 version of FXAA Console.
// For everything but 360, just use the same input here as for "tex".
// For 360, same texture, just alias with a 3nd sampler.
// This sampler needs to have an exponent bias of -2.
FxaaTex fxaaConsole360TexExpBiasNegTwo,
//
// Only used on FXAA Quality.
// This must be from a constant/uniform.
// {x_} = 1.0/screenWidthInPixels
// {_y} = 1.0/screenHeightInPixels
FxaaFloat2 fxaaQualityRcpFrame,
//
// Only used on FXAA Console.
// This must be from a constant/uniform.
// This effects sub-pixel AA quality and inversely sharpness.
// Where N ranges between,
// N = 0.50 (default)
// N = 0.33 (sharper)
// {x___} = -N/screenWidthInPixels
// {_y__} = -N/screenHeightInPixels
// {__z_} = N/screenWidthInPixels
// {___w} = N/screenHeightInPixels
FxaaFloat4 fxaaConsoleRcpFrameOpt,
//
// Only used on FXAA Console.
// Not used on 360, but used on PS3 and PC.
// This must be from a constant/uniform.
// {x___} = -2.0/screenWidthInPixels
// {_y__} = -2.0/screenHeightInPixels
// {__z_} = 2.0/screenWidthInPixels
// {___w} = 2.0/screenHeightInPixels
FxaaFloat4 fxaaConsoleRcpFrameOpt2,
//
// Only used on FXAA Console.
// Only used on 360 in place of fxaaConsoleRcpFrameOpt2.
// This must be from a constant/uniform.
// {x___} = 8.0/screenWidthInPixels
// {_y__} = 8.0/screenHeightInPixels
// {__z_} = -4.0/screenWidthInPixels
// {___w} = -4.0/screenHeightInPixels
FxaaFloat4 fxaaConsole360RcpFrameOpt2,
//
// Only used on FXAA Quality.
// This used to be the FXAA_QUALITY__SUBPIX define.
// It is here now to allow easier tuning.
// Choose the amount of sub-pixel aliasing removal.
// This can effect sharpness.
// 1.00 - upper limit (softer)
// 0.75 - default amount of filtering
// 0.50 - lower limit (sharper, less sub-pixel aliasing removal)
// 0.25 - almost off
// 0.00 - completely off
FxaaFloat fxaaQualitySubpix,
//
// Only used on FXAA Quality.
// This used to be the FXAA_QUALITY__EDGE_THRESHOLD define.
// It is here now to allow easier tuning.
// The minimum amount of local contrast required to apply algorithm.
// 0.333 - too little (faster)
// 0.250 - low quality
// 0.166 - default
// 0.125 - high quality
// 0.063 - overkill (slower)
FxaaFloat fxaaQualityEdgeThreshold,
//
// Only used on FXAA Quality.
// This used to be the FXAA_QUALITY__EDGE_THRESHOLD_MIN define.
// It is here now to allow easier tuning.
// Trims the algorithm from processing darks.
// 0.0833 - upper limit (default, the start of visible unfiltered edges)
// 0.0625 - high quality (faster)
// 0.0312 - visible limit (slower)
// Special notes when using FXAA_GREEN_AS_LUMA,
// Likely want to set this to zero.
// As colors that are mostly not-green
// will appear very dark in the green channel!
// Tune by looking at mostly non-green content,
// then start at zero and increase until aliasing is a problem.
FxaaFloat fxaaQualityEdgeThresholdMin,
//
// Only used on FXAA Console.
// This used to be the FXAA_CONSOLE__EDGE_SHARPNESS define.
// It is here now to allow easier tuning.
// This does not effect PS3, as this needs to be compiled in.
// Use FXAA_CONSOLE__PS3_EDGE_SHARPNESS for PS3.
// Due to the PS3 being ALU bound,
// there are only three safe values here: 2 and 4 and 8.
// These options use the shaders ability to a free *|/ by 2|4|8.
// For all other platforms can be a non-power of two.
// 8.0 is sharper (default!!!)
// 4.0 is softer
// 2.0 is really soft (good only for vector graphics inputs)
FxaaFloat fxaaConsoleEdgeSharpness,
//
// Only used on FXAA Console.
// This used to be the FXAA_CONSOLE__EDGE_THRESHOLD define.
// It is here now to allow easier tuning.
// This does not effect PS3, as this needs to be compiled in.
// Use FXAA_CONSOLE__PS3_EDGE_THRESHOLD for PS3.
// Due to the PS3 being ALU bound,
// there are only two safe values here: 1/4 and 1/8.
// These options use the shaders ability to a free *|/ by 2|4|8.
// The console setting has a different mapping than the quality setting.
// Other platforms can use other values.
// 0.125 leaves less aliasing, but is softer (default!!!)
// 0.25 leaves more aliasing, and is sharper
FxaaFloat fxaaConsoleEdgeThreshold,
//
// Only used on FXAA Console.
// This used to be the FXAA_CONSOLE__EDGE_THRESHOLD_MIN define.
// It is here now to allow easier tuning.
// Trims the algorithm from processing darks.
// The console setting has a different mapping than the quality setting.
// This only applies when FXAA_EARLY_EXIT is 1.
// This does not apply to PS3,
// PS3 was simplified to avoid more shader instructions.
// 0.06 - faster but more aliasing in darks
// 0.05 - default
// 0.04 - slower and less aliasing in darks
// Special notes when using FXAA_GREEN_AS_LUMA,
// Likely want to set this to zero.
// As colors that are mostly not-green
// will appear very dark in the green channel!
// Tune by looking at mostly non-green content,
// then start at zero and increase until aliasing is a problem.
FxaaFloat fxaaConsoleEdgeThresholdMin,
//
// Extra constants for 360 FXAA Console only.
// Use zeros or anything else for other platforms.
// These must be in physical constant registers and NOT immedates.
// Immedates will result in compiler un-optimizing.
// {xyzw} = float4(1.0, -1.0, 0.25, -0.25)
FxaaFloat4 fxaaConsole360ConstDir
) {
/*--------------------------------------------------------------------------*/
FxaaFloat2 posM;
posM.x = pos.x;
posM.y = pos.y;
#if (FXAA_GATHER4_ALPHA == 1)
#if (FXAA_DISCARD == 0)
FxaaFloat4 rgbyM = FxaaTexTop(tex, posM);
#if (FXAA_GREEN_AS_LUMA == 0)
#define lumaM rgbyM.w
#else
#define lumaM rgbyM.y
#endif
#endif
#if (FXAA_GREEN_AS_LUMA == 0)
FxaaFloat4 luma4A = FxaaTexAlpha4(tex, posM);
FxaaFloat4 luma4B = FxaaTexOffAlpha4(tex, posM, FxaaInt2(-1, -1));
#else
FxaaFloat4 luma4A = FxaaTexGreen4(tex, posM);
FxaaFloat4 luma4B = FxaaTexOffGreen4(tex, posM, FxaaInt2(-1, -1));
#endif
#if (FXAA_DISCARD == 1)
#define lumaM luma4A.w
#endif
#define lumaE luma4A.z
#define lumaS luma4A.x
#define lumaSE luma4A.y
#define lumaNW luma4B.w
#define lumaN luma4B.z
#define lumaW luma4B.x
#else
FxaaFloat4 rgbyM = FxaaTexTop(tex, posM);
#if (FXAA_GREEN_AS_LUMA == 0)
#define lumaM rgbyM.w
#else
#define lumaM rgbyM.y
#endif
FxaaFloat lumaS = FxaaLuma(FxaaTexOff(tex, posM, FxaaInt2( 0, 1), fxaaQualityRcpFrame.xy));
FxaaFloat lumaE = FxaaLuma(FxaaTexOff(tex, posM, FxaaInt2( 1, 0), fxaaQualityRcpFrame.xy));
FxaaFloat lumaN = FxaaLuma(FxaaTexOff(tex, posM, FxaaInt2( 0,-1), fxaaQualityRcpFrame.xy));
FxaaFloat lumaW = FxaaLuma(FxaaTexOff(tex, posM, FxaaInt2(-1, 0), fxaaQualityRcpFrame.xy));
#endif
/*--------------------------------------------------------------------------*/
FxaaFloat maxSM = max(lumaS, lumaM);
FxaaFloat minSM = min(lumaS, lumaM);
FxaaFloat maxESM = max(lumaE, maxSM);
FxaaFloat minESM = min(lumaE, minSM);
FxaaFloat maxWN = max(lumaN, lumaW);
FxaaFloat minWN = min(lumaN, lumaW);
FxaaFloat rangeMax = max(maxWN, maxESM);
FxaaFloat rangeMin = min(minWN, minESM);
FxaaFloat rangeMaxScaled = rangeMax * fxaaQualityEdgeThreshold;
FxaaFloat range = rangeMax - rangeMin;
FxaaFloat rangeMaxClamped = max(fxaaQualityEdgeThresholdMin, rangeMaxScaled);
FxaaBool earlyExit = range < rangeMaxClamped;
/*--------------------------------------------------------------------------*/
if(earlyExit)
#if (FXAA_DISCARD == 1)
FxaaDiscard;
#else
return rgbyM;
#endif
/*--------------------------------------------------------------------------*/
#if (FXAA_GATHER4_ALPHA == 0)
FxaaFloat lumaNW = FxaaLuma(FxaaTexOff(tex, posM, FxaaInt2(-1,-1), fxaaQualityRcpFrame.xy));
FxaaFloat lumaSE = FxaaLuma(FxaaTexOff(tex, posM, FxaaInt2( 1, 1), fxaaQualityRcpFrame.xy));
FxaaFloat lumaNE = FxaaLuma(FxaaTexOff(tex, posM, FxaaInt2( 1,-1), fxaaQualityRcpFrame.xy));
FxaaFloat lumaSW = FxaaLuma(FxaaTexOff(tex, posM, FxaaInt2(-1, 1), fxaaQualityRcpFrame.xy));
#else
FxaaFloat lumaNE = FxaaLuma(FxaaTexOff(tex, posM, FxaaInt2(1, -1), fxaaQualityRcpFrame.xy));
FxaaFloat lumaSW = FxaaLuma(FxaaTexOff(tex, posM, FxaaInt2(-1, 1), fxaaQualityRcpFrame.xy));
#endif
/*--------------------------------------------------------------------------*/
FxaaFloat lumaNS = lumaN + lumaS;
FxaaFloat lumaWE = lumaW + lumaE;
FxaaFloat subpixRcpRange = 1.0/range;
FxaaFloat subpixNSWE = lumaNS + lumaWE;
FxaaFloat edgeHorz1 = (-2.0 * lumaM) + lumaNS;
FxaaFloat edgeVert1 = (-2.0 * lumaM) + lumaWE;
/*--------------------------------------------------------------------------*/
FxaaFloat lumaNESE = lumaNE + lumaSE;
FxaaFloat lumaNWNE = lumaNW + lumaNE;
FxaaFloat edgeHorz2 = (-2.0 * lumaE) + lumaNESE;
FxaaFloat edgeVert2 = (-2.0 * lumaN) + lumaNWNE;
/*--------------------------------------------------------------------------*/
FxaaFloat lumaNWSW = lumaNW + lumaSW;
FxaaFloat lumaSWSE = lumaSW + lumaSE;
FxaaFloat edgeHorz4 = (abs(edgeHorz1) * 2.0) + abs(edgeHorz2);
FxaaFloat edgeVert4 = (abs(edgeVert1) * 2.0) + abs(edgeVert2);
FxaaFloat edgeHorz3 = (-2.0 * lumaW) + lumaNWSW;
FxaaFloat edgeVert3 = (-2.0 * lumaS) + lumaSWSE;
FxaaFloat edgeHorz = abs(edgeHorz3) + edgeHorz4;
FxaaFloat edgeVert = abs(edgeVert3) + edgeVert4;
/*--------------------------------------------------------------------------*/
FxaaFloat subpixNWSWNESE = lumaNWSW + lumaNESE;
FxaaFloat lengthSign = fxaaQualityRcpFrame.x;
FxaaBool horzSpan = edgeHorz >= edgeVert;
FxaaFloat subpixA = subpixNSWE * 2.0 + subpixNWSWNESE;
/*--------------------------------------------------------------------------*/
if(!horzSpan) lumaN = lumaW;
if(!horzSpan) lumaS = lumaE;
if(horzSpan) lengthSign = fxaaQualityRcpFrame.y;
FxaaFloat subpixB = (subpixA * (1.0/12.0)) - lumaM;
/*--------------------------------------------------------------------------*/
FxaaFloat gradientN = lumaN - lumaM;
FxaaFloat gradientS = lumaS - lumaM;
FxaaFloat lumaNN = lumaN + lumaM;
FxaaFloat lumaSS = lumaS + lumaM;
FxaaBool pairN = abs(gradientN) >= abs(gradientS);
FxaaFloat gradient = max(abs(gradientN), abs(gradientS));
if(pairN) lengthSign = -lengthSign;
FxaaFloat subpixC = FxaaSat(abs(subpixB) * subpixRcpRange);
/*--------------------------------------------------------------------------*/
FxaaFloat2 posB;
posB.x = posM.x;
posB.y = posM.y;
FxaaFloat2 offNP;
offNP.x = (!horzSpan) ? 0.0 : fxaaQualityRcpFrame.x;
offNP.y = ( horzSpan) ? 0.0 : fxaaQualityRcpFrame.y;
if(!horzSpan) posB.x += lengthSign * 0.5;
if( horzSpan) posB.y += lengthSign * 0.5;
