Ryujinx/Ryujinx.Graphics.Gpu/Shader/ShaderSpecializationState.cs
gdkchan 2232e4ae87
Vulkan backend (#2518)
* WIP Vulkan implementation

* No need to initialize attributes on the SPIR-V backend anymore

* Allow multithreading shaderc and vkCreateShaderModule

You'll only really see the benefit here with threaded-gal or parallel shader cache compile.

Fix shaderc multithreaded changes

Thread safety for shaderc Options constructor

Dunno how they managed to make a constructor not thread safe, but you do you. May avoid some freezes.

* Support multiple levels/layers for blit.

Fixes MK8D when scaled, maybe a few other games. AMD software "safe" blit not supported right now.

* TextureStorage should hold a ref of the foreign storage, otherwise it might be freed while in use

* New depth-stencil blit method for AMD

* Workaround for AMD driver bug

* Fix some tessellation related issues (still doesn't work?)

* Submit command buffer before Texture GetData. (UE4 fix)

* DrawTexture support

* Fix BGRA on OpenGL backend

* Fix rebase build break

* Support format aliasing on SetImage

* Fix uniform buffers being lost when bindings are out of order

* Fix storage buffers being lost when bindings are out of order

(also avoid allocations when changing bindings)

* Use current command buffer for unscaled copy (perf)

Avoids flushing commands and renting a command buffer when fulfilling copy dependencies and when games do unscaled copies.

* Update to .net6

* Update Silk.NET to version 2.10.1

Somehow, massive performance boost. Seems like their vtable for looking up vulkan methods was really slow before.

* Fix PrimitivesGenerated query, disable Transform Feedback queries for now

Lets Splatoon 2 work on nvidia. (mostly)

* Update counter queue to be similar to the OGL one

Fixes softlocks when games had to flush counters.

* Don't throw when ending conditional rendering for now

This should be re-enabled when conditional rendering is enabled on nvidia etc.

* Update findMSB/findLSB to match master's instruction enum

* Fix triangle overlay on SMO, Captain Toad, maybe others?

* Don't make Intel Mesa pay for Intel Windows bugs

* Fix samplers with MinFilter Linear or Nearest (fixes New Super Mario Bros U Deluxe black borders)

* Update Spv.Generator

* Add alpha test emulation on shader (but no shader specialisation yet...)

* Fix R4G4B4A4Unorm texture format permutation

* Validation layers should be enabled for any log level other than None

* Add barriers around vkCmdCopyImage

Write->Read barrier for src image (we want to wait for a write to read it)
Write->Read barrier for dst image (we want to wait for the copy to complete before use)

* Be a bit more careful with texture access flags, since it can be used for anything

* Device local mapping for all buffers

May avoid issues with drivers with NVIDIA on linux/older gpus on windows when using large buffers (?)
Also some performance things and fixes issues with opengl games loading textures weird.

* Cleanup, disable device local buffers for now.

* Add single queue support

Multiqueue seems to be a bit more responsive on NVIDIA. Should fix texture flush on intel. AMD has been forced to single queue for an experiment.

* Fix some validation errors around extended dynamic state

* Remove Intel bug workaround, it was fixed on the latest driver

* Use circular queue for checking consumption on command buffers

Speeds up games that spam command buffers a little. Avoids checking multiple command buffers if multiple are active at once.

* Use SupportBufferUpdater, add single layer flush

* Fix counter queue leak when game decides to use host conditional rendering

* Force device local storage for textures (fixes linux performance)

* Port #3019

* Insert barriers around vkCmdBlitImage (may fix some amd flicker)

* Fix transform feedback on Intel, gl_Position feedback and clears to inexistent depth buffers

* Don't pause transform feedback for multi draw

* Fix draw outside of render pass and missing capability

* Workaround for wrong last attribute on AMD (affects FFVII, STRIKERS1945, probably more)

* Better workaround for AMD vertex buffer size alignment issue

* More instructions + fixes on SPIR-V backend

* Allow custom aspect ratio on Vulkan

* Correct GTK UI status bar positions

* SPIR-V: Functions must always end with a return

* SPIR-V: Fix ImageQuerySizeLod

* SPIR-V: Set DepthReplacing execution mode when FragDepth is modified

* SPIR-V: Implement LoopContinue IR instruction

* SPIR-V: Geometry shader support

* SPIR-V: Use correct binding number on storage buffers array

* Reduce allocations for Spir-v serialization

Passes BinaryWriter instead of the stream to Write and WriteOperand

- Removes creation of BinaryWriter for each instruction
- Removes allocations for literal string

* Some optimizations to Spv.Generator

- Dictionary for lookups of type declarations, constants, extinst
- LiteralInteger internal data format -> ushort
- Deterministic HashCode implementation to avoid spirv result not being the same between runs
- Inline operand list instead of List<T>, falls back to array if many operands. (large performance boost)

TODO: improve instruction allocation, structured program creator, ssa?

* Pool Spv.Generator resources, cache delegates, spv opts

- Pools for Instructions and LiteralIntegers. Can be passed in when creating the generator module.
  - NewInstruction is called instead of new Instruction()
  - Ryujinx SpirvGenerator passes in some pools that are static. The idea is for these to be shared between threads eventually.
- Estimate code size when creating the output MemoryStream
- LiteralInteger pools using ThreadStatic pools that are initialized before and after creation... not sure of a better way since the way these are created is via implicit cast.

Also, cache delegates for Spv.Generator for functions that are passed around to GenerateBinary etc, since passing the function raw creates a delegate on each call.

