Geometry shader emulation for macOS (#5551)

* Implement vertex and geometry shader conversion to compute

* Call InitializeReservedCounts for compute too

* PR feedback

* Set clip distance mask for geometry and tessellation shaders too

* Transform feedback emulation only for vertex

3 files changed, 155 insertions, 102 deletions

diff --git a/src/Ryujinx.Graphics.Gpu/Memory/BufferManager.cs b/src/Ryujinx.Graphics.Gpu/Memory/BufferManager.cs
index bf4cb5d0..8e9b4b85 100644
--- a/src/Ryujinx.Graphics.Gpu/Memory/BufferManager.cs
+++ b/src/Ryujinx.Graphics.Gpu/Memory/BufferManager.cs
@@ -6,7 +6,6 @@ using Ryujinx.Graphics.Shader;
 using System;
 using System.Collections.Generic;
 using System.Runtime.CompilerServices;
-using System.Runtime.InteropServices;
 
 namespace Ryujinx.Graphics.Gpu.Memory
 {
@@ -15,9 +14,6 @@ namespace Ryujinx.Graphics.Gpu.Memory
     /// </summary>
     class BufferManager
     {
-        private const int TfInfoVertexCountOffset = Constants.TotalTransformFeedbackBuffers * sizeof(int);
-        private const int TfInfoBufferSize = TfInfoVertexCountOffset + sizeof(int);
-
         private readonly GpuContext _context;
         private readonly GpuChannel _channel;
 
@@ -104,9 +100,6 @@ namespace Ryujinx.Graphics.Gpu.Memory
         private readonly BuffersPerStage[] _gpStorageBuffers;
         private readonly BuffersPerStage[] _gpUniformBuffers;
 
-        private BufferHandle _tfInfoBuffer;
-        private readonly int[] _tfInfoData;
-
         private bool _gpStorageBuffersDirty;
         private bool _gpUniformBuffersDirty;
 
@@ -146,11 +139,6 @@ namespace Ryujinx.Graphics.Gpu.Memory
             _bufferTextures = new List<BufferTextureBinding>();
 
             _ranges = new BufferAssignment[Constants.TotalGpUniformBuffers * Constants.ShaderStages];
-
-            if (!context.Capabilities.SupportsTransformFeedback)
-            {
-                _tfInfoData = new int[Constants.TotalTransformFeedbackBuffers];
-            }
         }
 
 
@@ -339,13 +327,10 @@ namespace Ryujinx.Graphics.Gpu.Memory
         /// <param name="vertexCount">Vertex count per instance</param>
         public void SetInstancedDrawVertexCount(int vertexCount)
         {
-            if (!_context.Capabilities.SupportsTransformFeedback &&
-                HasTransformFeedbackOutputs &&
-                _tfInfoBuffer != BufferHandle.Null)
+            if (!_context.Capabilities.SupportsTransformFeedback && HasTransformFeedbackOutputs)
             {
-                Span<byte> data = stackalloc byte[sizeof(int)];
-                MemoryMarshal.Cast<byte, int>(data)[0] = vertexCount;
-                _context.Renderer.SetBufferData(_tfInfoBuffer, TfInfoVertexCountOffset, data);
+                _context.SupportBufferUpdater.SetTfeVertexCount(vertexCount);
+                _context.SupportBufferUpdater.Commit();
             }
         }
 
@@ -607,17 +592,7 @@ namespace Ryujinx.Graphics.Gpu.Memory
                 }
                 else if (HasTransformFeedbackOutputs)
                 {
-                    Span<int> info = _tfInfoData.AsSpan();
-                    Span<BufferAssignment> buffers = stackalloc BufferAssignment[Constants.TotalTransformFeedbackBuffers + 1];
-
-                    bool needsDataUpdate = false;
-
-                    if (_tfInfoBuffer == BufferHandle.Null)
-                    {
-                        _tfInfoBuffer = _context.Renderer.CreateBuffer(TfInfoBufferSize, BufferAccess.Stream);
-                    }
-
-                    buffers[0] = new BufferAssignment(0, new BufferRange(_tfInfoBuffer, 0, TfInfoBufferSize));
+                    Span<BufferAssignment> buffers = stackalloc BufferAssignment[Constants.TotalTransformFeedbackBuffers];
 
                     int alignment = _context.Capabilities.StorageBufferOffsetAlignment;
 
@@ -627,7 +602,7 @@ namespace Ryujinx.Graphics.Gpu.Memory
 
                         if (tfb.Address == 0)
                         {
-                            buffers[1 + index] = new BufferAssignment(1 + index, BufferRange.Empty);
+                            buffers[index] = new BufferAssignment(index, BufferRange.Empty);
                         }
                         else
                         {
@@ -637,22 +612,12 @@ namespace Ryujinx.Graphics.Gpu.Memory
 
                             int tfeOffset = ((int)tfb.Address & (alignment - 1)) / 4;
 
-                            if (info[index] != tfeOffset)
-                            {
-                                info[index] = tfeOffset;
-                                needsDataUpdate = true;
-                            }
+                            _context.SupportBufferUpdater.SetTfeOffset(index, tfeOffset);
 
