From 14f6bbadef2c39e58a3b54c0c6212949acf50e45 Mon Sep 17 00:00:00 2001 From: Dave Parks Date: Mon, 8 Aug 2011 15:29:23 -0500 Subject: SH-2242 Work in progress migrating to glVertexAttrib everywhere --- .../shaders/class1/deferred/alphaSkinnedV.glsl | 20 ++++++++------ .../shaders/class1/deferred/alphaV.glsl | 29 +++++++++++--------- .../shaders/class1/deferred/attachmentShadowV.glsl | 10 ++++--- .../shaders/class1/deferred/avatarAlphaV.glsl | 32 ++++++++++++---------- .../shaders/class1/deferred/avatarEyesV.glsl | 12 +++++--- .../shaders/class1/deferred/avatarShadowV.glsl | 23 ++++++++++------ .../shaders/class1/deferred/avatarV.glsl | 25 +++++++++-------- .../shaders/class1/deferred/blurLightV.glsl | 6 ++-- .../shaders/class1/deferred/bumpSkinnedV.glsl | 16 +++++++---- .../shaders/class1/deferred/bumpV.glsl | 16 +++++++---- .../shaders/class1/deferred/cloudsV.glsl | 11 ++++---- .../shaders/class1/deferred/diffuseSkinnedV.glsl | 15 ++++++---- .../shaders/class1/deferred/diffuseV.glsl | 14 ++++++---- .../shaders/class1/deferred/fullbrightV.glsl | 16 ++++++----- .../app_settings/shaders/class1/deferred/giV.glsl | 12 +++++--- .../shaders/class1/deferred/impostorV.glsl | 10 ++++--- .../shaders/class1/deferred/luminanceV.glsl | 12 ++++---- .../shaders/class1/deferred/multiPointLightV.glsl | 6 ++-- .../shaders/class1/deferred/pointLightV.glsl | 12 ++++---- .../shaders/class1/deferred/postDeferredV.glsl | 6 ++-- .../shaders/class1/deferred/postgiV.glsl | 5 ++-- .../shaders/class1/deferred/shadowAlphaMaskV.glsl | 10 ++++--- .../shaders/class1/deferred/shadowV.glsl | 4 +-- .../app_settings/shaders/class1/deferred/skyV.glsl | 11 ++++---- .../shaders/class1/deferred/softenLightF.glsl | 6 ++-- .../shaders/class1/deferred/softenLightV.glsl | 13 +++------ .../shaders/class1/deferred/starsV.glsl | 10 ++++--- .../shaders/class1/deferred/sunLightV.glsl | 16 +++++++---- .../shaders/class1/deferred/terrainV.glsl | 14 ++++++---- .../shaders/class1/deferred/treeV.glsl | 12 +++++--- .../shaders/class1/deferred/waterV.glsl | 23 ++++++++-------- 31 files changed, 249 insertions(+), 178 deletions(-) (limited to 'indra/newview/app_settings/shaders/class1/deferred') diff --git a/indra/newview/app_settings/shaders/class1/deferred/alphaSkinnedV.glsl b/indra/newview/app_settings/shaders/class1/deferred/alphaSkinnedV.glsl index ac3f7189c2..eeebae4464 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/alphaSkinnedV.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/alphaSkinnedV.glsl @@ -6,6 +6,10 @@ */ +attribute vec3 position; +attribute vec3 normal; +attribute vec4 diffuse_color; +attribute vec2 texcoord0; vec4 calcLighting(vec3 pos, vec3 norm, vec4 color, vec4 baseCol); mat4 getObjectSkinnedTransform(); @@ -59,7 +63,7 @@ float calcPointLightOrSpotLight(vec3 v, vec3 n, vec4 lp, vec3 ln, float la, floa void main() { - gl_TexCoord[0] = gl_MultiTexCoord0; + gl_TexCoord[0] = vec4(texcoord0,0,1); vec4 pos; vec3 norm; @@ -67,9 +71,9 @@ void main() mat4 trans = getObjectSkinnedTransform(); trans = gl_ModelViewMatrix * trans; - pos = trans * gl_Vertex; + pos = trans * vec4(position.xyz, 1.0); - norm = gl_Vertex.xyz + gl_Normal.xyz; + norm = position.xyz + normal.xyz; norm = normalize(( trans*vec4(norm, 1.0) ).xyz-pos.xyz); vec4 frag_pos = gl_ProjectionMatrix * pos; @@ -80,7 +84,7 @@ void main() calcAtmospherics(pos.xyz); - vec4 col = vec4(0.0, 0.0, 0.0, gl_Color.a); + vec4 col = vec4(0.0, 0.0, 0.0, diffuse_color.a); // Collect normal lights col.rgb += gl_LightSource[2].diffuse.rgb*calcPointLightOrSpotLight(pos.xyz, norm, gl_LightSource[2].position, gl_LightSource[2].spotDirection.xyz, gl_LightSource[2].linearAttenuation, gl_LightSource[2].quadraticAttenuation, gl_LightSource[2].specular.a); @@ -90,17 +94,17 @@ void main() col.rgb += gl_LightSource[6].diffuse.rgb*calcPointLightOrSpotLight(pos.xyz, norm, gl_LightSource[6].position, gl_LightSource[6].spotDirection.xyz, gl_LightSource[6].linearAttenuation, gl_LightSource[6].quadraticAttenuation, gl_LightSource[6].specular.a); col.rgb += gl_LightSource[7].diffuse.rgb*calcPointLightOrSpotLight(pos.xyz, norm, gl_LightSource[7].position, gl_LightSource[7].spotDirection.xyz, gl_LightSource[7].linearAttenuation, gl_LightSource[7].quadraticAttenuation, gl_LightSource[7].specular.a); - vary_pointlight_col = col.rgb*gl_Color.rgb; + vary_pointlight_col = col.rgb*diffuse_color.rgb; col.rgb = vec3(0,0,0); // Add windlight lights col.rgb = atmosAmbient(vec3(0.)); - vary_ambient = col.rgb*gl_Color.rgb; - vary_directional = gl_Color.rgb*atmosAffectDirectionalLight(max(calcDirectionalLight(norm, gl_LightSource[0].position.xyz), (1.0-gl_Color.a)*(1.0-gl_Color.a))); + vary_ambient = col.rgb*diffuse_color.rgb; + vary_directional = diffuse_color.rgb*atmosAffectDirectionalLight(max(calcDirectionalLight(norm, gl_LightSource[0].position.xyz), (1.0-diffuse_color.a)*(1.0-diffuse_color.a))); - col.rgb = min(col.rgb*gl_Color.rgb, 1.0); + col.rgb = min(col.rgb*diffuse_color.rgb, 1.0); gl_FrontColor = col; diff --git a/indra/newview/app_settings/shaders/class1/deferred/alphaV.glsl b/indra/newview/app_settings/shaders/class1/deferred/alphaV.glsl index 44cb78e914..3a17f6a709 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/alphaV.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/alphaV.glsl @@ -5,7 +5,10 @@ * $/LicenseInfo$ */ - +attribute vec4 position; +attribute vec3 normal; +attribute vec4 diffuse_color; +attribute vec2 texcoord0; vec4 calcLighting(vec3 pos, vec3 norm, vec4 color, vec4 baseCol); void calcAtmospherics(vec3 inPositionEye); @@ -62,22 +65,22 @@ float calcPointLightOrSpotLight(vec3 v, vec3 n, vec4 lp, vec3 ln, float la, floa void main() { //transform vertex - vec4 vert = vec4(gl_Vertex.xyz, 1.0); - vary_texture_index = gl_Vertex.w; - gl_Position = gl_ModelViewProjectionMatrix * vert; + vec4 vert = vec4(position.xyz, 1.0); + vary_texture_index = position.w; + vec4 pos = (gl_ModelViewMatrix * vert); + gl_Position = gl_ModelViewProjectionMatrix*vec4(position.xyz, 1.0); - gl_TexCoord[0] = gl_TextureMatrix[0] * gl_MultiTexCoord0; + gl_TexCoord[0] = gl_TextureMatrix[0] * vec4(texcoord0,0,1); - vec4 pos = (gl_ModelViewMatrix * vert); - vec3 norm = normalize(gl_NormalMatrix * gl_Normal); + vec3 norm = normalize(gl_NormalMatrix * normal); float dp_directional_light = max(0.0, dot(norm, gl_LightSource[0].position.xyz)); vary_position = pos.xyz + gl_LightSource[0].position.xyz * (1.0-dp_directional_light)*shadow_offset; calcAtmospherics(pos.xyz); - //vec4 color = calcLighting(pos.xyz, norm, gl_Color, vec4(0.)); - vec4 col = vec4(0.0, 0.0, 0.0, gl_Color.a); + //vec4 color = calcLighting(pos.xyz, norm, diffuse_color, vec4(0.)); + vec4 col = vec4(0.0, 0.0, 0.0, diffuse_color.a); // Collect normal lights col.rgb += gl_LightSource[2].diffuse.rgb*calcPointLightOrSpotLight(pos.xyz, norm, gl_LightSource[2].position, gl_LightSource[2].spotDirection.xyz, gl_LightSource[2].linearAttenuation, gl_LightSource[2].quadraticAttenuation, gl_LightSource[2].specular.a); @@ -87,7 +90,7 @@ void main() col.rgb += gl_LightSource[6].diffuse.rgb*calcPointLightOrSpotLight(pos.xyz, norm, gl_LightSource[6].position, gl_LightSource[6].spotDirection.xyz, gl_LightSource[6].linearAttenuation, gl_LightSource[6].quadraticAttenuation, gl_LightSource[6].specular.a); col.rgb += gl_LightSource[7].diffuse.rgb*calcPointLightOrSpotLight(pos.xyz, norm, gl_LightSource[7].position, gl_LightSource[7].spotDirection.xyz, gl_LightSource[7].linearAttenuation, gl_LightSource[7].quadraticAttenuation, gl_LightSource[7].specular.a); - vary_pointlight_col = col.rgb*gl_Color.rgb; + vary_pointlight_col = col.rgb*diffuse_color.rgb; col.rgb = vec3(0,0,0); @@ -96,10 +99,10 @@ void main() vary_light = gl_LightSource[0].position.xyz; - vary_ambient = col.rgb*gl_Color.rgb; - vary_directional.rgb = gl_Color.rgb*atmosAffectDirectionalLight(max(calcDirectionalLight(norm, gl_LightSource[0].position.xyz), (1.0-gl_Color.a)*(1.0-gl_Color.a))); + vary_ambient = col.rgb*diffuse_color.rgb; + vary_directional.rgb = diffuse_color.rgb*atmosAffectDirectionalLight(max(calcDirectionalLight(norm, gl_LightSource[0].position.xyz), (1.0-diffuse_color.a)*(1.0-diffuse_color.a))); - col.rgb = col.rgb*gl_Color.rgb; + col.rgb = col.rgb*diffuse_color.rgb; gl_FrontColor = col; diff --git a/indra/newview/app_settings/shaders/class1/deferred/attachmentShadowV.glsl b/indra/newview/app_settings/shaders/class1/deferred/attachmentShadowV.glsl index c7a4f86727..df61785aa1 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/attachmentShadowV.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/attachmentShadowV.glsl @@ -5,21 +5,23 @@ * $License$ */ - +attribute vec3 position; +attribute vec4 diffuse_color; +attribute vec2 texcoord0; mat4 getObjectSkinnedTransform(); void main() { //transform vertex - gl_TexCoord[0] = gl_TextureMatrix[0] * gl_MultiTexCoord0; + gl_TexCoord[0] = gl_TextureMatrix[0] * vec4(texcoord0,0,1); mat4 mat = getObjectSkinnedTransform(); mat = gl_ModelViewMatrix * mat; - vec3 pos = (mat*gl_Vertex).xyz; + vec3 pos = (mat*vec4(position.xyz, 1.0)).xyz; - gl_FrontColor = gl_Color; + gl_FrontColor = diffuse_color; vec4 p = gl_ProjectionMatrix * vec4(pos, 1.0); p.z = max(p.z, -p.w+0.01); diff --git a/indra/newview/app_settings/shaders/class1/deferred/avatarAlphaV.glsl b/indra/newview/app_settings/shaders/class1/deferred/avatarAlphaV.glsl index 68e4055cf2..842931ec17 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/avatarAlphaV.