/*--------------------------------------------------------------------------*/
FxaaFloat2 posN;
posN.x = posB.x - offNP.x * FXAA_QUALITY__P0;
posN.y = posB.y - offNP.y * FXAA_QUALITY__P0;
FxaaFloat2 posP;
posP.x = posB.x + offNP.x * FXAA_QUALITY__P0;
posP.y = posB.y + offNP.y * FXAA_QUALITY__P0;
FxaaFloat subpixD = ((-2.0)*subpixC) + 3.0;
FxaaFloat lumaEndN = FxaaLuma(FxaaTexTop(tex, posN));
FxaaFloat subpixE = subpixC * subpixC;
FxaaFloat lumaEndP = FxaaLuma(FxaaTexTop(tex, posP));
/*--------------------------------------------------------------------------*/
if(!pairN) lumaNN = lumaSS;
FxaaFloat gradientScaled = gradient * 1.0/4.0;
FxaaFloat lumaMM = lumaM - lumaNN * 0.5;
FxaaFloat subpixF = subpixD * subpixE;
FxaaBool lumaMLTZero = lumaMM < 0.0;
/*--------------------------------------------------------------------------*/
lumaEndN -= lumaNN * 0.5;
lumaEndP -= lumaNN * 0.5;
FxaaBool doneN = abs(lumaEndN) >= gradientScaled;
FxaaBool doneP = abs(lumaEndP) >= gradientScaled;
if(!doneN) posN.x -= offNP.x * FXAA_QUALITY__P1;
if(!doneN) posN.y -= offNP.y * FXAA_QUALITY__P1;
FxaaBool doneNP = (!doneN) || (!doneP);
if(!doneP) posP.x += offNP.x * FXAA_QUALITY__P1;
if(!doneP) posP.y += offNP.y * FXAA_QUALITY__P1;
/*--------------------------------------------------------------------------*/
if(doneNP) {
if(!doneN) lumaEndN = FxaaLuma(FxaaTexTop(tex, posN.xy));
if(!doneP) lumaEndP = FxaaLuma(FxaaTexTop(tex, posP.xy));
if(!doneN) lumaEndN = lumaEndN - lumaNN * 0.5;
if(!doneP) lumaEndP = lumaEndP - lumaNN * 0.5;
doneN = abs(lumaEndN) >= gradientScaled;
doneP = abs(lumaEndP) >= gradientScaled;
if(!doneN) posN.x -= offNP.x * FXAA_QUALITY__P2;
if(!doneN) posN.y -= offNP.y * FXAA_QUALITY__P2;
doneNP = (!doneN) || (!doneP);
if(!doneP) posP.x += offNP.x * FXAA_QUALITY__P2;
if(!doneP) posP.y += offNP.y * FXAA_QUALITY__P2;
/*--------------------------------------------------------------------------*/
#if (FXAA_QUALITY__PS > 3)
if(doneNP) {
if(!doneN) lumaEndN = FxaaLuma(FxaaTexTop(tex, posN.xy));
if(!doneP) lumaEndP = FxaaLuma(FxaaTexTop(tex, posP.xy));
if(!doneN) lumaEndN = lumaEndN - lumaNN * 0.5;
if(!doneP) lumaEndP = lumaEndP - lumaNN * 0.5;
doneN = abs(lumaEndN) >= gradientScaled;
doneP = abs(lumaEndP) >= gradientScaled;
if(!doneN) posN.x -= offNP.x * FXAA_QUALITY__P3;
if(!doneN) posN.y -= offNP.y * FXAA_QUALITY__P3;
doneNP = (!doneN) || (!doneP);
if(!doneP) posP.x += offNP.x * FXAA_QUALITY__P3;
if(!doneP) posP.y += offNP.y * FXAA_QUALITY__P3;
/*--------------------------------------------------------------------------*/
#if (FXAA_QUALITY__PS > 4)
if(doneNP) {
if(!doneN) lumaEndN = FxaaLuma(FxaaTexTop(tex, posN.xy));
if(!doneP) lumaEndP = FxaaLuma(FxaaTexTop(tex, posP.xy));
if(!doneN) lumaEndN = lumaEndN - lumaNN * 0.5;
if(!doneP) lumaEndP = lumaEndP - lumaNN * 0.5;
doneN = abs(lumaEndN) >= gradientScaled;
doneP = abs(lumaEndP) >= gradientScaled;
if(!doneN) posN.x -= offNP.x * FXAA_QUALITY__P4;
if(!doneN) posN.y -= offNP.y * FXAA_QUALITY__P4;
doneNP = (!doneN) || (!doneP);
if(!doneP) posP.x += offNP.x * FXAA_QUALITY__P4;
if(!doneP) posP.y += offNP.y * FXAA_QUALITY__P4;
/*--------------------------------------------------------------------------*/
#if (FXAA_QUALITY__PS > 5)
if(doneNP) {
if(!doneN) lumaEndN = FxaaLuma(FxaaTexTop(tex, posN.xy));
if(!doneP) lumaEndP = FxaaLuma(FxaaTexTop(tex, posP.xy));
if(!doneN) lumaEndN = lumaEndN - lumaNN * 0.5;
if(!doneP) lumaEndP = lumaEndP - lumaNN * 0.5;
doneN = abs(lumaEndN) >= gradientScaled;
doneP = abs(lumaEndP) >= gradientScaled;
if(!doneN) posN.x -= offNP.x * FXAA_QUALITY__P5;
if(!doneN) posN.y -= offNP.y * FXAA_QUALITY__P5;
doneNP = (!doneN) || (!doneP);
if(!doneP) posP.x += offNP.x * FXAA_QUALITY__P5;
if(!doneP) posP.y += offNP.y * FXAA_QUALITY__P5;
/*--------------------------------------------------------------------------*/
#if (FXAA_QUALITY__PS > 6)
if(doneNP) {
if(!doneN) lumaEndN = FxaaLuma(FxaaTexTop(tex, posN.xy));
if(!doneP) lumaEndP = FxaaLuma(FxaaTexTop(tex, posP.xy));
if(!doneN) lumaEndN = lumaEndN - lumaNN * 0.5;
if(!doneP) lumaEndP = lumaEndP - lumaNN * 0.5;
doneN = abs(lumaEndN) >= gradientScaled;
doneP = abs(lumaEndP) >= gradientScaled;
if(!doneN) posN.x -= offNP.x * FXAA_QUALITY__P6;
if(!doneN) posN.y -= offNP.y * FXAA_QUALITY__P6;
doneNP = (!doneN) || (!doneP);
if(!doneP) posP.x += offNP.x * FXAA_QUALITY__P6;
if(!doneP) posP.y += offNP.y * FXAA_QUALITY__P6;
/*--------------------------------------------------------------------------*/
#if (FXAA_QUALITY__PS > 7)
if(doneNP) {
if(!doneN) lumaEndN = FxaaLuma(FxaaTexTop(tex, posN.xy));
if(!doneP) lumaEndP = FxaaLuma(FxaaTexTop(tex, posP.xy));
if(!doneN) lumaEndN = lumaEndN - lumaNN * 0.5;
if(!doneP) lumaEndP = lumaEndP - lumaNN * 0.5;
doneN = abs(lumaEndN) >= gradientScaled;
doneP = abs(lumaEndP) >= gradientScaled;
if(!doneN) posN.x -= offNP.x * FXAA_QUALITY__P7;
if(!doneN) posN.y -= offNP.y * FXAA_QUALITY__P7;
doneNP = (!doneN) || (!doneP);
if(!doneP) posP.x += offNP.x * FXAA_QUALITY__P7;
if(!doneP) posP.y += offNP.y * FXAA_QUALITY__P7;
/*--------------------------------------------------------------------------*/
#if (FXAA_QUALITY__PS > 8)
if(doneNP) {
if(!doneN) lumaEndN = FxaaLuma(FxaaTexTop(tex, posN.xy));
if(!doneP) lumaEndP = FxaaLuma(FxaaTexTop(tex, posP.xy));
if(!doneN) lumaEndN = lumaEndN - lumaNN * 0.5;
if(!doneP) lumaEndP = lumaEndP - lumaNN * 0.5;
doneN = abs(lumaEndN) >= gradientScaled;
doneP = abs(lumaEndP) >= gradientScaled;
if(!doneN) posN.x -= offNP.x * FXAA_QUALITY__P8;
if(!doneN) posN.y -= offNP.y * FXAA_QUALITY__P8;
doneNP = (!doneN) || (!doneP);
if(!doneP) posP.x += offNP.x * FXAA_QUALITY__P8;
if(!doneP) posP.y += offNP.y * FXAA_QUALITY__P8;
/*--------------------------------------------------------------------------*/
#if (FXAA_QUALITY__PS > 9)
if(doneNP) {
if(!doneN) lumaEndN = FxaaLuma(FxaaTexTop(tex, posN.xy));
if(!doneP) lumaEndP = FxaaLuma(FxaaTexTop(tex, posP.xy));
if(!doneN) lumaEndN = lumaEndN - lumaNN * 0.5;
if(!doneP) lumaEndP = lumaEndP - lumaNN * 0.5;
doneN = abs(lumaEndN) >= gradientScaled;
doneP = abs(lumaEndP) >= gradientScaled;
if(!doneN) posN.x -= offNP.x * FXAA_QUALITY__P9;
if(!doneN) posN.y -= offNP.y * FXAA_QUALITY__P9;
doneNP = (!doneN) || (!doneP);
if(!doneP) posP.x += offNP.x * FXAA_QUALITY__P9;
if(!doneP) posP.y += offNP.y * FXAA_QUALITY__P9;
/*--------------------------------------------------------------------------*/
#if (FXAA_QUALITY__PS > 10)
if(doneNP) {
if(!doneN) lumaEndN = FxaaLuma(FxaaTexTop(tex, posN.xy));
if(!doneP) lumaEndP = FxaaLuma(FxaaTexTop(tex, posP.xy));
if(!doneN) lumaEndN = lumaEndN - lumaNN * 0.5;
if(!doneP) lumaEndP = lumaEndP - lumaNN * 0.5;
doneN = abs(lumaEndN) >= gradientScaled;
doneP = abs(lumaEndP) >= gradientScaled;
if(!doneN) posN.x -= offNP.x * FXAA_QUALITY__P10;
if(!doneN) posN.y -= offNP.y * FXAA_QUALITY__P10;
doneNP = (!doneN) || (!doneP);
if(!doneP) posP.x += offNP.x * FXAA_QUALITY__P10;
if(!doneP) posP.y += offNP.y * FXAA_QUALITY__P10;
/*--------------------------------------------------------------------------*/
#if (FXAA_QUALITY__PS > 11)
if(doneNP) {
if(!doneN) lumaEndN = FxaaLuma(FxaaTexTop(tex, posN.xy));
if(!doneP) lumaEndP = FxaaLuma(FxaaTexTop(tex, posP.xy));
if(!doneN) lumaEndN = lumaEndN - lumaNN * 0.5;
if(!doneP) lumaEndP = lumaEndP - lumaNN * 0.5;
doneN = abs(lumaEndN) >= gradientScaled;
doneP = abs(lumaEndP) >= gradientScaled;
if(!doneN) posN.x -= offNP.x * FXAA_QUALITY__P11;
if(!doneN) posN.y -= offNP.y * FXAA_QUALITY__P11;
doneNP = (!doneN) || (!doneP);
if(!doneP) posP.x += offNP.x * FXAA_QUALITY__P11;
if(!doneP) posP.y += offNP.y * FXAA_QUALITY__P11;
/*--------------------------------------------------------------------------*/
#if (FXAA_QUALITY__PS > 12)
if(doneNP) {
if(!doneN) lumaEndN = FxaaLuma(FxaaTexTop(tex, posN.xy));
if(!doneP) lumaEndP = FxaaLuma(FxaaTexTop(tex, posP.xy));
if(!doneN) lumaEndN = lumaEndN - lumaNN * 0.5;
if(!doneP) lumaEndP = lumaEndP - lumaNN * 0.5;
doneN = abs(lumaEndN) >= gradientScaled;
doneP = abs(lumaEndP) >= gradientScaled;
if(!doneN) posN.x -= offNP.x * FXAA_QUALITY__P12;
if(!doneN) posN.y -= offNP.y * FXAA_QUALITY__P12;
doneNP = (!doneN) || (!doneP);
if(!doneP) posP.x += offNP.x * FXAA_QUALITY__P12;
if(!doneP) posP.y += offNP.y * FXAA_QUALITY__P12;
/*--------------------------------------------------------------------------*/
}
#endif
/*--------------------------------------------------------------------------*/
}
#endif
/*--------------------------------------------------------------------------*/
}
#endif
/*--------------------------------------------------------------------------*/
}
#endif
/*--------------------------------------------------------------------------*/
}
#endif
/*--------------------------------------------------------------------------*/
}
#endif
/*--------------------------------------------------------------------------*/
}
#endif
/*--------------------------------------------------------------------------*/
}
#endif
/*--------------------------------------------------------------------------*/
}
#endif
/*--------------------------------------------------------------------------*/
}
#endif
/*--------------------------------------------------------------------------*/
}
/*--------------------------------------------------------------------------*/
FxaaFloat dstN = posM.x - posN.x;
FxaaFloat dstP = posP.x - posM.x;
if(!horzSpan) dstN = posM.y - posN.y;
if(!horzSpan) dstP = posP.y - posM.y;
/*--------------------------------------------------------------------------*/
FxaaBool goodSpanN = (lumaEndN < 0.0) != lumaMLTZero;
FxaaFloat spanLength = (dstP + dstN);
FxaaBool goodSpanP = (lumaEndP < 0.0) != lumaMLTZero;
FxaaFloat spanLengthRcp = 1.0/spanLength;
/*--------------------------------------------------------------------------*/
FxaaBool directionN = dstN < dstP;
FxaaFloat dst = min(dstN, dstP);
FxaaBool goodSpan = directionN ? goodSpanN : goodSpanP;
FxaaFloat subpixG = subpixF * subpixF;
FxaaFloat pixelOffset = (dst * (-spanLengthRcp)) + 0.5;
FxaaFloat subpixH = subpixG * fxaaQualitySubpix;
/*--------------------------------------------------------------------------*/
FxaaFloat pixelOffsetGood = goodSpan ? pixelOffset : 0.0;
FxaaFloat pixelOffsetSubpix = max(pixelOffsetGood, subpixH);
if(!horzSpan) posM.x += pixelOffsetSubpix * lengthSign;
