Emulation/ppsspp
1
0
Fork 0
mirror of https://github.com/hrydgard/ppsspp.git synced 2025-04-02 11:01:50 -04:00
Code Issues Projects Releases Packages Wiki Activity

Implement smoothed depal for the "old" depal path as well.

Browse source
This commit is contained in:
Henrik Rydgård 2022-08-22 11:07:25 +02:00
parent 2a6015c1e3
commit e3943f6d0d
5 changed files with 98 additions and 31 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

69
GPU/Common/DepalettizeShaderCommon.cpp
View file

@ -45,7 +45,7 @@ static const VaryingDef varyings[1] = {
};
// Uses integer instructions available since OpenGL 3.0, ES 3.0 (and 2.0 with extensions), and of course Vulkan and D3D11.
void GenerateDepalShader300(ShaderWriter &writer, const DepalConfig &config, const ShaderLanguageDesc &lang) {
void GenerateDepalShader300(ShaderWriter &writer, const DepalConfig &config) {
const int shift = config.shift;
const int mask = config.mask;
@ -140,7 +140,7 @@ void GenerateDepalShader300(ShaderWriter &writer, const DepalConfig &config, con
}
// FP only, to suit GL(ES) 2.0 and DX9
void GenerateDepalShaderFloat(ShaderWriter &writer, const DepalConfig &config, const ShaderLanguageDesc &lang) {
void GenerateDepalShaderFloat(ShaderWriter &writer, const DepalConfig &config) {
char lookupMethod[128] = "index.r";
const int shift = config.shift;
@ -288,23 +288,64 @@ void GenerateDepalShaderFloat(ShaderWriter &writer, const DepalConfig &config, c
writer.C(" vec4 outColor = ").SampleTexture2D("pal", "vec2(coord, 0.0)").C(";\n");
}
void GenerateDepalSmoothed(ShaderWriter &writer, const DepalConfig &config) {
const char *sourceChannel = "error";
float indexMultiplier = 32.0f;
if (config.bufferFormat == GE_FORMAT_5551) {
_dbg_assert_(config.mask == 0x1F);
switch (config.shift) {
case 0: sourceChannel = "r"; break;
case 5: sourceChannel = "g"; break;
case 10: sourceChannel = "b"; break;
default: _dbg_assert_(false);
}
} else if (config.bufferFormat == GE_FORMAT_565) {
_dbg_assert_(config.mask == 0x1F || config.mask == 0x3F);
switch (config.shift) {
case 0: sourceChannel = "r"; break;
case 5: sourceChannel = "g"; indexMultiplier = 64.0f; break;
case 11: sourceChannel = "b"; break;
default: _dbg_assert_(false);
}
} else {
_dbg_assert_(false);
}
writer.C(" float index = ").SampleTexture2D("tex", "v_texcoord").F(".%s * %0.1f;\n", sourceChannel, indexMultiplier);
float texturePixels = 256.f;
if (config.clutFormat != GE_CMODE_32BIT_ABGR8888) {
texturePixels = 512.f;
}
writer.F(" float coord = (index + 0.5) * %f;\n", 1.0 / texturePixels);
writer.C(" vec4 outColor = ").SampleTexture2D("pal", "vec2(coord, 0.0)").C(";\n");
}
void GenerateDepalFs(char *buffer, const DepalConfig &config, const ShaderLanguageDesc &lang) {
ShaderWriter writer(buffer, lang, ShaderStage::Fragment);
writer.DeclareSamplers(samplers);
writer.HighPrecisionFloat();
writer.BeginFSMain(Slice<UniformDef>::empty(), varyings, FSFLAG_NONE);
switch (lang.shaderLanguage) {
case HLSL_D3D9:
case GLSL_1xx:
GenerateDepalShaderFloat(writer, config, lang);
break;
case GLSL_VULKAN:
case GLSL_3xx:
case HLSL_D3D11:
GenerateDepalShader300(writer, config, lang);
break;
default:
_assert_msg_(false, "Depal shader language not supported: %d", (int)lang.shaderLanguage);
if (config.smoothedDepal) {
// Handles a limited set of cases, but doesn't need any integer math so we don't
// need two variants.
GenerateDepalSmoothed(writer, config);
} else {
switch (lang.shaderLanguage) {
case HLSL_D3D9:
case GLSL_1xx:
GenerateDepalShaderFloat(writer, config);
break;
case GLSL_VULKAN:
case GLSL_3xx:
case HLSL_D3D11:
GenerateDepalShader300(writer, config);
break;
default:
_assert_msg_(false, "Depal shader language not supported: %d", (int)lang.shaderLanguage);
}
}
writer.EndFSMain("outColor", FSFLAG_NONE);
}

