diff --git a/plugins/GSdx/GSDeviceOGL.cpp b/plugins/GSdx/GSDeviceOGL.cpp index 0a43a81c94..73a84fb948 100644 --- a/plugins/GSdx/GSDeviceOGL.cpp +++ b/plugins/GSdx/GSDeviceOGL.cpp @@ -584,7 +584,7 @@ void GSDeviceOGL::DebugOutput() } else { if (m_state.rtv != NULL) m_state.rtv->Save(format("/tmp/out_f%d__d%d__tex.bmp", g_frame_count, g_draw_count)); } - //if (m_state.dsv != NULL) m_state.dsv->Save(format("/tmp/ds_out_%d.bmp", g_draw_count)); + if (m_state.dsv != NULL) m_state.dsv->Save(format("/tmp/ds_out_%d.bmp", g_draw_count)); fprintf(stderr, "\n"); //DebugBB(); @@ -668,7 +668,17 @@ void GSDeviceOGL::ClearDepth(GSTexture* t, float c) OMSetFBO(m_fbo); static_cast(t)->Attach(GL_DEPTH_STENCIL_ATTACHMENT); // FIXME can you clean depth and stencil separately - glClearBufferfv(GL_DEPTH, 0, &c); + // XXX: glClear* depends on the scissor test!!! Disable it because the viewport + // could be smaller than the texture and we really want to clean all pixels. + glDisable(GL_SCISSOR_TEST); + if (m_state.dss != NULL && m_state.dss->IsMaskEnable()) { + glClearBufferfv(GL_DEPTH, 0, &c); + } else { + glDepthMask(true); + glClearBufferfv(GL_DEPTH, 0, &c); + glDepthMask(false); + } + glEnable(GL_SCISSOR_TEST); OMSetFBO(fbo_old); } diff --git a/plugins/GSdx/GSDeviceOGL.h b/plugins/GSdx/GSDeviceOGL.h index 07b8bd1486..8ad6b4554e 100644 --- a/plugins/GSdx/GSDeviceOGL.h +++ b/plugins/GSdx/GSDeviceOGL.h @@ -228,6 +228,8 @@ public: if (!m_stencil_enable) return; fprintf(stderr, "Stencil %s. Both pass op %s\n", NameOfParam(m_stencil_func), NameOfParam(m_stencil_spass_dpass_op)); } + + bool IsMaskEnable() { return m_depth_mask; } }; class GSDeviceOGL : public GSDevice diff --git a/plugins/GSdx/GSTextureFXOGL.cpp b/plugins/GSdx/GSTextureFXOGL.cpp index 1eb11535a6..6b08be207b 100644 --- a/plugins/GSdx/GSTextureFXOGL.cpp +++ b/plugins/GSdx/GSTextureFXOGL.cpp @@ -46,21 +46,6 @@ void GSDeviceOGL::CreateTextureFX() glSamplerParameteri(m_rt_ss, GL_TEXTURE_COMPARE_FUNC, GL_NEVER); // FIXME: need ogl extension sd.MaxAnisotropy = 16; - //{"TEXCOORD", 0, DXGI_FORMAT_R32G32_FLOAT, 0, 0, D3D11_INPUT_PER_VERTEX_DATA, 0}, - //{"TEXCOORD", 1, DXGI_FORMAT_R32_FLOAT, 0, 12, D3D11_INPUT_PER_VERTEX_DATA, 0}, - //float2 t : TEXCOORD0; - //float q : TEXCOORD1; - // - //{"POSITION", 0, DXGI_FORMAT_R16G16_UINT, 0, 16, D3D11_INPUT_PER_VERTEX_DATA, 0}, - //{"POSITION", 1, DXGI_FORMAT_R32_UINT, 0, 20, D3D11_INPUT_PER_VERTEX_DATA, 0}, - //uint2 p : POSITION0; - //uint z : POSITION1; - // - //{"COLOR", 0, DXGI_FORMAT_R8G8B8A8_UNORM, 0, 8, D3D11_INPUT_PER_VERTEX_DATA, 0}, - //{"COLOR", 1, DXGI_FORMAT_R8G8B8A8_UNORM, 0, 28, D3D11_INPUT_PER_VERTEX_DATA, 0}, - //float4 c : COLOR0; - //float4 f : COLOR1; - GSInputLayoutOGL vert_format[] = { // FIXME @@ -74,6 +59,13 @@ void GSDeviceOGL::CreateTextureFX() {6 , 4 , GL_UNSIGNED_BYTE , GL_TRUE , sizeof(GSVertex) , (const GLvoid*)(28) } , }; m_vb = new