Ryujinx/Ryujinx.Graphics.GAL/IPipeline.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

104 lines
3.7 KiB
C#

using Ryujinx.Graphics.Shader;
using System;
namespace Ryujinx.Graphics.GAL
{
public interface IPipeline
{
void Barrier();
void BeginTransformFeedback(PrimitiveTopology topology);
void ClearBuffer(BufferHandle destination, int offset, int size, uint value);
void ClearRenderTargetColor(int index, uint componentMask, ColorF color);
void ClearRenderTargetDepthStencil(
float depthValue,
bool depthMask,
int stencilValue,
int stencilMask);
void CommandBufferBarrier();
void CopyBuffer(BufferHandle source, BufferHandle destination, int srcOffset, int dstOffset, int size);
void DispatchCompute(int groupsX, int groupsY, int groupsZ);
void Draw(int vertexCount, int instanceCount, int firstVertex, int firstInstance);
void DrawIndexed(
int indexCount,
int instanceCount,
int firstIndex,
int firstVertex,
int firstInstance);
void EndTransformFeedback();
void MultiDrawIndirectCount(BufferRange indirectBuffer, BufferRange parameterBuffer, int maxDrawCount, int stride);
void MultiDrawIndexedIndirectCount(BufferRange indirectBuffer, BufferRange parameterBuffer, int maxDrawCount, int stride);
void SetAlphaTest(bool enable, float reference, CompareOp op);
void SetBlendState(int index, BlendDescriptor blend);
void SetDepthBias(PolygonModeMask enables, float factor, float units, float clamp);
void SetDepthClamp(bool clamp);
void SetDepthMode(DepthMode mode);
void SetDepthTest(DepthTestDescriptor depthTest);
void SetFaceCulling(bool enable, Face face);
void SetFrontFace(FrontFace frontFace);
void SetIndexBuffer(BufferRange buffer, IndexType type);
void SetImage(int binding, ITexture texture, Format imageFormat);
void SetLogicOpState(bool enable, LogicalOp op);
void SetLineParameters(float width, bool smooth);
void SetPointParameters(float size, bool isProgramPointSize, bool enablePointSprite, Origin origin);
void SetPrimitiveRestart(bool enable, int index);
void SetPrimitiveTopology(PrimitiveTopology topology);
void SetProgram(IProgram program);
void SetRasterizerDiscard(bool discard);
void SetRenderTargetScale(float scale);
void SetRenderTargetColorMasks(ReadOnlySpan<uint> componentMask);
void SetRenderTargets(ITexture[] colors, ITexture depthStencil);
void SetSampler(int binding, ISampler sampler);
void SetScissor(int index, bool enable, int x, int y, int width, int height);
void SetStencilTest(StencilTestDescriptor stencilTest);
void SetStorageBuffers(int first, ReadOnlySpan<BufferRange> buffers);
void SetTexture(int binding, ITexture texture);
void SetTransformFeedbackBuffers(ReadOnlySpan<BufferRange> buffers);
void SetUniformBuffers(int first, ReadOnlySpan<BufferRange> buffers);
void SetUserClipDistance(int index, bool enableClip);
void SetVertexAttribs(ReadOnlySpan<VertexAttribDescriptor> vertexAttribs);
void SetVertexBuffers(ReadOnlySpan<VertexBufferDescriptor> vertexBuffers);
void SetViewports(int first, ReadOnlySpan<Viewport> viewports);
void TextureBarrier();
void TextureBarrierTiled();
bool TryHostConditionalRendering(ICounterEvent value, ulong compare, bool isEqual);
bool TryHostConditionalRendering(ICounterEvent value, ICounterEvent compare, bool isEqual);
void EndHostConditionalRendering();
void UpdateRenderScale(ShaderStage stage, ReadOnlySpan<float> scales, int textureCount, int imageCount);
}
}