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/avatarAlphaV.glsl @@ -5,7 +5,10 @@ * $/LicenseInfo$ */ - +attribute vec3 position; +attribute vec3 normal; +attribute vec4 diffuse_color; +attribute vec2 texcoord0; vec4 calcLighting(vec3 pos, vec3 norm, vec4 color, vec4 baseCol); mat4 getSkinnedTransform(); @@ -59,20 +62,21 @@ float calcPointLightOrSpotLight(vec3 v, vec3 n, vec4 lp, vec3 ln, float la, floa void main() { - gl_TexCoord[0] = gl_MultiTexCoord0; + gl_TexCoord[0] = vec4(texcoord0,0,1); vec4 pos; vec3 norm; mat4 trans = getSkinnedTransform(); - pos.x = dot(trans[0], gl_Vertex); - pos.y = dot(trans[1], gl_Vertex); - pos.z = dot(trans[2], gl_Vertex); + vec4 pos_in = vec4(position.xyz, 1.0); + pos.x = dot(trans[0], pos_in); + pos.y = dot(trans[1], pos_in); + pos.z = dot(trans[2], pos_in); pos.w = 1.0; - norm.x = dot(trans[0].xyz, gl_Normal); - norm.y = dot(trans[1].xyz, gl_Normal); - norm.z = dot(trans[2].xyz, gl_Normal); + norm.x = dot(trans[0].xyz, normal); + norm.y = dot(trans[1].xyz, normal); + norm.z = dot(trans[2].xyz, normal); norm = normalize(norm); vec4 frag_pos = gl_ProjectionMatrix * pos; @@ -82,9 +86,9 @@ void main() calcAtmospherics(pos.xyz); - //vec4 color = calcLighting(pos.xyz, norm, gl_Color, vec4(0.)); + //vec4 color = calcLighting(pos.xyz, norm, diffuse_color, vec4(0.)); - vec4 col = vec4(0.0, 0.0, 0.0, gl_Color.a); + vec4 col = vec4(0.0, 0.0, 0.0, diffuse_color.a); // Collect normal lights col.rgb += gl_LightSource[2].diffuse.rgb*calcPointLightOrSpotLight(pos.xyz, norm, gl_LightSource[2].position, gl_LightSource[2].spotDirection.xyz, gl_LightSource[2].linearAttenuation, gl_LightSource[2].quadraticAttenuation, gl_LightSource[2].specular.a); @@ -94,17 +98,17 @@ void main() col.rgb += gl_LightSource[6].diffuse.rgb*calcPointLightOrSpotLight(pos.xyz, norm, gl_LightSource[6].position, gl_LightSource[6].spotDirection.xyz, gl_LightSource[6].linearAttenuation, gl_LightSource[6].quadraticAttenuation, gl_LightSource[6].specular.a); col.rgb += gl_LightSource[7].diffuse.rgb*calcPointLightOrSpotLight(pos.xyz, norm, gl_LightSource[7].position, gl_LightSource[7].spotDirection.xyz, gl_LightSource[7].linearAttenuation, gl_LightSource[7].quadraticAttenuation, gl_LightSource[7].specular.a); - vary_pointlight_col = col.rgb*gl_Color.rgb; + vary_pointlight_col = col.rgb*diffuse_color.rgb; col.rgb = vec3(0,0,0); // Add windlight lights col.rgb = atmosAmbient(vec3(0.)); - vary_ambient = col.rgb*gl_Color.rgb; - vary_directional = gl_Color.rgb*atmosAffectDirectionalLight(max(calcDirectionalLight(norm, gl_LightSource[0].position.xyz), (1.0-gl_Color.a)*(1.0-gl_Color.a))); + vary_ambient = col.rgb*diffuse_color.rgb; + vary_directional = diffuse_color.rgb*atmosAffectDirectionalLight(max(calcDirectionalLight(norm, gl_LightSource[0].position.xyz), (1.0-diffuse_color.a)*(1.0-diffuse_color.a))); - col.rgb = min(col.rgb*gl_Color.rgb, 1.0); + col.rgb = min(col.rgb*diffuse_color.rgb, 1.0); gl_FrontColor = col; diff --git a/indra/newview/app_settings/shaders/class1/deferred/avatarEyesV.glsl b/indra/newview/app_settings/shaders/class1/deferred/avatarEyesV.glsl index 7bc78fe407..bdea3d2b57 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/avatarEyesV.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/avatarEyesV.glsl @@ -6,16 +6,20 @@ */ +attribute vec3 position; +attribute vec3 normal; +attribute vec4 diffuse_color; +attribute vec2 texcoord0; varying vec3 vary_normal; void main() { //transform vertex - gl_Position = gl_ModelViewProjectionMatrix * gl_Vertex; - gl_TexCoord[0] = gl_TextureMatrix[0] * gl_MultiTexCoord0; + gl_Position = gl_ModelViewProjectionMatrix * vec4(position.xyz, 1.0); + gl_TexCoord[0] = gl_TextureMatrix[0] * vec4(texcoord0,0,1); - vary_normal = normalize(gl_NormalMatrix * gl_Normal); + vary_normal = normalize(gl_NormalMatrix * normal); - gl_FrontColor = gl_Color; + gl_FrontColor = diffuse_color; } diff --git a/indra/newview/app_settings/shaders/class1/deferred/avatarShadowV.glsl b/indra/newview/app_settings/shaders/class1/deferred/avatarShadowV.glsl index f177fcd8f1..cf6fc1c0ed 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/avatarShadowV.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/avatarShadowV.glsl @@ -9,26 +9,31 @@ mat4 getSkinnedTransform(); -attribute vec4 weight; +attribute vec3 position; +attribute vec3 normal; +attribute vec4 diffuse_color; +attribute vec2 texcoord0; + varying vec4 post_pos; void main() { - gl_TexCoord[0] = gl_MultiTexCoord0; + gl_TexCoord[0] = vec4(texcoord0,0,1); vec4 pos; vec3 norm; + vec4 pos_in = vec4(position.xyz, 1.0); mat4 trans = getSkinnedTransform(); - pos.x = dot(trans[0], gl_Vertex); - pos.y = dot(trans[1], gl_Vertex); - pos.z = dot(trans[2], gl_Vertex); + pos.x = dot(trans[0], pos_in); + pos.y = dot(trans[1], pos_in); + pos.z = dot(trans[2], pos_in); pos.w = 1.0; - norm.x = dot(trans[0].xyz, gl_Normal); - norm.y = dot(trans[1].xyz, gl_Normal); - norm.z = dot(trans[2].xyz, gl_Normal); + norm.x = dot(trans[0].xyz, normal); + norm.y = dot(trans[1].xyz, normal); + norm.z = dot(trans[2].xyz, normal); norm = normalize(norm); pos = gl_ProjectionMatrix * pos; @@ -36,7 +41,7 @@ void main() gl_Position = vec4(pos.x, pos.y, pos.w*0.5, pos.w); - gl_FrontColor = gl_Color; + gl_FrontColor = diffuse_color; } diff --git a/indra/newview/app_settings/shaders/class1/deferred/avatarV.glsl b/indra/newview/app_settings/shaders/class1/deferred/avatarV.glsl index 7eac11287a..e66f8c8483 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/avatarV.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/avatarV.glsl @@ -5,7 +5,10 @@ * $/LicenseInfo$ */ - +attribute vec3 position; +attribute vec4 diffuse_color; +attribute vec3 normal; +attribute vec2 texcoord0; mat4 getSkinnedTransform(); @@ -15,28 +18,28 @@ varying vec3 vary_normal; void main() { - gl_TexCoord[0] = gl_MultiTexCoord0; + gl_TexCoord[0] = vec4(texcoord0,0,1); vec4 pos; vec3 norm; + vec4 pos_in = vec4(position.xyz, 1.0); mat4 trans = getSkinnedTransform(); - pos.x = dot(trans[0], gl_Vertex); - pos.y = dot(trans[1], gl_Vertex); - pos.z = dot(trans[2], gl_Vertex); + pos.x = dot(trans[0], pos_in); + pos.y = dot(trans[1], pos_in); + pos.z = dot(trans[2], pos_in); pos.w = 1.0; - norm.x = dot(trans[0].xyz, gl_Normal); - norm.y = dot(trans[1].xyz, gl_Normal); - norm.z = dot(trans[2].xyz, gl_Normal); + norm.x = dot(trans[0].xyz, normal); + norm.y = dot(trans[1].xyz, normal); + norm.z = dot(trans[2].xyz, normal); norm = normalize(norm); vary_normal = norm; gl_Position = gl_ProjectionMatrix * pos; - //gl_Position = gl_ModelViewProjectionMatrix * gl_Vertex; - - gl_FrontColor = gl_Color; + + gl_FrontColor = diffuse_color; } diff --git a/indra/newview/app_settings/shaders/class1/deferred/blurLightV.glsl b/indra/newview/app_settings/shaders/class1/deferred/blurLightV.glsl index 862f809de5..016b5e1008 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/blurLightV.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/blurLightV.glsl @@ -5,7 +5,7 @@ * $/LicenseInfo$ */ - +attribute vec3 position; varying vec2 vary_fragcoord; uniform vec2 screen_res; @@ -13,7 +13,7 @@ uniform vec2 screen_res; void main() { //transform vertex - gl_Position = ftransform(); - vec4 pos = gl_ModelViewProjectionMatrix * gl_Vertex; + vec4 pos = gl_ModelViewProjectionMatrix * vec4(position.xyz, 1.0); + gl_Position = pos; vary_fragcoord = (pos.xy*0.5+0.5)*screen_res; } diff --git a/indra/newview/app_settings/shaders/class1/deferred/bumpSkinnedV.glsl b/indra/newview/app_settings/shaders/class1/deferred/bumpSkinnedV.glsl index dc69519a85..93e00fe523 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/bumpSkinnedV.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/bumpSkinnedV.glsl @@ -5,7 +5,11 @@ * $License$ */ - +attribute vec3 position; +attribute vec4 diffuse_color; +attribute vec3 normal; +attribute vec2 texcoord0; +attribute vec2 texcoord2; varying vec3 vary_mat0; varying vec3 vary_mat1; @@ -15,17 +19,17 @@ mat4 getObjectSkinnedTransform(); void main() { - gl_TexCoord[0] = gl_TextureMatrix[0] * gl_MultiTexCoord0; + gl_TexCoord[0] = gl_TextureMatrix[0] * vec4(texcoord0,0,1); mat4 mat = getObjectSkinnedTransform(); mat = gl_ModelViewMatrix * mat; - vec3 pos = (mat*gl_Vertex).xyz; + vec3 pos = (mat*vec4(position.xyz, 1.0)).xyz; - vec3 n = normalize((mat * vec4(gl_Normal.xyz+gl_Vertex.xyz, 1.0)).xyz-pos.xyz); - vec3 b = normalize((mat * vec4(gl_MultiTexCoord2.xyz+gl_Vertex.xyz, 1.0)).xyz-pos.xyz); + vec3 n = normalize((mat * vec4(normal.xyz+position.xyz, 1.0)).xyz-pos.xyz); + vec3 b = normalize((mat * vec4(vec4(texcoord2,0,1).xyz+position.xyz, 1.0)).xyz-pos.xyz); vec3 t = cross(b, n); vary_mat0 = vec3(t.x, b.x, n.x); @@ -33,5 +37,5 @@ void main() vary_mat2 = vec3(t.z, b.z, n.z); gl_Position = gl_ProjectionMatrix*vec4(pos, 1.0); - gl_FrontColor = gl_Color; + gl_FrontColor = diffuse_color; } diff --git a/indra/newview/app_settings/shaders/class1/deferred/bumpV.glsl b/indra/newview/app_settings/shaders/class1/deferred/bumpV.glsl index 5b6726488b..3c28776045 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/bumpV.