GSVertexBufferStateOGL(sizeof(GSVertex), vert_format, countof(vert_format)); + + // Compile some dummy shaders to allow modification inside Apitrace for debug + GLuint dummy; + std::string macro = ""; + CompileShaderFromSource("tfx.glsl", "vs_main", GL_VERTEX_SHADER, &dummy, macro); + CompileShaderFromSource("tfx.glsl", "gs_main", GL_GEOMETRY_SHADER, &dummy, macro); + CompileShaderFromSource("tfx.glsl", "ps_main", GL_FRAGMENT_SHADER, &dummy, macro); } void GSDeviceOGL::SetupVS(VSSelector sel, const VSConstantBuffer* cb) diff --git a/plugins/GSdx/GSTextureOGL.cpp b/plugins/GSdx/GSTextureOGL.cpp index 73aef4a5d9..0cc0b6a8b2 100644 --- a/plugins/GSdx/GSTextureOGL.cpp +++ b/plugins/GSdx/GSTextureOGL.cpp @@ -21,6 +21,7 @@ #pragma once +#include #include "GSTextureOGL.h" static int g_state_texture_unit = -1; static int g_state_texture_id = -1; @@ -372,16 +373,22 @@ void GSTextureOGL::Save(const string& fn, const void* image, uint32 pitch) for(int h = m_size.y; h > 0; h--, data -= pitch) { - if (IsDss()) { + if (false && IsDss()) { // Only get the depth and convert it to an integer uint8* better_data = data; for (int w = m_size.x; w > 0; w--, better_data += 8) { float* input = (float*)better_data; // FIXME how to dump 32 bits value into 8bits component color - uint32 depth = (uint32)ldexpf(*input, 32); - uint8 small_depth = depth >> 24; - uint8 better_data[4] = {small_depth, small_depth, small_depth, 0 }; - fwrite(&better_data, 1, 4, fp); + GLuint depth_integer = (GLuint)(*input * (float)UINT_MAX); + uint8 r = (depth_integer >> 0) & 0xFF; + uint8 g = (depth_integer >> 8) & 0xFF; + uint8 b = (depth_integer >> 16) & 0xFF; + uint8 a = (depth_integer >> 24) & 0xFF; + + fwrite(&r, 1, 1, fp); + fwrite(&g, 1, 1, fp); + fwrite(&b, 1, 1, fp); + fwrite(&a, 1, 1, fp); } } else { // swap red and blue @@ -402,7 +409,6 @@ bool GSTextureOGL::Save(const string& fn, bool dds) { // Collect the texture data uint32 pitch = 4 * m_size.x; - if (IsDss()) pitch *= 2; char* image = (char*)malloc(pitch * m_size.y); bool status = true; @@ -413,8 +419,14 @@ bool GSTextureOGL::Save(const string& fn, bool dds) //glBindFramebuffer(GL_READ_FRAMEBUFFER, 0); glReadPixels(0, 0, m_size.x, m_size.y, GL_RGBA, GL_UNSIGNED_BYTE, image); } else if(IsDss()) { - EnableUnit(0); - glGetTexImage(m_texture_target, 0, GL_DEPTH_STENCIL, GL_FLOAT_32_UNSIGNED_INT_24_8_REV, image); + glBindFramebuffer(GL_READ_FRAMEBUFFER, m_fbo_read); + + //EnableUnit(0); + + glFramebufferTexture2D(GL_READ_FRAMEBUFFER, GL_DEPTH_ATTACHMENT, m_texture_target, m_texture_id, 0); + glReadPixels(0, 0, m_size.x, m_size.y, GL_DEPTH_COMPONENT, GL_UNSIGNED_INT, image); + + glBindFramebuffer(GL_READ_FRAMEBUFFER, 0); } else { glBindFramebuffer(GL_READ_FRAMEBUFFER, m_fbo_read); diff --git a/plugins/GSdx/res/tfx.glsl b/plugins/GSdx/res/tfx.glsl index dda0f1b7b2..7df9c2226b 100644 --- a/plugins/GSdx/res/tfx.glsl +++ b/plugins/GSdx/res/tfx.glsl @@ -11,6 +11,7 @@ #define VS_BPPZ 0 #define VS_TME 1 #define VS_FST 1 +#define VS_LOGZ 0 #endif #ifndef GS_IIP @@ -57,74 +58,74 @@ layout(location = 6) in vec4 i_f; layout(location = 0) out vertex VSout; out gl_PerVertex { - vec4 gl_Position; + invariant vec4 gl_Position; float gl_PointSize; float gl_ClipDistance[]; }; layout(std140, binding = 4) uniform cb0 { - vec4 VertexScale; - vec4 VertexOffset; - vec2 TextureScale; + vec4 VertexScale; + vec4 VertexOffset; + vec2 TextureScale; }; void vs_main() { uint z; - if(VS_BPPZ == 1) // 24 - z = i_z & uint(0xffffff); - else if(VS_BPPZ == 2) // 16 - z = i_z & uint(0xffff); + if(VS_BPPZ == 1) // 24 + z = i_z & uint(0xffffff); + else if(VS_BPPZ == 2) // 16 + z = i_z & uint(0xffff); else z = i_z; - // pos -= 0.05 (1/320 pixel) helps avoiding rounding problems (integral part of pos is usually 5 digits, 0.05 is about as low as we can go) - // example: ceil(afterseveralvertextransformations(y = 133)) => 134 => line 133 stays empty - // input granularity is 1/16 pixel, anything smaller than that won't step drawing up/left by one pixel - // example: 133.0625 (133 + 1/16) should start from line 134, ceil(133.0625 - 0.05) still above 133 + // pos -= 0.05 (1/320 pixel) helps avoiding rounding problems (integral part of pos is usually 5 digits, 0.05 is about as low as we can go) + // example: ceil(afterseveralvertextransformations(y = 133)) => 134 => line 133 stays empty + // input granularity is 1/16 pixel, anything smaller than that won't step drawing up/left by one pixel + // example: 133.0625 (133 + 1/16) should start from line 134, ceil(133.0625 - 0.05) still above 133 - vec4 p = vec4(i_p, z, 0) - vec4(0.05f, 0.05f, 0, 0); - vec4 final_p = p * VertexScale - VertexOffset; + vec4 p = vec4(i_p, z, 0) - vec4(0.05f, 0.05f, 0, 0); + vec4 final_p = p * VertexScale - VertexOffset; // FIXME // FLIP vertically final_p.y *= -1.0f; - if(VS_LOGZ == 1) - { - final_p.z = log2(1.0f + float(z)) / 32.0f; - } + if(VS_LOGZ == 1) + { + final_p.z = log2(1.0f + float(z)) / 32.0f; + } - VSout.p = final_p; + VSout.p = final_p; gl_Position = final_p; // NOTE I don't know if it is possible to merge POSITION_OUT and gl_Position #if VS_RTCOPY - VSout.tp = final_p * vec4(0.5, -0.5, 0, 0) + 0.5; + VSout.tp = final_p * vec4(0.5, -0.5, 0, 0) + 0.5; #endif - if(VS_TME != 0) - { - if(VS_FST != 0) - { - //VSout.t.xy = i_t * TextureScale; - VSout.t.xy = i_uv * TextureScale; - VSout.t.w = 1.0f; - } - else - { - //VSout.t.xy = i_t; - VSout.t.xy = i_st; - VSout.t.w = i_q; - } - } - else - { - VSout.t.xy = vec2(0.0f, 0.0f); - VSout.t.w = 1.0f; - } + if(VS_TME != 0) + { + if(VS_FST != 0) + { + //VSout.t.xy = i_t * TextureScale; + VSout.t.xy = i_uv * TextureScale; + VSout.t.w = 1.0f; + } + else + { + //VSout.t.xy = i_t; + VSout.t.xy = i_st; + VSout.t.w = i_q; + } + } + else + { + VSout.t.xy = vec2(0.0f, 0.0f); + VSout.t.w = 1.0f; + } - VSout.c = i_c; - VSout.t.z = i_f.r; + VSout.c = i_c; + VSout.t.z = i_f.r; } #endif @@ -212,17 +213,17 @@ void gs_main() lt.p.z = rb.p.z; lt.t.zw = rb.t.zw; - #if GS_IIP == 0 - lt.c = rb.c; - #endif +#if GS_IIP == 0 + lt.c = rb.c; +#endif vertex lb = rb; - lb.p.x = lt.p.x; - lb.t.x = lt.t.x; + lb.p.x = lt.p.x; + lb.t.x = lt.t.x; vertex rt = rb; - rt.p.y = lt.p.y; - rt.t.y = lt.t.y; + rt.p.y = lt.p.y; + rt.t.y = lt.t.y; // Triangle 1 gl_Position = lt.p; @@ -237,9 +238,9 @@ void gs_main() GSout = rt; EmitVertex(); - EndPrimitive(); + EndPrimitive(); - // Triangle 2 + // Triangle 2 gl_Position = lb.p; GSout = lb; EmitVertex(); @@ -273,369 +274,366 @@ layout(binding = 2) uniform sampler2D RTCopySampler; layout(std140, binding = 5) uniform cb1 { - vec3 FogColor; - float AREF; - vec4 HalfTexel; - vec4 WH; - vec4 MinMax; - vec2 MinF; - vec2 TA; - uvec4 MskFix; + vec3 FogColor; + float AREF; + vec4 HalfTexel; + vec4 WH; + vec4 MinMax; + vec2 MinF; + vec2 TA; + uvec4 MskFix; }; vec4 sample_c(vec2 uv) { // FIXME I'm not sure it is a good solution to flip texture - return texture(TextureSampler, uv); + return texture(TextureSampler, uv); //FIXME another way to FLIP vertically - //return texture(TextureSampler, vec2(uv.x, 1.0f-uv.y) ); + //return texture(TextureSampler, vec2(uv.x, 1.0f-uv.y) ); } vec4 sample_p(float u) { //FIXME do we need a 1D sampler. Big impact on opengl to find 1 dim // So for the moment cheat with 0.0f dunno if it work - return texture(PaletteSampler, vec2(u, 0.0f)); + return texture(PaletteSampler, vec2(u, 0.0f)); } vec4 sample_rt(vec2 uv) { - return texture(RTCopySampler, uv); + return texture(RTCopySampler, uv); } vec4 wrapuv(vec4 uv) { vec4 uv_out = uv; - if(PS_WMS == PS_WMT) - { - if(PS_WMS == 2) - { - uv_out = clamp(uv, MinMax.xyxy, MinMax.zwzw); - } - else if(PS_WMS == 3) - { - uv_out = vec4(((ivec4(uv * WH.xyxy) & ivec4(MskFix.xyxy)) | ivec4(MskFix.zwzw)) / WH.xyxy); - } - } - else - { - if(PS_WMS == 2) - { - uv_out.xz = clamp(uv.xz, MinMax.xx, MinMax.zz); - } - else if(PS_WMS == 3) - { - uv_out.xz = vec2(((ivec2(uv.xz * WH.xx) & ivec2(MskFix.xx)) | ivec2(MskFix.zz)) / WH.xx); - } - if(PS_WMT == 2) - { - uv_out.yw = clamp(uv.yw, MinMax.yy, MinMax.ww); - } - else if(PS_WMT == 3) - { - uv_out.yw = vec2(((ivec2(uv.yw * WH.yy) & ivec2(MskFix.yy)) | ivec2(MskFix.ww)) / WH.yy); - } - } - - return uv_out; + if(PS_WMS == PS_WMT) + { + if(PS_WMS == 2) + { + uv_out = clamp(uv, MinMax.xyxy, MinMax.zwzw); + } + else if(PS_WMS == 3) + { + uv_out = vec4(((ivec4(uv * WH.xyxy) & ivec4(MskFix.xyxy)) | ivec4(MskFix.zwzw)) / WH.xyxy); + } + } + else + { + if(PS_WMS == 2) + { + uv_out.xz = clamp(uv.xz, MinMax.xx, MinMax.zz); + } + else if(PS_WMS == 3) + { + uv_out.xz = vec2(((ivec2(uv.xz * WH.xx) & ivec2(MskFix.xx)) | ivec2(MskFix.zz)) / WH.xx); + } + if(PS_WMT == 2) + { + uv_out.yw = clamp(uv.yw, MinMax.yy, MinMax.ww); + } + else if(PS_WMT == 3) + { + uv_out.yw = vec2(((ivec2(uv.yw * WH.yy) & ivec2(MskFix.yy)) | ivec2(MskFix.ww)) / WH.yy); + } + } + + return