1
GPU/Common/DepalettizeShaderCommon.h
View file

@ -31,6 +31,7 @@ struct DepalConfig {
GEPaletteFormat clutFormat;
GETextureFormat textureFormat;
GEBufferFormat bufferFormat;
bool smoothedDepal;
};
void GenerateDepalFs(char *buffer, const DepalConfig &config, const ShaderLanguageDesc &lang);

18
GPU/Common/TextureCacheCommon.cpp
View file

@ -1906,12 +1906,17 @@ void TextureCacheCommon::ApplyTextureFramebuffer(VirtualFramebuffer *framebuffer
break;
}
const GEPaletteFormat clutFormat = gstate.getClutPaletteFormat();
ClutTexture clutTexture{};
bool smoothedDepal = false;
if (need_depalettize && !g_Config.bDisableSlowFramebufEffects) {
clutTexture = textureShaderCache_->GetClutTexture(clutFormat, clutHash_, clutBufRaw_);
smoothedDepal = CanUseSmoothDepal(gstate, framebuffer->drawnFormat, clutTexture.rampLength);
if (useShaderDepal) {
const GEPaletteFormat clutFormat = gstate.getClutPaletteFormat();
// Very icky conflation here of native and thin3d rendering. This will need careful work per backend in BindAsClutTexture.
ClutTexture clutTexture = textureShaderCache_->GetClutTexture(clutFormat, clutHash_, clutBufRaw_);
BindAsClutTexture(clutTexture.texture);
framebufferManager_->BindFramebufferAsColorTexture(0, framebuffer, BINDFBCOLOR_MAY_COPY_WITH_UV | BINDFBCOLOR_APPLY_TEX_OFFSET);
@ -1927,7 +1932,7 @@ void TextureCacheCommon::ApplyTextureFramebuffer(VirtualFramebuffer *framebuffer
// Since we started/ended render passes, might need these.
gstate_c.Dirty(DIRTY_DEPAL);
gstate_c.SetUseShaderDepal(true, CanUseSmoothDepal(gstate, framebuffer->drawnFormat, clutTexture.rampLength));
gstate_c.SetUseShaderDepal(true, smoothedDepal);
gstate_c.depalFramebufferFormat = framebuffer->drawnFormat;
const u32 bytesPerColor = clutFormat == GE_CMODE_32BIT_ABGR8888 ? sizeof(u32) : sizeof(u16);
const u32 clutTotalColors = clutMaxBytes_ / bytesPerColor;
@ -1939,7 +1944,7 @@ void TextureCacheCommon::ApplyTextureFramebuffer(VirtualFramebuffer *framebuffer
return;
}
textureShader = textureShaderCache_->GetDepalettizeShader(clutMode, texFormat, depth ? GE_FORMAT_DEPTH16 : framebuffer->drawnFormat);
textureShader = textureShaderCache_->GetDepalettizeShader(clutMode, texFormat, depth ? GE_FORMAT_DEPTH16 : framebuffer->drawnFormat, smoothedDepal);
gstate_c.SetUseShaderDepal(false, false);
}
@ -1957,9 +1962,10 @@ void TextureCacheCommon::ApplyTextureFramebuffer(VirtualFramebuffer *framebuffer
draw_->BindFramebufferAsTexture(framebuffer->fbo, 0, depth ? Draw::FB_DEPTH_BIT : Draw::FB_COLOR_BIT, 0);
draw_->BindTexture(1, clutTexture.texture);
Draw::SamplerState *nearest = textureShaderCache_->GetSampler();
Draw::SamplerState *nearest = textureShaderCache_->GetSampler(false);
Draw::SamplerState *clutSampler = textureShaderCache_->GetSampler(smoothedDepal);
draw_->BindSamplerStates(0, 1, &nearest);
draw_->BindSamplerStates(1, 1, &nearest);
draw_->BindSamplerStates(1, 1, &clutSampler);
textureShaderCache_->ApplyShader(textureShader,
framebuffer->bufferWidth, framebuffer->bufferHeight, framebuffer->renderWidth, framebuffer->renderHeight,

