Ryujinx/Ryujinx.Graphics.OpenGL/Renderer.cs
riperiperi ec3e848d79
Add a Multithreading layer for the GAL, multi-thread shader compilation at runtime (#2501)
* Initial Implementation

About as fast as nvidia GL multithreading, can be improved with faster command queuing.

* Struct based command list

Speeds up a bit. Still a lot of time lost to resource copy.

* Do shader init while the render thread is active.

* Introduce circular span pool V1

Ideally should be able to use structs instead of references for storing these spans on commands. Will try that next.

* Refactor SpanRef some more

Use a struct to represent SpanRef, rather than a reference.

* Flush buffers on background thread

* Use a span for UpdateRenderScale.

Much faster than copying the array.

* Calculate command size using reflection

* WIP parallel shaders

* Some minor optimisation

* Only 2 max refs per command now.

The command with 3 refs is gone. 😌

* Don't cast on the GPU side

* Remove redundant casts, force sync on window present

* Fix Shader Cache

* Fix host shader save.

* Fixup to work with new renderer stuff

* Make command Run static, use array of delegates as lookup

Profile says this takes less time than the previous way.

* Bring up to date

* Add settings toggle. Fix Muiltithreading Off mode.

* Fix warning.

* Release tracking lock for flushes

* Fix Conditional Render fast path with threaded gal

* Make handle iteration safe when releasing the lock

This is mostly temporary.

* Attempt to set backend threading on driver

Only really works on nvidia before launching a game.

* Fix race condition with BufferModifiedRangeList, exceptions in tracking actions

* Update buffer set commands

* Some cleanup

* Only use stutter workaround when using opengl renderer non-threaded

* Add host-conditional reservation of counter events

There has always been the possibility that conditional rendering could use a query object just as it is disposed by the counter queue. This change makes it so that when the host decides to use host conditional rendering, the query object is reserved so that it cannot be deleted. Counter events can optionally start reserved, as the threaded implementation can reserve them before the backend creates them, and there would otherwise be a short amount of time where the counter queue could dispose the event before a call to reserve it could be made.

* Address Feedback

* Make counter flush tracked again.

Hopefully does not cause any issues this time.

* Wait for FlushTo on the main queue thread.

Currently assumes only one thread will want to FlushTo (in this case, the GPU thread)

* Add SDL2 headless integration

* Add HLE macro commands.

