ryujinx/Ryujinx.Graphics.GAL/Multithreading/Resources/ThreadedTexture.cs
riperiperi bf77d1cab9
GPU: Pass SpanOrArray for Texture SetData to avoid copy (#3745)
* GPU: Pass SpanOrArray for Texture SetData to avoid copy

Texture data is often converted before upload, meaning that an array was allocated to perform the conversion into. However, the backend SetData methods were being passed a Span of that data, and the Multithreaded layer does `ToArray()` on it so that it can be stored for later! This method can't extract the original array, so it creates a copy.

This PR changes the type passed for textures to a new ref struct called SpanOrArray, which is backed by either a ReadOnlySpan or an array. The benefit here is that we can have a ToArray method that doesn't copy if it is originally backed by an array.

This will also avoid a copy when running the ASTC decoder.

On NieR this was taking 38% of texture upload time, which it does a _lot_ of when you move between areas, so there should be a 1.6x performance boost when strictly uploading textures. No doubt this will also improve texture streaming performance in UE4 games, and maybe a small reduction with video playback.

From the numbers, it's probably possible to improve the upload rate by a further 1.6x by performing layout conversion on GPU. I'm not sure if we could improve it further than that - multithreading conversion on CPU would probably result in memory bottleneck.

This doesn't extend to buffers, since we don't convert their data on the GPU emulator side.

* Remove implicit cast to array.
2022-10-08 12:04:47 -03:00

142 lines
4.7 KiB
C#

using Ryujinx.Common.Memory;
using Ryujinx.Graphics.GAL.Multithreading.Commands.Texture;
using Ryujinx.Graphics.GAL.Multithreading.Model;
using System;
namespace Ryujinx.Graphics.GAL.Multithreading.Resources
{
/// <summary>
/// Threaded representation of a texture.
/// </summary>
class ThreadedTexture : ITexture
{
private ThreadedRenderer _renderer;
private TextureCreateInfo _info;
public ITexture Base;
public int Width => _info.Width;
public int Height => _info.Height;
public float ScaleFactor { get; }
public ThreadedTexture(ThreadedRenderer renderer, TextureCreateInfo info, float scale)
{
_renderer = renderer;
_info = info;
ScaleFactor = scale;
}
private TableRef<T> Ref<T>(T reference)
{
return new TableRef<T>(_renderer, reference);
}
public void CopyTo(ITexture destination, int firstLayer, int firstLevel)
{
_renderer.New<TextureCopyToCommand>().Set(Ref(this), Ref((ThreadedTexture)destination), firstLayer, firstLevel);
_renderer.QueueCommand();
}
public void CopyTo(ITexture destination, int srcLayer, int dstLayer, int srcLevel, int dstLevel)
{
_renderer.New<TextureCopyToSliceCommand>().Set(Ref(this), Ref((ThreadedTexture)destination), srcLayer, dstLayer, srcLevel, dstLevel);
_renderer.QueueCommand();
}
public void CopyTo(ITexture destination, Extents2D srcRegion, Extents2D dstRegion, bool linearFilter)
{
ThreadedTexture dest = (ThreadedTexture)destination;
if (_renderer.IsGpuThread())
{
_renderer.New<TextureCopyToScaledCommand>().Set(Ref(this), Ref(dest), srcRegion, dstRegion, linearFilter);
_renderer.QueueCommand();
}
else
{
// Scaled copy can happen on another thread for a res scale flush.
ThreadedHelpers.SpinUntilNonNull(ref Base);
ThreadedHelpers.SpinUntilNonNull(ref dest.Base);
Base.CopyTo(dest.Base, srcRegion, dstRegion, linearFilter);
}
}
public ITexture CreateView(TextureCreateInfo info, int firstLayer, int firstLevel)
{
ThreadedTexture newTex = new ThreadedTexture(_renderer, info, ScaleFactor);
_renderer.New<TextureCreateViewCommand>().Set(Ref(this), Ref(newTex), info, firstLayer, firstLevel);
_renderer.QueueCommand();
return newTex;
}
public ReadOnlySpan<byte> GetData()
{
if (_renderer.IsGpuThread())
{
ResultBox<PinnedSpan<byte>> box = new ResultBox<PinnedSpan<byte>>();
_renderer.New<TextureGetDataCommand>().Set(Ref(this), Ref(box));
_renderer.InvokeCommand();
return box.Result.Get();
}
else
{
ThreadedHelpers.SpinUntilNonNull(ref Base);
return Base.GetData();
}
}
public ReadOnlySpan<byte> GetData(int layer, int level)
{
if (_renderer.IsGpuThread())
{
ResultBox<PinnedSpan<byte>> box = new ResultBox<PinnedSpan<byte>>();
_renderer.New<TextureGetDataSliceCommand>().Set(Ref(this), Ref(box), layer, level);
_renderer.InvokeCommand();
return box.Result.Get();
}
else
{
ThreadedHelpers.SpinUntilNonNull(ref Base);
return Base.GetData(layer, level);
}
}
public void SetData(SpanOrArray<byte> data)
{
_renderer.New<TextureSetDataCommand>().Set(Ref(this), Ref(data.ToArray()));
_renderer.QueueCommand();
}
public void SetData(SpanOrArray<byte> data, int layer, int level)
{
_renderer.New<TextureSetDataSliceCommand>().Set(Ref(this), Ref(data.ToArray()), layer, level);
_renderer.QueueCommand();
}
public void SetData(SpanOrArray<byte> data, int layer, int level, Rectangle<int> region)
{
_renderer.New<TextureSetDataSliceRegionCommand>().Set(Ref(this), Ref(data.ToArray()), layer, level, region);
_renderer.QueueCommand();
}
public void SetStorage(BufferRange buffer)
{
_renderer.New<TextureSetStorageCommand>().Set(Ref(this), buffer);
_renderer.QueueCommand();
}
public void Release()
{
_renderer.New<TextureReleaseCommand>().Set(Ref(this));
_renderer.QueueCommand();
}
}
}