-                            buffers[1 + index] = new BufferAssignment(1 + index, bufferCache.GetBufferRange(address, size, write: true));
+                            buffers[index] = new BufferAssignment(index, bufferCache.GetBufferRange(address, size, write: true));
                         }
                     }
 
-                    if (needsDataUpdate)
-                    {
-                        Span<byte> infoData = MemoryMarshal.Cast<int, byte>(info);
-                        _context.Renderer.SetBufferData(_tfInfoBuffer, 0, infoData);
-                    }
-
                     _context.Renderer.Pipeline.SetStorageBuffers(buffers);
                 }
             }
diff --git a/src/Ryujinx.Graphics.Gpu/Memory/BufferUpdater.cs b/src/Ryujinx.Graphics.Gpu/Memory/BufferUpdater.cs
new file mode 100644
index 00000000..02090c04
--- /dev/null
+++ b/src/Ryujinx.Graphics.Gpu/Memory/BufferUpdater.cs
@@ -0,0 +1,123 @@
+using Ryujinx.Graphics.GAL;
+using Ryujinx.Graphics.Shader;
+using System;
+
+namespace Ryujinx.Graphics.Gpu.Memory
+{
+    /// <summary>
+    /// Buffer data updater.
+    /// </summary>
+    class BufferUpdater : IDisposable
+    {
+        private BufferHandle _handle;
+
+        /// <summary>
+        /// Handle of the buffer.
+        /// </summary>
+        public BufferHandle Handle => _handle;
+
+        private readonly IRenderer _renderer;
+        private int _startOffset = -1;
+        private int _endOffset = -1;
+
+        /// <summary>
+        /// Creates a new instance of the buffer updater.
+        /// </summary>
+        /// <param name="renderer">Renderer that the buffer will be used with</param>
+        public BufferUpdater(IRenderer renderer)
+        {
+            _renderer = renderer;
+        }
+
+        /// <summary>
+        /// Mark a region of the buffer as modified and needing to be sent to the GPU.
+        /// </summary>
+        /// <param name="startOffset">Start offset of the region in bytes</param>
+        /// <param name="byteSize">Size of the region in bytes</param>
+        protected void MarkDirty(int startOffset, int byteSize)
+        {
+            int endOffset = startOffset + byteSize;
+
+            if (_startOffset == -1)
+            {
+                _startOffset = startOffset;
+                _endOffset = endOffset;
+            }
+            else
+            {
+                if (startOffset < _startOffset)
+                {
+                    _startOffset = startOffset;
+                }
+
+                if (endOffset > _endOffset)
+                {
+                    _endOffset = endOffset;
+                }
+            }
+        }
+
+        /// <summary>
+        /// Submits all pending buffer updates to the GPU.
+        /// </summary>
+        /// <param name="data">All data that should be sent to the GPU. Only the modified regions will be updated</param>
+        /// <param name="binding">Optional binding to bind the buffer if a new buffer was created</param>
+        protected void Commit(ReadOnlySpan<byte> data, int binding = -1)
+        {
+            if (_startOffset != -1)
+            {
+                if (_handle == BufferHandle.Null)
+                {
+                    _handle = _renderer.CreateBuffer(data.Length, BufferAccess.Stream);
+                    _renderer.Pipeline.ClearBuffer(_handle, 0, data.Length, 0);
+
+                    if (binding >= 0)
+                    {
+                        var range = new BufferRange(_handle, 0, data.Length);
+                        _renderer.Pipeline.SetUniformBuffers(stackalloc[] { new BufferAssignment(0, range) });
+                    }
+                };
+
+                _renderer.SetBufferData(_handle, _startOffset, data[_startOffset.._endOffset]);
+
+                _startOffset = -1;
+                _endOffset = -1;
+            }
+        }
+
+        /// <summary>
+        /// Gets a reference to a given element of a vector.
+        /// </summary>
+        /// <param name="vector">Vector to get the element reference from</param>
+        /// <param name="elementIndex">Element index</param>
+        /// <returns>Reference to the specified element</returns>
+        protected static ref T GetElementRef<T>(ref Vector4<T> vector, int elementIndex)
+        {
+            switch (elementIndex)
+            {
+                case 0:
+                    return ref vector.X;
+                case 1:
+                    return ref vector.Y;
+                case 2:
+                    return ref vector.Z;
+                case 3:
+                    return ref vector.W;
+                default:
+                    throw new ArgumentOutOfRangeException(nameof(elementIndex));
+            }
+        }
+
+        /// <summary>
+        /// Destroys the buffer.
+        /// </summary>
+        public void Dispose()
+        {
+            if (_handle != BufferHandle.Null)
+            {
+                _renderer.DeleteBuffer(_handle);
+                _handle = BufferHandle.Null;
+            }
+        }
+    }
+}
diff --git a/src/Ryujinx.Graphics.Gpu/Memory/SupportBufferUpdater.cs b/src/Ryujinx.Graphics.Gpu/Memory/SupportBufferUpdater.cs
index c1e91c54..fb141db4 100644
--- a/src/Ryujinx.Graphics.Gpu/Memory/SupportBufferUpdater.cs
+++ b/src/Ryujinx.Graphics.Gpu/Memory/SupportBufferUpdater.cs
@@ -9,57 +9,22 @@ namespace Ryujinx.Graphics.Gpu.Memory
     /// <summary>
     /// Support buffer data updater.
     /// </summary>
-    class SupportBufferUpdater : IDisposable
+    class SupportBufferUpdater : BufferUpdater
     {
         private SupportBuffer _data;
-        private BufferHandle _handle;
-
-        private readonly IRenderer _renderer;
-        private int _startOffset = -1;
-        private int _endOffset = -1;
 