if( horzSpan) posM.y += pixelOffsetSubpix * lengthSign;
#if (FXAA_DISCARD == 1)
return FxaaTexTop(tex, posM);
#else
return FxaaFloat4(FxaaTexTop(tex, posM).xyz, lumaM);
#endif
}
/*==========================================================================*/
#endif
/*============================================================================
FXAA3 CONSOLE - PC VERSION
------------------------------------------------------------------------------
Instead of using this on PC, I'd suggest just using FXAA Quality with
#define FXAA_QUALITY__PRESET 10
Or
#define FXAA_QUALITY__PRESET 20
Either are higher qualilty and almost as fast as this on modern PC GPUs.
============================================================================*/
#if (FXAA_PC_CONSOLE == 1)
/*--------------------------------------------------------------------------*/
FxaaFloat4 FxaaPixelShader(
// See FXAA Quality FxaaPixelShader() source for docs on Inputs!
FxaaFloat2 pos,
FxaaFloat4 fxaaConsolePosPos,
FxaaTex tex,
FxaaTex fxaaConsole360TexExpBiasNegOne,
FxaaTex fxaaConsole360TexExpBiasNegTwo,
FxaaFloat2 fxaaQualityRcpFrame,
FxaaFloat4 fxaaConsoleRcpFrameOpt,
FxaaFloat4 fxaaConsoleRcpFrameOpt2,
FxaaFloat4 fxaaConsole360RcpFrameOpt2,
FxaaFloat fxaaQualitySubpix,
FxaaFloat fxaaQualityEdgeThreshold,
FxaaFloat fxaaQualityEdgeThresholdMin,
FxaaFloat fxaaConsoleEdgeSharpness,
FxaaFloat fxaaConsoleEdgeThreshold,
FxaaFloat fxaaConsoleEdgeThresholdMin,
FxaaFloat4 fxaaConsole360ConstDir
) {
/*--------------------------------------------------------------------------*/
FxaaFloat lumaNw = FxaaLuma(FxaaTexTop(tex, fxaaConsolePosPos.xy));
FxaaFloat lumaSw = FxaaLuma(FxaaTexTop(tex, fxaaConsolePosPos.xw));
FxaaFloat lumaNe = FxaaLuma(FxaaTexTop(tex, fxaaConsolePosPos.zy));
FxaaFloat lumaSe = FxaaLuma(FxaaTexTop(tex, fxaaConsolePosPos.zw));
/*--------------------------------------------------------------------------*/
FxaaFloat4 rgbyM = FxaaTexTop(tex, pos.xy);
#if (FXAA_GREEN_AS_LUMA == 0)
FxaaFloat lumaM = rgbyM.w;
#else
FxaaFloat lumaM = rgbyM.y;
#endif
/*--------------------------------------------------------------------------*/
FxaaFloat lumaMaxNwSw = max(lumaNw, lumaSw);
lumaNe += 1.0/384.0;
FxaaFloat lumaMinNwSw = min(lumaNw, lumaSw);
/*--------------------------------------------------------------------------*/
FxaaFloat lumaMaxNeSe = max(lumaNe, lumaSe);
FxaaFloat lumaMinNeSe = min(lumaNe, lumaSe);
/*--------------------------------------------------------------------------*/
FxaaFloat lumaMax = max(lumaMaxNeSe, lumaMaxNwSw);
FxaaFloat lumaMin = min(lumaMinNeSe, lumaMinNwSw);
/*--------------------------------------------------------------------------*/
FxaaFloat lumaMaxScaled = lumaMax * fxaaConsoleEdgeThreshold;
/*--------------------------------------------------------------------------*/
FxaaFloat lumaMinM = min(lumaMin, lumaM);
FxaaFloat lumaMaxScaledClamped = max(fxaaConsoleEdgeThresholdMin, lumaMaxScaled);
FxaaFloat lumaMaxM = max(lumaMax, lumaM);
FxaaFloat dirSwMinusNe = lumaSw - lumaNe;
FxaaFloat lumaMaxSubMinM = lumaMaxM - lumaMinM;
FxaaFloat dirSeMinusNw = lumaSe - lumaNw;
if(lumaMaxSubMinM < lumaMaxScaledClamped) return rgbyM;
/*--------------------------------------------------------------------------*/
FxaaFloat2 dir;
dir.x = dirSwMinusNe + dirSeMinusNw;
dir.y = dirSwMinusNe - dirSeMinusNw;
/*--------------------------------------------------------------------------*/
FxaaFloat2 dir1 = normalize(dir.xy);
FxaaFloat4 rgbyN1 = FxaaTexTop(tex, pos.xy - dir1 * fxaaConsoleRcpFrameOpt.zw);
FxaaFloat4 rgbyP1 = FxaaTexTop(tex, pos.xy + dir1 * fxaaConsoleRcpFrameOpt.zw);
/*--------------------------------------------------------------------------*/
FxaaFloat dirAbsMinTimesC = min(abs(dir1.x), abs(dir1.y)) * fxaaConsoleEdgeSharpness;
FxaaFloat2 dir2 = clamp(dir1.xy / dirAbsMinTimesC, -2.0, 2.0);
/*--------------------------------------------------------------------------*/
FxaaFloat4 rgbyN2 = FxaaTexTop(tex, pos.xy - dir2 * fxaaConsoleRcpFrameOpt2.zw);
FxaaFloat4 rgbyP2 = FxaaTexTop(tex, pos.xy + dir2 * fxaaConsoleRcpFrameOpt2.zw);
/*--------------------------------------------------------------------------*/
FxaaFloat4 rgbyA = rgbyN1 + rgbyP1;
FxaaFloat4 rgbyB = ((rgbyN2 + rgbyP2) * 0.25) + (rgbyA * 0.25);
/*--------------------------------------------------------------------------*/
#if (FXAA_GREEN_AS_LUMA == 0)
FxaaBool twoTap = (rgbyB.w < lumaMin) || (rgbyB.w > lumaMax);
#else
FxaaBool twoTap = (rgbyB.y < lumaMin) || (rgbyB.y > lumaMax);
#endif
if(twoTap) rgbyB.xyz = rgbyA.xyz * 0.5;
return rgbyB; }
/*==========================================================================*/
#endif
/*============================================================================
FXAA3 CONSOLE - 360 PIXEL SHADER
------------------------------------------------------------------------------
This optimized version thanks to suggestions from Andy Luedke.
Should be fully tex bound in all cases.
As of the FXAA 3.11 release, I have still not tested this code,
however I fixed a bug which was in both FXAA 3.9 and FXAA 3.10.
And note this is replacing the old unoptimized version.
If it does not work, please let me know so I can fix it.
============================================================================*/
#if (FXAA_360 == 1)
/*--------------------------------------------------------------------------*/
[reduceTempRegUsage(4)]
float4 FxaaPixelShader(
// See FXAA Quality FxaaPixelShader() source for docs on Inputs!
FxaaFloat2 pos,
FxaaFloat4 fxaaConsolePosPos,
FxaaTex tex,
FxaaTex fxaaConsole360TexExpBiasNegOne,
FxaaTex fxaaConsole360TexExpBiasNegTwo,
FxaaFloat2 fxaaQualityRcpFrame,
FxaaFloat4 fxaaConsoleRcpFrameOpt,
FxaaFloat4 fxaaConsoleRcpFrameOpt2,
FxaaFloat4 fxaaConsole360RcpFrameOpt2,
FxaaFloat fxaaQualitySubpix,
FxaaFloat fxaaQualityEdgeThreshold,
FxaaFloat fxaaQualityEdgeThresholdMin,
FxaaFloat fxaaConsoleEdgeSharpness,
FxaaFloat fxaaConsoleEdgeThreshold,
FxaaFloat fxaaConsoleEdgeThresholdMin,
FxaaFloat4 fxaaConsole360ConstDir
) {
/*--------------------------------------------------------------------------*/
float4 lumaNwNeSwSe;
#if (FXAA_GREEN_AS_LUMA == 0)
asm {
tfetch2D lumaNwNeSwSe.w___, tex, pos.xy, OffsetX = -0.5, OffsetY = -0.5, UseComputedLOD=false
tfetch2D lumaNwNeSwSe._w__, tex, pos.xy, OffsetX = 0.5, OffsetY = -0.5, UseComputedLOD=false
tfetch2D lumaNwNeSwSe.__w_, tex, pos.xy, OffsetX = -0.5, OffsetY = 0.5, UseComputedLOD=false
tfetch2D lumaNwNeSwSe.___w, tex, pos.xy, OffsetX = 0.5, OffsetY = 0.5, UseComputedLOD=false
};
#else
asm {
tfetch2D lumaNwNeSwSe.y___, tex, pos.xy, OffsetX = -0.5, OffsetY = -0.5, UseComputedLOD=false
tfetch2D lumaNwNeSwSe._y__, tex, pos.xy, OffsetX = 0.5, OffsetY = -0.5, UseComputedLOD=false
tfetch2D lumaNwNeSwSe.__y_, tex, pos.xy, OffsetX = -0.5, OffsetY = 0.5, UseComputedLOD=false
tfetch2D lumaNwNeSwSe.___y, tex, pos.xy, OffsetX = 0.5, OffsetY = 0.5, UseComputedLOD=false
};
#endif
/*--------------------------------------------------------------------------*/
lumaNwNeSwSe.y += 1.0/384.0;
float2 lumaMinTemp = min(lumaNwNeSwSe.xy, lumaNwNeSwSe.zw);
float2 lumaMaxTemp = max(lumaNwNeSwSe.xy, lumaNwNeSwSe.zw);
float lumaMin = min(lumaMinTemp.x, lumaMinTemp.y);
float lumaMax = max(lumaMaxTemp.x, lumaMaxTemp.y);
/*--------------------------------------------------------------------------*/
float4 rgbyM = tex2Dlod(tex, float4(pos.xy, 0.0, 0.0));
#if (FXAA_GREEN_AS_LUMA == 0)
float lumaMinM = min(lumaMin, rgbyM.w);
float lumaMaxM = max(lumaMax, rgbyM.w);
#else
float lumaMinM = min(lumaMin, rgbyM.y);
float lumaMaxM = max(lumaMax, rgbyM.y);
#endif
if((lumaMaxM - lumaMinM) < max(fxaaConsoleEdgeThresholdMin, lumaMax * fxaaConsoleEdgeThreshold)) return rgbyM;
/*--------------------------------------------------------------------------*/
float2 dir;
dir.x = dot(lumaNwNeSwSe, fxaaConsole360ConstDir.yyxx);
dir.y = dot(lumaNwNeSwSe, fxaaConsole360ConstDir.xyxy);
dir = normalize(dir);
/*--------------------------------------------------------------------------*/
float4 dir1 = dir.xyxy * fxaaConsoleRcpFrameOpt.xyzw;
/*--------------------------------------------------------------------------*/
float4 dir2;
float dirAbsMinTimesC = min(abs(dir.x), abs(dir.y)) * fxaaConsoleEdgeSharpness;
dir2 = saturate(fxaaConsole360ConstDir.zzww * dir.xyxy / dirAbsMinTimesC + 0.5);
dir2 = dir2 * fxaaConsole360RcpFrameOpt2.xyxy + fxaaConsole360RcpFrameOpt2.zwzw;
/*--------------------------------------------------------------------------*/
float4 rgbyN1 = tex2Dlod(fxaaConsole360TexExpBiasNegOne, float4(pos.xy + dir1.xy, 0.0, 0.0));
float4 rgbyP1 = tex2Dlod(fxaaConsole360TexExpBiasNegOne, float4(pos.xy + dir1.zw, 0.0, 0.0));
float4 rgbyN2 = tex2Dlod(fxaaConsole360TexExpBiasNegTwo, float4(pos.xy + dir2.xy, 0.0, 0.0));
float4 rgbyP2 = tex2Dlod(fxaaConsole360TexExpBiasNegTwo, float4(pos.xy + dir2.zw, 0.0, 0.0));
/*--------------------------------------------------------------------------*/
float4 rgbyA = rgbyN1 + rgbyP1;
float4 rgbyB = rgbyN2 + rgbyP2 + rgbyA * 0.5;
/*--------------------------------------------------------------------------*/
float4 rgbyR = ((FxaaLuma(rgbyB) - lumaMax) > 0.0) ? rgbyA : rgbyB;
rgbyR = ((FxaaLuma(rgbyB) - lumaMin) > 0.0) ? rgbyR : rgbyA;
return rgbyR; }
/*==========================================================================*/
#endif
/*============================================================================
FXAA3 CONSOLE - OPTIMIZED PS3 PIXEL SHADER (NO EARLY EXIT)
==============================================================================
The code below does not exactly match the assembly.
I have a feeling that 12 cycles is possible, but was not able to get there.
Might have to increase register count to get full performance.
Note this shader does not use perspective interpolation.
Use the following cgc options,
--fenable-bx2 --fastmath --fastprecision --nofloatbindings
------------------------------------------------------------------------------
NVSHADERPERF OUTPUT
------------------------------------------------------------------------------
For reference and to aid in debug, output of NVShaderPerf should match this,
Shader to schedule:
0: texpkb h0.w(TRUE), v5.zyxx, #0
2: addh h2.z(TRUE), h0.w, constant(0.001953, 0.000000, 0.000000, 0.000000).x
4: texpkb h0.w(TRUE), v5.xwxx, #0
6: addh h0.z(TRUE), -h2, h0.w