36
GPU/Common/TextureShaderCommon.cpp
View file

@ -147,6 +147,10 @@ void TextureShaderCache::Clear() {
nearestSampler_->Release();
nearestSampler_ = nullptr;
}
if (linearSampler_) {
linearSampler_->Release();
linearSampler_ = nullptr;
}
}
void TextureShaderCache::Decimate() {
@ -161,15 +165,28 @@ void TextureShaderCache::Decimate() {
}
}
Draw::SamplerState *TextureShaderCache::GetSampler() {
if (!nearestSampler_) {
Draw::SamplerStateDesc desc{};
desc.wrapU = Draw::TextureAddressMode::CLAMP_TO_EDGE;
desc.wrapV = Draw::TextureAddressMode::CLAMP_TO_EDGE;
desc.wrapW = Draw::TextureAddressMode::CLAMP_TO_EDGE;
nearestSampler_ = draw_->CreateSamplerState(desc);
Draw::SamplerState *TextureShaderCache::GetSampler(bool linearFilter) {
if (linearFilter) {
if (!linearSampler_) {
Draw::SamplerStateDesc desc{};
desc.magFilter = Draw::TextureFilter::LINEAR;
desc.minFilter = Draw::TextureFilter::LINEAR;
desc.wrapU = Draw::TextureAddressMode::CLAMP_TO_EDGE;
desc.wrapV = Draw::TextureAddressMode::CLAMP_TO_EDGE;
desc.wrapW = Draw::TextureAddressMode::CLAMP_TO_EDGE;
linearSampler_ = draw_->CreateSamplerState(desc);
}
return linearSampler_;
} else {
if (!nearestSampler_) {
Draw::SamplerStateDesc desc{};
desc.wrapU = Draw::TextureAddressMode::CLAMP_TO_EDGE;
desc.wrapV = Draw::TextureAddressMode::CLAMP_TO_EDGE;
desc.wrapW = Draw::TextureAddressMode::CLAMP_TO_EDGE;
nearestSampler_ = draw_->CreateSamplerState(desc);
}
return nearestSampler_;
}
return nearestSampler_;
}
TextureShader *TextureShaderCache::CreateShader(const char *fs) {
@ -220,7 +237,7 @@ TextureShader *TextureShaderCache::CreateShader(const char *fs) {
return depal;
}
TextureShader *TextureShaderCache::GetDepalettizeShader(uint32_t clutMode, GETextureFormat textureFormat, GEBufferFormat bufferFormat) {
TextureShader *TextureShaderCache::GetDepalettizeShader(uint32_t clutMode, GETextureFormat textureFormat, GEBufferFormat bufferFormat, bool smoothedDepal) {
using namespace Draw;
// Generate an ID for depal shaders.
@ -240,6 +257,7 @@ TextureShader *TextureShaderCache::GetDepalettizeShader(uint32_t clutMode, GETex
config.mask = gstate.getClutIndexMask();
config.bufferFormat = bufferFormat;
config.textureFormat = textureFormat;
config.smoothedDepal = smoothedDepal;
char *buffer = new char[4096];
GenerateDepalFs(buffer, config, draw_->GetShaderLanguageDesc());

5
GPU/Common/TextureShaderCommon.h
View file

@ -49,10 +49,10 @@ public:
TextureShaderCache(Draw::DrawContext *draw);
~TextureShaderCache();
TextureShader *GetDepalettizeShader(uint32_t clutMode, GETextureFormat texFormat, GEBufferFormat pixelFormat);
TextureShader *GetDepalettizeShader(uint32_t clutMode, GETextureFormat texFormat, GEBufferFormat pixelFormat, bool smoothedDepal);
ClutTexture GetClutTexture(GEPaletteFormat clutFormat, const u32 clutHash, u32 *rawClut);
Draw::SamplerState *GetSampler();
Draw::SamplerState *GetSampler(bool linearFilter);
void ApplyShader(TextureShader *shader, float bufferW, float bufferH, int renderW, int renderH, const KnownVertexBounds &bounds, u32 uoff, u32 voff);
@ -70,6 +70,7 @@ private:
Draw::DrawContext *draw_;
Draw::ShaderModule *vertexShader_ = nullptr;
Draw::SamplerState *nearestSampler_ = nullptr;
Draw::SamplerState *linearSampler_ = nullptr;
std::map<u32, TextureShader *> depalCache_;
std::map<u32, ClutTexture *> texCache_;