TODO: update python spv cs generator to make the coregrammar with NewInstruction and the `params` overloads.

* LocalDefMap for Ssa Rewriter

Rather than allocating a large array of all registers for each block in the shader, allocate one array of all registers and clear it between blocks. Reduces allocations in the shader translator.

* SPIR-V: Transform feedback support

* SPIR-V: Fragment shader interlock support (and image coherency)

* SPIR-V: Add early fragment tests support

* SPIR-V: Implement SwizzleAdd, add missing Triangles ExecutionMode for geometry shaders, remove SamplerType field from TextureMeta

* Don't pass depth clip state right now (fix decals)

Explicitly disabling it is incorrect. OpenGL currently automatically disables based on depth clamp, which is the behaviour if this state is omitted.

* Multisampling support

* Multisampling: Use resolve if src samples count > dst samples count

* Multisampling: We can only resolve for unscaled copies

* SPIR-V: Only add FSI exec mode if used.

* SPIR-V: Use ConstantComposite for Texture Offset Vector

Fixes a bunch of freezes with SPIR-V on AMD hardware, and validation errors. Note: Obviously assumes input offsets are constant, which they currently are.

* SPIR-V: Don't OpReturn if we already OpExit'ed

Fixes spir-v parse failure and stack smashing in RADV (obviously you still need bolist)

* SPIR-V: Only use input attribute type for input attributes

Output vertex attributes should always be of type float.

* Multithreaded Pipeline Compilation

* Address some feedback

* Make this 32

* Update topology with GpuAccessorState

* Cleanup for merge (note: disables spir-v)

* Make more robust to shader compilation failure

- Don't freeze when GLSL compilation fails
- Background SPIR-V pipeline compile failure results in skipped draws, similar to GLSL compilation failure.

* Fix Multisampling

* Only update fragment scale count if a vertex texture needs a scale.

Fixes a performance regression introduced by texture scaling in the vertex stage where support buffer updates would be very frequent, even at 1x, if any textures were used on the vertex stage.

This check doesn't exactly look cheap (a flag in the shader stage would probably be preferred), but it is much cheaper than uploading scales in both vulkan and opengl, so it will do for now.

* Use a bitmap to do granular tracking for buffer uploads.

This path is only taken if the much faster check of "is the buffer rented at all" is triggered, so it doesn't actually end up costing too much, and the time saved by not ending render passes (and on gpu for not waiting on barriers) is probably helpful.

Avoids ending render passes to update buffer data (not all the time)
- 140-180 to 35-45 in SMO metro kingdom (these updates are in the UI)
- Very variable 60-150(!) to 16-25 in mario kart 8 (these updates are in the UI)

As well as allowing more data to be preloaded persistently, this will also allow more data to be loaded in the preload buffer, which should be faster as it doesn't need to insert barriers between draws. (and on tbdr, does not need to flush and reload tile memory)

Improves performance in GPU limited scenarios. Should notably improve performance on TBDR gpus. Still a lot more to do here.

* Copy query results after RP ends, rather than ending to copy

We need to end the render pass to get the data (submit command buffer) anyways...

Reduces render passes created in games that use queries.

* Rework Query stuff a bit to avoid render pass end

Tries to reset returned queries in background when possible, rather than ending the render pass.

Still ends render pass when resetting a counter after draws, but maybe that can be solved too. (by just pulling an empty object off the pool?)

* Remove unnecessary lines

Was for testing

* Fix validation error for query reset

Need to think of a better way to do this.

* SPIR-V: Fix SwizzleAdd and some validation errors

* SPIR-V: Implement attribute indexing and StoreAttribute

* SPIR-V: Fix TextureSize for MS and Buffer sampler types

* Fix relaunch issues

* SPIR-V: Implement LogicalExclusiveOr

* SPIR-V: Constant buffer indexing support

* Ignore unsupported attributes rather than throwing (matches current GLSL behaviour)

* SPIR-V: Implement tessellation support

* SPIR-V: Geometry shader passthrough support

* SPIR-V: Implement StoreShader8/16 and StoreStorage8/16

* SPIR-V: Resolution scale support and fix TextureSample multisample with LOD bug

* SPIR-V: Fix field index for scale count

* SPIR-V: Fix another case of wrong field index

* SPIRV/GLSL: More scaling related fixes

* SPIR-V: Fix ImageLoad CompositeExtract component type

* SPIR-V: Workaround for Intel FrontFacing bug

* Enable SPIR-V backend by default

* Allow null samplers (samplers are not required when only using texelFetch to access the texture)

* Fix some validation errors related to texel block view usage flag and invalid image barrier base level

* Use explicit subgroup size if we can (might fix some block flickering on AMD)

* Take componentMask and scissor into account when clearing framebuffer attachments

* Add missing barriers around CmdFillBuffer (fixes Monster Hunter Rise flickering on NVIDIA)

* Use ClampToEdge for Clamp sampler address mode on Vulkan (fixes Hollow Knight)

Clamp is unsupported on Vulkan, but ClampToEdge behaves almost the same. ClampToBorder on the other hand (which was being used before) is pretty different

* Shader specialization for new Vulkan required state (fixes remaining alpha test issues, vertex stretching on AMD on Crash Bandicoot, etc)

* Check if the subgroup size is supported before passing a explicit size

* Only enable ShaderFloat64 if the GPU supports it

* We don't need to recompile shaders if alpha test state changed but alpha test is disabled

* Enable shader cache on Vulkan and implement MultiplyHighS32/U32 on SPIR-V (missed those before)

* Fix pipeline state saving before it is updated.