7: texpkb h1.w(TRUE), v5, #0
9: addh h0.x(TRUE), h0.z, -h1.w
10: addh h3.w(TRUE), h0.z, h1
11: texpkb h2.w(TRUE), v5.zwzz, #0
13: addh h0.z(TRUE), h3.w, -h2.w
14: addh h0.x(TRUE), h2.w, h0
15: nrmh h1.xz(TRUE), h0_n
16: minh_m8 h0.x(TRUE), |h1|, |h1.z|
17: maxh h4.w(TRUE), h0, h1
18: divx h2.xy(TRUE), h1_n.xzzw, h0_n
19: movr r1.zw(TRUE), v4.xxxy
20: madr r2.xz(TRUE), -h1, constant(cConst5.x, cConst5.y, cConst5.z, cConst5.w).zzww, r1.zzww
22: minh h5.w(TRUE), h0, h1
23: texpkb h0(TRUE), r2.xzxx, #0
25: madr r0.zw(TRUE), h1.xzxz, constant(cConst5.x, cConst5.y, cConst5.z, cConst5.w), r1
27: maxh h4.x(TRUE), h2.z, h2.w
28: texpkb h1(TRUE), r0.zwzz, #0
30: addh_d2 h1(TRUE), h0, h1
31: madr r0.xy(TRUE), -h2, constant(cConst5.x, cConst5.y, cConst5.z, cConst5.w).xyxx, r1.zwzz
33: texpkb h0(TRUE), r0, #0
35: minh h4.z(TRUE), h2, h2.w
36: fenct TRUE
37: madr r1.xy(TRUE), h2, constant(cConst5.x, cConst5.y, cConst5.z, cConst5.w).xyxx, r1.zwzz
39: texpkb h2(TRUE), r1, #0
41: addh_d2 h0(TRUE), h0, h2
42: maxh h2.w(TRUE), h4, h4.x
43: minh h2.x(TRUE), h5.w, h4.z
44: addh_d2 h0(TRUE), h0, h1
45: slth h2.x(TRUE), h0.w, h2
46: sgth h2.w(TRUE), h0, h2
47: movh h0(TRUE), h0
48: addx.c0 rc(TRUE), h2, h2.w
49: movh h0(c0.NE.x), h1
IPU0 ------ Simplified schedule: --------
Pass | Unit | uOp | PC: Op
-----+--------+------+-------------------------
1 | SCT0/1 | mov | 0: TXLr h0.w, g[TEX1].zyxx, const.xxxx, TEX0;
| TEX | txl | 0: TXLr h0.w, g[TEX1].zyxx, const.xxxx, TEX0;
| SCB1 | add | 2: ADDh h2.z, h0.--w-, const.--x-;
| | |
2 | SCT0/1 | mov | 4: TXLr h0.w, g[TEX1].xwxx, const.xxxx, TEX0;
| TEX | txl | 4: TXLr h0.w, g[TEX1].xwxx, const.xxxx, TEX0;
| SCB1 | add | 6: ADDh h0.z,-h2, h0.--w-;
| | |
3 | SCT0/1 | mov | 7: TXLr h1.w, g[TEX1], const.xxxx, TEX0;
| TEX | txl | 7: TXLr h1.w, g[TEX1], const.xxxx, TEX0;
| SCB0 | add | 9: ADDh h0.x, h0.z---,-h1.w---;
| SCB1 | add | 10: ADDh h3.w, h0.---z, h1;
| | |
4 | SCT0/1 | mov | 11: TXLr h2.w, g[TEX1].zwzz, const.xxxx, TEX0;
| TEX | txl | 11: TXLr h2.w, g[TEX1].zwzz, const.xxxx, TEX0;
| SCB0 | add | 14: ADDh h0.x, h2.w---, h0;
| SCB1 | add | 13: ADDh h0.z, h3.--w-,-h2.--w-;
| | |
5 | SCT1 | mov | 15: NRMh h1.xz, h0;
| SRB | nrm | 15: NRMh h1.xz, h0;
| SCB0 | min | 16: MINh*8 h0.x, |h1|, |h1.z---|;
| SCB1 | max | 17: MAXh h4.w, h0, h1;
| | |
6 | SCT0 | div | 18: DIVx h2.xy, h1.xz--, h0;
| SCT1 | mov | 19: MOVr r1.zw, g[TEX0].--xy;
| SCB0 | mad | 20: MADr r2.xz,-h1, const.z-w-, r1.z-w-;
| SCB1 | min | 22: MINh h5.w, h0, h1;
| | |
7 | SCT0/1 | mov | 23: TXLr h0, r2.xzxx, const.xxxx, TEX0;
| TEX | txl | 23: TXLr h0, r2.xzxx, const.xxxx, TEX0;
| SCB0 | max | 27: MAXh h4.x, h2.z---, h2.w---;
| SCB1 | mad | 25: MADr r0.zw, h1.--xz, const, r1;
| | |
8 | SCT0/1 | mov | 28: TXLr h1, r0.zwzz, const.xxxx, TEX0;
| TEX | txl | 28: TXLr h1, r0.zwzz, const.xxxx, TEX0;
| SCB0/1 | add | 30: ADDh/2 h1, h0, h1;
| | |
9 | SCT0 | mad | 31: MADr r0.xy,-h2, const.xy--, r1.zw--;
| SCT1 | mov | 33: TXLr h0, r0, const.zzzz, TEX0;
| TEX | txl | 33: TXLr h0, r0, const.zzzz, TEX0;
| SCB1 | min | 35: MINh h4.z, h2, h2.--w-;
| | |
10 | SCT0 | mad | 37: MADr r1.xy, h2, const.xy--, r1.zw--;
| SCT1 | mov | 39: TXLr h2, r1, const.zzzz, TEX0;
| TEX | txl | 39: TXLr h2, r1, const.zzzz, TEX0;
| SCB0/1 | add | 41: ADDh/2 h0, h0, h2;
| | |
11 | SCT0 | min | 43: MINh h2.x, h5.w---, h4.z---;
| SCT1 | max | 42: MAXh h2.w, h4, h4.---x;
| SCB0/1 | add | 44: ADDh/2 h0, h0, h1;
| | |
12 | SCT0 | set | 45: SLTh h2.x, h0.w---, h2;
| SCT1 | set | 46: SGTh h2.w, h0, h2;
| SCB0/1 | mul | 47: MOVh h0, h0;
| | |
13 | SCT0 | mad | 48: ADDxc0_s rc, h2, h2.w---;
| SCB0/1 | mul | 49: MOVh h0(NE0.xxxx), h1;
Pass SCT TEX SCB
1: 0% 100% 25%
2: 0% 100% 25%
3: 0% 100% 50%
4: 0% 100% 50%
5: 0% 0% 50%
6: 100% 0% 75%
7: 0% 100% 75%
8: 0% 100% 100%
9: 0% 100% 25%
10: 0% 100% 100%
11: 50% 0% 100%
12: 50% 0% 100%
13: 25% 0% 100%
MEAN: 17% 61% 67%
Pass SCT0 SCT1 TEX SCB0 SCB1
1: 0% 0% 100% 0% 100%
2: 0% 0% 100% 0% 100%
3: 0% 0% 100% 100% 100%
4: 0% 0% 100% 100% 100%
5: 0% 0% 0% 100% 100%
6: 100% 100% 0% 100% 100%
7: 0% 0% 100% 100% 100%
8: 0% 0% 100% 100% 100%
9: 0% 0% 100% 0% 100%
10: 0% 0% 100% 100% 100%
11: 100% 100% 0% 100% 100%
12: 100% 100% 0% 100% 100%
13: 100% 0% 0% 100% 100%
MEAN: 30% 23% 61% 76% 100%
Fragment Performance Setup: Driver RSX Compiler, GPU RSX, Flags 0x5
Results 13 cycles, 3 r regs, 923,076,923 pixels/s
============================================================================*/
#if (FXAA_PS3 == 1) && (FXAA_EARLY_EXIT == 0)
/*--------------------------------------------------------------------------*/
#pragma regcount 7
#pragma disablepc all
#pragma option O3
#pragma option OutColorPrec=fp16
#pragma texformat default RGBA8
/*==========================================================================*/
half4 FxaaPixelShader(
// See FXAA Quality FxaaPixelShader() source for docs on Inputs!
FxaaFloat2 pos,
FxaaFloat4 fxaaConsolePosPos,
FxaaTex tex,
FxaaTex fxaaConsole360TexExpBiasNegOne,
FxaaTex fxaaConsole360TexExpBiasNegTwo,
FxaaFloat2 fxaaQualityRcpFrame,
FxaaFloat4 fxaaConsoleRcpFrameOpt,
FxaaFloat4 fxaaConsoleRcpFrameOpt2,
FxaaFloat4 fxaaConsole360RcpFrameOpt2,
FxaaFloat fxaaQualitySubpix,
FxaaFloat fxaaQualityEdgeThreshold,
FxaaFloat fxaaQualityEdgeThresholdMin,
FxaaFloat fxaaConsoleEdgeSharpness,
FxaaFloat fxaaConsoleEdgeThreshold,
FxaaFloat fxaaConsoleEdgeThresholdMin,
FxaaFloat4 fxaaConsole360ConstDir
) {
/*--------------------------------------------------------------------------*/
// (1)
half4 dir;
half4 lumaNe = h4tex2Dlod(tex, half4(fxaaConsolePosPos.zy, 0, 0));
#if (FXAA_GREEN_AS_LUMA == 0)
lumaNe.w += half(1.0/512.0);
dir.x = -lumaNe.w;
dir.z = -lumaNe.w;
#else
lumaNe.y += half(1.0/512.0);
dir.x = -lumaNe.y;
dir.z = -lumaNe.y;
#endif
/*--------------------------------------------------------------------------*/
// (2)
half4 lumaSw = h4tex2Dlod(tex, half4(fxaaConsolePosPos.xw, 0, 0));
#if (FXAA_GREEN_AS_LUMA == 0)
dir.x += lumaSw.w;
dir.z += lumaSw.w;
#else
dir.x += lumaSw.y;
dir.z += lumaSw.y;
#endif
/*--------------------------------------------------------------------------*/
// (3)
half4 lumaNw = h4tex2Dlod(tex, half4(fxaaConsolePosPos.xy, 0, 0));
#if (FXAA_GREEN_AS_LUMA == 0)
dir.x -= lumaNw.w;
dir.z += lumaNw.w;
#else
dir.x -= lumaNw.y;
dir.z += lumaNw.y;
#endif
/*--------------------------------------------------------------------------*/
// (4)
half4 lumaSe = h4tex2Dlod(tex, half4(fxaaConsolePosPos.zw, 0, 0));
#if (FXAA_GREEN_AS_LUMA == 0)
dir.x += lumaSe.w;
dir.z -= lumaSe.w;
#else
dir.x += lumaSe.y;
dir.z -= lumaSe.y;
#endif
/*--------------------------------------------------------------------------*/
// (5)
half4 dir1_pos;
dir1_pos.xy = normalize(dir.xyz).xz;
half dirAbsMinTimesC = min(abs(dir1_pos.x), abs(dir1_pos.y)) * half(FXAA_CONSOLE__PS3_EDGE_SHARPNESS);
/*--------------------------------------------------------------------------*/
// (6)
half4 dir2_pos;
dir2_pos.xy = clamp(dir1_pos.xy / dirAbsMinTimesC, half(-2.0), half(2.0));
dir1_pos.zw = pos.xy;
dir2_pos.zw = pos.xy;
half4 temp1N;
temp1N.xy = dir1_pos.zw - dir1_pos.xy * fxaaConsoleRcpFrameOpt.zw;
/*--------------------------------------------------------------------------*/
// (7)
temp1N = h4tex2Dlod(tex, half4(temp1N.xy, 0.0, 0.0));
half4 rgby1;
rgby1.xy = dir1_pos.zw + dir1_pos.xy * fxaaConsoleRcpFrameOpt.zw;
/*--------------------------------------------------------------------------*/
// (8)
rgby1 = h4tex2Dlod(tex, half4(rgby1.xy, 0.0, 0.0));
rgby1 = (temp1N + rgby1) * 0.5;
/*--------------------------------------------------------------------------*/
// (9)
half4 temp2N;
temp2N.xy = dir2_pos.zw - dir2_pos.xy * fxaaConsoleRcpFrameOpt2.zw;
temp2N = h4tex2Dlod(tex, half4(temp2N.xy, 0.0, 0.0));
/*--------------------------------------------------------------------------*/
// (10)
half4 rgby2;
rgby2.xy = dir2_pos.zw + dir2_pos.xy * fxaaConsoleRcpFrameOpt2.zw;
rgby2 = h4tex2Dlod(tex, half4(rgby2.xy, 0.0, 0.0));
rgby2 = (temp2N + rgby2) * 0.5;
/*--------------------------------------------------------------------------*/
// (11)
// compilier moves these scalar ops up to other cycles
#if (FXAA_GREEN_AS_LUMA == 0)
half lumaMin = min(min(lumaNw.w, lumaSw.w), min(lumaNe.w, lumaSe.w));
half lumaMax = max(max(lumaNw.w, lumaSw.w), max(lumaNe.w, lumaSe.w));
#else
half lumaMin = min(min(lumaNw.y, lumaSw.y), min(lumaNe.y, lumaSe.y));
half lumaMax = max(max(lumaNw.y, lumaSw.y), max(lumaNe.y, lumaSe.y));
#endif
rgby2 = (rgby2 + rgby1) * 0.5;
/*--------------------------------------------------------------------------*/
// (12)
#if (FXAA_GREEN_AS_LUMA == 0)
bool twoTapLt = rgby2.w < lumaMin;
bool twoTapGt = rgby2.w > lumaMax;
#else
bool twoTapLt = rgby2.y < lumaMin;
bool twoTapGt = rgby2.y > lumaMax;
#endif
/*--------------------------------------------------------------------------*/
// (13)
if(twoTapLt || twoTapGt) rgby2 = rgby1;
/*--------------------------------------------------------------------------*/
return rgby2; }
/*==========================================================================*/
#endif
/*============================================================================
FXAA3 CONSOLE - OPTIMIZED PS3 PIXEL SHADER (WITH EARLY EXIT)
==============================================================================
The code mostly matches the assembly.
I have a feeling that 14 cycles is possible, but was not able to get there.
Might have to increase register count to get full performance.
Note this shader does not use perspective interpolation.
Use the following cgc options,
--fenable-bx2 --fastmath --fastprecision --nofloatbindings
Use of FXAA_GREEN_AS_LUMA currently adds a cycle (16 clks).
Will look at fixing this for FXAA 3.12.
------------------------------------------------------------------------------
NVSHADERPERF OUTPUT
------------------------------------------------------------------------------
For reference and to aid in debug, output of NVShaderPerf should match this,
Shader to schedule:
0: texpkb h0.w(TRUE), v5.zyxx, #0
2: addh h2.y(TRUE), h0.w, constant(0.001953, 0.000000, 0.000000, 0.000000).x
4: texpkb h1.w(TRUE), v5.xwxx, #0
6: addh h0.x(TRUE), h1.w, -h2.y
7: texpkb h2.w(TRUE), v5.zwzz, #0
9: minh h4.w(TRUE), h2.y, h2
10: maxh h5.x(TRUE), h2.y, h2.w
11: texpkb h0.w(TRUE), v5, #0
13: addh h3.w(TRUE), -h0, h0.x
14: addh h0.x(TRUE), h0.w, h0