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/bumpV.glsl @@ -5,7 +5,11 @@ * $/LicenseInfo$ */ - +attribute vec3 position; +attribute vec4 diffuse_color; +attribute vec3 normal; +attribute vec2 texcoord0; +attribute vec2 texcoord2; varying vec3 vary_mat0; varying vec3 vary_mat1; @@ -14,16 +18,16 @@ varying vec3 vary_mat2; void main() { //transform vertex - gl_Position = ftransform(); - gl_TexCoord[0] = gl_TextureMatrix[0] * gl_MultiTexCoord0; + gl_Position = gl_ModelViewProjectionMatrix * vec4(position.xyz, 1.0); + gl_TexCoord[0] = gl_TextureMatrix[0] * vec4(texcoord0,0,1); - vec3 n = normalize(gl_NormalMatrix * gl_Normal); - vec3 b = normalize(gl_NormalMatrix * gl_MultiTexCoord2.xyz); + vec3 n = normalize(gl_NormalMatrix * normal); + vec3 b = normalize(gl_NormalMatrix * vec4(texcoord2,0,1).xyz); vec3 t = cross(b, n); vary_mat0 = vec3(t.x, b.x, n.x); vary_mat1 = vec3(t.y, b.y, n.y); vary_mat2 = vec3(t.z, b.z, n.z); - gl_FrontColor = gl_Color; + gl_FrontColor = diffuse_color; } diff --git a/indra/newview/app_settings/shaders/class1/deferred/cloudsV.glsl b/indra/newview/app_settings/shaders/class1/deferred/cloudsV.glsl index 3eac63076c..9ba5e97a95 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/cloudsV.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/cloudsV.glsl @@ -5,7 +5,8 @@ * $/LicenseInfo$ */ - +attribute vec3 position; +attribute vec2 texcoord0; ////////////////////////////////////////////////////////////////////////// // The vertex shader for creating the atmospheric sky @@ -41,12 +42,12 @@ void main() { // World / view / projection - gl_Position = ftransform(); + gl_Position = gl_ModelViewProjectionMatrix * vec4(position.xyz, 1.0); - gl_TexCoord[0] = gl_MultiTexCoord0; + gl_TexCoord[0] = vec4(texcoord0,0,1); // Get relative position - vec3 P = gl_Vertex.xyz - camPosLocal.xyz + vec3(0,50,0); + vec3 P = position.xyz - camPosLocal.xyz + vec3(0,50,0); // Set altitude if (P.y > 0.) @@ -142,7 +143,7 @@ void main() // Texture coords - gl_TexCoord[0] = gl_MultiTexCoord0; + gl_TexCoord[0] = vec4(texcoord0,0,1); gl_TexCoord[0].xy -= 0.5; gl_TexCoord[0].xy /= cloud_scale.x; gl_TexCoord[0].xy += 0.5; diff --git a/indra/newview/app_settings/shaders/class1/deferred/diffuseSkinnedV.glsl b/indra/newview/app_settings/shaders/class1/deferred/diffuseSkinnedV.glsl index 2c4caea109..fadbe5b9ef 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/diffuseSkinnedV.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/diffuseSkinnedV.glsl @@ -7,27 +7,32 @@ +attribute vec3 position; +attribute vec4 diffuse_color; +attribute vec3 normal; +attribute vec2 texcoord0; + varying vec3 vary_normal; mat4 getObjectSkinnedTransform(); void main() { - gl_TexCoord[0] = gl_TextureMatrix[0] * gl_MultiTexCoord0; + gl_TexCoord[0] = gl_TextureMatrix[0] * vec4(texcoord0,0,1); mat4 mat = getObjectSkinnedTransform(); mat = gl_ModelViewMatrix * mat; - vec3 pos = (mat*gl_Vertex).xyz; + vec3 pos = (mat*vec4(position.xyz, 1.0)).xyz; - vec4 norm = gl_Vertex; - norm.xyz += gl_Normal.xyz; + vec4 norm = vec4(position.xyz, 1.0); + norm.xyz += normal.xyz; norm.xyz = (mat*norm).xyz; norm.xyz = normalize(norm.xyz-pos.xyz); vary_normal = norm.xyz; - gl_FrontColor = gl_Color; + gl_FrontColor = diffuse_color; gl_Position = gl_ProjectionMatrix*vec4(pos, 1.0); } diff --git a/indra/newview/app_settings/shaders/class1/deferred/diffuseV.glsl b/indra/newview/app_settings/shaders/class1/deferred/diffuseV.glsl index b56d1493c3..e424737702 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/diffuseV.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/diffuseV.glsl @@ -6,6 +6,10 @@ */ +attribute vec4 position; +attribute vec4 diffuse_color; +attribute vec3 normal; +attribute vec2 texcoord0; varying vec3 vary_normal; varying float vary_texture_index; @@ -13,11 +17,11 @@ varying float vary_texture_index; void main() { //transform vertex - gl_Position = gl_ModelViewProjectionMatrix * vec4(gl_Vertex.xyz, 1.0); - gl_TexCoord[0] = gl_TextureMatrix[0] * gl_MultiTexCoord0; + gl_Position = gl_ModelViewProjectionMatrix * vec4(position.xyz, 1.0); + gl_TexCoord[0] = gl_TextureMatrix[0] * vec4(texcoord0,0,1); - vary_texture_index = gl_Vertex.w; - vary_normal = normalize(gl_NormalMatrix * gl_Normal); + vary_texture_index = position.w; + vary_normal = normalize(gl_NormalMatrix * normal); - gl_FrontColor = gl_Color; + gl_FrontColor = diffuse_color; } diff --git a/indra/newview/app_settings/shaders/class1/deferred/fullbrightV.glsl b/indra/newview/app_settings/shaders/class1/deferred/fullbrightV.glsl index 2eed044b7c..3e5fc7a36b 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/fullbrightV.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/fullbrightV.glsl @@ -6,6 +6,9 @@ */ +attribute vec4 position; +attribute vec4 diffuse_color; +attribute vec2 texcoord0; void calcAtmospherics(vec3 inPositionEye); @@ -19,18 +22,17 @@ varying float vary_texture_index; void main() { //transform vertex - vec4 vert = vec4(gl_Vertex.xyz, 1.0); - vary_texture_index = gl_Vertex.w; + vec4 vert = vec4(position.xyz, 1.0); + vec4 pos = (gl_ModelViewMatrix * vert); + vary_texture_index = position.w; - gl_Position = gl_ModelViewProjectionMatrix*vert; + gl_Position = gl_ModelViewProjectionMatrix*vec4(position.xyz, 1.0); - gl_TexCoord[0] = gl_TextureMatrix[0] * gl_MultiTexCoord0; + gl_TexCoord[0] = gl_TextureMatrix[0] * vec4(texcoord0,0,1); - vec4 pos = (gl_ModelViewMatrix * vert); - calcAtmospherics(pos.xyz); - gl_FrontColor = gl_Color; + gl_FrontColor = diffuse_color; gl_FogFragCoord = pos.z; } diff --git a/indra/newview/app_settings/shaders/class1/deferred/giV.glsl b/indra/newview/app_settings/shaders/class1/deferred/giV.glsl index e86f2896da..d97d7ea82d 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/giV.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/giV.glsl @@ -5,6 +5,9 @@ * $/LicenseInfo$ */ +attribute vec3 position; +attribute vec4 diffuse_color; +attribute vec2 texcoord0; varying vec2 vary_fragcoord; @@ -14,11 +17,12 @@ uniform vec2 screen_res; void main() { //transform vertex - gl_Position = ftransform(); - vec4 pos = gl_ModelViewProjectionMatrix * gl_Vertex; + vec4 pos = gl_ModelViewProjectionMatrix * vec4(position.xyz, 1.0); + gl_Position = pos; + vary_fragcoord = (pos.xy * 0.5 + 0.5)*screen_res; - vec4 tex = gl_MultiTexCoord0; + vec4 tex = vec4(texcoord0,0,1); tex.w = 1.0; - gl_FrontColor = gl_Color; + gl_FrontColor = diffuse_color; } diff --git a/indra/newview/app_settings/shaders/class1/deferred/impostorV.glsl b/indra/newview/app_settings/shaders/class1/deferred/impostorV.glsl index 723777bd3a..cb47f62bbf 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/impostorV.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/impostorV.glsl @@ -5,13 +5,15 @@ * $/LicenseInfo$ */ - +attribute vec3 position; +attribute vec4 diffuse_color; +attribute vec2 texcoord0; void main() { //transform vertex - gl_Position = ftransform(); - gl_TexCoord[0] = gl_TextureMatrix[0] * gl_MultiTexCoord0; + gl_Position = gl_ModelViewProjectionMatrix * vec4(position.xyz, 1.0); + gl_TexCoord[0] = gl_TextureMatrix[0] * vec4(texcoord0,0,1); - gl_FrontColor = gl_Color; + gl_FrontColor = diffuse_color; } diff --git a/indra/newview/app_settings/shaders/class1/deferred/luminanceV.glsl b/indra/newview/app_settings/shaders/class1/deferred/luminanceV.glsl index 4baf1fc65a..6a53644723 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/luminanceV.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/luminanceV.glsl @@ -5,8 +5,9 @@ * $/LicenseInfo$ */ - - + +attribute vec3 position; +attribute vec4 diffuse_color; varying vec2 vary_fragcoord; @@ -15,9 +16,10 @@ uniform vec2 screen_res; void main() { //transform vertex - gl_Position = ftransform(); - vec4 pos = gl_ModelViewProjectionMatrix * gl_Vertex; + vec4 pos = gl_ModelViewProjectionMatrix * vec4(position.xyz, 1.0); + gl_Position = pos; + vary_fragcoord = (pos.xy * 0.5 + 0.5)*screen_res; - gl_FrontColor = gl_Color; + gl_FrontColor = diffuse_color; } diff --git a/indra/newview/app_settings/shaders/class1/deferred/multiPointLightV.glsl b/indra/newview/app_settings/shaders/class1/deferred/multiPointLightV.glsl index 434fb6f534..7db577c07a 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/multiPointLightV.