This should fix a few warnings and potential stutters due to bad pipeline states being saved in the cache. You may need to clear your guest cache.

* Allow null samplers on OpenGL backend

* _unit0Sampler should be set only for binding 0

* Remove unused PipelineConverter format variable (was causing IOR)

* Raise textures limit to 64 on Vulkan

* No need to pack the shader binaries if shader cache is disabled

* Fix backbuffer not being cleared and scissor not being re-enabled on OpenGL

* Do not clear unbound framebuffer color attachments

* Geometry shader passthrough emulation

* Consolidate UpdateDepthMode and GetDepthMode implementation

* Fix A1B5G5R5 texture format and support R4G4 on Vulkan

* Add barrier before use of some modified images

* Report 32 bit query result on AMD windows (smo issue)

* Add texture recompression support (disabled for now)

It recompresses ASTC textures into BC7, which might reduce VRAM usage significantly on games that uses ASTC textures

* Do not report R4G4 format as supported on Vulkan

It was causing mario head to become white on Super Mario 64 (???)

* Improvements to -1 to 1 depth mode.

- Transformation is only applied on the last stage in the vertex pipeline.
- Should fix some issues with geometry and tessellation (hopefully)
- Reading back FragCoord Z on fragment will transform back to -1 to 1.

* Geometry Shader index count from ThreadsPerInputPrimitive

Generally fixes SPIR-V emitting too many triangles, may change games in OpenGL

* Remove gl_FragDepth scaling

This is always 0-1; the other two issues were causing the problems. Fixes regression with Xenoblade.

* Add Gl StencilOp enum values to Vulkan

* Update guest cache to v1.1 (due to specialization state changes)

This will explode your shader cache from earlier vulkan build, but it must be done. 😔

* Vulkan/SPIR-V support for viewport inverse

* Fix typo

* Don't create query pools for unsupported query types

* Return of the Vector Indexing Bug

One day, everyone will get this right.

* Check for transform feedback query support

Sometimes transform feedback is supported without the query type.

* Fix gl_FragCoord.z transformation

FragCoord.z is always in 0-1, even when the real depth range is -1 to 1. Turns out the only bug was geo and tess stage outputs.

Fixes Pokemon Sword/Shield, possibly others.

* Fix Avalonia Rebase

Vulkan is currently not available on Avalonia, but the build does work and you can use opengl.

* Fix headless build

* Add support for BC6 and BC7 decompression, decompress all BC formats if they are not supported by the host

* Fix BCn 4/5 conversion, GetTextureTarget

BCn 4/5 could generate invalid data when a line's size in bytes was not divisible by 4, which both backends expect.

GetTextureTarget was not creating a view with the replacement format.

* Fix dependency

* Fix inverse viewport transform vector type on SPIR-V

* Do not require null descriptors support

* If MultiViewport is not supported, do not try to set more than one viewport/scissor

* Bounds check on bitmap add.

* Flush queries on attachment change rather than program change

Occlusion queries are usually used in a depth only pass so the attachments changing is a better indication of the query block ending.

Write mask changes are also considered since some games do depth only pass by setting 0 write mask on all the colour targets.

* Add support for avalonia (#6)

* add avalonia support

* only lock around skia flush

* addressed review

* cleanup

* add fallback size if avalonia attempts to render but the window size is 0. read desktop scale after enabling dpi check

* fix getting window handle on linux. skip render is size is 0

* Combine non-buffer with buffer image descriptor sets

* Support multisample texture copy with automatic resolve on Vulkan

* Remove old CompileShader methods from the Vulkan backend

* Add minimal pipeline layouts that only contains used bindings

They are used by helper shaders, the intention is avoiding needing to recompile the shaders (from GLSL to SPIR-V) if the bindings changes on the translated guest shaders

* Pre-compile helper shader as SPIR-V, and some fixes

* Remove pre-compiled shaderc binary for Windows as its no longer needed by default

* Workaround RADV crash

Enabling the descriptor indexing extension, even if it is not used, forces the radv driver to use "bolist".

* Use RobustBufferAccess on NVIDIA gpus

Avoids the SMO waterfall triangle on older NVIDIA gpus.

* Implement GPU selector and expose texture recompression on the UI and config

* Fix and enable background compute shader compilation

Also disables warnings from shader cache pipeline misses.

* Fix error due to missing subpass dependency when Attachment Write -> Shader Read barriers are added

* If S8D24 is not supported, use D32FS8

* Ensure all fences are destroyed on dispose

* Pre-allocate arrays up front on DescriptorSetUpdater, allows the removal of some checks

* Add missing clear layer parameter after rebase

* Use selected gpu from config for avalonia (#7)

* use configured device

* address review

* Fix D32S8 copy workaround (AMD)

Fixes water in Pokemon Legends Arceus on AMD GPUs. Possibly fixes other things.

* Use push descriptors for uniform buffer updates (disabled for now)

* Push descriptor support check, buffer redundancy checks

Should make push descriptors faster, needs more testing though.

* Increase light command buffer pool to 2 command buffers, throw rather than returning invalid cbs

* Adjust bindings array sizes

* Force submit command buffers if memory in use by its resources is high

* Add workaround for AMD GCN cubemap view sins

`ImageCreateCubeCompatibleBit` seems to generally break 2D array textures with mipmaps... even if they are eventually aliased as a cubemap with mipmaps. Forcing a copy here works around the issue.

This could be used in future if enabling this bit reduces performance on certain GPUs. (mobile class is generally a worry)

Currently also enabled on Linux as I don't know if they managed to dodge this bug (someone please tell me). Not enabled on Vega at the moment, but easy to add if the issue is there.