15: addh h0.z(TRUE), -h2.w, h0.x
16: addh h0.x(TRUE), h2.w, h3.w
17: minh h5.y(TRUE), h0.w, h1.w
18: nrmh h2.xz(TRUE), h0_n
19: minh_m8 h2.w(TRUE), |h2.x|, |h2.z|
20: divx h4.xy(TRUE), h2_n.xzzw, h2_n.w
21: movr r1.zw(TRUE), v4.xxxy
22: maxh h2.w(TRUE), h0, h1
23: fenct TRUE
24: madr r0.xy(TRUE), -h2.xzzw, constant(cConst5.x, cConst5.y, cConst5.z, cConst5.w).zwzz, r1.zwzz
26: texpkb h0(TRUE), r0, #0
28: maxh h5.x(TRUE), h2.w, h5
29: minh h5.w(TRUE), h5.y, h4
30: madr r1.xy(TRUE), h2.xzzw, constant(cConst5.x, cConst5.y, cConst5.z, cConst5.w).zwzz, r1.zwzz
32: texpkb h2(TRUE), r1, #0
34: addh_d2 h2(TRUE), h0, h2
35: texpkb h1(TRUE), v4, #0
37: maxh h5.y(TRUE), h5.x, h1.w
38: minh h4.w(TRUE), h1, h5
39: madr r0.xy(TRUE), -h4, constant(cConst5.x, cConst5.y, cConst5.z, cConst5.w).xyxx, r1.zwzz
41: texpkb h0(TRUE), r0, #0
43: addh_m8 h5.z(TRUE), h5.y, -h4.w
44: madr r2.xy(TRUE), h4, constant(cConst5.x, cConst5.y, cConst5.z, cConst5.w).xyxx, r1.zwzz
46: texpkb h3(TRUE), r2, #0
48: addh_d2 h0(TRUE), h0, h3
49: addh_d2 h3(TRUE), h0, h2
50: movh h0(TRUE), h3
51: slth h3.x(TRUE), h3.w, h5.w
52: sgth h3.w(TRUE), h3, h5.x
53: addx.c0 rc(TRUE), h3.x, h3
54: slth.c0 rc(TRUE), h5.z, h5
55: movh h0(c0.NE.w), h2
56: movh h0(c0.NE.x), h1
IPU0 ------ Simplified schedule: --------
Pass | Unit | uOp | PC: Op
-----+--------+------+-------------------------
1 | SCT0/1 | mov | 0: TXLr h0.w, g[TEX1].zyxx, const.xxxx, TEX0;
| TEX | txl | 0: TXLr h0.w, g[TEX1].zyxx, const.xxxx, TEX0;
| SCB0 | add | 2: ADDh h2.y, h0.-w--, const.-x--;
| | |
2 | SCT0/1 | mov | 4: TXLr h1.w, g[TEX1].xwxx, const.xxxx, TEX0;
| TEX | txl | 4: TXLr h1.w, g[TEX1].xwxx, const.xxxx, TEX0;
| SCB0 | add | 6: ADDh h0.x, h1.w---,-h2.y---;
| | |
3 | SCT0/1 | mov | 7: TXLr h2.w, g[TEX1].zwzz, const.xxxx, TEX0;
| TEX | txl | 7: TXLr h2.w, g[TEX1].zwzz, const.xxxx, TEX0;
| SCB0 | max | 10: MAXh h5.x, h2.y---, h2.w---;
| SCB1 | min | 9: MINh h4.w, h2.---y, h2;
| | |
4 | SCT0/1 | mov | 11: TXLr h0.w, g[TEX1], const.xxxx, TEX0;
| TEX | txl | 11: TXLr h0.w, g[TEX1], const.xxxx, TEX0;
| SCB0 | add | 14: ADDh h0.x, h0.w---, h0;
| SCB1 | add | 13: ADDh h3.w,-h0, h0.---x;
| | |
5 | SCT0 | mad | 16: ADDh h0.x, h2.w---, h3.w---;
| SCT1 | mad | 15: ADDh h0.z,-h2.--w-, h0.--x-;
| SCB0 | min | 17: MINh h5.y, h0.-w--, h1.-w--;
| | |
6 | SCT1 | mov | 18: NRMh h2.xz, h0;
| SRB | nrm | 18: NRMh h2.xz, h0;
| SCB1 | min | 19: MINh*8 h2.w, |h2.---x|, |h2.---z|;
| | |
7 | SCT0 | div | 20: DIVx h4.xy, h2.xz--, h2.ww--;
| SCT1 | mov | 21: MOVr r1.zw, g[TEX0].--xy;
| SCB1 | max | 22: MAXh h2.w, h0, h1;
| | |
8 | SCT0 | mad | 24: MADr r0.xy,-h2.xz--, const.zw--, r1.zw--;
| SCT1 | mov | 26: TXLr h0, r0, const.xxxx, TEX0;
| TEX | txl | 26: TXLr h0, r0, const.xxxx, TEX0;
| SCB0 | max | 28: MAXh h5.x, h2.w---, h5;
| SCB1 | min | 29: MINh h5.w, h5.---y, h4;
| | |
9 | SCT0 | mad | 30: MADr r1.xy, h2.xz--, const.zw--, r1.zw--;
| SCT1 | mov | 32: TXLr h2, r1, const.xxxx, TEX0;
| TEX | txl | 32: TXLr h2, r1, const.xxxx, TEX0;
| SCB0/1 | add | 34: ADDh/2 h2, h0, h2;
| | |
10 | SCT0/1 | mov | 35: TXLr h1, g[TEX0], const.xxxx, TEX0;
| TEX | txl | 35: TXLr h1, g[TEX0], const.xxxx, TEX0;
| SCB0 | max | 37: MAXh h5.y, h5.-x--, h1.-w--;
| SCB1 | min | 38: MINh h4.w, h1, h5;
| | |
11 | SCT0 | mad | 39: MADr r0.xy,-h4, const.xy--, r1.zw--;
| SCT1 | mov | 41: TXLr h0, r0, const.zzzz, TEX0;
| TEX | txl | 41: TXLr h0, r0, const.zzzz, TEX0;
| SCB0 | mad | 44: MADr r2.xy, h4, const.xy--, r1.zw--;
| SCB1 | add | 43: ADDh*8 h5.z, h5.--y-,-h4.--w-;
| | |
12 | SCT0/1 | mov | 46: TXLr h3, r2, const.xxxx, TEX0;
| TEX | txl | 46: TXLr h3, r2, const.xxxx, TEX0;
| SCB0/1 | add | 48: ADDh/2 h0, h0, h3;
| | |
13 | SCT0/1 | mad | 49: ADDh/2 h3, h0, h2;
| SCB0/1 | mul | 50: MOVh h0, h3;
| | |
14 | SCT0 | set | 51: SLTh h3.x, h3.w---, h5.w---;
| SCT1 | set | 52: SGTh h3.w, h3, h5.---x;
| SCB0 | set | 54: SLThc0 rc, h5.z---, h5;
| SCB1 | add | 53: ADDxc0_s rc, h3.---x, h3;
| | |
15 | SCT0/1 | mul | 55: MOVh h0(NE0.wwww), h2;
| SCB0/1 | mul | 56: MOVh h0(NE0.xxxx), h1;
Pass SCT TEX SCB
1: 0% 100% 25%
2: 0% 100% 25%
3: 0% 100% 50%
4: 0% 100% 50%
5: 50% 0% 25%
6: 0% 0% 25%
7: 100% 0% 25%
8: 0% 100% 50%
9: 0% 100% 100%
10: 0% 100% 50%
11: 0% 100% 75%
12: 0% 100% 100%
13: 100% 0% 100%
14: 50% 0% 50%
15: 100% 0% 100%
MEAN: 26% 60% 56%
Pass SCT0 SCT1 TEX SCB0 SCB1
1: 0% 0% 100% 100% 0%
2: 0% 0% 100% 100% 0%
3: 0% 0% 100% 100% 100%
4: 0% 0% 100% 100% 100%
5: 100% 100% 0% 100% 0%
6: 0% 0% 0% 0% 100%
7: 100% 100% 0% 0% 100%
8: 0% 0% 100% 100% 100%
9: 0% 0% 100% 100% 100%
10: 0% 0% 100% 100% 100%
11: 0% 0% 100% 100% 100%
12: 0% 0% 100% 100% 100%
13: 100% 100% 0% 100% 100%
14: 100% 100% 0% 100% 100%
15: 100% 100% 0% 100% 100%
MEAN: 33% 33% 60% 86% 80%
Fragment Performance Setup: Driver RSX Compiler, GPU RSX, Flags 0x5
Results 15 cycles, 3 r regs, 800,000,000 pixels/s
============================================================================*/
#if (FXAA_PS3 == 1) && (FXAA_EARLY_EXIT == 1)
/*--------------------------------------------------------------------------*/
#pragma regcount 7
#pragma disablepc all
#pragma option O2
#pragma option OutColorPrec=fp16
#pragma texformat default RGBA8
/*==========================================================================*/
half4 FxaaPixelShader(
// See FXAA Quality FxaaPixelShader() source for docs on Inputs!
FxaaFloat2 pos,
FxaaFloat4 fxaaConsolePosPos,
FxaaTex tex,
FxaaTex fxaaConsole360TexExpBiasNegOne,
FxaaTex fxaaConsole360TexExpBiasNegTwo,
FxaaFloat2 fxaaQualityRcpFrame,
FxaaFloat4 fxaaConsoleRcpFrameOpt,
FxaaFloat4 fxaaConsoleRcpFrameOpt2,
FxaaFloat4 fxaaConsole360RcpFrameOpt2,
FxaaFloat fxaaQualitySubpix,
FxaaFloat fxaaQualityEdgeThreshold,
FxaaFloat fxaaQualityEdgeThresholdMin,
FxaaFloat fxaaConsoleEdgeSharpness,
FxaaFloat fxaaConsoleEdgeThreshold,
FxaaFloat fxaaConsoleEdgeThresholdMin,
FxaaFloat4 fxaaConsole360ConstDir
) {
/*--------------------------------------------------------------------------*/
// (1)
half4 rgbyNe = h4tex2Dlod(tex, half4(fxaaConsolePosPos.zy, 0, 0));
#if (FXAA_GREEN_AS_LUMA == 0)
half lumaNe = rgbyNe.w + half(1.0/512.0);
#else
half lumaNe = rgbyNe.y + half(1.0/512.0);
#endif
/*--------------------------------------------------------------------------*/
// (2)
half4 lumaSw = h4tex2Dlod(tex, half4(fxaaConsolePosPos.xw, 0, 0));
#if (FXAA_GREEN_AS_LUMA == 0)
half lumaSwNegNe = lumaSw.w - lumaNe;
#else
half lumaSwNegNe = lumaSw.y - lumaNe;
#endif
/*--------------------------------------------------------------------------*/
// (3)
half4 lumaNw = h4tex2Dlod(tex, half4(fxaaConsolePosPos.xy, 0, 0));
#if (FXAA_GREEN_AS_LUMA == 0)
half lumaMaxNwSw = max(lumaNw.w, lumaSw.w);
half lumaMinNwSw = min(lumaNw.w, lumaSw.w);
#else
half lumaMaxNwSw = max(lumaNw.y, lumaSw.y);
half lumaMinNwSw = min(lumaNw.y, lumaSw.y);
#endif
/*--------------------------------------------------------------------------*/
// (4)
half4 lumaSe = h4tex2Dlod(tex, half4(fxaaConsolePosPos.zw, 0, 0));
#if (FXAA_GREEN_AS_LUMA == 0)
half dirZ = lumaNw.w + lumaSwNegNe;
half dirX = -lumaNw.w + lumaSwNegNe;
#else
half dirZ = lumaNw.y + lumaSwNegNe;
half dirX = -lumaNw.y + lumaSwNegNe;
#endif
/*--------------------------------------------------------------------------*/
// (5)
half3 dir;
dir.y = 0.0;
#if (FXAA_GREEN_AS_LUMA == 0)
dir.x = lumaSe.w + dirX;
dir.z = -lumaSe.w + dirZ;
half lumaMinNeSe = min(lumaNe, lumaSe.w);
#else
dir.x = lumaSe.y + dirX;
dir.z = -lumaSe.y + dirZ;
half lumaMinNeSe = min(lumaNe, lumaSe.y);
#endif
/*--------------------------------------------------------------------------*/
// (6)
half4 dir1_pos;
dir1_pos.xy = normalize(dir).xz;
half dirAbsMinTimes8 = min(abs(dir1_pos.x), abs(dir1_pos.y)) * half(FXAA_CONSOLE__PS3_EDGE_SHARPNESS);
/*--------------------------------------------------------------------------*/
// (7)
half4 dir2_pos;
dir2_pos.xy = clamp(dir1_pos.xy / dirAbsMinTimes8, half(-2.0), half(2.0));
dir1_pos.zw = pos.xy;
dir2_pos.zw = pos.xy;
#if (FXAA_GREEN_AS_LUMA == 0)
half lumaMaxNeSe = max(lumaNe, lumaSe.w);
#else
half lumaMaxNeSe = max(lumaNe, lumaSe.y);
#endif
/*--------------------------------------------------------------------------*/
// (8)
half4 temp1N;
temp1N.xy = dir1_pos.zw - dir1_pos.xy * fxaaConsoleRcpFrameOpt.zw;
temp1N = h4tex2Dlod(tex, half4(temp1N.xy, 0.0, 0.0));
half lumaMax = max(lumaMaxNwSw, lumaMaxNeSe);
half lumaMin = min(lumaMinNwSw, lumaMinNeSe);
/*--------------------------------------------------------------------------*/
// (9)
half4 rgby1;
rgby1.xy = dir1_pos.zw + dir1_pos.xy * fxaaConsoleRcpFrameOpt.zw;
rgby1 = h4tex2Dlod(tex, half4(rgby1.xy, 0.0, 0.0));
rgby1 = (temp1N + rgby1) * 0.5;
/*--------------------------------------------------------------------------*/
// (10)
half4 rgbyM = h4tex2Dlod(tex, half4(pos.xy, 0.0, 0.0));
#if (FXAA_GREEN_AS_LUMA == 0)
half lumaMaxM = max(lumaMax, rgbyM.w);
half lumaMinM = min(lumaMin, rgbyM.w);
#else
half lumaMaxM = max(lumaMax, rgbyM.y);
half lumaMinM = min(lumaMin, rgbyM.y);
#endif
/*--------------------------------------------------------------------------*/
// (11)
half4 temp2N;
temp2N.xy = dir2_pos.zw - dir2_pos.xy * fxaaConsoleRcpFrameOpt2.zw;
temp2N = h4tex2Dlod(tex, half4(temp2N.xy, 0.0, 0.0));
half4 rgby2;
rgby2.xy = dir2_pos.zw + dir2_pos.xy * fxaaConsoleRcpFrameOpt2.zw;
half lumaRangeM = (lumaMaxM - lumaMinM) / FXAA_CONSOLE__PS3_EDGE_THRESHOLD;
/*--------------------------------------------------------------------------*/
// (12)
rgby2 = h4tex2Dlod(tex, half4(rgby2.xy, 0.0, 0.0));
rgby2 = (temp2N + rgby2) * 0.5;
/*--------------------------------------------------------------------------*/
// (13)
rgby2 = (rgby2 + rgby1) * 0.5;
/*--------------------------------------------------------------------------*/
// (14)
#if (FXAA_GREEN_AS_LUMA == 0)
bool twoTapLt = rgby2.w < lumaMin;
bool twoTapGt = rgby2.w > lumaMax;
#else
bool twoTapLt = rgby2.y < lumaMin;
bool twoTapGt = rgby2.y > lumaMax;
#endif
bool earlyExit = lumaRangeM < lumaMax;
bool twoTap = twoTapLt || twoTapGt;
/*--------------------------------------------------------------------------*/
// (15)
if(twoTap) rgby2 = rgby1;
if(earlyExit) rgby2 = rgbyM;
/*--------------------------------------------------------------------------*/
return rgby2; }
/*==========================================================================*/
#endif