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/multiPointLightV.glsl @@ -6,15 +6,17 @@ */ +attribute vec3 position; +attribute vec4 diffuse_color; varying vec4 vary_fragcoord; void main() { //transform vertex - vec4 pos = gl_ModelViewProjectionMatrix * gl_Vertex; + vec4 pos = gl_ModelViewProjectionMatrix * vec4(position.xyz, 1.0); vary_fragcoord = pos; gl_Position = pos; - gl_FrontColor = gl_Color; + gl_FrontColor = diffuse_color; } diff --git a/indra/newview/app_settings/shaders/class1/deferred/pointLightV.glsl b/indra/newview/app_settings/shaders/class1/deferred/pointLightV.glsl index c510d8ad77..ac3170d16d 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/pointLightV.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/pointLightV.glsl @@ -5,7 +5,9 @@ * $/LicenseInfo$ */ - +attribute vec3 position; +attribute vec4 diffuse_color; +attribute vec2 texcoord0; varying vec4 vary_light; varying vec4 vary_fragcoord; @@ -13,15 +15,15 @@ varying vec4 vary_fragcoord; void main() { //transform vertex - vec4 pos = gl_ModelViewProjectionMatrix * gl_Vertex; + vec4 pos = gl_ModelViewProjectionMatrix * vec4(position.xyz, 1.0); vary_fragcoord = pos; - vec4 tex = gl_MultiTexCoord0; + vec4 tex = vec4(texcoord0,0,1); tex.w = 1.0; - vary_light = gl_MultiTexCoord0; + vary_light = vec4(texcoord0,0,1); gl_Position = pos; - gl_FrontColor = gl_Color; + gl_FrontColor = diffuse_color; } diff --git a/indra/newview/app_settings/shaders/class1/deferred/postDeferredV.glsl b/indra/newview/app_settings/shaders/class1/deferred/postDeferredV.glsl index 876f65ee3a..30dbe3f75e 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/postDeferredV.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/postDeferredV.glsl @@ -5,7 +5,7 @@ * $/LicenseInfo$ */ - +attribute vec3 position; varying vec2 vary_fragcoord; uniform vec2 screen_res; @@ -13,7 +13,7 @@ uniform vec2 screen_res; void main() { //transform vertex - gl_Position = ftransform(); - vec4 pos = gl_ModelViewProjectionMatrix * gl_Vertex; + vec4 pos = gl_ModelViewProjectionMatrix * vec4(position.xyz, 1.0); + gl_Position = pos; vary_fragcoord = (pos.xy*0.5+0.5)*screen_res; } diff --git a/indra/newview/app_settings/shaders/class1/deferred/postgiV.glsl b/indra/newview/app_settings/shaders/class1/deferred/postgiV.glsl index eebe930666..38525044ba 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/postgiV.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/postgiV.glsl @@ -5,6 +5,7 @@ * $/LicenseInfo$ */ +attribute vec3 position; varying vec2 vary_fragcoord; @@ -13,7 +14,7 @@ uniform vec2 screen_res; void main() { //transform vertex - gl_Position = ftransform(); - vec4 pos = gl_ModelViewProjectionMatrix * gl_Vertex; + vec4 pos = gl_ModelViewProjectionMatrix * vec4(position.xyz, 1.0); + gl_Position = pos; vary_fragcoord = (pos.xy*0.5+0.5)*screen_res; } diff --git a/indra/newview/app_settings/shaders/class1/deferred/shadowAlphaMaskV.glsl b/indra/newview/app_settings/shaders/class1/deferred/shadowAlphaMaskV.glsl index 58e9bcec58..6bbbfdd8ee 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/shadowAlphaMaskV.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/shadowAlphaMaskV.glsl @@ -5,19 +5,21 @@ * $/LicenseInfo$ */ - +attribute vec3 position; +attribute vec4 diffuse_color; +attribute vec2 texcoord0; varying vec4 post_pos; void main() { //transform vertex - vec4 pos = gl_ModelViewProjectionMatrix*gl_Vertex; + vec4 pos = gl_ModelViewProjectionMatrix*vec4(position.xyz, 1.0); post_pos = pos; gl_Position = vec4(pos.x, pos.y, pos.w*0.5, pos.w); - gl_TexCoord[0] = gl_TextureMatrix[0] * gl_MultiTexCoord0; - gl_FrontColor = gl_Color; + gl_TexCoord[0] = gl_TextureMatrix[0] * vec4(texcoord0,0,1); + gl_FrontColor = diffuse_color; } diff --git a/indra/newview/app_settings/shaders/class1/deferred/shadowV.glsl b/indra/newview/app_settings/shaders/class1/deferred/shadowV.glsl index d40c2d9f78..7a8ac14f5e 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/shadowV.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/shadowV.glsl @@ -5,14 +5,14 @@ * $/LicenseInfo$ */ - +attribute vec3 position; varying vec4 post_pos; void main() { //transform vertex - vec4 pos = gl_ModelViewProjectionMatrix*gl_Vertex; + vec4 pos = gl_ModelViewProjectionMatrix*vec4(position.xyz, 1.0); post_pos = pos; diff --git a/indra/newview/app_settings/shaders/class1/deferred/skyV.glsl b/indra/newview/app_settings/shaders/class1/deferred/skyV.glsl index 1ea00f723a..8dfb466e88 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/skyV.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/skyV.glsl @@ -5,7 +5,8 @@ * $/LicenseInfo$ */ - +attribute vec3 position; +attribute vec2 texcoord0; // SKY //////////////////////////////////////////////////////////////////////// // The vertex shader for creating the atmospheric sky @@ -39,12 +40,12 @@ void main() { // World / view / projection - gl_Position = ftransform(); - gl_TexCoord[0] = gl_MultiTexCoord0; + gl_Position = gl_ModelViewProjectionMatrix * vec4(position.xyz, 1.0); + gl_TexCoord[0] = vec4(texcoord0,0,1); // Get relative position - vec3 P = gl_Vertex.xyz - camPosLocal.xyz + vec3(0,50,0); - //vec3 P = gl_Vertex.xyz + vec3(0,50,0); + vec3 P = position.xyz - camPosLocal.xyz + vec3(0,50,0); + //vec3 P = position.xyz + vec3(0,50,0); // Set altitude if (P.y > 0.) diff --git a/indra/newview/app_settings/shaders/class1/deferred/softenLightF.glsl b/indra/newview/app_settings/shaders/class1/deferred/softenLightF.glsl index d327216a0c..3ba5ee5bd2 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/softenLightF.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/softenLightF.glsl @@ -45,7 +45,7 @@ uniform vec3 env_mat[3]; //uniform vec4 shadow_clip; uniform mat3 ssao_effect_mat; -varying vec4 vary_light; +uniform vec3 sun_dir; varying vec2 vary_fragcoord; vec3 vary_PositionEye; @@ -265,7 +265,7 @@ void main() norm = vec3((norm.xy-0.5)*2.0,norm.z); // unpack norm //vec3 nz = texture2D(noiseMap, vary_fragcoord.xy/128.0).xyz; - float da = max(dot(norm.xyz, vary_light.xyz), 0.0); + float da = max(dot(norm.xyz, sun_dir.xyz), 0.0); vec4 diffuse = texture2DRect(diffuseRect, tc); vec4 spec = texture2DRect(specularRect, vary_fragcoord.xy); @@ -286,7 +286,7 @@ void main() // the old infinite-sky shiny reflection // vec3 refnormpersp = normalize(reflect(pos.xyz, norm.xyz)); - float sa = dot(refnormpersp, vary_light.xyz); + float sa = dot(refnormpersp, sun_dir.xyz); vec3 dumbshiny = vary_SunlitColor*texture2D(lightFunc, vec2(sa, spec.a)).a; // add the two types of shiny together diff --git a/indra/newview/app_settings/shaders/class1/deferred/softenLightV.glsl b/indra/newview/app_settings/shaders/class1/deferred/softenLightV.glsl index 745cc01992..5b3f655edf 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/softenLightV.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/softenLightV.glsl @@ -6,21 +6,16 @@ */ +attribute vec3 position; uniform vec2 screen_res; -varying vec4 vary_light; varying vec2 vary_fragcoord; void main() { //transform vertex - gl_Position = ftransform(); - - vec4 pos = gl_ModelViewProjectionMatrix * gl_Vertex; - vary_fragcoord = (pos.xy*0.5+0.5)*screen_res; + vec4 pos = gl_ModelViewProjectionMatrix * vec4(position.xyz, 1.0); + gl_Position = pos; - vec4 tex = gl_MultiTexCoord0; - tex.w = 1.0; - - vary_light = gl_MultiTexCoord0; + vary_fragcoord = (pos.xy*0.5+0.5)*screen_res; } diff --git a/indra/newview/app_settings/shaders/class1/deferred/starsV.glsl b/indra/newview/app_settings/shaders/class1/deferred/starsV.glsl index c43125dad9..7cdfe445df 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/starsV.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/starsV.glsl @@ -6,12 +6,14 @@ */ - +attribute vec3 position; +attribute vec4 diffuse_color; +attribute vec2 texcoord0; void main() { //transform vertex - gl_Position = gl_ModelViewProjectionMatrix * gl_Vertex; - gl_TexCoord[0] = gl_TextureMatrix[0] * gl_MultiTexCoord0; - gl_FrontColor = gl_Color; + gl_Position = gl_ModelViewProjectionMatrix * vec4(position.xyz, 1.0); + gl_TexCoord[0] = gl_TextureMatrix[0] * vec4(texcoord0,0,1); + gl_FrontColor = diffuse_color; } diff --git a/indra/newview/app_settings/shaders/class1/deferred/sunLightV.glsl b/indra/newview/app_settings/shaders/class1/deferred/sunLightV.glsl index 814deb3677..65fa288e88 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/sunLightV.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/sunLightV.glsl @@ -5,7 +5,10 @@ * $/LicenseInfo$ */ - +attribute vec3 position; +attribute vec3 normal; +attribute vec4 diffuse_color; +attribute vec2 texcoord0; varying vec4 vary_light; varying vec2 vary_fragcoord; @@ -15,13 +18,14 @@ uniform vec2 screen_res; void main() { //transform vertex - gl_Position = ftransform(); - vec4 pos = gl_ModelViewProjectionMatrix * gl_Vertex; + vec4 pos = gl_ModelViewProjectionMatrix * vec4(position.xyz, 1.0); + gl_Position = pos; + vary_fragcoord = (pos.xy * 0.5 + 0.5)*screen_res; - vec4 tex = gl_MultiTexCoord0; + vec4 tex = vec4(texcoord0,0,1); tex.w = 1.0; - vary_light = gl_MultiTexCoord0; + vary_light = vec4(texcoord0,0,1); - gl_FrontColor = gl_Color; + gl_FrontColor = diffuse_color; } diff --git a/indra/newview/app_settings/shaders/class1/deferred/terrainV.glsl b/indra/newview/app_settings/shaders/class1/deferred/terrainV.glsl index 3038fd2966..33b379d70c 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/terrainV.