* Add mobile, non-RX variants to the GCN regex.

Also make sure that the 3 digit ones only include numbers starting with 7 or 8.

* Increase image limit per stage from 8 to 16

Xenoblade Chronicles 2 was hiting the limit of 8

* Minor code cleanup

* Fix NRE caused by SupportBufferUpdater calling pipeline ClearBuffer

* Add gpu selector to Avalonia (#8)

* Add gpu selector to avalonia settings

* show backend label on window

* some fixes

* address review

* Minor changes to the Avalonia UI

* Update graphics window UI and locales. (#9)

* Update xaml and update locales

* locale updates

Did my best here but likely needs to be checked by native speakers, especially the use of ampersands in greek, russian and turkish?

* Fix locales with more (?) correct translations.

* add separator to render widget

* fix spanish and portuguese

* Add new IdList, replaces buffer list that could not remove elements and had unbounded growth

* Don't crash the settings window if Vulkan is not supported

* Fix Actions menu not being clickable on GTK UI after relaunch

* Rename VulkanGraphicsDevice to VulkanRenderer and Renderer to OpenGLRenderer

* Fix IdList and make it not thread safe

* Revert useless OpenGL format table changes

* Fix headless project build

* List throws ArgumentOutOfRangeException

* SPIR-V: Fix tessellation

* Increase shader cache version due to tessellation fix

* Reduce number of Sync objects created (improves perf in some specific titles)

* Fix vulkan validation errors for NPOT compressed upload and GCN workaround.

* Add timestamp to the shader cache and force rebuild if host cache is outdated

* Prefer Mail box present mode for popups (#11)

* Prefer Mail box present mode

* fix debug

* switch present mode when vsync is toggled

* only disable vsync on the main window

* SPIR-V: Fix geometry shader input load with transform feedback

* BC7 Encoder: Prefer more precision on alpha rather than RGB when alpha is 0

* Fix Avalonia build

* Address initial PR feedback

* Only set transform feedback outputs on last vertex stage

* Address riperiperi PR feedback

* Remove outdated comment

* Remove unused constructor

* Only throw for negative results

* Throw for QueueSubmit and other errors

No point in delaying the inevitable

* Transform feedback decorations inside gl_PerVertex struct breaks the NVIDIA compiler

* Fix some resolution scale issues

* No need for two UpdateScale calls

* Fix comments on SPIR-V generator project

* Try to fix shader local memory size

On DOOM, a shader is using local memory, but both Low and High size are 0, CRS size is 1536, it seems to store on that region?

* Remove RectangleF that is now unused

* Fix ImageGather with multiple offsets

Needs ImageGatherExtended capability, and must use `ConstantComposite` instead of `CompositeConstruct`

* Address PR feedback from jD in all projects except Avalonia

* Address most of jD PR feedback on Avalonia

* Remove unsafe

* Fix VulkanSkiaGpu

* move present mode request out of Create Swapchain method

* split more parts of create swapchain

* addressed reviews

* addressed review

* Address second batch of jD PR feedback

* Fix buffer <-> image copy row length and height alignment

AlignUp helper does not support NPOT alignment, and ASTC textures can have NPOT block sizes

* Better fix for NPOT alignment issue

* Use switch expressions on Vulkan EnumConversion

Thanks jD

* Fix Avalonia build

* Add Vulkan selection prompt on startup

* Grammar fixes on Vulkan prompt message

* Add missing Vulkan migration flag

Co-authored-by: riperiperi <rhy3756547@hotmail.com>
Co-authored-by: Emmanuel Hansen <emmausssss@gmail.com>
Co-authored-by: MutantAura <44103205+MutantAura@users.noreply.github.com>
2022-07-31 18:26:06 -03:00