29
libs/qglview/shaders/hdr.frag Normal file
View File

@@ -0,0 +1,29 @@
#version 150
uniform sampler2D t0;
uniform float exposure;
float tA = 0.15;
float tB = 0.50;
float tC = 0.10;
float tD = 0.20;
float tE = 0.02;
float tF = 0.30;
float tW = 11.2;
vec3 Uncharted2Tonemap(vec3 x) {
return ((x*(tA*x+tC*tB)+tD*tE)/(x*(tA*x+tB)+tD*tF))-tE/tF;
}
void main(void) {
//qgl_FragData[0].rgb = texelFetch(t0, ivec2(gl_FragCoord.xy), 0).rgb;
//return;
vec3 inColor = texelFetch(t0, ivec2(gl_FragCoord.xy), 0).rgb;
inColor *= exposure / 1.45;
float ExposureBias = 1.;
vec3 curr = Uncharted2Tonemap(ExposureBias*inColor);
vec3 whiteScale = 1. / Uncharted2Tonemap(vec3(tW));
vec3 color = curr * whiteScale;
vec3 retColor = color;//pow(color, vec3(1 / 1));
qgl_FragData[0].rgb = retColor;
}

6
libs/qglview/shaders/hdr.vert Normal file
View File

@@ -0,0 +1,6 @@
#version 150
void main(void) {
qgl_FragTexture = qgl_Texture;
gl_Position = qgl_ftransform();
}

13
libs/qglview/shaders/hdr_scale_0.frag Normal file
View File

@@ -0,0 +1,13 @@
#version 130
uniform sampler2D t0;
uniform vec2 vsize;
const vec3 luma = vec3(0.299, 0.587, 0.114);
void main(void) {
vec2 tc = gl_TexCoord[0].xy;//, dt = 1. / vsize;
vec3 dc0 = texture2D(t0, tc).rgb, dc1 = textureOffset(t0, tc, ivec2(1, 0)).rgb, dc2 = textureOffset(t0, tc, ivec2(0, 1)).rgb, dc3 = textureOffset(t0, tc, ivec2(1, 1)).rgb;
float l0 = dot(dc0, luma), l1 = dot(dc1, luma), l2 = dot(dc2, luma), l3 = dot(dc3, luma);
gl_FragColor.rgb = vec3(max(max(max(l0, l1), l2), l3), min(min(min(l0, l1), l2), l3), (l0 + l1 + l2 + l3) / 4.);
}

10
libs/qglview/shaders/hdr_scale_1.frag Normal file
View File

@@ -0,0 +1,10 @@
#version 130
uniform sampler2D t0;
uniform vec2 vsize;
void main(void) {
vec2 tc = gl_TexCoord[0].xy;//, dt = 1. / vsize;
vec3 dc0 = texture2D(t0, tc).rgb, dc1 = textureOffset(t0, tc, ivec2(1, 0)).rgb, dc2 = textureOffset(t0, tc, ivec2(0, 1)).rgb, dc3 = textureOffset(t0, tc, ivec2(1, 1)).rgb;
gl_FragColor.rgb = vec3(max(max(max(dc0.r, dc1.r), dc2.r), dc3.r), min(min(min(dc0.g, dc1.g), dc2.g), dc3.g), (dc0.b + dc1.b + dc2.b + dc3.b) / 4.);
}

161
libs/qglview/shaders/light_models.frag Normal file
View File

@@ -0,0 +1,161 @@
#version 130
const float e = 2.7182818284;
const float pi = 3.1415926;
float Phong_diffuse(vec3 l, vec3 n, vec3 h, vec3 v, float shininess) {
return max(dot(n, l), 0.);
}
float Phong_specular(vec3 l, vec3 n, vec3 h, vec3 v, float shininess) {
return pow(max(dot(n, h), 0.), shininess);
}
float Cook_Torrance_diffuse(vec3 l, vec3 n, vec3 h, vec3 v, float shininess) {
return max(dot(n, l), 0.);
}
float Cook_Torrance_specular(vec3 l, vec3 n, vec3 h, vec3 v, float shininess) {
float NdotL = max( dot( n, l ), 0. );
float NdotV = max( dot( n, v ), 0. );
float NdotH = max( dot( n, h ), 1.e-7 );
float VdotH = max( dot( v, h ), 0. );
float geometric = 2. * NdotH / VdotH;
geometric = min(1., geometric * min(NdotV, NdotL));
float r_sq = 1. / (shininess * shininess);
float NdotH_sq = NdotH * NdotH;
float NdotH_sq_r = 1. / (NdotH_sq * r_sq);
float roughness_exp = (NdotH_sq - 1.) * (NdotH_sq_r);
float roughness = exp(roughness_exp) * NdotH_sq_r / (4. * NdotH_sq);
float fresnel = 1. / (1. + NdotV);
return min(1., (fresnel * geometric * roughness) / (NdotV * NdotL + 1.e-7));
}
float Minnaert_diffuse(vec3 l, vec3 n, vec3 h, vec3 v, float shininess) {
return max(dot(n, l), 0.);
}
float Minnaert_specular(vec3 l, vec3 n, vec3 h, vec3 v, float shininess) {
float k = shininess / 128.;
float d1 = pow(max(dot(n, l), 0.), 1. + k);
float d2 = pow(1. - dot(n, v), 1. - k);
return d1*d2;
}
float fresnel(float x, float kf) {
float dx = x - kf;
float d1 = 1.0 - kf;
float kf2 = kf * kf;
return (1.0 / (dx * dx) - 1.0 / kf2) / (1.0 / (d1 * d1) - 1.0 / kf2 );
//return 1.0;
}
float shadow(float x, float ks) {
float dx = x - ks;
float d1 = 1.0 - ks;
float ks2 = ks * ks;
//return (1.0 / (dx * dx) - 1.0 / ks2) / (1.0 / (d1 * d1) - 1.0 / ks2 );
return 1.0;
}
const float smooth_ = 0.5;
const float transp = 0;
const float k = 0.1;
const float kf = 1.12;
const float ks = 1.01;
float Strauss_diffuse(vec3 l, vec3 n, vec3 h, vec3 v, float shininess) {
vec3 h2 = reflect(l, n);
float metal = shininess / 20.;
float nl = dot( n, l);
float nv = dot( n, v);
float hv = dot( h2, v);
float f = fresnel( nl, kf );
float s3 = smooth_ * smooth_ * smooth_;
// diffuse term
float d = ( 1.0 - metal * smooth_ );
float Rd = ( 1.0 - s3 ) * ( 1.0 - transp );
float diff = nl * d * Rd;
// inputs into the specular term
// composite the final result, ensuring
return max(diff, 0.);
}
float Strauss_specular(vec3 l, vec3 n, vec3 h, vec3 v, float shininess) {
vec3 h2 = reflect(l, n);
float metal = shininess / 20.;
float nl = dot( n, l);
float nv = dot( n, v);
float hv = dot( h2, v);
float f = fresnel( nl, kf );
float s3 = smooth_ * smooth_ * smooth_;
// diffuse term
float d = ( 1.0 - metal * smooth_ );
float Rd = ( 1.0 - s3 ) * ( 1.0 - transp );
float diff = nl * d * Rd;
// inputs into the specular term
float r = (1.0 - transp) - Rd;
float j = f * shadow ( nl, ks ) * shadow ( nv, ks );
float refl = min ( 1.0, r + j * ( r + k ) );
float Cs = 1. + metal * (1.0 - f);
float spec = Cs * refl;
spec *= pow ( -hv, 3.0 / (1.0 - smooth_) );
// composite the final result, ensuring
return max(spec, 0.);
}
uniform float a, b;
float Oren_Nayar_diffuse(vec3 l, vec3 n, vec3 h, vec3 v, float shininess) {
float nl = dot ( n, l );
float nv = dot ( n, v );
vec3 lProj = normalize ( l - n * nl );
vec3 vProj = normalize ( v - n * nv );
float cx = max ( dot ( lProj, vProj ), 0.0 );
float cosAlpha = nl > nv ? nl : nv;
float cosBeta = nl > nv ? nv : nl;
float dx = sqrt ( ( 1.0 - cosAlpha * cosAlpha ) * ( 1.0 - cosBeta * cosBeta ) ) / cosBeta;
return max(0. , nl) * (a + b * cx * dx);
//return max(dot(n, l), 0.);
}
float Oren_Nayar_specular(vec3 l, vec3 n, vec3 h, vec3 v, float shininess) {
return pow(max(dot(n, h), 0.), shininess);
}
/*
float light_diffuse(int model, vec3 l, vec3 n, vec3 h, vec3 v, float shininess) {
if (model == 0) return Phong_diffuse(l, n, h, v, shininess);
if (model == 1) return Cook_Torrance_diffuse(l, n, h, v, shininess);
if (model == 2) return Minnaert_diffuse(l, n, h, v, shininess);
if (model == 3) return Strauss_diffuse(l, n, h, v, shininess);
if (model == 4) return Oren_Nayar_diffuse(l, n, h, v, shininess);
return 0.;
}
float light_specular(int model, vec3 l, vec3 n, vec3 h, vec3 v, float shininess) {
if (model == 0) return Phong_specular(l, n, h, v, shininess);
if (model == 1) return Cook_Torrance_specular(l, n, h, v, shininess);
if (model == 2) return Minnaert_specular(l, n, h, v, shininess);
if (model == 3) return Strauss_specular(l, n, h, v, shininess);
if (model == 4) return Oren_Nayar_specular(l, n, h, v, shininess);
return 0.;
}*/

24
libs/qglview/shaders/motion_blur.frag Normal file
View File

@@ -0,0 +1,24 @@
#version 150
uniform sampler2D t0, ts;
uniform vec2 dt;
uniform float factor = 1.;
uniform int steps = 8;
void main(void) {
vec2 cdt = dt / steps;
vec2 ct = qgl_FragTexture.xy;
vec3 speed = texelFetch(ts, ivec2(gl_FragCoord.xy), 0).rgb * 256 * factor;
int hsteps = steps / 2;
ct -= speed.xy * cdt * hsteps;
vec3 scol = vec3(0);//texture(t0, ct).rgb;
float sum = 0.;
for (int i = 0; i < steps; ++i) {
ct += speed.xy * cdt;
float mul = 1. - abs(i - hsteps) * 2. / steps;
scol += texture(t0, ct).rgb * mul;
sum += mul;
}
scol /= sum;
qgl_FragData[0].rgb = scol;
}

6
libs/qglview/shaders/motion_blur.vert Normal file
View File

@@ -0,0 +1,6 @@
#version 150
void main(void) {
qgl_FragTexture = qgl_Texture;
gl_Position = vec4(qgl_Vertex,1);
}

42
libs/qglview/shaders/post.frag Normal file
View File

@@ -0,0 +1,42 @@
#version 130
uniform sampler2D t0, t1;//, t2;
uniform vec2 vsize;
uniform float clum;
uniform bool has_bloom;
float unpackDepth(vec4 dv) {
return dot(dv.rgb, vec3(65025., 255., 1.));
}
void main(void) {
vec2 tc = gl_TexCoord[0].xy;//, dt = 2. / vsize, dt2 = dt + dt;
vec4 bloom;
float tone = 1. / clum;
if (has_bloom) {
bloom = (texture2D(t1, tc) * 3. +
textureOffset(t1, tc, ivec2(2, 0)) * 2. +
textureOffset(t1, tc, ivec2(0, 2)) * 2. +
textureOffset(t1, tc, ivec2(-2, 0)) * 2. +
textureOffset(t1, tc, ivec2(0, -2)) * 2. +
textureOffset(t1, tc, ivec2(2, 2)) * 1.5 +
textureOffset(t1, tc, ivec2(2, -2)) * 1.5 +
textureOffset(t1, tc, ivec2(-2, -2)) * 1.5 +
textureOffset(t1, tc, ivec2(-2, 2)) * 1.5 +
textureOffset(t1, tc, ivec2(4, 0)) +
textureOffset(t1, tc, ivec2(0, 4)) +
textureOffset(t1, tc, ivec2(-4, 0)) +
textureOffset(t1, tc, ivec2(0, -4)) +
textureOffset(t1, tc, ivec2(4, 2)) +
textureOffset(t1, tc, ivec2(4, -2)) +
textureOffset(t1, tc, ivec2(-4, -2)) +
textureOffset(t1, tc, ivec2(-4, 2)) +
textureOffset(t1, tc, ivec2(2, 4)) +
textureOffset(t1, tc, ivec2(2, -4)) +
textureOffset(t1, tc, ivec2(-2, -4)) +
textureOffset(t1, tc, ivec2(-2, 4))) / 29.;
vec4 diff = texture2D(t0, tc);
gl_FragColor = max(diff * tone, bloom);// + vec4(0.01/(clum+0.1));
} else
gl_FragColor = texture2D(t0, tc) * tone;// + vec4(0.01/(clum+0.1));
}