uv_out; } vec2 clampuv(vec2 uv) { vec2 uv_out = uv; - if(PS_WMS == 2 && PS_WMT == 2) - { - uv_out = clamp(uv, MinF, MinMax.zw); - } - else if(PS_WMS == 2) - { - uv_out.x = clamp(uv.x, MinF.x, MinMax.z); - } - else if(PS_WMT == 2) - { - uv_out.y = clamp(uv.y, MinF.y, MinMax.w); - } - - return uv_out; + if(PS_WMS == 2 && PS_WMT == 2) + { + uv_out = clamp(uv, MinF, MinMax.zw); + } + else if(PS_WMS == 2) + { + uv_out.x = clamp(uv.x, MinF.x, MinMax.z); + } + else if(PS_WMT == 2) + { + uv_out.y = clamp(uv.y, MinF.y, MinMax.w); + } + + return uv_out; } mat4 sample_4c(vec4 uv) { - mat4 c; - - c[0] = sample_c(uv.xy); - c[1] = sample_c(uv.zy); - c[2] = sample_c(uv.xw); - c[3] = sample_c(uv.zw); + mat4 c; - return c; + c[0] = sample_c(uv.xy); + c[1] = sample_c(uv.zy); + c[2] = sample_c(uv.xw); + c[3] = sample_c(uv.zw); + + return c; } vec4 sample_4a(vec4 uv) { - vec4 c; + vec4 c; - c.x = sample_c(uv.xy).a; - c.y = sample_c(uv.zy).a; - c.z = sample_c(uv.xw).a; - c.w = sample_c(uv.zw).a; - - return c; + c.x = sample_c(uv.xy).a; + c.y = sample_c(uv.zy).a; + c.z = sample_c(uv.xw).a; + c.w = sample_c(uv.zw).a; + + return c; } mat4 sample_4p(vec4 u) { - mat4 c; - - c[0] = sample_p(u.x); - c[1] = sample_p(u.y); - c[2] = sample_p(u.z); - c[3] = sample_p(u.w); + mat4 c; - return c; + c[0] = sample_p(u.x); + c[1] = sample_p(u.y); + c[2] = sample_p(u.z); + c[3] = sample_p(u.w); + + return c; } vec4 sample_color(vec2 st, float q) { - if(PS_FST == 0) - { - st /= q; - } - - vec4 t; - if((PS_FMT <= FMT_16) && (PS_WMS < 3) && (PS_WMT < 3)) - { - t = sample_c(clampuv(st)); - } - else - { - vec4 uv; - vec2 dd; - - if(PS_LTF != 0) - { - uv = st.xyxy + HalfTexel; - dd = fract(uv.xy * WH.zw); - } - else - { - uv = st.xyxy; - } - - uv = wrapuv(uv); + if(PS_FST == 0) + { + st /= q; + } - mat4 c; + vec4 t; + if((PS_FMT <= FMT_16) && (PS_WMS < 3) && (PS_WMT < 3)) + { + t = sample_c(clampuv(st)); + } + else + { + vec4 uv; + vec2 dd; - if((PS_FMT & FMT_PAL) != 0) - c = sample_4p(sample_4a(uv)); - else - c = sample_4c(uv); + if(PS_LTF != 0) + { + uv = st.xyxy + HalfTexel; + dd = fract(uv.xy * WH.zw); + } + else + { + uv = st.xyxy; + } - // PERF: see the impact of the exansion before/after the interpolation - for (int i = 0; i < 4; i++) { - if((PS_FMT & ~FMT_PAL) == FMT_16) - { - // FIXME GLSL any only support bvec so try to mix it with notEqual - bvec3 rgb_check = notEqual( t.rgb, vec3(0.0f, 0.0f, 0.0f) ); - t.a = t.a >= 0.5 ? TA.y : ( (PS_AEM == 0) || any(rgb_check) ) ? TA.x : 0.0f; - } - } + uv = wrapuv(uv); - if(PS_LTF != 0) - { - t = mix(mix(c[0], c[1], dd.x), mix(c[2], c[3], dd.x), dd.y); - } - else - { - t = c[0]; - } - } - - if(PS_FMT == FMT_24) - { + mat4 c; + + if((PS_FMT & FMT_PAL) != 0) + c = sample_4p(sample_4a(uv)); + else + c = sample_4c(uv); + + // PERF: see the impact of the exansion before/after the interpolation + for (int i = 0; i < 4; i++) { + if((PS_FMT & ~FMT_PAL) == FMT_16) + { + // FIXME GLSL any only support bvec so try to mix it with notEqual + bvec3 rgb_check = notEqual( t.rgb, vec3(0.0f, 0.0f, 0.0f) ); + t.a = t.a >= 0.5 ? TA.y : ( (PS_AEM == 0) || any(rgb_check) ) ? TA.x : 0.0f; + } + } + + if(PS_LTF != 0) + { + t = mix(mix(c[0], c[1], dd.x), mix(c[2], c[3], dd.x), dd.y); + } + else + { + t = c[0]; + } + } + + if(PS_FMT == FMT_24) + { // FIXME GLSL any only support bvec so try to mix it with notEqual bvec3 rgb_check = notEqual( t.rgb, vec3(0.0f, 0.0f, 0.0f) ); - t.a = ( (PS_AEM == 0) || any(rgb_check) ) ? TA.x : 0.0f; - } - else if(PS_FMT == FMT_16) - { - // a bit incompatible with up-scaling because the 1 bit alpha is interpolated + t.a = ( (PS_AEM == 0) || any(rgb_check) ) ? TA.x : 0.0f; + } + else if(PS_FMT == FMT_16) + { + // a bit incompatible with up-scaling because the 1 bit alpha is interpolated // FIXME GLSL any only support bvec so try to mix it with notEqual bvec3 rgb_check = notEqual( t.rgb, vec3(0.0f, 0.0f, 0.0f) ); - t.a = t.a >= 0.5 ? TA.y : ( (PS_AEM == 0) || any(rgb_check) ) ? TA.x : 0.0f; - } - - return t; + t.a = t.a >= 0.5 ? TA.y : ( (PS_AEM == 0) || any(rgb_check) ) ? TA.x : 0.0f; + } + + return t; } vec4 tfx(vec4 t, vec4 c) { vec4 c_out = c; - if(PS_TFX == 0) - { - if(PS_TCC != 0) - { - c_out = c * t * 255.0f / 128; - } - else - { - c_out.rgb = c.rgb * t.rgb * 255.0f / 128; - } - } - else if(PS_TFX == 1) - { - if(PS_TCC != 0) - { - c_out = t; - } - else - { - c_out.rgb = t.rgb; - } - } - else if(PS_TFX == 2) - { - c_out.rgb = c.rgb * t.rgb * 255.0f / 128 + c.a; + if(PS_TFX == 0) + { + if(PS_TCC != 0) + { + c_out = c * t * 255.0f / 128; + } + else + { + c_out.rgb = c.rgb * t.rgb * 255.0f / 128; + } + } + else if(PS_TFX == 1) + { + if(PS_TCC != 0) + { + c_out = t; + } + else + { + c_out.rgb = t.rgb; + } + } + else if(PS_TFX == 2) + { + c_out.rgb = c.rgb * t.rgb * 255.0f / 128 + c.a; - if(PS_TCC != 0) - { - c_out.a += t.a; - } - } - else if(PS_TFX == 3) - { - c_out.rgb = c.rgb * t.rgb * 255.0f / 128 + c.a; + if(PS_TCC != 0) + { + c_out.a += t.a; + } + } + else if(PS_TFX == 3) + { + c_out.rgb = c.rgb * t.rgb * 255.0f / 128 + c.a; - if(PS_TCC != 0) - { - c_out.a = t.a; - } - } - - return clamp(c_out, vec4(0.0f, 0.0f, 0.0f, 0.0f), vec4(1.0f, 1.0f, 1.0f, 1.0f)); + if(PS_TCC != 0) + { + c_out.a = t.a; + } + } + + return clamp(c_out, vec4(0.0f, 0.0f, 0.0f, 0.0f), vec4(1.0f, 1.0f, 1.0f, 1.0f)); } void datst() { #if PS_DATE > 0 - float alpha = sample_rt(PSin.tp.xy).a; - float alpha0x80 = 128. / 255; + float alpha = sample_rt(PSin.tp.xy).a; + float alpha0x80 = 128. / 255; - if (PS_DATE == 1 && alpha >= alpha0x80) - discard; - else if (PS_DATE == 2 && alpha < alpha0x80) - discard; + if (PS_DATE == 1 && alpha >= alpha0x80) + discard; + else if (PS_DATE == 2 && alpha < alpha0x80) + discard; #endif } void atst(vec4 c) { - float a = trunc(c.a * 255); - - if(PS_ATST == 0) // never - { - discard; - } - else