848 lines
36 KiB
C#

using Ryujinx.Common.Memory;
using Ryujinx.Graphics.Gpu.Image;
using Ryujinx.Graphics.Gpu.Memory;
using Ryujinx.Graphics.GAL;
using Ryujinx.Graphics.Gpu.Shader.DiskCache;
using Ryujinx.Graphics.Shader;
using System;
using System.Collections.Generic;
using System.Linq;
using System.Numerics;
using System.Runtime.CompilerServices;
using System.Runtime.InteropServices;
namespace Ryujinx.Graphics.Gpu.Shader
{
class ShaderSpecializationState
{
private const uint ComsMagic = (byte)'C' | ((byte)'O' << 8) | ((byte)'M' << 16) | ((byte)'S' << 24);
private const uint GfxsMagic = (byte)'G' | ((byte)'F' << 8) | ((byte)'X' << 16) | ((byte)'S' << 24);
private const uint TfbdMagic = (byte)'T' | ((byte)'F' << 8) | ((byte)'B' << 16) | ((byte)'D' << 24);
private const uint TexkMagic = (byte)'T' | ((byte)'E' << 8) | ((byte)'X' << 16) | ((byte)'K' << 24);
private const uint TexsMagic = (byte)'T' | ((byte)'E' << 8) | ((byte)'X' << 16) | ((byte)'S' << 24);
private const uint PgpsMagic = (byte)'P' | ((byte)'G' << 8) | ((byte)'P' << 16) | ((byte)'S' << 24);
/// <summary>
/// Flags indicating GPU state that is used by the shader.
/// </summary>
[Flags]
private enum QueriedStateFlags
{
EarlyZForce = 1 << 0,
PrimitiveTopology = 1 << 1,
TessellationMode = 1 << 2,
TransformFeedback = 1 << 3
}
private QueriedStateFlags _queriedState;
private bool _compute;
private byte _constantBufferUsePerStage;
/// <summary>
/// Compute engine state.
/// </summary>
public GpuChannelComputeState ComputeState;
/// <summary>
/// 3D engine state.
/// </summary>
public GpuChannelGraphicsState GraphicsState;
/// <summary>
/// Contant buffers bound at the time the shader was compiled, per stage.
/// </summary>
public Array5<uint> ConstantBufferUse;
/// <summary>
/// Pipeline state captured at the time of shader use.
/// </summary>
public ProgramPipelineState? PipelineState;
/// <summary>
/// Transform feedback buffers active at the time the shader was compiled.
/// </summary>
public TransformFeedbackDescriptor[] TransformFeedbackDescriptors;
/// <summary>
/// Flags indicating texture state that is used by the shader.
/// </summary>
[Flags]
private enum QueriedTextureStateFlags
{
TextureFormat = 1 << 0,
SamplerType = 1 << 1,
CoordNormalized = 1 << 2
}
/// <summary>
/// Reference type wrapping a value.
/// </summary>
private class Box<T>
{
/// <summary>
/// Wrapped value.
/// </summary>
public T Value;
}
/// <summary>
/// State of a texture or image that is accessed by the shader.
/// </summary>
private struct TextureSpecializationState
{
// New fields should be added to the end of the struct to keep disk shader cache compatibility.
/// <summary>
/// Flags indicating which state of the texture the shader depends on.
/// </summary>
public QueriedTextureStateFlags QueriedFlags;
/// <summary>
/// Encoded texture format value.
/// </summary>
public uint Format;
/// <summary>
/// True if the texture format is sRGB, false otherwise.
/// </summary>
public bool FormatSrgb;
/// <summary>
/// Texture target.
/// </summary>
public Image.TextureTarget TextureTarget;
/// <summary>
/// Indicates if the coordinates used to sample the texture are normalized or not (0.0..1.0 or 0..Width/Height).
/// </summary>
public bool CoordNormalized;
}
/// <summary>
/// Texture binding information, used to identify each texture accessed by the shader.
/// </summary>
private struct TextureKey : IEquatable<TextureKey>
{
// New fields should be added to the end of the struct to keep disk shader cache compatibility.
/// <summary>
/// Shader stage where the texture is used.
/// </summary>
public readonly int StageIndex;
/// <summary>
/// Texture handle offset in words on the texture buffer.
/// </summary>
public readonly int Handle;
/// <summary>
/// Constant buffer slot of the texture buffer (-1 to use the texture buffer index GPU register).
/// </summary>
public readonly int CbufSlot;
/// <summary>
/// Creates a new texture key.
/// </summary>
/// <param name="stageIndex">Shader stage where the texture is used</param>
/// <param name="handle">Texture handle offset in words on the texture buffer</param>
/// <param name="cbufSlot">Constant buffer slot of the texture buffer (-1 to use the texture buffer index GPU register)</param>
public TextureKey(int stageIndex, int handle, int cbufSlot)
{
StageIndex = stageIndex;
Handle = handle;
CbufSlot = cbufSlot;
}
public override bool Equals(object obj)
{
return obj is TextureKey textureKey && Equals(textureKey);
}
public bool Equals(TextureKey other)
{
return StageIndex == other.StageIndex && Handle == other.Handle && CbufSlot == other.CbufSlot;
}
public override int GetHashCode()
{
return HashCode.Combine(StageIndex, Handle, CbufSlot);
}
}
private readonly Dictionary<TextureKey, Box<TextureSpecializationState>> _textureSpecialization;
private KeyValuePair<TextureKey, Box<TextureSpecializationState>>[] _allTextures;
private Box<TextureSpecializationState>[][] _textureByBinding;
private Box<TextureSpecializationState>[][] _imageByBinding;
/// <summary>
/// Creates a new instance of the shader specialization state.
/// </summary>
private ShaderSpecializationState()
{
_textureSpecialization = new Dictionary<TextureKey, Box<TextureSpecializationState>>();
}
/// <summary>
/// Creates a new instance of the shader specialization state.
/// </summary>
/// <param name="state">Current compute engine state</param>
public ShaderSpecializationState(ref GpuChannelComputeState state) : this()
{
ComputeState = state;
_compute = true;
}
/// <summary>
/// Creates a new instance of the shader specialization state.
/// </summary>
/// <param name="state">Current 3D engine state</param>
