Remove SmoothedDepal compat setting, instead detect the ramp directly.

hrydgard · Aug 21, 2022 · 97959f6 · 97959f6
1 parent cfa7483
commit 97959f6
Show file tree

Hide file tree

Showing 12 changed files with 51 additions and 29 deletions.
diff --git a/Core/Compatibility.cpp b/Core/Compatibility.cpp
@@ -98,7 +98,6 @@ void Compatibility::CheckSettings(IniFile &iniFile, const std::string &gameID) {
 	CheckSetting(iniFile, gameID, "AllowLargeFBTextureOffsets", &flags_.AllowLargeFBTextureOffsets);
 	CheckSetting(iniFile, gameID, "AtracLoopHack", &flags_.AtracLoopHack);
 	CheckSetting(iniFile, gameID, "DeswizzleDepth", &flags_.DeswizzleDepth);
-	CheckSetting(iniFile, gameID, "SmoothedDepal", &flags_.SmoothedDepal);
 }
 
 void Compatibility::CheckSetting(IniFile &iniFile, const std::string &gameID, const char *option, bool *flag) {

diff --git a/Core/Compatibility.h b/Core/Compatibility.h
@@ -88,7 +88,6 @@ struct CompatFlags {
 	bool AllowLargeFBTextureOffsets;
 	bool AtracLoopHack;
 	bool DeswizzleDepth;
-	bool SmoothedDepal;
 };
 
 class IniFile;

diff --git a/GPU/Common/DepalettizeCommon.cpp b/GPU/Common/DepalettizeCommon.cpp
@@ -51,21 +51,21 @@ void DepalShaderCache::DeviceLost() {
 	Clear();
 }
 
-Draw::Texture *DepalShaderCache::GetClutTexture(GEPaletteFormat clutFormat, const u32 clutHash, u32 *rawClut) {
+DepalTexture DepalShaderCache::GetClutTexture(GEPaletteFormat clutFormat, const u32 clutHash, u32 *rawClut) {
 	u32 clutId = GetClutID(clutFormat, clutHash);
 
 	auto oldtex = texCache_.find(clutId);
 	if (oldtex != texCache_.end()) {
 		oldtex->second->lastFrame = gpuStats.numFlips;
-		return oldtex->second->texture;
+		return *oldtex->second;
 	}
 
-	int texturePixels = clutFormat == GE_CMODE_32BIT_ABGR8888 ? 256 : 512;
+	int maxClutEntries = clutFormat == GE_CMODE_32BIT_ABGR8888 ? 256 : 512;
 
 	DepalTexture *tex = new DepalTexture();
 
 	Draw::TextureDesc desc{};
-	desc.width = texturePixels;
+	desc.width = maxClutEntries;
 	desc.height = 1;
 	desc.depth = 1;
 	desc.mipLevels = 1;
@@ -80,24 +80,49 @@ Draw::Texture *DepalShaderCache::GetClutTexture(GEPaletteFormat clutFormat, cons
 		desc.initData.push_back((const uint8_t *)rawClut);
 		break;
 	case GEPaletteFormat::GE_CMODE_16BIT_BGR5650:
-		ConvertRGB565ToRGBA8888((u32 *)convTemp, (const u16 *)rawClut, texturePixels);
+		ConvertRGB565ToRGBA8888((u32 *)convTemp, (const u16 *)rawClut, maxClutEntries);
 		desc.initData.push_back(convTemp);
 		break;
 	case GEPaletteFormat::GE_CMODE_16BIT_ABGR5551:
-		ConvertRGBA5551ToRGBA8888((u32 *)convTemp, (const u16 *)rawClut, texturePixels);
+		ConvertRGBA5551ToRGBA8888((u32 *)convTemp, (const u16 *)rawClut, maxClutEntries);
 		desc.initData.push_back(convTemp);
 		break;
 	case GEPaletteFormat::GE_CMODE_16BIT_ABGR4444:
-		ConvertRGBA4444ToRGBA8888((u32 *)convTemp, (const u16 *)rawClut, texturePixels);
+		ConvertRGBA4444ToRGBA8888((u32 *)convTemp, (const u16 *)rawClut, maxClutEntries);
 		desc.initData.push_back(convTemp);
 		break;
 	}
 