179
libs/qglview/shaders/ppl.frag Normal file
View File

@@ -0,0 +1,179 @@
#version 130
#define lc 4
varying vec4 diffuse[lc], pos, spos;//, ambient;//, col;
varying vec3 lightDir[lc]/*halfVector[lc], */;
//varying vec3 lightDir[lc]/*halfVector[lc], */;
varying vec3 normal, srcn;
varying float fogCoord, alpha;
uniform int lightsCount;
uniform bool acc_light, acc_fog, has_diffuse, has_bump, is_glass, shadows, soft_shadows;
uniform float bump_scale, reflectivity, iof, cdis;
uniform vec2 vsize;
uniform sampler2D t0, t1, t2;
uniform sampler2D s0;
uniform samplerCube tc, tc0;
uniform mat4 mat;
float light_diffuse(vec3 l, vec3 n, vec3 h, vec3 v, float shininess);
float light_specular(vec3 l, vec3 n, vec3 h, vec3 v, float shininess);
const float bias = 1.;
vec2 sp;
vec4 sc, dc;//ambient;
void calcLight(in int index, in vec3 n, in vec3 v) {
vec2 scoord, sdt, sdt2;
vec3 halfV, ldir;
vec4 lpos = gl_LightSource[index].position;
float spot, ldist = length(lpos.xyz - pos.xyz), shadow = 1., sdep, ddep;
ldir = normalize(lpos.xyz - (pos.xyz * lpos.w));
halfV = normalize(ldir + v);
//if (dot(ldir, n) > 0) {
spot = step(0., dot(ldir, n));
if (gl_LightSource[index].spotCutoff < 180.) {
spot = max(dot(-ldir, gl_LightSource[index].spotDirection.xyz), 0.);
spot *= step(gl_LightSource[index].spotExponent, spot);
spot = pow(spot, (gl_LightSource[index].spotCosCutoff + 0.001));
if (spot > 0. && shadows) {
scoord = (spos.xyz / spos.w).xy / 2 + vec2(0.5);
sdep = texture(s0, scoord.xy).r + bias;
ddep = pow((spos.z - sdep) / 4., 0.5) * 2.;
shadow = clamp(sdep - spos.z, 0., 1.);
if (soft_shadows) {
sdt = ddep / vsize;
sdt2 = sdt + sdt;
shadow += (clamp(texture(s0, scoord.xy + vec2(sdt.x, 0.)).r + bias - spos.z, 0., 1.) +
clamp(texture(s0, scoord.xy + vec2(0, sdt.y)).r + bias - spos.z, 0., 1.) +
clamp(texture(s0, scoord.xy + vec2(-sdt.x, 0.)).r + bias - spos.z, 0., 1.) +
clamp(texture(s0, scoord.xy + vec2(0, -sdt.y)).r + bias - spos.z, 0., 1.) +
clamp(texture(s0, scoord.xy + vec2(sdt.x, sdt.y)).r + bias - spos.z, 0., 1.) +
clamp(texture(s0, scoord.xy + vec2(sdt.x, -sdt.y)).r + bias - spos.z, 0., 1.) +
clamp(texture(s0, scoord.xy + vec2(-sdt.x, sdt.y)).r + bias - spos.z, 0., 1.) +
clamp(texture(s0, scoord.xy + vec2(-sdt.x, -sdt.y)).r + bias - spos.z, 0., 1.) +
clamp(texture(s0, scoord.xy + vec2(sdt.x, 0)).r + bias - spos.z, 0., 1.) +
clamp(texture(s0, scoord.xy + vec2(0, sdt.y)).r + bias - spos.z, 0., 1.) +
clamp(texture(s0, scoord.xy + vec2(-sdt.x, 0)).r + bias - spos.z, 0., 1.) +
clamp(texture(s0, scoord.xy + vec2(0, -sdt.y)).r + bias - spos.z, 0., 1.) +
clamp(texture(s0, scoord.xy + vec2(sdt.x, sdt.y)).r + bias - spos.z, 0., 1.) +
clamp(texture(s0, scoord.xy + vec2(sdt.x, -sdt.y)).r + bias - spos.z, 0., 1.) +
clamp(texture(s0, scoord.xy + vec2(-sdt.x, -sdt.y)).r + bias - spos.z, 0., 1.) +
clamp(texture(s0, scoord.xy + vec2(-sdt.x, sdt.y)).r + bias - spos.z, 0., 1.) +
clamp(texture(s0, scoord.xy + vec2(sdt2.x, 0)).r + bias - spos.z, 0., 1.) +
clamp(texture(s0, scoord.xy + vec2(0, sdt2.y)).r + bias - spos.z, 0., 1.) +
clamp(texture(s0, scoord.xy + vec2(-sdt2.x, 0)).r + bias - spos.z, 0., 1.) +
clamp(texture(s0, scoord.xy + vec2(0, -sdt2.y)).r + bias - spos.z, 0., 1.) +
clamp(texture(s0, scoord.xy + vec2(sdt2.x, sdt.y)).r + bias - spos.z, 0., 1.) +
clamp(texture(s0, scoord.xy + vec2(sdt2.x, -sdt.y)).r + bias - spos.z, 0., 1.) +
clamp(texture(s0, scoord.xy + vec2(-sdt2.x, -sdt.y)).r + bias - spos.z, 0., 1.) +
clamp(texture(s0, scoord.xy + vec2(-sdt2.x, sdt.y)).r + bias - spos.z, 0., 1.) +
clamp(texture(s0, scoord.xy + vec2(sdt.x, sdt2.y)).r + bias - spos.z, 0., 1.) +
clamp(texture(s0, scoord.xy + vec2(sdt.x, -sdt2.y)).r + bias - spos.z, 0., 1.) +
clamp(texture(s0, scoord.xy + vec2(-sdt.x, -sdt2.y)).r + bias - spos.z, 0., 1.) +
clamp(texture(s0, scoord.xy + vec2(-sdt.x, sdt2.y)).r + bias - spos.z, 0., 1.)) / 29.;
shadow = clamp(pow(shadow, 0.5), 0., 1);
}
spot *= shadow;
}
}
spot /= (gl_LightSource[index].constantAttenuation + ldist * (gl_LightSource[index].linearAttenuation + ldist * gl_LightSource[index].quadraticAttenuation));
dc += spot * diffuse[index] * light_diffuse(ldir, n, halfV, v, gl_FrontMaterial.shininess);
sc += spot * gl_FrontMaterial.specular * gl_LightSource[index].specular * light_specular(ldir, n, halfV, v, gl_FrontMaterial.shininess);
//}
}
void main(void) {
/*vec3 scoord = spos.xyz / spos.w;
float sdep = texture(s0, scoord.xy / 2 + vec2(0.5)).r + 1;
//gl_FragColor.rgb = vec3(step(spos.z, sdep));
gl_FragColor.rgb = vec3(spos.z - sdep)/10;
//gl_FragColor.rgb = vec3(texture(s0, scoord.xy+vec2(0.5)).r/100);
//gl_FragColor.rgb = vec3(texture(s0,).r/100);
return;*/
//bias = (vsize.x - vsize.y) / max(vsize.x, vsize.y)*5 - 1.;
if (!acc_light) {
if (has_diffuse) gl_FragColor = texture2D(t0, gl_TexCoord[0].xy);
//else gl_FragColor = gl_Color;
if (acc_fog)
gl_FragColor.xyz = mix(gl_FragColor.xyz, gl_Fog.color.xyz, fogCoord);
return;
}
sp = gl_FragCoord.xy / vsize;
vec3 n, v = normalize(-pos.xyz);
//v.xy = vec2(1,1)-gl_FragCoord.xy / vsize*2 ;//- vec2(1,1);
if (has_bump) n = normalize(normal + (texture2D(t1, gl_TexCoord[0].xy).xyz - vec3(0.5, 0.5, 1.)) * bump_scale);
else n = normalize(normal);
vec4 color;
sc = vec4(0.);
dc = gl_LightModel.ambient * gl_FrontMaterial.ambient;//ambient;
if (lightsCount > 0) {
calcLight(0, n, v);
if (lightsCount > 1) {
calcLight(1, n, v);
if (lightsCount > 2) {
calcLight(2, n, v);
if (lightsCount > 3) {
calcLight(3, n, v);
/*if (lightsCount > 4) {
calcLight(4, n, v);
if (lightsCount > 5) {
calcLight(5, n, v);
if (lightsCount > 6) {
calcLight(6, n, v);
if (lightsCount > 7) {
calcLight(7, n, v);
}
}
}
}*/
}
}
}
}
sc = max(sc, vec4(0.));
vec2 spr = sp, spg = sp, spb = sp, spc = sp, spm = sp, spy = sp, dsp;
vec3 bgf;
float fresnel = pow(1. - max(dot(v, n), 0.), 1);
dsp = fresnel * n.xy * (1. - iof);
spg += dsp;
if (cdis > 0.) {
spr += dsp * (1. - cdis - cdis);
spy += dsp * (1. - cdis);
spc += dsp * (1. + cdis);
spb += dsp * (1. + cdis + cdis);
vec3 bg0 = texture2D(t2, spr).rgb, bg1 = texture2D(t2, spy).rgb, bg2 = texture2D(t2, spg).rgb, bg3 = texture2D(t2, spc).rgb, bg4 = texture2D(t2, spb).rgb;
//bgf = vec3(bg0.r, bg2.g, bg4.b);
bgf = vec3((bg0.r + bg1.r) / 2., (bg1.g + bg2.g + bg3.g) / 3., (bg3.b + bg4.b) / 2.);
} else bgf = texture2D(t2, spg).rgb;
if (has_diffuse) {
vec4 tex = texture2D(t0, gl_TexCoord[0].xy);
dc *= tex;
color.a = tex.a * alpha;
} else color.a = alpha;
color.rgb = dc.rgb;
vec3 ln = vec3(0);
if (is_glass) {
ln = reflect(v, n);
ln = ln * mat3(gl_ModelViewMatrix);
ln.y = -ln.y;
color.rgb = (mix(bgf, textureCube(tc, ln).rgb, 0.2 + fresnel * 0.8) * gl_FrontMaterial.diffuse.rgb + gl_FrontMaterial.emission.rgb) + sc.rgb * color.a;
color.a = 1.;
} else {
if (reflectivity > 0.) {
ln = reflect(v, n);
ln = ln * mat3(gl_ModelViewMatrix);
ln.y = -ln.y;
color.rgb = mix(color.rgb, textureCube(tc, ln).rgb, reflectivity);
}
color.rgb = mix(color.rgb * gl_FrontMaterial.diffuse.rgb + gl_FrontMaterial.emission.rgb, bgf, 1. - alpha) + sc.rgb * color.a;
color.a = 1;
}
if (acc_fog)
color.rgb = mix(color.rgb, gl_Fog.color.rgb, fogCoord);
color.r = 250;
gl_FragColor = color;
//gl_FragColor.rgb = mix(ldir, texture2D(t2, sp).rgb, 1. - alpha);
}

66
libs/qglview/shaders/ppl.vert Normal file
View File

@@ -0,0 +1,66 @@
#version 130
#define lc 4
varying vec4 diffuse[lc], pos, spos;//, ambient;//, col;
varying vec3 lightDir[lc]/*halfVector[lc], */;
//varying vec3 lightDir[lc]/*halfVector[lc], */;
varying vec3 normal, srcn;
varying float fogCoord, alpha;
uniform int lightsCount;
uniform bool acc_fog, shadows;
uniform mat4 mat;
void prepareLight(in int index, in vec3 p) {
vec4 lpos = gl_LightSource[index].position;
lightDir[index] = normalize(lpos.xyz - (p * lpos.w));
//halfVector[index] = normalize(lightDir[index] - normalize(p));
diffuse[index] = gl_FrontMaterial.diffuse * gl_LightSource[index].diffuse;
}
void main(void) {
float NdotL;
//col = gl_Color;
alpha = gl_Color.a;
normal = normalize(gl_NormalMatrix * gl_Normal);
srcn = gl_Normal;
pos = gl_ModelViewMatrix * gl_Vertex;
//v = normalize(-pos);
if (acc_fog) {
fogCoord = (gl_Fog.end - length(pos) * 0.85) / (gl_Fog.end - gl_Fog.start);
fogCoord = 1. - clamp(fogCoord, 0., 1.);
}
vec3 ldir;
if (lightsCount > 0) {
prepareLight(0, pos.xyz);
if (lightsCount > 1) {
prepareLight(1, pos.xyz);
if (lightsCount > 2) {
prepareLight(2, pos.xyz);
if (lightsCount > 3) {
prepareLight(3, pos.xyz);
diffuse[3] = gl_FrontMaterial.diffuse * gl_LightSource[3].diffuse;
/*if (lightsCount > 4) {
diffuse[4] = gl_FrontMaterial.diffuse * gl_LightSource[4].diffuse;
if (lightsCount > 5) {
diffuse[5] = gl_FrontMaterial.diffuse * gl_LightSource[5].diffuse;
if (lightsCount > 6) {
diffuse[6] = gl_FrontMaterial.diffuse * gl_LightSource[6].diffuse;
if (lightsCount > 6) {
diffuse[7] = gl_FrontMaterial.diffuse * gl_LightSource[7].diffuse;
}
}
}
}*/
}
}
}
}
//ambient = gl_LightModel.ambient * gl_FrontMaterial.ambient;
gl_TexCoord[0] = gl_MultiTexCoord0;
gl_TexCoord[1] = gl_MultiTexCoord1;
gl_TexCoord[2] = gl_MultiTexCoord2;
gl_TexCoord[3] = gl_MultiTexCoord3;
gl_Position = ftransform();
spos = pos * mat;
}

7
libs/qglview/shaders/selection.frag Normal file
View File

@@ -0,0 +1,7 @@
#version 150
uniform vec4 id;
void main(void) {
qgl_FragData[0] = id;
}

8
libs/qglview/shaders/selection.vert Normal file
View File

@@ -0,0 +1,8 @@
#version 150
uniform float z_near, z_far;
void main(void) {
vec4 pos = qgl_ftransform();
gl_Position = pos;
}

21
libs/qglview/shaders/selection_halo.frag Normal file
View File

@@ -0,0 +1,21 @@
#version 150
uniform vec2 dt;
uniform vec4 selected, color;
uniform sampler2D t0;
uniform float fill;
void main(void) {
ivec2 tc = ivec2(gl_FragCoord.xy);
vec4 ds0 = abs(texelFetchOffset(t0, tc, 0, ivec2(-1, 0)) - selected);
vec4 ds1 = abs(texelFetchOffset(t0, tc, 0, ivec2( 1, 0)) - selected);
vec4 ds2 = abs(texelFetchOffset(t0, tc, 0, ivec2(0, -1)) - selected);
vec4 ds3 = abs(texelFetchOffset(t0, tc, 0, ivec2(0, 1)) - selected);
float d0 = dot(ds0, vec4(1., 1., 1., 1.)), d1 = dot(ds1, vec4(1., 1., 1., 1.)), d2 = dot(ds2, vec4(1., 1., 1., 1.)), d3 = dot(ds3, vec4(1., 1., 1., 1.));
float vs = step(1e-6, d0 + d1 + d2 + d3);
float vm = step(1e-3, (d0 * 25.) * (d1 * 25.) * (d2 * 255.) * (d3 * 255.));
float v = mix(vs - vm, vs - vm - vm + 1, fill);
//qgl_FragData[0] = vec4(1,0,0,0.5);//vec4(color.rgb, v * color.a);
gl_FragColor = v*vec4(color.bgr, v * color.a);
//qgl_FragData[0] = vec4(1);
}