/// <param name="descriptors">Optional transform feedback buffers in use, if any</param>
private ShaderSpecializationState(ref GpuChannelGraphicsState state, TransformFeedbackDescriptor[] descriptors) : this()
{
GraphicsState = state;
_compute = false;
if (descriptors != null)
{
TransformFeedbackDescriptors = descriptors;
_queriedState |= QueriedStateFlags.TransformFeedback;
}
}
/// <summary>
/// Prepare the shader specialization state for quick binding lookups.
/// </summary>
/// <param name="stages">The shader stages</param>
public void Prepare(CachedShaderStage[] stages)
{
_allTextures = _textureSpecialization.ToArray();
_textureByBinding = new Box<TextureSpecializationState>[stages.Length][];
_imageByBinding = new Box<TextureSpecializationState>[stages.Length][];
for (int i = 0; i < stages.Length; i++)
{
CachedShaderStage stage = stages[i];
if (stage?.Info != null)
{
var textures = stage.Info.Textures;
var images = stage.Info.Images;
var texBindings = new Box<TextureSpecializationState>[textures.Count];
var imageBindings = new Box<TextureSpecializationState>[images.Count];
int stageIndex = Math.Max(i - 1, 0); // Don't count VertexA for looking up spec state. No-Op for compute.
for (int j = 0; j < textures.Count; j++)
{
var texture = textures[j];
texBindings[j] = GetTextureSpecState(stageIndex, texture.HandleIndex, texture.CbufSlot);
}
for (int j = 0; j < images.Count; j++)
{
var image = images[j];
imageBindings[j] = GetTextureSpecState(stageIndex, image.HandleIndex, image.CbufSlot);
}
_textureByBinding[i] = texBindings;
_imageByBinding[i] = imageBindings;
}
}
}
/// <summary>
/// Creates a new instance of the shader specialization state.
/// </summary>
/// <param name="state">Current 3D engine state</param>
/// <param name="pipelineState">Current program pipeline state</param>
/// <param name="descriptors">Optional transform feedback buffers in use, if any</param>
public ShaderSpecializationState(
ref GpuChannelGraphicsState state,
ref ProgramPipelineState pipelineState,
TransformFeedbackDescriptor[] descriptors) : this(ref state, descriptors)
{
PipelineState = pipelineState;
}
/// <summary>
/// Creates a new instance of the shader specialization state.
/// </summary>
/// <param name="state">Current 3D engine state</param>
/// <param name="pipelineState">Current program pipeline state</param>
/// <param name="descriptors">Optional transform feedback buffers in use, if any</param>
public ShaderSpecializationState(
ref GpuChannelGraphicsState state,
ProgramPipelineState? pipelineState,
TransformFeedbackDescriptor[] descriptors) : this(ref state, descriptors)
{
PipelineState = pipelineState;
}
/// <summary>
/// Indicates that the shader accesses the early Z force state.
/// </summary>
public void RecordEarlyZForce()
{
_queriedState |= QueriedStateFlags.EarlyZForce;
}
/// <summary>
/// Indicates that the shader accesses the primitive topology state.
/// </summary>
public void RecordPrimitiveTopology()
{
_queriedState |= QueriedStateFlags.PrimitiveTopology;
}
/// <summary>
/// Indicates that the shader accesses the tessellation mode state.
/// </summary>
public void RecordTessellationMode()
{
_queriedState |= QueriedStateFlags.TessellationMode;
}
/// <summary>
/// Indicates that the shader accesses the constant buffer use state.
/// </summary>
/// <param name="stageIndex">Shader stage index</param>
/// <param name="useMask">Mask indicating the constant buffers bound at the time of the shader compilation</param>
public void RecordConstantBufferUse(int stageIndex, uint useMask)
{
ConstantBufferUse[stageIndex] = useMask;
_constantBufferUsePerStage |= (byte)(1 << stageIndex);
}
/// <summary>
/// Indicates that a given texture is accessed by the shader.
/// </summary>
/// <param name="stageIndex">Shader stage where the texture is used</param>
/// <param name="handle">Offset in words of the texture handle on the texture buffer</param>
/// <param name="cbufSlot">Slot of the texture buffer constant buffer</param>
/// <param name="descriptor">Descriptor of the texture</param>
public void RegisterTexture(int stageIndex, int handle, int cbufSlot, Image.TextureDescriptor descriptor)
{
Box<TextureSpecializationState> state = GetOrCreateTextureSpecState(stageIndex, handle, cbufSlot);
state.Value.Format = descriptor.UnpackFormat();
state.Value.FormatSrgb = descriptor.UnpackSrgb();
state.Value.TextureTarget = descriptor.UnpackTextureTarget();
state.Value.CoordNormalized = descriptor.UnpackTextureCoordNormalized();
}
/// <summary>
/// Indicates that a given texture is accessed by the shader.
/// </summary>
/// <param name="stageIndex">Shader stage where the texture is used</param>
/// <param name="handle">Offset in words of the texture handle on the texture buffer</param>
/// <param name="cbufSlot">Slot of the texture buffer constant buffer</param>
/// <param name="format">Maxwell texture format value</param>
/// <param name="formatSrgb">Whenever the texture format is a sRGB format</param>
/// <param name="target">Texture target type</param>
/// <param name="coordNormalized">Whenever the texture coordinates used on the shader are considered normalized</param>
public void RegisterTexture(
int stageIndex,
int handle,
int cbufSlot,
uint format,
bool formatSrgb,
Image.TextureTarget target,
bool coordNormalized)
{
Box<TextureSpecializationState> state = GetOrCreateTextureSpecState(stageIndex, handle, cbufSlot);
state.Value.Format = format;
state.Value.FormatSrgb = formatSrgb;
state.Value.TextureTarget = target;
state.Value.CoordNormalized = coordNormalized;
}
/// <summary>
