GPU: 24-bit display depth support

src/core/gpu_hw.cpp

@@ -378,6 +378,68 @@ void main()
   return ss.str();
 }
 
+std::string GPU_HW::GenerateRGB24DecodeFragmentShader()
+{
+  std::stringstream ss;
+  GenerateShaderHeader(ss);
+
+  ss << R"(
+in vec2 v_tex0;
+out vec4 o_col0;
+
+uniform sampler2D samp0;
+uniform ivec2 u_base_coords;
+
+void main()
+{
+  // compute offset in dwords from the start of the 24-bit values
+  ivec2 base = ivec2(u_base_coords.x, u_base_coords.y + int(gl_FragCoord.y));
+  int xoff = int(gl_FragCoord.x);
+  int dword_index = (xoff / 2) + (xoff / 4);
+
+  // sample two adjacent dwords, or four 16-bit values as the 24-bit value will lie somewhere between these
+  uint s0 = RGBA8ToRGBA5551(texelFetch(samp0, ivec2(base.x + dword_index * 2 + 0, base.y), 0));
+  uint s1 = RGBA8ToRGBA5551(texelFetch(samp0, ivec2(base.x + dword_index * 2 + 1, base.y), 0));
+  uint s2 = RGBA8ToRGBA5551(texelFetch(samp0, ivec2(base.x + (dword_index + 1) * 2 + 0, base.y), 0));
+  uint s3 = RGBA8ToRGBA5551(texelFetch(samp0, ivec2(base.x + (dword_index + 1) * 2 + 1, base.y), 0));
+
+  // select the bit for this pixel depending on its offset in the 4-pixel block
+  uint r, g, b;
+  switch (xoff & 3)
+  {
+    case 0:
+      r = s0 & 0xFFu;
+      g = s0 >> 8;
+      b = s1 & 0xFFu;
+      break;
+
+    case 1:
+      r = s1 >> 8;
+      g = s2 & 0xFFu;
+      b = s2 >> 8;
+      break;
+
+    case 2:
+      r = s1 & 0xFFu;
+      g = s1 >> 8;
+      b = s2 & 0xFFu;
+      break;
+
+    case 3:
+      r = s2 >> 8;
+      g = s3 & 0xFFu;
+      b = s3 >> 8;
+      break;
+  }
+
+  // and normalize
+  o_col0 = vec4(float(r) / 255.0, float(g) / 255.0, float(b) / 255, 1.0);
+}
+)";
+
+  return ss.str();
+}
+
 GPU_HW::HWRenderBatch::Primitive GPU_HW::GetPrimitiveForCommand(RenderCommand rc)
 {
   if (rc.primitive == Primitive::Line)

src/core/gpu_hw.h

@@ -88,6 +88,7 @@ protected:
                                      bool blending);
   std::string GenerateScreenQuadVertexShader();
   std::string GenerateFillFragmentShader();
+  std::string GenerateRGB24DecodeFragmentShader();
 
   u32 m_resolution_scale = 1;
   HWRenderBatch m_batch = {};

src/core/gpu_hw_opengl.cpp

@@ -300,6 +300,21 @@ bool GPU_HW_OpenGL::CompilePrograms()
     }
   }
 
+  // TODO: Use string_view
+  if (!m_reinterpret_rgb8_program.Compile(GenerateScreenQuadVertexShader().c_str(),
+                                          GenerateRGB24DecodeFragmentShader().c_str()))
+  {
+    return false;
+  }
+  m_reinterpret_rgb8_program.BindFragData(0, "o_col0");
+  if (!m_reinterpret_rgb8_program.Link())
+    return false;
+
+  m_reinterpret_rgb8_program.Bind();
+  m_reinterpret_rgb8_program.RegisterUniform("u_base_coords");
+  m_reinterpret_rgb8_program.RegisterUniform("samp0");
+  m_reinterpret_rgb8_program.Uniform1i(1, 0);
+
   return true;
 }
 
@@ -404,7 +419,6 @@ void GPU_HW_OpenGL::UpdateDisplay()
   const u32 texture_width = m_vram_texture->GetWidth();
   const u32 texture_height = m_vram_texture->GetHeight();
 
-  // TODO: 24-bit support.
   if (m_debug_options.show_vram)
   {
     m_system->GetHostInterface()->SetDisplayTexture(m_vram_texture.get(), 0, 0, texture_width, texture_height, 1.0f);
@@ -419,9 +433,31 @@ void GPU_HW_OpenGL::UpdateDisplay()
       ((vram_offset_x + display_width) > texture_width) ? (texture_width - vram_offset_x) : display_width;
     const u32 copy_height =
       ((vram_offset_y + display_height) > texture_height) ? (texture_height - vram_offset_y) : display_height;
-    glCopyImageSubData(m_vram_texture->GetGLId(), GL_TEXTURE_2D, 0, vram_offset_x,
-                       texture_height - vram_offset_y - copy_height, 0, m_display_texture->GetGLId(), GL_TEXTURE_2D, 0,
-                       0, 0, 0, copy_width, copy_height, 1);
+
+    if (m_GPUSTAT.display_area_color_depth_24)
+    {
+      glBindFramebuffer(GL_FRAMEBUFFER, m_display_fbo);
+      glViewport(0, 0, copy_width, copy_height);
+      glDisable(GL_BLEND);
+      glDisable(GL_SCISSOR_TEST);
+      m_reinterpret_rgb8_program.Bind();
+      m_reinterpret_rgb8_program.Uniform2i(0, vram_offset_x, texture_height - vram_offset_y - copy_height);
+      m_vram_texture->Bind();
+      glDrawArrays(GL_TRIANGLES, 0, 3);
+
+      // restore state
+      glBindFramebuffer(GL_FRAMEBUFFER, m_vram_fbo);
+      glViewport(0, 0, m_vram_texture->GetWidth(), m_vram_texture->GetHeight());
+      glEnable(GL_SCISSOR_TEST);
+      if (m_last_transparency_enable)
+        glEnable(GL_BLEND);
+    }
+    else
+    {
+      glCopyImageSubData(m_vram_texture->GetGLId(), GL_TEXTURE_2D, 0, vram_offset_x,
+                         texture_height - vram_offset_y - copy_height, 0, m_display_texture->GetGLId(), GL_TEXTURE_2D,
+                         0, 0, 0, 0, copy_width, copy_height, 1);
+    }
 
     m_system->GetHostInterface()->SetDisplayTexture(m_display_texture.get(), 0, 0, copy_width, copy_height,
                                                     DISPLAY_ASPECT_RATIO);

src/core/gpu_hw_opengl.h

@@ -75,7 +75,7 @@ private:
   TransparencyMode m_last_transparency_mode = TransparencyMode::BackgroundMinusForeground;
 
   std::array<std::array<std::array<std::array<GL::Program, 2>, 3>, 2>, 2> m_render_programs;
-  std::array<GL::Program, 3> m_texture_page_programs;
+  GL::Program m_reinterpret_rgb8_program;
 
   GLStats m_stats = {};
   GLStats m_last_stats = {};