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/terrainV.glsl @@ -5,7 +5,11 @@ * $/LicenseInfo$ */ - +attribute vec3 position; +attribute vec3 normal; +attribute vec4 diffuse_color; +attribute vec2 texcoord0; +attribute vec2 texcoord1; varying vec3 vary_normal; @@ -26,14 +30,14 @@ vec4 texgen_object(vec4 vpos, vec4 tc, mat4 mat, vec4 tp0, vec4 tp1) void main() { //transform vertex - gl_Position = gl_ModelViewProjectionMatrix * gl_Vertex; + gl_Position = gl_ModelViewProjectionMatrix * vec4(position.xyz, 1.0); - vary_normal = normalize(gl_NormalMatrix * gl_Normal); + vary_normal = normalize(gl_NormalMatrix * normal); // Transform and pass tex coords - gl_TexCoord[0].xy = texgen_object(gl_Vertex, gl_MultiTexCoord0, gl_TextureMatrix[0], gl_ObjectPlaneS[0], gl_ObjectPlaneT[0]).xy; + gl_TexCoord[0].xy = texgen_object(vec4(position, 1.0), vec4(texcoord0,0,1), gl_TextureMatrix[0], gl_ObjectPlaneS[0], gl_ObjectPlaneT[0]).xy; - vec4 t = gl_MultiTexCoord1; + vec4 t = vec4(texcoord1,0,1); gl_TexCoord[0].zw = t.xy; gl_TexCoord[1].xy = t.xy-vec2(2.0, 0.0); diff --git a/indra/newview/app_settings/shaders/class1/deferred/treeV.glsl b/indra/newview/app_settings/shaders/class1/deferred/treeV.glsl index a9bef4292d..07e56e84db 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/treeV.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/treeV.glsl @@ -6,16 +6,20 @@ */ +attribute vec3 position; +attribute vec3 normal; +attribute vec2 texcoord0; + varying vec3 vary_normal; void main() { //transform vertex - gl_Position = ftransform(); - gl_TexCoord[0] = gl_TextureMatrix[0] * gl_MultiTexCoord0; + gl_Position = gl_ModelViewProjectionMatrix * vec4(position.xyz, 1.0); + gl_TexCoord[0] = gl_TextureMatrix[0] * vec4(texcoord0,0,1); - vary_normal = normalize(gl_NormalMatrix * gl_Normal); + vary_normal = normalize(gl_NormalMatrix * normal); - gl_FrontColor = gl_Color; + gl_FrontColor = vec4(1,1,1,1); } diff --git a/indra/newview/app_settings/shaders/class1/deferred/waterV.glsl b/indra/newview/app_settings/shaders/class1/deferred/waterV.glsl index 5397290b11..b5869e6cb2 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/waterV.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/waterV.glsl @@ -6,6 +6,8 @@ */ +attribute vec3 position; + void calcAtmospherics(vec3 inPositionEye); @@ -29,25 +31,25 @@ float wave(vec2 v, float t, float f, vec2 d, float s) void main() { //transform vertex - vec4 position = gl_Vertex; + vec4 pos = vec4(position.xyz, 1.0); mat4 modelViewProj = gl_ModelViewProjectionMatrix; vec4 oPosition; //get view vector vec3 oEyeVec; - oEyeVec.xyz = position.xyz-eyeVec; + oEyeVec.xyz = pos.xyz-eyeVec; float d = length(oEyeVec.xy); float ld = min(d, 2560.0); - position.xy = eyeVec.xy + oEyeVec.xy/d*ld; + pos.xy = eyeVec.xy + oEyeVec.xy/d*ld; view.xyz = oEyeVec; d = clamp(ld/1536.0-0.5, 0.0, 1.0); d *= d; - oPosition = position; + oPosition = vec4(position, 1.0); oPosition.z = mix(oPosition.z, max(eyeVec.z*0.75, 0.0), d); vary_position = gl_ModelViewMatrix * oPosition; oPosition = modelViewProj * oPosition; @@ -55,17 +57,16 @@ void main() refCoord.xyz = oPosition.xyz + vec3(0,0,0.2); //get wave position parameter (create sweeping horizontal waves) - vec3 v = position.xyz; + vec3 v = pos.xyz; v.x += (cos(v.x*0.08/*+time*0.01*/)+sin(v.y*0.02))*6.0; //push position for further horizon effect. - position.xyz = oEyeVec.xyz*(waterHeight/oEyeVec.z); - position.w = 1.0; - position = position*gl_ModelViewMatrix; - - calcAtmospherics((gl_ModelViewMatrix * gl_Vertex).xyz); - + pos.xyz = oEyeVec.xyz*(waterHeight/oEyeVec.z); + pos.w = 1.0; + pos = gl_ModelViewMatrix*pos; + calcAtmospherics(pos.xyz); + //pass wave parameters to pixel shader vec2 bigWave = (v.xy) * vec2(0.04,0.04) + d1 * time * 0.055; //get two normal map (detail map) texture coordinates -- cgit v1.2.3 From 2ee815478043c4d5845f094f744a055707dba0e0 Mon Sep 17 00:00:00 2001 From: Dave Parks Date: Wed, 10 Aug 2011 13:01:14 -0500 Subject: SH-2238, SH-2223, SH-SH-2242 glVertexAttrib throughout main render pipeline complete, preview renders and debug displays still pending. Also fixed a render glitch and a crash (JIRAs listed). --- .../class1/deferred/alphaNonIndexedNoColorF.glsl | 63 ++++++++++++++++++++++ .../shaders/class1/deferred/avatarAlphaV.glsl | 13 ++--- .../shaders/class1/deferred/avatarF.glsl | 2 +- .../shaders/class1/deferred/avatarShadowF.glsl | 1 - .../shaders/class1/deferred/avatarShadowV.glsl | 4 -- .../shaders/class1/deferred/avatarV.glsl | 3 -- .../shaders/class1/deferred/diffuseAlphaMaskF.glsl | 4 +- .../class1/deferred/diffuseAlphaMaskNoColorF.glsl | 30 +++++++++++ .../shaders/class1/deferred/diffuseNoColorV.glsl | 23 ++++++++ .../shaders/class1/deferred/emissiveF.glsl | 28 ++++++++++ .../shaders/class1/deferred/emissiveV.glsl | 38 +++++++++++++ .../shaders/class1/deferred/multiPointLightV.glsl | 2 - .../shaders/class1/deferred/multiSpotLightF.glsl | 23 ++++---- .../shaders/class1/deferred/pointLightF.glsl | 15 +++--- .../shaders/class1/deferred/pointLightV.glsl | 10 ---- .../shaders/class1/deferred/softenLightF.glsl | 1 + .../shaders/class1/deferred/spotLightF.glsl | 18 ++++--- .../shaders/class1/deferred/sunLightSSAOF.glsl | 1 - .../shaders/class1/deferred/sunLightV.glsl | 10 ---- .../shaders/class1/deferred/treeF.glsl | 10 +++- .../shaders/class1/deferred/treeShadowF.glsl | 27 ++++++++++ .../shaders/class1/deferred/treeShadowV.glsl | 23 ++++++++ .../shaders/class1/deferred/treeV.glsl | 1 - 23 files changed, 282 insertions(+), 68 deletions(-) create mode 100644 indra/newview/app_settings/shaders/class1/deferred/alphaNonIndexedNoColorF.glsl create mode 100644 indra/newview/app_settings/shaders/class1/deferred/diffuseAlphaMaskNoColorF.glsl create mode 100644 indra/newview/app_settings/shaders/class1/deferred/diffuseNoColorV.glsl create mode 100644 indra/newview/app_settings/shaders/class1/deferred/emissiveF.glsl create mode 100644 indra/newview/app_settings/shaders/class1/deferred/emissiveV.glsl create mode 100644 indra/newview/app_settings/shaders/class1/deferred/treeShadowF.glsl create mode 100644 indra/newview/app_settings/shaders/class1/deferred/treeShadowV.glsl (limited to 'indra/newview/app_settings/shaders/class1/deferred') diff --git a/indra/newview/app_settings/shaders/class1/deferred/alphaNonIndexedNoColorF.glsl b/indra/newview/app_settings/shaders/class1/deferred/alphaNonIndexedNoColorF.glsl new file mode 100644 index 0000000000..5d1306bfc9 --- /dev/null +++ b/indra/newview/app_settings/shaders/class1/deferred/alphaNonIndexedNoColorF.glsl @@ -0,0 +1,63 @@ +/** + * @file alphaNonIndexedNoColorF.glsl + * + * $LicenseInfo:firstyear=2007&license=viewerlgpl$ + * $/LicenseInfo$ + */ + + + +#extension GL_ARB_texture_rectangle : enable + +uniform sampler2DRect depthMap; +uniform sampler2D diffuseMap; + +uniform mat4 shadow_matrix[6]; +uniform vec4 shadow_clip; +uniform vec2 screen_res; + +vec3 atmosLighting(vec3 light); +vec3 scaleSoftClip(vec3 light); + +varying vec3 vary_ambient; +varying vec3 vary_directional; +varying vec3 vary_fragcoord; +varying vec3 vary_position; +varying vec3 vary_pointlight_col; + +uniform mat4 inv_proj; + +vec4 getPosition(vec2 pos_screen) +{ + float depth = texture2DRect(depthMap, pos_screen.xy).a; + vec2 sc = pos_screen.xy*2.0; + sc /= screen_res; + sc -= vec2(1.0,1.0); + vec4 ndc = vec4(sc.x, sc.y, 2.0*depth-1.0, 1.0); + vec4 pos = inv_proj * ndc; + pos /= pos.w; + pos.w = 1.0; + return pos; +} + +void main() +{ + vec2 frag = vary_fragcoord.xy/vary_fragcoord.z*0.5+0.5; + frag *= screen_res; + + vec4 pos = vec4(vary_position, 1.0); + + vec4 diff= texture2D(diffuseMap,gl_TexCoord[0].xy); + + vec4 col = vec4(vary_ambient + vary_directional.rgb, 1.0); + vec4 color = diff * col; + + color.rgb = atmosLighting(color.rgb); + + color.rgb = scaleSoftClip(color.rgb); + + color.rgb += diff.rgb * vary_pointlight_col.rgb; + + gl_FragColor = color; +} + diff --git a/indra/newview/app_settings/shaders/class1/deferred/avatarAlphaV.glsl b/indra/newview/app_settings/shaders/class1/deferred/avatarAlphaV.glsl index 842931ec17..468d7332a6 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/avatarAlphaV.