/// Indicates that the format of a given texture was used during the shader translation process.
/// </summary>
/// <param name="stageIndex">Shader stage where the texture is used</param>
/// <param name="handle">Offset in words of the texture handle on the texture buffer</param>
/// <param name="cbufSlot">Slot of the texture buffer constant buffer</param>
public void RecordTextureFormat(int stageIndex, int handle, int cbufSlot)
{
Box<TextureSpecializationState> state = GetOrCreateTextureSpecState(stageIndex, handle, cbufSlot);
state.Value.QueriedFlags |= QueriedTextureStateFlags.TextureFormat;
}
/// <summary>
/// Indicates that the target of a given texture was used during the shader translation process.
/// </summary>
/// <param name="stageIndex">Shader stage where the texture is used</param>
/// <param name="handle">Offset in words of the texture handle on the texture buffer</param>
/// <param name="cbufSlot">Slot of the texture buffer constant buffer</param>
public void RecordTextureSamplerType(int stageIndex, int handle, int cbufSlot)
{
Box<TextureSpecializationState> state = GetOrCreateTextureSpecState(stageIndex, handle, cbufSlot);
state.Value.QueriedFlags |= QueriedTextureStateFlags.SamplerType;
}
/// <summary>
/// Indicates that the coordinate normalization state of a given texture was used during the shader translation process.
/// </summary>
/// <param name="stageIndex">Shader stage where the texture is used</param>
/// <param name="handle">Offset in words of the texture handle on the texture buffer</param>
/// <param name="cbufSlot">Slot of the texture buffer constant buffer</param>
public void RecordTextureCoordNormalized(int stageIndex, int handle, int cbufSlot)
{
Box<TextureSpecializationState> state = GetOrCreateTextureSpecState(stageIndex, handle, cbufSlot);
state.Value.QueriedFlags |= QueriedTextureStateFlags.CoordNormalized;
}
/// <summary>
/// Checks if a given texture was registerd on this specialization state.
/// </summary>
/// <param name="stageIndex">Shader stage where the texture is used</param>
/// <param name="handle">Offset in words of the texture handle on the texture buffer</param>
/// <param name="cbufSlot">Slot of the texture buffer constant buffer</param>
public bool TextureRegistered(int stageIndex, int handle, int cbufSlot)
{
return GetTextureSpecState(stageIndex, handle, cbufSlot) != null;
}
/// <summary>
/// Gets the recorded format of a given texture.
/// </summary>
/// <param name="stageIndex">Shader stage where the texture is used</param>
/// <param name="handle">Offset in words of the texture handle on the texture buffer</param>
/// <param name="cbufSlot">Slot of the texture buffer constant buffer</param>
public (uint, bool) GetFormat(int stageIndex, int handle, int cbufSlot)
{
TextureSpecializationState state = GetTextureSpecState(stageIndex, handle, cbufSlot).Value;
return (state.Format, state.FormatSrgb);
}
/// <summary>
/// Gets the recorded target of a given texture.
/// </summary>
/// <param name="stageIndex">Shader stage where the texture is used</param>
/// <param name="handle">Offset in words of the texture handle on the texture buffer</param>
/// <param name="cbufSlot">Slot of the texture buffer constant buffer</param>
public Image.TextureTarget GetTextureTarget(int stageIndex, int handle, int cbufSlot)
{
return GetTextureSpecState(stageIndex, handle, cbufSlot).Value.TextureTarget;
}
/// <summary>
/// Gets the recorded coordinate normalization state of a given texture.
/// </summary>
/// <param name="stageIndex">Shader stage where the texture is used</param>
/// <param name="handle">Offset in words of the texture handle on the texture buffer</param>
/// <param name="cbufSlot">Slot of the texture buffer constant buffer</param>
public bool GetCoordNormalized(int stageIndex, int handle, int cbufSlot)
{
return GetTextureSpecState(stageIndex, handle, cbufSlot).Value.CoordNormalized;
}
/// <summary>
/// Gets texture specialization state for a given texture, or create a new one if not present.
/// </summary>
/// <param name="stageIndex">Shader stage where the texture is used</param>
/// <param name="handle">Offset in words of the texture handle on the texture buffer</param>
/// <param name="cbufSlot">Slot of the texture buffer constant buffer</param>
/// <returns>Texture specialization state</returns>
private Box<TextureSpecializationState> GetOrCreateTextureSpecState(int stageIndex, int handle, int cbufSlot)
{
TextureKey key = new TextureKey(stageIndex, handle, cbufSlot);
if (!_textureSpecialization.TryGetValue(key, out Box<TextureSpecializationState> state))
{
_textureSpecialization.Add(key, state = new Box<TextureSpecializationState>());
}
return state;
}
/// <summary>
/// Gets texture specialization state for a given texture.
/// </summary>
/// <param name="stageIndex">Shader stage where the texture is used</param>
/// <param name="handle">Offset in words of the texture handle on the texture buffer</param>
/// <param name="cbufSlot">Slot of the texture buffer constant buffer</param>
/// <returns>Texture specialization state</returns>
private Box<TextureSpecializationState> GetTextureSpecState(int stageIndex, int handle, int cbufSlot)
{
TextureKey key = new TextureKey(stageIndex, handle, cbufSlot);
if (_textureSpecialization.TryGetValue(key, out Box<TextureSpecializationState> state))
{
return state;
}
return null;
}
/// <summary>
/// Checks if the recorded state matches the current GPU 3D engine state.
/// </summary>
/// <param name="channel">GPU channel</param>
/// <param name="poolState">Texture pool state</param>
/// <param name="graphicsState">Graphics state</param>