+	int lastR = 0;
+	int lastG = 0;
+	int lastB = 0;
+	int lastA = 0;
+
+	int rampLength = 0;
+	// Quick check for how many continouosly growing entries we have at the start.
+	// Bilinearly filtering CLUTs only really makes sense for this kind of ramp.
+	for (int i = 0; i < maxClutEntries; i++) {
+		rampLength = i + 1;
+		int r = desc.initData[0][i * 4];
+		int g = desc.initData[0][i * 4 + 1];
+		int b = desc.initData[0][i * 4 + 2];
+		int a = desc.initData[0][i * 4 + 3];
+		if (r < lastR || g < lastG || b < lastB || a < lastA) {
+			break;
+		} else {
+			lastR = r;
+			lastG = g;
+			lastB = b;
+			lastA = a;
+		}
+	}
+
 	tex->texture = draw_->CreateTexture(desc);
 	tex->lastFrame = gpuStats.numFlips;
+	tex->rampLength = rampLength;
 
 	texCache_[clutId] = tex;
-	return tex->texture;
+	return *tex;
 }
 
 void DepalShaderCache::Clear() {

diff --git a/GPU/Common/DepalettizeCommon.h b/GPU/Common/DepalettizeCommon.h
@@ -40,6 +40,7 @@ class DepalTexture {
 public:
 	Draw::Texture *texture;
 	int lastFrame;
+	int rampLength;  // How many entries are continuously growing from entry 0.
 };
 
 // Caches both shaders and palette textures.
@@ -50,7 +51,7 @@ class DepalShaderCache {
 
 	// This also uploads the palette and binds the correct texture.
 	DepalShader *GetDepalettizeShader(uint32_t clutMode, GETextureFormat texFormat, GEBufferFormat pixelFormat);
-	Draw::Texture *GetClutTexture(GEPaletteFormat clutFormat, const u32 clutHash, u32 *rawClut);
+	DepalTexture GetClutTexture(GEPaletteFormat clutFormat, const u32 clutHash, u32 *rawClut);
 
 	Draw::SamplerState *GetSampler();
 

diff --git a/GPU/Common/FragmentShaderGenerator.cpp b/GPU/Common/FragmentShaderGenerator.cpp
@@ -90,7 +90,7 @@ bool GenerateFragmentShader(const FShaderID &id, char *buffer, const ShaderLangu
 
 	bool doFlatShading = id.Bit(FS_BIT_FLATSHADE) && !flatBug;
 	bool shaderDepal = id.Bit(FS_BIT_SHADER_DEPAL) && !texture3D;  // combination with texture3D not supported. Enforced elsewhere too.
-	bool smoothedDepal = PSP_CoreParameter().compat.flags().SmoothedDepal;
+	bool smoothedDepal = id.Bit(FS_BIT_SHADER_SMOOTHED_DEPAL);
 	bool bgraTexture = id.Bit(FS_BIT_BGRA_TEXTURE);
 	bool colorWriteMask = id.Bit(FS_BIT_COLOR_WRITEMASK) && compat.bitwiseOps;
 

diff --git a/GPU/Common/ShaderId.cpp b/GPU/Common/ShaderId.cpp
@@ -261,6 +261,7 @@ void ComputeFragmentShaderID(FShaderID *id_out, const Draw::Bugs &bugs) {
 		bool doTextureAlpha = gstate.isTextureAlphaUsed();
 		bool doFlatShading = gstate.getShadeMode() == GE_SHADE_FLAT;
 		bool useShaderDepal = gstate_c.useShaderDepal;
+		bool useSmoothedDepal = gstate_c.useSmoothedShaderDepal;
 		bool colorWriteMask = IsColorWriteMaskComplex(gstate_c.allowFramebufferRead);
 