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/avatarAlphaV.glsl @@ -7,7 +7,6 @@ attribute vec3 position; attribute vec3 normal; -attribute vec4 diffuse_color; attribute vec2 texcoord0; vec4 calcLighting(vec3 pos, vec3 norm, vec4 color, vec4 baseCol); @@ -86,9 +85,7 @@ void main() calcAtmospherics(pos.xyz); - //vec4 color = calcLighting(pos.xyz, norm, diffuse_color, vec4(0.)); - - vec4 col = vec4(0.0, 0.0, 0.0, diffuse_color.a); + vec4 col = vec4(0.0, 0.0, 0.0, 1.0); // Collect normal lights col.rgb += gl_LightSource[2].diffuse.rgb*calcPointLightOrSpotLight(pos.xyz, norm, gl_LightSource[2].position, gl_LightSource[2].spotDirection.xyz, gl_LightSource[2].linearAttenuation, gl_LightSource[2].quadraticAttenuation, gl_LightSource[2].specular.a); @@ -98,17 +95,17 @@ void main() col.rgb += gl_LightSource[6].diffuse.rgb*calcPointLightOrSpotLight(pos.xyz, norm, gl_LightSource[6].position, gl_LightSource[6].spotDirection.xyz, gl_LightSource[6].linearAttenuation, gl_LightSource[6].quadraticAttenuation, gl_LightSource[6].specular.a); col.rgb += gl_LightSource[7].diffuse.rgb*calcPointLightOrSpotLight(pos.xyz, norm, gl_LightSource[7].position, gl_LightSource[7].spotDirection.xyz, gl_LightSource[7].linearAttenuation, gl_LightSource[7].quadraticAttenuation, gl_LightSource[7].specular.a); - vary_pointlight_col = col.rgb*diffuse_color.rgb; + vary_pointlight_col = col.rgb; col.rgb = vec3(0,0,0); // Add windlight lights col.rgb = atmosAmbient(vec3(0.)); - vary_ambient = col.rgb*diffuse_color.rgb; - vary_directional = diffuse_color.rgb*atmosAffectDirectionalLight(max(calcDirectionalLight(norm, gl_LightSource[0].position.xyz), (1.0-diffuse_color.a)*(1.0-diffuse_color.a))); + vary_ambient = col.rgb; + vary_directional = atmosAffectDirectionalLight(max(calcDirectionalLight(norm, gl_LightSource[0].position.xyz), 0.0)); - col.rgb = min(col.rgb*diffuse_color.rgb, 1.0); + col.rgb = min(col.rgb, 1.0); gl_FrontColor = col; diff --git a/indra/newview/app_settings/shaders/class1/deferred/avatarF.glsl b/indra/newview/app_settings/shaders/class1/deferred/avatarF.glsl index 3268618093..d8e8f6088d 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/avatarF.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/avatarF.glsl @@ -13,7 +13,7 @@ varying vec3 vary_normal; void main() { - vec4 diff = gl_Color*texture2D(diffuseMap, gl_TexCoord[0].xy); + vec4 diff = texture2D(diffuseMap, gl_TexCoord[0].xy); if (diff.a < 0.2) { diff --git a/indra/newview/app_settings/shaders/class1/deferred/avatarShadowF.glsl b/indra/newview/app_settings/shaders/class1/deferred/avatarShadowF.glsl index 78986ab12e..c693725074 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/avatarShadowF.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/avatarShadowF.glsl @@ -13,7 +13,6 @@ varying vec4 post_pos; void main() { - //gl_FragColor = vec4(1,1,1,gl_Color.a * texture2D(diffuseMap, gl_TexCoord[0].xy).a); gl_FragColor = vec4(1,1,1,1); gl_FragDepth = max(post_pos.z/post_pos.w*0.5+0.5, 0.0); diff --git a/indra/newview/app_settings/shaders/class1/deferred/avatarShadowV.glsl b/indra/newview/app_settings/shaders/class1/deferred/avatarShadowV.glsl index cf6fc1c0ed..35d0bb5603 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/avatarShadowV.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/avatarShadowV.glsl @@ -11,10 +11,8 @@ mat4 getSkinnedTransform(); attribute vec3 position; attribute vec3 normal; -attribute vec4 diffuse_color; attribute vec2 texcoord0; - varying vec4 post_pos; void main() @@ -40,8 +38,6 @@ void main() post_pos = pos; gl_Position = vec4(pos.x, pos.y, pos.w*0.5, pos.w); - - gl_FrontColor = diffuse_color; } diff --git a/indra/newview/app_settings/shaders/class1/deferred/avatarV.glsl b/indra/newview/app_settings/shaders/class1/deferred/avatarV.glsl index e66f8c8483..9ef11109ed 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/avatarV.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/avatarV.glsl @@ -6,7 +6,6 @@ */ attribute vec3 position; -attribute vec4 diffuse_color; attribute vec3 normal; attribute vec2 texcoord0; @@ -38,8 +37,6 @@ void main() vary_normal = norm; gl_Position = gl_ProjectionMatrix * pos; - - gl_FrontColor = diffuse_color; } diff --git a/indra/newview/app_settings/shaders/class1/deferred/diffuseAlphaMaskF.glsl b/indra/newview/app_settings/shaders/class1/deferred/diffuseAlphaMaskF.glsl index 338d0ebb2b..26355731ae 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/diffuseAlphaMaskF.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/diffuseAlphaMaskF.glsl @@ -1,5 +1,5 @@ /** - * @file diffuseF.glsl + * @file diffuseAlphaMaskF.glsl * * $LicenseInfo:firstyear=2007&license=viewerlgpl$ * $/LicenseInfo$ @@ -15,7 +15,7 @@ varying vec3 vary_normal; void main() { - vec4 col = gl_Color * texture2D(diffuseMap, gl_TexCoord[0].xy) * gl_Color; + vec4 col = texture2D(diffuseMap, gl_TexCoord[0].xy) * gl_Color; if (col.a < minimum_alpha || col.a > maximum_alpha) { diff --git a/indra/newview/app_settings/shaders/class1/deferred/diffuseAlphaMaskNoColorF.glsl b/indra/newview/app_settings/shaders/class1/deferred/diffuseAlphaMaskNoColorF.glsl new file mode 100644 index 0000000000..dfc1b52c2e --- /dev/null +++ b/indra/newview/app_settings/shaders/class1/deferred/diffuseAlphaMaskNoColorF.glsl @@ -0,0 +1,30 @@ +/** + * @file diffuseAlphaMaskNoColorF.glsl + * + * $LicenseInfo:firstyear=2007&license=viewerlgpl$ + * $/LicenseInfo$ + */ + + +uniform float minimum_alpha; +uniform float maximum_alpha; + +uniform sampler2D diffuseMap; + +varying vec3 vary_normal; + +void main() +{ + vec4 col = texture2D(diffuseMap, gl_TexCoord[0].xy); + + if (col.a < minimum_alpha || col.a > maximum_alpha) + { + discard; + } + + gl_FragData[0] = vec4(col.rgb, 0.0); + gl_FragData[1] = vec4(0,0,0,0); // spec + vec3 nvn = normalize(vary_normal); + gl_FragData[2] = vec4(nvn.xy * 0.5 + 0.5, nvn.z, 0.0); +} + diff --git a/indra/newview/app_settings/shaders/class1/deferred/diffuseNoColorV.glsl b/indra/newview/app_settings/shaders/class1/deferred/diffuseNoColorV.glsl new file mode 100644 index 0000000000..ff9578e253 --- /dev/null +++ b/indra/newview/app_settings/shaders/class1/deferred/diffuseNoColorV.glsl @@ -0,0 +1,23 @@ +/** + * @file diffuseNoColorV.glsl + * + * $LicenseInfo:firstyear=2007&license=viewerlgpl$ + * $/LicenseInfo$ + */ + + +attribute vec3 position; +attribute vec3 normal; +attribute vec2 texcoord0; + +varying vec3 vary_normal; +varying float vary_texture_index; + +void main() +{ + //transform vertex + gl_Position = gl_ModelViewProjectionMatrix * vec4(position.xyz, 1.0); + gl_TexCoord[0] = gl_TextureMatrix[0] * vec4(texcoord0,0,1); + + vary_normal = normalize(gl_NormalMatrix * normal); +} diff --git a/indra/newview/app_settings/shaders/class1/deferred/emissiveF.glsl b/indra/newview/app_settings/shaders/class1/deferred/emissiveF.glsl new file mode 100644 index 0000000000..5a9a6196f3 --- /dev/null +++ b/indra/newview/app_settings/shaders/class1/deferred/emissiveF.glsl @@ -0,0 +1,28 @@ +/** + * @file emissiveF.glsl + * + * $LicenseInfo:firstyear=2007&license=viewerlgpl$ + * $/LicenseInfo$ + */ + + + +#extension GL_ARB_texture_rectangle : enable + +vec3 fullbrightAtmosTransport(vec3 light); +vec3 fullbrightScaleSoftClip(vec3 light); + + +void main() +{ + float shadow = 1.0; + + vec4 color = diffuseLookup(gl_TexCoord[0].xy)*gl_Color; + + color.rgb = fullbrightAtmosTransport(color.rgb); + + color.rgb = fullbrightScaleSoftClip(color.rgb); + + gl_FragColor = color; +} + diff --git a/indra/newview/app_settings/shaders/class1/deferred/emissiveV.glsl b/indra/newview/app_settings/shaders/class1/deferred/emissiveV.glsl new file mode 100644 index 0000000000..9841943fe6 --- /dev/null +++ b/indra/newview/app_settings/shaders/class1/deferred/emissiveV.glsl @@ -0,0 +1,38 @@ +/** + * @file emissiveV.glsl + * + * $LicenseInfo:firstyear=2007&license=viewerlgpl$ + * $/LicenseInfo$ + */ + + +attribute vec4 position; +attribute float emissive; +attribute vec2 texcoord0; + +void calcAtmospherics(vec3 inPositionEye); + +vec3 atmosAmbient(vec3 light); +vec3 atmosAffectDirectionalLight(float lightIntensity); +vec3 scaleDownLight(vec3 light); +vec3 scaleUpLight(vec3 light); + +varying float vary_texture_index; + +void main() +{ + //transform vertex + vec4 vert = vec4(position.xyz, 1.0); + vec4 pos = (gl_ModelViewMatrix * vert); + vary_texture_index = position.w; + + gl_Position = gl_ModelViewProjectionMatrix*vec4(position.xyz, 1.0); + + gl_TexCoord[0] = gl_TextureMatrix[0] * vec4(texcoord0,0,1); + + calcAtmospherics(pos.xyz); + + gl_FrontColor = vec4(0,0,0,emissive); + + gl_FogFragCoord = pos.z; +} diff --git a/indra/newview/app_settings/shaders/class1/deferred/multiPointLightV.glsl b/indra/newview/app_settings/shaders/class1/deferred/multiPointLightV.glsl index 7db577c07a..bb0497b309 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/multiPointLightV.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/multiPointLightV.glsl @@ -7,7 +7,6 @@ attribute vec3 position; -attribute vec4 diffuse_color; varying vec4 vary_fragcoord; @@ -18,5 +17,4 @@ void main() vary_fragcoord = pos; gl_Position = pos; - gl_FrontColor = diffuse_color; } diff --git a/indra/newview/app_settings/shaders/class1/deferred/multiSpotLightF.glsl b/indra/newview/app_settings/shaders/class1/deferred/multiSpotLightF.glsl index 0d25d7792d..6c08f7b51f 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/multiSpotLightF.