7
libs/qglview/shaders/selection_halo.vert Normal file
View File

@@ -0,0 +1,7 @@
#version 150
void main(void) {
qgl_FragTexture = qgl_Texture;
qgl_FragColor = qgl_Color;
gl_Position = qgl_ftransform();
}

7
libs/qglview/shaders/shadow.frag Normal file
View File

@@ -0,0 +1,7 @@
#version 150
in float w;
void main(void) {
//;qgl_FragData[0].r = w;
}

10
libs/qglview/shaders/shadow.vert Normal file
View File

@@ -0,0 +1,10 @@
#version 150
out float w;
void main(void) {
qgl_FragTexture = qgl_Texture;
vec4 pos = qgl_ftransform();
w = pos.w;
gl_Position = pos;
}

55
libs/qglview/shaders/ssao_blur.frag Normal file
View File

@@ -0,0 +1,55 @@
#version 150
uniform sampler2D t0, ts, tg1;
uniform float radius = 2;
uniform vec2 dt;
vec4 st;
vec4 getTexel(vec2 tc, vec4 ptc, float mul) {
vec4 tv = texture(t0, tc), ts = texture(ts, tc);
if (radius == 1) {
tv = vec4(tv.w);
ts = tv;
}
return vec4(min(ptc.r, ts.r), max(ptc.g, ts.g), ptc.b + /*mix(tv.b, st.b, clamp(abs(st.w - tv.w), 0, 1))*/tv.b * mul, 0);
}
void main(void) {
ivec2 itc = ivec2(gl_FragCoord.xy);
vec4 vg1 = texelFetch(tg1, itc, 0);
vec2 tc = qgl_FragTexture.xy;
float o = radius, o2 = radius * 2;
vec4 scol = texture(t0, tc);
if (radius == 1)
scol = vec4(scol.w);
st = scol;
scol.b *= 3.;
scol = getTexel(tc + dt * vec2( o, 0 ), scol, 2);
scol = getTexel(tc + dt * vec2( 0, o ), scol, 2);
scol = getTexel(tc + dt * vec2( -o, 0 ), scol, 2);
scol = getTexel(tc + dt * vec2( 0, -o), scol, 2);
scol = getTexel(tc + dt * vec2( o, o ), scol, 1.5);
scol = getTexel(tc + dt * vec2( o, -o), scol, 1.5);
scol = getTexel(tc + dt * vec2( -o, -o ), scol, 1.5);
scol = getTexel(tc + dt * vec2( -o, o ), scol, 1.5);
scol = getTexel(tc + dt * vec2( o2, 0 ), scol, 1);
scol = getTexel(tc + dt * vec2( 0, o2), scol, 1);
scol = getTexel(tc + dt * vec2(-o2, 0 ), scol, 1);
scol = getTexel(tc + dt * vec2( 0, -o2), scol, 1);
scol.b /= 21.;
/*vec4 scol = fp;
scol = min(scol, getTexel(tc + dt * vec2( o, 0 ), fp, fps));
scol = min(scol, getTexel(tc + dt * vec2( 0, o ), fp, fps));
scol = min(scol, getTexel(tc + dt * vec2( -o, 0 ), fp, fps));
scol = min(scol, getTexel(tc + dt * vec2( 0, -o), fp, fps));
scol = min(scol, getTexel(tc + dt * vec2( o, o ), fp, fps));
scol = min(scol, getTexel(tc + dt * vec2( o, -o), fp, fps));
scol = min(scol, getTexel(tc + dt * vec2( -o, -o ), fp, fps));
scol = min(scol, getTexel(tc + dt * vec2( -o, o ), fp, fps));
scol = min(scol, getTexel(tc + dt * vec2( o2, 0 ), fp, fps));
scol = min(scol, getTexel(tc + dt * vec2( 0, o2), fp, fps));
scol = min(scol, getTexel(tc + dt * vec2(-o2, 0 ), fp, fps));
scol = min(scol, getTexel(tc + dt * vec2( 0, -o2), fp, fps));*/
qgl_FragData[0].rgba = vec4(scol.rgb, texture(t0, tc).w);
}

6
libs/qglview/shaders/ssao_blur.vert Normal file
View File

@@ -0,0 +1,6 @@
#version 150
void main(void) {
qgl_FragTexture = qgl_Texture;
gl_Position = qgl_ftransform();
}

53
libs/qglview/shaders/ssao_merge.frag Normal file
View File

@@ -0,0 +1,53 @@
#version 150
uniform sampler2D t0, ts, tg1;
uniform sampler1D n0;
uniform float z_near, z_far;
uniform mat4 mat_proj;
in vec3 view_dir;
void main(void) {
ivec2 tc = ivec2(gl_FragCoord.xy);
vec4 v0 = texelFetch(t0, tc, 0), vs = texelFetch(ts, tc, 0), vg1 = texelFetch(tg1, tc, 0);
vec3 n = vec3(vg1.xyz);
vec3 bn = cross(n, vec3(0, 0, 1));
vec3 bn2 = cross(n, bn);
vec4 pos;
pos.w = 1;
pos.xyz = view_dir * vs.w;
vec4 spos = pos, tpos, tv0;
vec2 tsp;
float sclz = dot(vec3(0,0,1), n);
/*float l = 20 * 0.5;
pos.xyz += bn2 * l;
for (int i = 0; i < 16; ++i) {
tpos = mat_proj * pos;
tsp = -(tpos.xy / tpos.w) / 2. + 0.5;
tv0 = texture(ts, tsp);
l *= 0.5;
pos.xyz += bn2 * (step(pos.z, tv0.w) * 2. - 1.) * l;
}*/
/*vec3 rn;
float ss = 0.;
for (int i = 0; i < 32; ++i) {
rn = texelFetch(n0, i, 0).rgb * 2 - 1;
rn *= step(0., dot(n, rn)) * 2 - 1.;
//rn /= 10;
rn /= vs.w;
spos = pos + vec4(rn, 0);
tpos = mat_proj * spos;
tsp = -(tpos.xy / tpos.w) / 2. + 0.5;
tv0 = texture(ts, tsp);
//spos.z = tv0.w;
ss += step(-0.1, tv0.w-vs.w);
//ss += step(vs.w, tv0.w);
}
ss /= 32;*/
float minz = v0.r, maxz = v0.g, blurz = v0.b, curz = v0.w, avgz = (minz+maxz)/2;
float dz = maxz - minz;
//qgl_FragData[0].rgb = vec3(max(-(blurz - curz) / maxz,0.)* (curz-minz) / dz * 10);
qgl_FragData[0].rgb = vec3(blurz/10);
//qgl_FragData[0].rgb = vec3(length(pos.z - spos.z)/15);
//qgl_FragData[0].rgb = vec3(abs(v0.w/1));
}

10
libs/qglview/shaders/ssao_merge.vert Normal file
View File

@@ -0,0 +1,10 @@
#version 150
in vec3 view_corner;
out vec3 view_dir;
void main(void) {
view_dir = view_corner / view_corner.z;
qgl_FragTexture = qgl_Texture;
gl_Position = qgl_ftransform();
}

68
libs/qglview/shaders/ssr.frag Normal file
View File

@@ -0,0 +1,68 @@
#version 150
uniform sampler2D t0, t1, ts, td, tbs;
uniform float z_near, z_far;
uniform mat4 mat_proj;
uniform vec3 cam_aim, cam_pos;
in vec3 view_dir;
const float _pe = 2.4e-7;
void main(void) {
ivec2 tc = ivec2(gl_FragCoord.xy);
vec4 v0 = texelFetch(t0, tc, 0), v1 = texelFetch(t1, tc, 0), vs = texelFetch(ts, tc, 0);
vec3 sp = vec3(qgl_FragTexture.xy, v0.w);
vec2 tsp;
vec4 pos;
float z = texelFetch(td, tc, 0).r;
z = z + z - 1;
z = ((_pe - 2.) * z_near) / (z + _pe - 1.); // infinite depth
pos.w = 1;
pos.xyz = view_dir * z;
pos.z = -pos.z;
vec4 spos = pos;
vec4 tpos;
vec3 dc = v0.rgb, n = v1.xyz;
vec3 vd = normalize(view_dir);
vec3 rn = reflect(vd, n);
//rn.z += 1.;
float coeff = clamp(1. - (dot(vec3(0,0,1), n)), 0, 1);
coeff = coeff*coeff;
/*coeff = coeff*coeff;
coeff = coeff*coeff;
coeff = coeff*coeff;*/
float reflectivity = 0.;
float specularity = modf(v1.w, reflectivity);
rn.z = -rn.z;
int i = 0;
vec4 tv0;
float l = z_far * 0.5;
pos.xyz += rn * l;
float cz;
for (i = 0; i < 24; ++i) {
tpos = mat_proj * pos;
tsp = -(tpos.xy / tpos.w) / 2. + 0.5;
cz = texture(td, tsp).r;
cz = cz + cz - 1;
cz = ((_pe - 2.) * z_near) / (cz + _pe - 1.); // infinite depth
l *= 0.5;
pos.xyz += rn * (step(pos.z, cz) * 2. - 1.) * l;
}
vec2 ess = abs(tsp - vec2(0.5, 0.5)) - vec2(0.3, 0.3);
ess = clamp(ess, vec2(0, 0), vec2(0.2, 0.2));
ess = smoothstep(vec2(0.2, 0.2), vec2(0, 0), ess);
coeff *= min(ess.x, ess.y);
vec4 pr_pos = mat_proj * pos, pr_spos = mat_proj * spos;
pr_pos.xyz /= pr_pos.w;
pr_spos.xyz /= pr_spos.w;
float blur = step(0., coeff) * length(pr_pos.xyz - pr_spos.xyz) * (1. - specularity);
vec3 rvs = texture(ts, tsp).rgb;
qgl_FragData[0] = vec4(rvs.rgb, coeff / 1.1 + clamp(round(blur * 10), 0, 1000));
//qgl_FragData[0] = vec4(rvs.rgb, cz/5);
//qgl_FragData[0].rgb = vec3(tpos/10);
}

10
libs/qglview/shaders/ssr.vert Normal file
View File

@@ -0,0 +1,10 @@
#version 150
in vec3 view_corner;
out vec3 view_dir;
void main(void) {
view_dir = vec3(view_corner.xyz);
qgl_FragTexture = qgl_Texture;
gl_Position = qgl_ftransform();
}

38
libs/qglview/shaders/ssr_blur.frag Normal file
View File

@@ -0,0 +1,38 @@
#version 150
uniform sampler2D t0;
uniform float radius = 2;
uniform vec2 dt;
void main(void) {
vec2 tc = qgl_FragTexture.xy;
float r = float(radius);
vec4 v0 = texture(t0, tc);
float rad;
float coeff = modf(v0.w, rad) * 1.1;
rad /= 10.;
rad *= 2;
float o = radius * rad, o2 = radius * rad * 2;
vec3 scol = (v0.rgb * 3. +
texture(t0, tc + dt * vec2( o, 0 )).rgb * 2. +
texture(t0, tc + dt * vec2( 0, o )).rgb * 2. +
texture(t0, tc + dt * vec2( -o, 0 )).rgb * 2. +
texture(t0, tc + dt * vec2( 0, -o)).rgb * 2. +
texture(t0, tc + dt * vec2( o, o )).rgb * 1.5 +
texture(t0, tc + dt * vec2( o, -o)).rgb * 1.5 +
texture(t0, tc + dt * vec2( -o, -o )).rgb * 1.5 +
texture(t0, tc + dt * vec2( -o, o )).rgb * 1.5 +
texture(t0, tc + dt * vec2( o2, 0 )).rgb +
texture(t0, tc + dt * vec2( 0, o2)).rgb +
texture(t0, tc + dt * vec2(-o2, 0 )).rgb +
texture(t0, tc + dt * vec2( 0, -o2)).rgb/* +
texture(t0, tc + dt * vec2( o2, o )).rgb +
texture(t0, tc + dt * vec2( o2, -o)).rgb +
texture(t0, tc + dt * vec2(-o2, -o )).rgb +
texture(t0, tc + dt * vec2(-o2, o )).rgb +
texture(t0, tc + dt * vec2( o, o2)).rgb +
texture(t0, tc + dt * vec2( o, -o2)).rgb +
texture(t0, tc + dt * vec2( -o, -o2)).rgb +
texture(t0, tc + dt * vec2( -o, o2)).rgb*/) / 21.;
qgl_FragData[0] = vec4(scol, v0.w);
}

6
libs/qglview/shaders/ssr_blur.vert Normal file
View File

@@ -0,0 +1,6 @@
#version 150
void main(void) {
qgl_FragTexture = qgl_Texture;
gl_Position = qgl_ftransform();
}

15
libs/qglview/shaders/ssr_merge.frag Normal file
View File

@@ -0,0 +1,15 @@
#version 150
uniform sampler2D t0, tg1, ts;
void main(void) {
ivec2 tc = ivec2(gl_FragCoord.xy);
vec4 v0 = texelFetch(t0, tc, 0), vg1 = texelFetch(tg1, tc, 0), vs = texelFetch(ts, tc, 0);
float rad;
float coeff = clamp(modf(v0.w, rad) * 1.1, 0., 1.);
float reflectivity = 0.;
float specularity = modf(vg1.w, reflectivity);
reflectivity = clamp(reflectivity / 100., 0., 1.);
qgl_FragData[0].rgb = mix(vs.rgb, v0.rgb, coeff * reflectivity);
//qgl_FragData[0].rgb = vec3(v0.w);
}

6
libs/qglview/shaders/ssr_merge.vert Normal file
View File

@@ -0,0 +1,6 @@
#version 150
void main(void) {
qgl_FragTexture = qgl_Texture;
gl_Position = qgl_ftransform();
}