if(PS_ATST == 1) // always - { - // nothing to do - } - else if(PS_ATST == 2) - { - } - else if(PS_ATST == 2 ) // l - { - if (PS_SPRITEHACK == 0) - if ((AREF - a) < 0.0f) - discard; - } - else if(PS_ATST == 2 ) // le - { - if ((AREF - a) < 0.0f) + float a = trunc(c.a * 255); + + if(PS_ATST == 0) // never + { + discard; + } + else if(PS_ATST == 1) // always + { + // nothing to do + } + else if(PS_ATST == 2 ) // l + { + if (PS_SPRITEHACK == 0) + if ((AREF - a) < 0.0f) + discard; + } + else if(PS_ATST == 3 ) // le + { + if ((AREF - a) < 0.0f) discard; - } - else if(PS_ATST == 4) // e - { + } + else if(PS_ATST == 4) // e + { if ((0.5f - abs(a - AREF)) < 0.0f) discard; - } - else if(PS_ATST == 5 || PS_ATST == 6) // ge, g - { + } + else if(PS_ATST == 5 || PS_ATST == 6) // ge, g + { if ((a-AREF) < 0.0f) discard; - } - else if(PS_ATST == 7) // ne - { - if ((abs(a - AREF) - 0.5f) < 0.0f) + } + else if(PS_ATST == 7) // ne + { + if ((abs(a - AREF) - 0.5f) < 0.0f) discard; - } + } } vec4 fog(vec4 c, float f) { vec4 c_out = c; - if(PS_FOG != 0) - { - c_out.rgb = mix(FogColor, c.rgb, f); - } + if(PS_FOG != 0) + { + c_out.rgb = mix(FogColor, c.rgb, f); + } - return c_out; + return c_out; } vec4 ps_color() { - datst(); + datst(); - vec4 t = sample_color(PSin.t.xy, PSin.t.w); + vec4 t = sample_color(PSin.t.xy, PSin.t.w); - vec4 c = tfx(t, PSin.c); + vec4 c = tfx(t, PSin.c); - atst(c); + atst(c); - c = fog(c, PSin.t.z); + c = fog(c, PSin.t.z); - if (PS_COLCLIP == 2) - { - c.rgb = 256.0f/255.0f - c.rgb; - } - if (PS_COLCLIP > 0) - { + if (PS_COLCLIP == 2) + { + c.rgb = 256.0f/255.0f - c.rgb; + } + if (PS_COLCLIP > 0) + { // FIXME !!!! - //c.rgb *= c.rgb < 128./255; - bvec3 factor = bvec3(128.0f/255.0f, 128.0f/255.0f, 128.0f/255.0f); - c.rgb *= vec3(factor); - } + //c.rgb *= c.rgb < 128./255; + bvec3 factor = bvec3(128.0f/255.0f, 128.0f/255.0f, 128.0f/255.0f); + c.rgb *= vec3(factor); + } - if(PS_CLR1 != 0) // needed for Cd * (As/Ad/F + 1) blending modes - { - c.rgb = vec3(1.0f, 1.0f, 1.0f); - } + if(PS_CLR1 != 0) // needed for Cd * (As/Ad/F + 1) blending modes + { + c.rgb = vec3(1.0f, 1.0f, 1.0f); + } - return c; + return c; } void ps_main() { - //FIXME - vec4 c = ps_color(); + //FIXME + vec4 c = ps_color(); // FIXME: I'm not sure about the value of others field - // output.c1 = c.a * 2; // used for alpha blending + // output.c1 = c.a * 2; // used for alpha blending - float alpha = c.a * 2; + float alpha = c.a * 2; - if(PS_AOUT != 0) // 16 bit output - { - float a = 128.0f / 255; // alpha output will be 0x80 - - c.a = (PS_FBA != 0) ? a : step(0.5, c.a) * a; - } - else if(PS_FBA != 0) - { - if(c.a < 0.5) c.a += 0.5; - } + if(PS_AOUT != 0) // 16 bit output + { + float a = 128.0f / 255; // alpha output will be 0x80 + + c.a = (PS_FBA != 0) ? a : step(0.5, c.a) * a; + } + else if(PS_FBA != 0) + { + if(c.a < 0.5) c.a += 0.5; + } SV_Target0 = c; SV_Target1 = vec4(alpha, alpha, alpha, alpha);