         /// <summary>
         /// Creates a new instance of the support buffer updater.
         /// </summary>
         /// <param name="renderer">Renderer that the support buffer will be used with</param>
-        public SupportBufferUpdater(IRenderer renderer)
+        public SupportBufferUpdater(IRenderer renderer) : base(renderer)
         {
-            _renderer = renderer;
-
             var defaultScale = new Vector4<float> { X = 1f, Y = 0f, Z = 0f, W = 0f };
             _data.RenderScale.AsSpan().Fill(defaultScale);
             DirtyRenderScale(0, SupportBuffer.RenderScaleMaxCount);
         }
 
         /// <summary>
-        /// Mark a region of the support buffer as modified and needing to be sent to the GPU.
-        /// </summary>
-        /// <param name="startOffset">Start offset of the region in bytes</param>
-        /// <param name="byteSize">Size of the region in bytes</param>
-        private void MarkDirty(int startOffset, int byteSize)
-        {
-            int endOffset = startOffset + byteSize;
-
-            if (_startOffset == -1)
-            {
-                _startOffset = startOffset;
-                _endOffset = endOffset;
-            }
-            else
-            {
-                if (startOffset < _startOffset)
-                {
-                    _startOffset = startOffset;
-                }
-
-                if (endOffset > _endOffset)
-                {
-                    _endOffset = endOffset;
-                }
-            }
-        }
-
-        /// <summary>
         /// Marks the fragment render scale count as being modified.
         /// </summary>
         private void DirtyFragmentRenderScaleCount()
@@ -220,40 +185,40 @@ namespace Ryujinx.Graphics.Gpu.Memory
         }
 
         /// <summary>
-        /// Submits all pending buffer updates to the GPU.
+        /// Sets offset for the misaligned portion of a transform feedback buffer, and the buffer size, for transform feedback emulation.
         /// </summary>
-        public void Commit()
+        /// <param name="bufferIndex">Index of the transform feedback buffer</param>
+        /// <param name="offset">Misaligned offset of the buffer</param>
+        public void SetTfeOffset(int bufferIndex, int offset)
         {
-            if (_startOffset != -1)
-            {
-                if (_handle == BufferHandle.Null)
-                {
-                    _handle = _renderer.CreateBuffer(SupportBuffer.RequiredSize, BufferAccess.Stream);
-                    _renderer.Pipeline.ClearBuffer(_handle, 0, SupportBuffer.RequiredSize, 0);
+            ref int currentOffset = ref GetElementRef(ref _data.TfeOffset, bufferIndex);
 
-                    var range = new BufferRange(_handle, 0, SupportBuffer.RequiredSize);
-                    _renderer.Pipeline.SetUniformBuffers(stackalloc[] { new BufferAssignment(0, range) });
-                }
-
-                ReadOnlySpan<byte> data = MemoryMarshal.Cast<SupportBuffer, byte>(MemoryMarshal.CreateSpan(ref _data, 1));
-
-                _renderer.SetBufferData(_handle, _startOffset, data[_startOffset.._endOffset]);
-
-                _startOffset = -1;
-                _endOffset = -1;
+            if (currentOffset != offset)
+            {
+                currentOffset = offset;
+                MarkDirty(SupportBuffer.TfeOffsetOffset + bufferIndex * sizeof(int), sizeof(int));
             }
         }
 
         /// <summary>
-        /// Destroys the support buffer.
+        /// Sets the vertex count used for transform feedback emulation with instanced draws.
         /// </summary>
-        public void Dispose()
+        /// <param name="vertexCount">Vertex count of the instanced draw</param>
+        public void SetTfeVertexCount(int vertexCount)
         {
-            if (_handle != BufferHandle.Null)
+            if (_data.TfeVertexCount.X != vertexCount)
             {
-                _renderer.DeleteBuffer(_handle);
-                _handle = BufferHandle.Null;
+                _data.TfeVertexCount.X = vertexCount;
+                MarkDirty(SupportBuffer.TfeVertexCountOffset, sizeof(int));
             }
         }
+
+        /// <summary>
+        /// Submits all pending buffer updates to the GPU.
+        /// </summary>
+        public void Commit()
+        {
+            Commit(MemoryMarshal.Cast<SupportBuffer, byte>(MemoryMarshal.CreateSpan(ref _data, 1)), SupportBuffer.Binding);
+        }
     }
 }