New shader cache implementation (#3194)

* New shader cache implementation

* Remove some debug code

* Take transform feedback varying count into account

* Create shader cache directory if it does not exist + fragment output map related fixes

* Remove debug code

* Only check texture descriptors if the constant buffer is bound

* Also check CPU VA on GetSpanMapped

* Remove more unused code and move cache related code

* XML docs + remove more unused methods

* Better codegen for TransformFeedbackDescriptor.AsSpan

* Support migration from old cache format, remove more unused code

Shader cache rebuild now also rewrites the shared toc and data files

* Fix migration error with BRX shaders

* Add a limit to the async translation queue

 Avoid async translation threads not being able to keep up and the queue growing very large

* Re-create specialization state on recompile

This might be required if a new version of the shader translator requires more or less state, or if there is a bug related to the GPU state access

* Make shader cache more error resilient

* Add some missing XML docs and move GpuAccessor docs to the interface/use inheritdoc

* Address early PR feedback

* Fix rebase

* Remove IRenderer.CompileShader and IShader interface, replace with new ShaderSource struct passed to CreateProgram directly

* Handle some missing exceptions

* Make shader cache purge delete both old and new shader caches

* Register textures on new specialization state

* Translate and compile shaders in forward order (eliminates diffs due to different binding numbers)

* Limit in-flight shader compilation to the maximum number of compilation threads

* Replace ParallelDiskCacheLoader state changed event with a callback function

* Better handling for invalid constant buffer 1 data length

* Do not create the old cache directory structure if the old cache does not exist

* Constant buffer use should be per-stage. This change will invalidate existing new caches (file format version was incremented)

* Replace rectangle texture with just coordinate normalization

* Skip incompatible shaders that are missing texture information, instead of crashing

This is required if we, for example, support new texture instruction to the shader translator, and then they allow access to textures that were not accessed before. In this scenario, the old cache entry is no longer usable

* Fix coordinates normalization on cubemap textures

* Check if title ID is null before combining shader cache path

* More robust constant buffer address validation on spec state

* More robust constant buffer address validation on spec state (2)

* Regenerate shader cache with one stream, rather than one per shader.

* Only create shader cache directory during initialization

* Logging improvements

* Proper shader program disposal

* PR feedback, and add a comment on serialized structs

* XML docs for RegisterTexture

Co-authored-by: riperiperi <rhy3756547@hotmail.com>

Ryujinx.Graphics.Gpu/Shader/GpuAccessorState.cs

@@ -1,72 +1,61 @@
-using Ryujinx.Graphics.GAL;
-using Ryujinx.Graphics.Gpu.Engine.Threed;
-
 namespace Ryujinx.Graphics.Gpu.Shader
 {
     /// <summary>
     /// State used by the <see cref="GpuAccessor"/>.
     /// </summary>
-    struct GpuAccessorState
+    class GpuAccessorState
     {
         /// <summary>
-        /// GPU virtual address of the texture pool.
+        /// GPU texture pool state.
         /// </summary>
-        public ulong TexturePoolGpuVa { get; }
+        public readonly GpuChannelPoolState PoolState;
 
         /// <summary>
-        /// Maximum ID of the texture pool.
+        /// GPU compute state, for compute shaders.
         /// </summary>
-        public int TexturePoolMaximumId { get; }
+        public readonly GpuChannelComputeState ComputeState;
 
         /// <summary>
-        /// Constant buffer slot where the texture handles are located.
+        /// GPU graphics state, for vertex, tessellation, geometry and fragment shaders.
         /// </summary>
-        public int TextureBufferIndex { get; }
+        public readonly GpuChannelGraphicsState GraphicsState;
 
         /// <summary>
-        /// Early Z force enable.
+        /// Shader specialization state (shared by all stages).
         /// </summary>
-        public bool EarlyZForce { get; }
-
-        /// <summary>
-        /// Primitive topology of current draw.
-        /// </summary>
-        public PrimitiveTopology Topology { get; }
-
-        /// <summary>
-        /// Tessellation mode.
-        /// </summary>
-        public TessMode TessellationMode { get; }
+        public readonly ShaderSpecializationState SpecializationState;
 
         /// <summary>
         /// Transform feedback information, if the shader uses transform feedback. Otherwise, should be null.
         /// </summary>
-        public TransformFeedbackDescriptor[] TransformFeedbackDescriptors { get; set; }
+        public readonly TransformFeedbackDescriptor[] TransformFeedbackDescriptors;
 
         /// <summary>
-        /// Creates a new instance of the GPU accessor state.
+        /// Shader resource counts (shared by all stages).
         /// </summary>
-        /// <param name="texturePoolGpuVa">GPU virtual address of the texture pool</param>
-        /// <param name="texturePoolMaximumId">Maximum ID of the texture pool</param>
-        /// <param name="textureBufferIndex">Constant buffer slot where the texture handles are located</param>
-        /// <param name="earlyZForce">Early Z force enable</param>
-        /// <param name="topology">Primitive topology</param>
-        /// <param name="tessellationMode">Tessellation mode</param>
+        public readonly ResourceCounts ResourceCounts;
+
+        /// <summary>
+        /// Creates a new GPU accessor state.
+        /// </summary>
+        /// <param name="poolState">GPU texture pool state</param>
+        /// <param name="computeState">GPU compute state, for compute shaders</param>
+        /// <param name="graphicsState">GPU graphics state, for vertex, tessellation, geometry and fragment shaders</param>
+        /// <param name="specializationState">Shader specialization state (shared by all stages)</param>
+        /// <param name="transformFeedbackDescriptors">Transform feedback information, if the shader uses transform feedback. Otherwise, should be null</param>
         public GpuAccessorState(
-            ulong texturePoolGpuVa,
-            int texturePoolMaximumId,
-            int textureBufferIndex,
-            bool earlyZForce,
-            PrimitiveTopology topology,
-            TessMode tessellationMode)
+            GpuChannelPoolState poolState,
+            GpuChannelComputeState computeState,
+            GpuChannelGraphicsState graphicsState,
+            ShaderSpecializationState specializationState,
+            TransformFeedbackDescriptor[] transformFeedbackDescriptors = null)
         {
-            TexturePoolGpuVa = texturePoolGpuVa;
-            TexturePoolMaximumId = texturePoolMaximumId;
-            TextureBufferIndex = textureBufferIndex;
-            EarlyZForce = earlyZForce;
-            Topology = topology;
-            TessellationMode = tessellationMode;
-            TransformFeedbackDescriptors = null;
+            PoolState = poolState;
+            GraphicsState = graphicsState;
+            ComputeState = computeState;
+            SpecializationState = specializationState;
+            TransformFeedbackDescriptors = transformFeedbackDescriptors;
+            ResourceCounts = new ResourceCounts();
         }
     }
 }