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/multiSpotLightF.glsl @@ -37,7 +37,10 @@ uniform float sun_wash; uniform int proj_shadow_idx; uniform float shadow_fade; -varying vec4 vary_light; +uniform vec3 center; +uniform vec3 color; +uniform float falloff; +uniform float size; varying vec4 vary_fragcoord; uniform vec2 screen_res; @@ -92,7 +95,7 @@ vec4 texture2DLodAmbient(sampler2D projectionMap, vec2 tc, float lod) vec4 getPosition(vec2 pos_screen) { - float depth = texture2DRect(depthMap, pos_screen.xy).a; + float depth = texture2DRect(depthMap, pos_screen.xy).r; vec2 sc = pos_screen.xy*2.0; sc /= screen_res; sc -= vec2(1.0,1.0); @@ -111,9 +114,9 @@ void main() frag.xy *= screen_res; vec3 pos = getPosition(frag.xy).xyz; - vec3 lv = vary_light.xyz-pos.xyz; + vec3 lv = center.xyz-pos.xyz; float dist2 = dot(lv,lv); - dist2 /= vary_light.w; + dist2 /= size; if (dist2 > 1.0) { discard; @@ -127,16 +130,16 @@ void main() vec4 proj_tc = (proj_mat * vec4(pos.xyz, 1.0)); if (proj_tc.z < 0.0) { - discard; + //discard; } proj_tc.xyz /= proj_tc.w; - float fa = gl_Color.a+1.0; + float fa = falloff+1.0; float dist_atten = min(1.0-(dist2-1.0*(1.0-fa))/fa, 1.0); if (dist_atten <= 0.0) { - discard; + //discard; } lv = proj_origin-pos.xyz; @@ -164,7 +167,7 @@ void main() vec4 plcol = texture2DLodDiffuse(projectionMap, proj_tc.xy, lod); - vec3 lcol = gl_Color.rgb * plcol.rgb * plcol.a; + vec3 lcol = color.rgb * plcol.rgb * plcol.a; lit = da * dist_atten * noise; @@ -181,7 +184,7 @@ void main() amb_da = min(amb_da, 1.0-lit); - col += amb_da*gl_Color.rgb*diff_tex.rgb*amb_plcol.rgb*amb_plcol.a; + col += amb_da*color.rgb*diff_tex.rgb*amb_plcol.rgb*amb_plcol.a; } @@ -214,7 +217,7 @@ void main() stc.y > 0.0) { vec4 scol = texture2DLodSpecular(projectionMap, stc.xy, proj_lod-spec.a*proj_lod); - col += dist_atten*scol.rgb*gl_Color.rgb*scol.a*spec.rgb; + col += dist_atten*scol.rgb*color.rgb*scol.a*spec.rgb; } } } diff --git a/indra/newview/app_settings/shaders/class1/deferred/pointLightF.glsl b/indra/newview/app_settings/shaders/class1/deferred/pointLightF.glsl index 5efa3200d4..601bb17bc7 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/pointLightF.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/pointLightF.glsl @@ -20,7 +20,10 @@ uniform sampler2DRect depthMap; uniform vec3 env_mat[3]; uniform float sun_wash; -varying vec4 vary_light; +uniform vec3 center; +uniform vec3 color; +uniform float falloff; +uniform float size; varying vec4 vary_fragcoord; uniform vec2 screen_res; @@ -49,9 +52,9 @@ void main() frag.xy *= screen_res; vec3 pos = getPosition(frag.xy).xyz; - vec3 lv = vary_light.xyz-pos; + vec3 lv = center.xyz-pos; float dist2 = dot(lv,lv); - dist2 /= vary_light.w; + dist2 /= size; if (dist2 > 1.0) { discard; @@ -72,11 +75,11 @@ void main() float noise = texture2D(noiseMap, frag.xy/128.0).b; vec3 col = texture2DRect(diffuseRect, frag.xy).rgb; - float fa = gl_Color.a+1.0; + float fa = falloff+1.0; float dist_atten = clamp(1.0-(dist2-1.0*(1.0-fa))/fa, 0.0, 1.0); float lit = da * dist_atten * noise; - col = gl_Color.rgb*lit*col; + col = color.rgb*lit*col; vec4 spec = texture2DRect(specularRect, frag.xy); if (spec.a > 0.0) @@ -86,7 +89,7 @@ void main() { sa = texture2D(lightFunc, vec2(sa, spec.a)).a * min(dist_atten*4.0, 1.0); sa *= noise; - col += da*sa*gl_Color.rgb*spec.rgb; + col += da*sa*color.rgb*spec.rgb; } } diff --git a/indra/newview/app_settings/shaders/class1/deferred/pointLightV.glsl b/indra/newview/app_settings/shaders/class1/deferred/pointLightV.glsl index ac3170d16d..a09cfa2661 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/pointLightV.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/pointLightV.glsl @@ -6,10 +6,7 @@ */ attribute vec3 position; -attribute vec4 diffuse_color; -attribute vec2 texcoord0; -varying vec4 vary_light; varying vec4 vary_fragcoord; void main() @@ -18,12 +15,5 @@ void main() vec4 pos = gl_ModelViewProjectionMatrix * vec4(position.xyz, 1.0); vary_fragcoord = pos; - vec4 tex = vec4(texcoord0,0,1); - tex.w = 1.0; - - vary_light = vec4(texcoord0,0,1); - gl_Position = pos; - - gl_FrontColor = diffuse_color; } diff --git a/indra/newview/app_settings/shaders/class1/deferred/softenLightF.glsl b/indra/newview/app_settings/shaders/class1/deferred/softenLightF.glsl index 3ba5ee5bd2..35ab77d3cc 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/softenLightF.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/softenLightF.glsl @@ -306,5 +306,6 @@ void main() } gl_FragColor.rgb = col; + gl_FragColor.a = bloom; } diff --git a/indra/newview/app_settings/shaders/class1/deferred/spotLightF.glsl b/indra/newview/app_settings/shaders/class1/deferred/spotLightF.glsl index 9aaffc15bf..ed67dc32d5 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/spotLightF.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/spotLightF.glsl @@ -13,7 +13,6 @@ uniform sampler2DRect diffuseRect; uniform sampler2DRect specularRect; uniform sampler2DRect depthMap; uniform sampler2DRect normalMap; -uniform samplerCube environmentMap; uniform sampler2D noiseMap; uniform sampler2D lightFunc; uniform sampler2D projectionMap; @@ -32,7 +31,10 @@ uniform float far_clip; uniform vec3 proj_origin; //origin of projection to be used for angular attenuation uniform float sun_wash; -varying vec4 vary_light; +uniform vec3 center; +uniform vec3 color; +uniform float falloff; +uniform float size; varying vec4 vary_fragcoord; uniform vec2 screen_res; @@ -60,9 +62,9 @@ void main() frag.xy *= screen_res; vec3 pos = getPosition(frag.xy).xyz; - vec3 lv = vary_light.xyz-pos.xyz; + vec3 lv = center.xyz-pos.xyz; float dist2 = dot(lv,lv); - dist2 /= vary_light.w; + dist2 /= size; if (dist2 > 1.0) { discard; @@ -82,7 +84,7 @@ void main() proj_tc.xyz /= proj_tc.w; - float fa = gl_Color.a+1.0; + float fa = falloff+1.0; float dist_atten = clamp(1.0-(dist2-1.0*(1.0-fa))/fa, 0.0, 1.0); lv = proj_origin-pos.xyz; @@ -108,7 +110,7 @@ void main() vec4 plcol = texture2DLod(projectionMap, proj_tc.xy, lod); - vec3 lcol = gl_Color.rgb * plcol.rgb * plcol.a; + vec3 lcol = color.rgb * plcol.rgb * plcol.a; lit = da * dist_atten * noise; @@ -127,7 +129,7 @@ void main() amb_da = min(amb_da, 1.0-lit); - col += amb_da*gl_Color.rgb*diff_tex.rgb*amb_plcol.rgb*amb_plcol.a; + col += amb_da*color.rgb*diff_tex.rgb*amb_plcol.rgb*amb_plcol.a; } @@ -156,7 +158,7 @@ void main() stc.y > 0.0) { vec4 scol = texture2DLod(projectionMap, stc.xy, proj_lod-spec.a*proj_lod); - col += dist_atten*scol.rgb*gl_Color.rgb*scol.a*spec.rgb; + col += dist_atten*scol.rgb*color.rgb*scol.a*spec.rgb; } } } diff --git a/indra/newview/app_settings/shaders/class1/deferred/sunLightSSAOF.glsl b/indra/newview/app_settings/shaders/class1/deferred/sunLightSSAOF.glsl index 665d8126a0..6bbf86177a 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/sunLightSSAOF.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/sunLightSSAOF.glsl @@ -25,7 +25,6 @@ uniform float ssao_factor; uniform float ssao_factor_inv; varying vec2 vary_fragcoord; -varying vec4 vary_light; uniform mat4 inv_proj; uniform vec2 screen_res; diff --git a/indra/newview/app_settings/shaders/class1/deferred/sunLightV.glsl b/indra/newview/app_settings/shaders/class1/deferred/sunLightV.glsl index 65fa288e88..d39bfef4ae 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/sunLightV.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/sunLightV.glsl @@ -6,11 +6,7 @@ */ attribute vec3 position; -attribute vec3 normal; -attribute vec4 diffuse_color; -attribute vec2 texcoord0; -varying vec4 vary_light; varying vec2 vary_fragcoord; uniform vec2 screen_res; @@ -22,10 +18,4 @@ void main() gl_Position = pos; vary_fragcoord = (pos.xy * 0.5 + 0.5)*screen_res; - vec4 tex = vec4(texcoord0,0,1); - tex.w = 1.0; - - vary_light = vec4(texcoord0,0,1); - - gl_FrontColor = diffuse_color; } diff --git a/indra/newview/app_settings/shaders/class1/deferred/treeF.glsl b/indra/newview/app_settings/shaders/class1/deferred/treeF.glsl index de7e038402..08a3bc251a 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/treeF.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/treeF.glsl @@ -11,10 +11,18 @@ uniform sampler2D diffuseMap; varying vec3 vary_normal; +uniform float minimum_alpha; +uniform float maximum_alpha; + void main() { vec4 col = texture2D(diffuseMap, gl_TexCoord[0].xy); - gl_FragData[0] = vec4(gl_Color.rgb*col.rgb, col.a <= 0.5 ? 