 		// Note how we here recompute some of the work already done in state mapping.
@@ -290,6 +291,7 @@ void ComputeFragmentShaderID(FShaderID *id_out, const Draw::Bugs &bugs) {
 			}
 			id.SetBit(FS_BIT_BGRA_TEXTURE, gstate_c.bgraTexture);
 			id.SetBit(FS_BIT_SHADER_DEPAL, useShaderDepal);
+			id.SetBit(FS_BIT_SHADER_SMOOTHED_DEPAL, useSmoothedDepal);
 			id.SetBit(FS_BIT_3D_TEXTURE, gstate_c.curTextureIs3D);
 		}
 

diff --git a/GPU/Common/ShaderId.h b/GPU/Common/ShaderId.h
@@ -94,6 +94,7 @@ enum FShaderBit : uint8_t {
 	FS_BIT_NO_DEPTH_CANNOT_DISCARD_STENCIL = 49,
 	FS_BIT_COLOR_WRITEMASK = 50,
 	FS_BIT_3D_TEXTURE = 51,
+	FS_BIT_SHADER_SMOOTHED_DEPAL = 52,
 };
 
 static inline FShaderBit operator +(FShaderBit bit, int i) {

diff --git a/GPU/Common/TextureCacheCommon.cpp b/GPU/Common/TextureCacheCommon.cpp
@@ -1879,8 +1879,8 @@ void TextureCacheCommon::ApplyTextureFramebuffer(VirtualFramebuffer *framebuffer
 			const GEPaletteFormat clutFormat = gstate.getClutPaletteFormat();
 
 			// Very icky conflation here of native and thin3d rendering. This will need careful work per backend in BindAsClutTexture.
-			Draw::Texture *clutTexture = depalShaderCache_->GetClutTexture(clutFormat, clutHash_, clutBufRaw_);
-			BindAsClutTexture(clutTexture);
+			DepalTexture clutTexture = depalShaderCache_->GetClutTexture(clutFormat, clutHash_, clutBufRaw_);
+			BindAsClutTexture(clutTexture.texture);
 
 			framebufferManager_->BindFramebufferAsColorTexture(0, framebuffer, BINDFBCOLOR_MAY_COPY_WITH_UV | BINDFBCOLOR_APPLY_TEX_OFFSET);
 			// Vulkan needs to do some extra work here to pick out the native handle from Draw.
@@ -1894,7 +1894,7 @@ void TextureCacheCommon::ApplyTextureFramebuffer(VirtualFramebuffer *framebuffer
 
 			// Since we started/ended render passes, might need these.
 			gstate_c.Dirty(DIRTY_DEPAL);
-			gstate_c.SetUseShaderDepal(true);
+			gstate_c.SetUseShaderDepal(true, gstate.getClutIndexStartPos() == 0 && gstate.getClutIndexMask() <= clutTexture.rampLength);
 			gstate_c.depalFramebufferFormat = framebuffer->drawnFormat;
 			const u32 bytesPerColor = clutFormat == GE_CMODE_32BIT_ABGR8888 ? sizeof(u32) : sizeof(u16);
 			const u32 clutTotalColors = clutMaxBytes_ / bytesPerColor;
@@ -1907,12 +1907,12 @@ void TextureCacheCommon::ApplyTextureFramebuffer(VirtualFramebuffer *framebuffer
 		}
 
 		depalShader = depalShaderCache_->GetDepalettizeShader(clutMode, texFormat, depth ? GE_FORMAT_DEPTH16 : framebuffer->drawnFormat);
-		gstate_c.SetUseShaderDepal(false);
+		gstate_c.SetUseShaderDepal(false, false);
 	}
 
 	if (depalShader) {
 		const GEPaletteFormat clutFormat = gstate.getClutPaletteFormat();
-		Draw::Texture *clutTexture = depalShaderCache_->GetClutTexture(clutFormat, clutHash_, clutBufRaw_);
+		DepalTexture clutTexture = depalShaderCache_->GetClutTexture(clutFormat, clutHash_, clutBufRaw_);
 		Draw::Framebuffer *depalFBO = framebufferManager_->GetTempFBO(TempFBO::DEPAL, framebuffer->renderWidth, framebuffer->renderHeight);
 		draw_->BindTexture(0, nullptr);
 		draw_->BindTexture(1, nullptr);
@@ -1927,7 +1927,7 @@ void TextureCacheCommon::ApplyTextureFramebuffer(VirtualFramebuffer *framebuffer
 		shaderApply.Use();
 
