Better checks for smoothed depal

hrydgard · Aug 22, 2022 · 89d05b7 · 89d05b7
1 parent 91b1421
commit 89d05b7
Show file tree

Hide file tree

Showing 3 changed files with 32 additions and 2 deletions.
diff --git a/GPU/Common/DepalettizeCommon.h b/GPU/Common/DepalettizeCommon.h
@@ -40,7 +40,8 @@ class DepalTexture {
 public:
 	Draw::Texture *texture;
 	int lastFrame;
-	int rampLength;  // How many entries are continuously growing from entry 0.
+	// How many entries are continuously growing (each value larger than the previous) from entry 0.
+	int rampLength;
 };
 
 // Caches both shaders and palette textures.

diff --git a/GPU/Common/FragmentShaderGenerator.cpp b/GPU/Common/FragmentShaderGenerator.cpp
@@ -602,6 +602,9 @@ bool GenerateFragmentShader(const FShaderID &id, char *buffer, const ShaderLangu
 				} else {
 					WRITE(p, "  vec2 uv = %s.xy;\n  vec2 uv_round;\n", texcoord);
 				}
+				// Restrictions on this are checked before setting the smoothed flag.
+				// Only RGB565 and RGBA5551 are supported, and only the specific shifts hitting the
+				// channels directly.
 				WRITE(p, "  vec4 t = %s(tex, %s.xy);\n", compat.texture, texcoord);
 				WRITE(p, "  uint depalShift = (u_depal_mask_shift_off_fmt >> 8) & 0xFFU;\n");
 				WRITE(p, "  uint depalFmt = (u_depal_mask_shift_off_fmt >> 24) & 0x3U;\n");

diff --git a/GPU/Common/TextureCacheCommon.cpp b/GPU/Common/TextureCacheCommon.cpp
@@ -1852,6 +1852,31 @@ bool CanDepalettize(GETextureFormat texFormat, GEBufferFormat bufferFormat) {
 	}
 }
 
+// If the palette is detected as a smooth ramp, we can interpolate for higher color precision.
+// But we only do it if the mask/shift exactly matches a color channel, else something different might be going
+// on and we definitely don't want to interpolate.
+// Great enhancement for Test Drive.
+static bool CanUseSmoothDepal(const GPUgstate &gstate, GEBufferFormat framebufferFormat, int rampLength) {
+	if (gstate.getClutIndexStartPos() == 0 &&
+		gstate.getClutIndexMask() <= rampLength) {
+		switch (framebufferFormat) {
+		case GE_FORMAT_565:
+			if (gstate.getClutIndexShift() == 0 || gstate.getClutIndexShift() == 11) {
+				return gstate.getClutIndexMask() == 0x1F;
+			} else if (gstate.getClutIndexShift() == 5) {
+				return gstate.getClutIndexMask() == 0x3F;
+			}
+			break;
+		case GE_FORMAT_5551:
+			if (gstate.getClutIndexShift() == 0 || gstate.getClutIndexShift() == 5 || gstate.getClutIndexShift() == 10) {
+				return gstate.getClutIndexMask() == 0x1F;
+			}
+			break;
+		}
+	}
+	return false;
+}
+
 void TextureCacheCommon::ApplyTextureFramebuffer(VirtualFramebuffer *framebuffer, GETextureFormat texFormat, RasterChannel channel) {
 	DepalShader *depalShader = nullptr;
 	uint32_t clutMode = gstate.clutformat & 0xFFFFFF;
@@ -1894,7 +1919,8 @@ void TextureCacheCommon::ApplyTextureFramebuffer(VirtualFramebuffer *framebuffer
 
 			// Since we started/ended render passes, might need these.
 			gstate_c.Dirty(DIRTY_DEPAL);
-			gstate_c.SetUseShaderDepal(true, gstate.getClutIndexStartPos() == 0 && gstate.getClutIndexMask() <= clutTexture.rampLength);
+
+			gstate_c.SetUseShaderDepal(true, CanUseSmoothDepal(gstate, framebuffer->drawnFormat, clutTexture.rampLength));
 			gstate_c.depalFramebufferFormat = framebuffer->drawnFormat;
 			const u32 bytesPerColor = clutFormat == GE_CMODE_32BIT_ABGR8888 ? sizeof(u32) : sizeof(u16);
 			const u32 clutTotalColors = clutMaxBytes_ / bytesPerColor;