Co-authored-by: Mary <mary@mary.zone>
2021-08-27 00:31:29 +02:00

225 lines
6.7 KiB
C#

using OpenTK.Graphics;
using OpenTK.Graphics.OpenGL;
using Ryujinx.Common.Configuration;
using Ryujinx.Common.Logging;
using Ryujinx.Graphics.GAL;
using Ryujinx.Graphics.OpenGL.Image;
using Ryujinx.Graphics.OpenGL.Queries;
using Ryujinx.Graphics.Shader;
using System;
namespace Ryujinx.Graphics.OpenGL
{
public sealed class Renderer : IRenderer
{
private readonly Pipeline _pipeline;
public IPipeline Pipeline => _pipeline;
private readonly Counters _counters;
private readonly Window _window;
public IWindow Window => _window;
private TextureCopy _textureCopy;
private TextureCopy _backgroundTextureCopy;
internal TextureCopy TextureCopy => BackgroundContextWorker.InBackground ? _backgroundTextureCopy : _textureCopy;
private Sync _sync;
public event EventHandler<ScreenCaptureImageInfo> ScreenCaptured;
internal PersistentBuffers PersistentBuffers { get; }
internal ResourcePool ResourcePool { get; }
internal int BufferCount { get; private set; }
public string GpuVendor { get; private set; }
public string GpuRenderer { get; private set; }
public string GpuVersion { get; private set; }
public bool PreferThreading => true;
public Renderer()
{
_pipeline = new Pipeline();
_counters = new Counters();
_window = new Window(this);
_textureCopy = new TextureCopy(this);
_backgroundTextureCopy = new TextureCopy(this);
_sync = new Sync();
PersistentBuffers = new PersistentBuffers();
ResourcePool = new ResourcePool();
}
public IShader CompileShader(ShaderStage stage, string code)
{
return new Shader(stage, code);
}
public BufferHandle CreateBuffer(int size)
{
BufferCount++;
return Buffer.Create(size);
}
public IProgram CreateProgram(IShader[] shaders, TransformFeedbackDescriptor[] transformFeedbackDescriptors)
{
return new Program(shaders, transformFeedbackDescriptors);
}
public ISampler CreateSampler(SamplerCreateInfo info)
{
return new Sampler(info);
}
public ITexture CreateTexture(TextureCreateInfo info, float scaleFactor)
{
if (info.Target == Target.TextureBuffer)
{
return new TextureBuffer(this, info);
}
else
{
return ResourcePool.GetTextureOrNull(info, scaleFactor) ?? new TextureStorage(this, info, scaleFactor).CreateDefaultView();
}
}
public void DeleteBuffer(BufferHandle buffer)
{
Buffer.Delete(buffer);
}
public ReadOnlySpan<byte> GetBufferData(BufferHandle buffer, int offset, int size)
{
return Buffer.GetData(this, buffer, offset, size);
}
public Capabilities GetCapabilities()
{
return new Capabilities(
HwCapabilities.Vendor == HwCapabilities.GpuVendor.IntelWindows,
HwCapabilities.Vendor == HwCapabilities.GpuVendor.AmdWindows,
HwCapabilities.SupportsAstcCompression,
HwCapabilities.SupportsImageLoadFormatted,
HwCapabilities.SupportsMismatchingViewFormat,
HwCapabilities.SupportsNonConstantTextureOffset,
HwCapabilities.SupportsTextureShadowLod,
HwCapabilities.SupportsViewportSwizzle,
HwCapabilities.SupportsIndirectParameters,
HwCapabilities.MaximumComputeSharedMemorySize,
HwCapabilities.MaximumSupportedAnisotropy,
HwCapabilities.StorageBufferOffsetAlignment);
}
public void SetBufferData(BufferHandle buffer, int offset, ReadOnlySpan<byte> data)
{
Buffer.SetData(buffer, offset, data);
}
public void UpdateCounters()
{
_counters.Update();
}
public void PreFrame()
{
_sync.Cleanup();
ResourcePool.Tick();
}
public ICounterEvent ReportCounter(CounterType type, EventHandler<ulong> resultHandler, bool hostReserved)
{
return _counters.QueueReport(type, resultHandler, _pipeline.DrawCount, hostReserved);
}
public void Initialize(GraphicsDebugLevel glLogLevel)
{
Debugger.Initialize(glLogLevel);
PrintGpuInformation();
if (HwCapabilities.SupportsParallelShaderCompile)
{
GL.Arb.MaxShaderCompilerThreads(Math.Min(Environment.ProcessorCount, 8));
}
_pipeline.Initialize();
_counters.Initialize();
}
private void PrintGpuInformation()
{
GpuVendor = GL.GetString(StringName.Vendor);
GpuRenderer = GL.GetString(StringName.Renderer);
GpuVersion = GL.GetString(StringName.Version);
Logger.Notice.Print(LogClass.Gpu, $"{GpuVendor} {GpuRenderer} ({GpuVersion})");
}
public void ResetCounter(CounterType type)
{
_counters.QueueReset(type);
}
public void BackgroundContextAction(Action action, bool alwaysBackground = false)
{
// alwaysBackground is ignored, since we cannot switch from the current context.
if (IOpenGLContext.HasContext())
{
action(); // We have a context already - use that (assuming it is the main one).
}
else
{
_window.BackgroundContext.Invoke(action);
}
}
public void InitializeBackgroundContext(IOpenGLContext baseContext)
{
_window.InitializeBackgroundContext(baseContext);
}
public void Dispose()
{
_textureCopy.Dispose();
_backgroundTextureCopy.Dispose();
PersistentBuffers.Dispose();
ResourcePool.Dispose();
_pipeline.Dispose();
_window.Dispose();
_counters.Dispose();
_sync.Dispose();
}
public IProgram LoadProgramBinary(byte[] programBinary)
{
return new Program(programBinary);
}
public void CreateSync(ulong id)
{
_sync.Create(id);
}
public void WaitSync(ulong id)
{
_sync.Wait(id);
}
public void Screenshot()
{
_window.ScreenCaptureRequested = true;
}
public void OnScreenCaptured(ScreenCaptureImageInfo bitmap)
{
ScreenCaptured?.Invoke(this, bitmap);
}
}
}