 		draw_->BindFramebufferAsTexture(framebuffer->fbo, 0, depth ? Draw::FB_DEPTH_BIT : Draw::FB_COLOR_BIT, 0);
-		draw_->BindTexture(1, clutTexture);
+		draw_->BindTexture(1, clutTexture.texture);
 		Draw::SamplerState *nearest = depalShaderCache_->GetSampler();
 		draw_->BindSamplerStates(0, 1, &nearest);
 		draw_->BindSamplerStates(1, 1, &nearest);
@@ -1952,7 +1952,7 @@ void TextureCacheCommon::ApplyTextureFramebuffer(VirtualFramebuffer *framebuffer
 		framebufferManager_->BindFramebufferAsColorTexture(0, framebuffer, BINDFBCOLOR_MAY_COPY_WITH_UV | BINDFBCOLOR_APPLY_TEX_OFFSET);
 		BoundFramebufferTexture();
 
-		gstate_c.SetUseShaderDepal(false);
+		gstate_c.SetUseShaderDepal(false, false);
 		gstate_c.SetTextureFullAlpha(gstate.getTextureFormat() == GE_TFMT_5650);
 	}
 

diff --git a/GPU/GLES/TextureCacheGLES.cpp b/GPU/GLES/TextureCacheGLES.cpp
@@ -225,7 +225,7 @@ void TextureCacheGLES::BindTexture(TexCacheEntry *entry) {
 	int maxLevel = (entry->status & TexCacheEntry::STATUS_NO_MIPS) ? 0 : entry->maxLevel;
 	SamplerCacheKey samplerKey = GetSamplingParams(maxLevel, entry);
 	ApplySamplingParams(samplerKey);
-	gstate_c.SetUseShaderDepal(false);
+	gstate_c.SetUseShaderDepal(false, false);
 }
 
 void TextureCacheGLES::Unbind() {

diff --git a/GPU/GPUState.h b/GPU/GPUState.h
@@ -529,9 +529,10 @@ struct GPUStateCache {
 	bool IsDirty(u64 what) const {
 		return (dirty & what) != 0ULL;
 	}
-	void SetUseShaderDepal(bool depal) {
+	void SetUseShaderDepal(bool depal, bool smoothed) {
 		if (depal != useShaderDepal) {
 			useShaderDepal = depal;
+			useSmoothedShaderDepal = smoothed;
 			Dirty(DIRTY_FRAGMENTSHADER_STATE);
 		}
 	}
@@ -635,6 +636,7 @@ struct GPUStateCache {
 	int spline_num_points_u;
 
 	bool useShaderDepal;
+	bool useSmoothedShaderDepal;
 	GEBufferFormat depalFramebufferFormat;
 
 	u32 getRelativeAddress(u32 data) const;

diff --git a/GPU/Vulkan/TextureCacheVulkan.cpp b/GPU/Vulkan/TextureCacheVulkan.cpp
@@ -402,7 +402,7 @@ void TextureCacheVulkan::BindTexture(TexCacheEntry *entry) {
 	curSampler_ = samplerCache_.GetOrCreateSampler(samplerKey);
 	imageView_ = entry->vkTex->GetImageView();
 	drawEngine_->SetDepalTexture(VK_NULL_HANDLE);
-	gstate_c.SetUseShaderDepal(false);
+	gstate_c.SetUseShaderDepal(false, false);
 }
 
 void TextureCacheVulkan::ApplySamplingParams(const SamplerCacheKey &key) {

diff --git a/assets/compat.ini b/assets/compat.ini
@@ -1276,10 +1276,3 @@ UCKS45048 = true
 UCJS18030 = true
 UCJS18047 = true
 NPJG00015 = true
-
-[SmoothedDepal]
-# Test Drive Unlimited smoothed CLUT lookups. See comments in #13355
-ULET00386 = true
-ULES00637 = true
-ULKS46126 = true
-ULUS10249 = true