0.0 : 0.005); + if (col.a < minimum_alpha || col.a > maximum_alpha) + { + discard; + } + + gl_FragData[0] = vec4(gl_Color.rgb*col.rgb, 0.0); gl_FragData[1] = vec4(0,0,0,0); vec3 nvn = normalize(vary_normal); gl_FragData[2] = vec4(nvn.xy * 0.5 + 0.5, nvn.z, 0.0); diff --git a/indra/newview/app_settings/shaders/class1/deferred/treeShadowF.glsl b/indra/newview/app_settings/shaders/class1/deferred/treeShadowF.glsl new file mode 100644 index 0000000000..9f0b902c96 --- /dev/null +++ b/indra/newview/app_settings/shaders/class1/deferred/treeShadowF.glsl @@ -0,0 +1,27 @@ +/** + * @file treeShadowF.glsl + * + * $LicenseInfo:firstyear=2007&license=viewerlgpl$ + * $/LicenseInfo$ + */ + +uniform float minimum_alpha; +uniform float maximum_alpha; + +uniform sampler2D diffuseMap; + +varying vec4 post_pos; + +void main() +{ + float alpha = texture2D(diffuseMap, gl_TexCoord[0].xy).a; + + if (alpha < minimum_alpha || alpha > maximum_alpha) + { + discard; + } + + gl_FragColor = vec4(1,1,1,1); + + gl_FragDepth = max(post_pos.z/post_pos.w*0.5+0.5, 0.0); +} diff --git a/indra/newview/app_settings/shaders/class1/deferred/treeShadowV.glsl b/indra/newview/app_settings/shaders/class1/deferred/treeShadowV.glsl new file mode 100644 index 0000000000..42ce2f5226 --- /dev/null +++ b/indra/newview/app_settings/shaders/class1/deferred/treeShadowV.glsl @@ -0,0 +1,23 @@ +/** + * @file treeShadowV.glsl + * + * $LicenseInfo:firstyear=2007&license=viewerlgpl$ + * $/LicenseInfo$ + */ + +attribute vec3 position; +attribute vec2 texcoord0; + +varying vec4 post_pos; + +void main() +{ + //transform vertex + vec4 pos = gl_ModelViewProjectionMatrix*vec4(position.xyz, 1.0); + + post_pos = pos; + + gl_Position = vec4(pos.x, pos.y, pos.w*0.5, pos.w); + + gl_TexCoord[0] = gl_TextureMatrix[0] * vec4(texcoord0,0,1); +} diff --git a/indra/newview/app_settings/shaders/class1/deferred/treeV.glsl b/indra/newview/app_settings/shaders/class1/deferred/treeV.glsl index 07e56e84db..f56f389348 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/treeV.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/treeV.glsl @@ -10,7 +10,6 @@ attribute vec3 position; attribute vec3 normal; attribute vec2 texcoord0; - varying vec3 vary_normal; void main() -- cgit v1.2.3 From 2dd8ce53e4e0d14f2bc20796eb6bdf1ef12a65df Mon Sep 17 00:00:00 2001 From: Dave Parks Date: Thu, 11 Aug 2011 14:19:58 -0500 Subject: SH-2242 FXAA support instead of unreliable multisample textures (done here because it's a smaller change than integrating glVertexAttrib with FSAA pipe). Shader integration with LLDynamicTexture subclasses. --- .../class1/deferred/postDeferredNoDoFF.glsl | 2086 +++++++++++++++++++- .../shaders/class1/deferred/postDeferredV.glsl | 5 + 2 files changed, 2084 insertions(+), 7 deletions(-) (limited to 'indra/newview/app_settings/shaders/class1/deferred') diff --git a/indra/newview/app_settings/shaders/class1/deferred/postDeferredNoDoFF.glsl b/indra/newview/app_settings/shaders/class1/deferred/postDeferredNoDoFF.glsl index bf829bfc56..4c531ed20b 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/postDeferredNoDoFF.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/postDeferredNoDoFF.glsl @@ -1,24 +1,2096 @@ /** - * @file postDeferredF.glsl + * @file postDeferredNoDoFF.glsl * * $LicenseInfo:firstyear=2007&license=viewerlgpl$ * $/LicenseInfo$ */ +#extension GL_ARB_texture_rectangle : enable +#define FXAA_PC 1 +#define FXAA_GLSL_130 1 +#define FXAA_QUALITY__PRESET 12 -#extension GL_ARB_texture_rectangle : enable +/*============================================================================ + + + 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 -uniform sampler2DRect diffuseRect; -uniform sampler2D bloomMap; +/*============================================================================ + 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; } +#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 * 0.5 + rgbyA; +/*--------------------------------------------------------------------------*/ + float4 rgbyR = ((rgbyB.w - lumaMax) > 0.0) ? rgbyA : rgbyB; + rgbyR = ((rgbyB.w - 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 + +uniform sampler2D diffuseMap; + +uniform vec2 rcp_screen_res; +uniform vec4 rcp_frame_opt; +uniform vec4 rcp_frame_opt2; uniform vec2 screen_res; varying vec2 vary_fragcoord; +varying vec2 vary_tc; void main() { - vec4 diff = texture2DRect(diffuseRect, vary_fragcoord.xy); + vec4 diff = FxaaPixelShader(vary_tc, //pos + vec4(vary_fragcoord.xy, 0, 0), //fxaaConsolePosPos + diffuseMap, //tex + diffuseMap, + diffuseMap, + rcp_screen_res, //fxaaQualityRcpFrame + vec4(0,0,0,0), //fxaaConsoleRcpFrameOpt + rcp_frame_opt, //fxaaConsoleRcpFrameOpt2 + rcp_frame_opt2, //fxaaConsole360RcpFrameOpt2 + 0.75, //fxaaQualitySubpix + 0.166, //fxaaQualityEdgeThreshold + 0.0833, //fxaaQualityEdgeThresholdMin + 8.0, //fxaaConsoleEdgeSharpness + 0.125, //fxaaConsoleEdgeThreshold + 0.05, //fxaaConsoleEdgeThresholdMin + vec4(0,0,0,0)); //fxaaConsole360ConstDir + + + + //diff = texture2D(diffuseMap, vary_tc); + + gl_FragColor = diff; - vec4 bloom = texture2D(bloomMap, vary_fragcoord.xy/screen_res); - gl_FragColor = diff + bloom; } diff --git a/indra/newview/app_settings/shaders/class1/deferred/postDeferredV.glsl b/indra/newview/app_settings/shaders/class1/deferred/postDeferredV.glsl index 30dbe3f75e..c327011184 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/postDeferredV.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/postDeferredV.glsl @@ -8,6 +8,10 @@ attribute vec3 position; varying vec2 vary_fragcoord; +varying vec2 vary_tc; + +uniform vec2 tc_scale; + uniform vec2 screen_res; void main() @@ -15,5 +19,6 @@ void main() //transform vertex vec4 pos = gl_ModelViewProjectionMatrix * vec4(position.xyz, 1.0); gl_Position = pos; + vary_tc = (pos.xy*0.5+0.5)*tc_scale; vary_fragcoord = (pos.xy*0.5+0.5)*screen_res; } -- cgit v1.2.3 From ee4fdd2c18c722164d78a7305777fad6e49cba8b Mon Sep 17 00:00:00 2001 From: Dave Parks Date: Sun, 21 Aug 2011 16:23:04 -0500 Subject: SH-2242 Work in progress on FXAA/glVertexAttrib -- DoF works, physics shape display still doesn't. --- .../shaders/class1/deferred/postDeferredF.glsl | 2099 +++++++++++++++++++- 1 file changed, 2087 insertions(+), 12 deletions(-) (limited to 'indra/newview/app_settings/shaders/class1/deferred') diff --git a/indra/newview/app_settings/shaders/class1/deferred/postDeferredF.glsl b/indra/newview/app_settings/shaders/class1/deferred/postDeferredF.glsl index 29f5f899ba..cfcd8585f1 100644 --- a/indra/newview/app_settings/shaders/class1/deferred/postDeferredF.glsl +++ b/indra/newview/app_settings/shaders/class1/deferred/postDeferredF.glsl @@ -22,16 +22,2070 @@ * Linden Research, Inc., 945 Battery Street, San Francisco, CA 94111 USA * $/LicenseInfo$ */ + +#extension GL_ARB_texture_rectangle : enable + +#define FXAA_PC 1 +#define FXAA_GLSL_130 1 +#define FXAA_QUALITY__PRESET 12 + +/*============================================================================ + + + 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; } +#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 * 0.5 + rgbyA; +/*--------------------------------------------------------------------------*/ + float4 rgbyR = ((rgbyB.w - lumaMax) > 0.0) ? rgbyA : rgbyB; + rgbyR = ((rgbyB.w - 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% -#extension GL_ARB_texture_rectangle : enable +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 -uniform sampler2DRect diffuseRect; -uniform sampler2DRect edgeMap; +uniform sampler2D diffuseMap; uniform sampler2DRect depthMap; uniform sampler2DRect normalMap; -uniform sampler2D bloomMap; + +uniform vec2 tc_scale; +uniform vec2 rcp_screen_res; +uniform vec4 rcp_frame_opt; +uniform vec4 rcp_frame_opt2; +uniform vec2 screen_res; uniform float depth_cutoff; uniform float norm_cutoff; @@ -41,9 +2095,10 @@ uniform float tan_pixel_angle; uniform float magnification; uniform mat4 inv_proj; -uniform vec2 screen_res; varying vec2 vary_fragcoord; +varying vec2 vary_tc; + float getDepth(vec2 pos_screen) { @@ -76,8 +2131,8 @@ void dofSampleNear(inout vec4 diff, inout float w, float cur_sc, vec2 tc) float sc = calc_cof(d); float wg = 0.25; - - vec4 s = texture2DRect(diffuseRect, tc); + + vec4 s = texture2D(diffuseMap, tc*tc_scale/screen_res); // de-weight dull areas to make highlights 'pop' wg += s.r+s.g+s.b; @@ -97,7 +2152,7 @@ void dofSample(inout vec4 diff, inout float w, float min_sc, float cur_depth, ve { float wg = 0.25; - vec4 s = texture2DRect(diffuseRect, tc); + vec4 s = texture2D(diffuseMap, tc*tc_scale/screen_res); // de-weight dull areas to make highlights 'pop' wg += s.r+s.g+s.b; @@ -107,7 +2162,6 @@ void dofSample(inout vec4 diff, inout float w, float min_sc, float cur_depth, ve } } - void main() { vec3 norm = texture2DRect(normalMap, vary_fragcoord.xy).xyz; @@ -117,7 +2171,7 @@ void main() float depth = getDepth(tc); - vec4 diff = texture2DRect(diffuseRect, vary_fragcoord.xy); + vec4 diff = texture2D(diffuseMap, vary_fragcoord.xy*tc_scale/screen_res); { float w = 1.0; @@ -131,6 +2185,7 @@ void main() // sample quite uniformly spaced points within a circle, for a circular 'bokeh' //if (depth < focal_distance) + if (sc > 0.5) { while (sc > 0.5) { @@ -146,10 +2201,30 @@ void main() sc -= 1.0; } } + else + { + diff = FxaaPixelShader(vary_tc, //pos + vec4(vary_fragcoord.xy, 0, 0), //fxaaConsolePosPos + diffuseMap, //tex + diffuseMap, + diffuseMap, + rcp_screen_res, //fxaaQualityRcpFrame + vec4(0,0,0,0), //fxaaConsoleRcpFrameOpt + rcp_frame_opt, //fxaaConsoleRcpFrameOpt2 + rcp_frame_opt2, //fxaaConsole360RcpFrameOpt2 + 0.75, //fxaaQualitySubpix + 0.166, //fxaaQualityEdgeThreshold + 0.0833, //fxaaQualityEdgeThresholdMin + 8.0, //fxaaConsoleEdgeSharpness + 0.125, //fxaaConsoleEdgeThreshold + 0.05, //fxaaConsoleEdgeThresholdMin + vec4(0,0,0,0)); //fxaaConsole360ConstDir + + + } diff /= w; } - vec4 bloom = texture2D(bloomMap, vary_fragcoord.xy/screen_res); - gl_FragColor = diff + bloom; + gl_FragColor = diff; } -- cgit v1.2.3