/// <param name="checkTextures">Indicates whether texture descriptors should be checked</param>
/// <returns>True if the state matches, false otherwise</returns>
public bool MatchesGraphics(GpuChannel channel, GpuChannelPoolState poolState, GpuChannelGraphicsState graphicsState, bool checkTextures)
{
if (graphicsState.ViewportTransformDisable != GraphicsState.ViewportTransformDisable)
{
return false;
}
bool thisA2cDitherEnable = GraphicsState.AlphaToCoverageEnable && GraphicsState.AlphaToCoverageDitherEnable;
bool otherA2cDitherEnable = graphicsState.AlphaToCoverageEnable && graphicsState.AlphaToCoverageDitherEnable;
if (otherA2cDitherEnable != thisA2cDitherEnable)
{
return false;
}
if (graphicsState.DepthMode != GraphicsState.DepthMode)
{
return false;
}
if (graphicsState.AlphaTestEnable != GraphicsState.AlphaTestEnable)
{
return false;
}
if (graphicsState.AlphaTestEnable &&
(graphicsState.AlphaTestCompare != GraphicsState.AlphaTestCompare ||
graphicsState.AlphaTestReference != GraphicsState.AlphaTestReference))
{
return false;
}
if (!graphicsState.AttributeTypes.ToSpan().SequenceEqual(GraphicsState.AttributeTypes.ToSpan()))
{
return false;
}
return Matches(channel, poolState, checkTextures, isCompute: false);
}
/// <summary>
/// Checks if the recorded state matches the current GPU compute engine state.
/// </summary>
/// <param name="channel">GPU channel</param>
/// <param name="poolState">Texture pool state</param>
/// <param name="checkTextures">Indicates whether texture descriptors should be checked</param>
/// <returns>True if the state matches, false otherwise</returns>
public bool MatchesCompute(GpuChannel channel, GpuChannelPoolState poolState, bool checkTextures)
{
return Matches(channel, poolState, checkTextures, isCompute: true);
}
/// <summary>
/// Fetch the constant buffers used for a texture to cache.
/// </summary>
/// <param name="channel">GPU channel</param>
/// <param name="isCompute">Indicates whenever the check is requested by the 3D or compute engine</param>
/// <param name="cachedTextureBufferIndex">The currently cached texture buffer index</param>
/// <param name="cachedSamplerBufferIndex">The currently cached sampler buffer index</param>
/// <param name="cachedTextureBuffer">The currently cached texture buffer data</param>
/// <param name="cachedSamplerBuffer">The currently cached sampler buffer data</param>
/// <param name="cachedStageIndex">The currently cached stage</param>
/// <param name="textureBufferIndex">The new texture buffer index</param>
/// <param name="samplerBufferIndex">The new sampler buffer index</param>
/// <param name="stageIndex">Stage index of the constant buffer</param>
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static void UpdateCachedBuffer(
GpuChannel channel,
bool isCompute,
ref int cachedTextureBufferIndex,
ref int cachedSamplerBufferIndex,
ref ReadOnlySpan<int> cachedTextureBuffer,
ref ReadOnlySpan<int> cachedSamplerBuffer,
ref int cachedStageIndex,
int textureBufferIndex,
int samplerBufferIndex,
int stageIndex)
{
bool stageChange = stageIndex != cachedStageIndex;
if (stageChange || textureBufferIndex != cachedTextureBufferIndex)
{
ref BufferBounds bounds = ref channel.BufferManager.GetUniformBufferBounds(isCompute, stageIndex, textureBufferIndex);
cachedTextureBuffer = MemoryMarshal.Cast<byte, int>(channel.MemoryManager.Physical.GetSpan(bounds.Address, (int)bounds.Size));
cachedTextureBufferIndex = textureBufferIndex;
if (samplerBufferIndex == textureBufferIndex)
{
cachedSamplerBuffer = cachedTextureBuffer;
cachedSamplerBufferIndex = samplerBufferIndex;
}
}
if (stageChange || samplerBufferIndex != cachedSamplerBufferIndex)
{
ref BufferBounds bounds = ref channel.BufferManager.GetUniformBufferBounds(isCompute, stageIndex, samplerBufferIndex);
cachedSamplerBuffer = MemoryMarshal.Cast<byte, int>(channel.MemoryManager.Physical.GetSpan(bounds.Address, (int)bounds.Size));
cachedSamplerBufferIndex = samplerBufferIndex;
}
cachedStageIndex = stageIndex;
}
/// <summary>
/// Checks if the recorded state matches the current GPU state.
/// </summary>
/// <param name="channel">GPU channel</param>
/// <param name="poolState">Texture pool state</param>
/// <param name="checkTextures">Indicates whether texture descriptors should be checked</param>
/// <param name="isCompute">Indicates whenever the check is requested by the 3D or compute engine</param>
/// <returns>True if the state matches, false otherwise</returns>
private bool Matches(GpuChannel channel, GpuChannelPoolState poolState, bool checkTextures, bool isCompute)
{
int constantBufferUsePerStageMask = _constantBufferUsePerStage;
while (constantBufferUsePerStageMask != 0)
{
int index = BitOperations.TrailingZeroCount(constantBufferUsePerStageMask);
uint useMask = isCompute
? channel.BufferManager.GetComputeUniformBufferUseMask()
: channel.BufferManager.GetGraphicsUniformBufferUseMask(index);
if (ConstantBufferUse[index] != useMask)
{
return false;
}
constantBufferUsePerStageMask &= ~(1 << index);
}
if (checkTextures)
{
TexturePool pool = channel.TextureManager.GetTexturePool(poolState.TexturePoolGpuVa, poolState.TexturePoolMaximumId);
int cachedTextureBufferIndex = -1;
int cachedSamplerBufferIndex = -1;
int cachedStageIndex = -1;
ReadOnlySpan<int> cachedTextureBuffer = Span<int>.Empty;
ReadOnlySpan<int> cachedSamplerBuffer = Span<int>.Empty;
foreach (var kv in _allTextures)
{
TextureKey textureKey = kv.Key;
(int textureBufferIndex, int samplerBufferIndex) = TextureHandle.UnpackSlots(textureKey.CbufSlot, poolState.TextureBufferIndex);
UpdateCachedBuffer(channel,
isCompute,
ref cachedTextureBufferIndex,
ref cachedSamplerBufferIndex,
ref cachedTextureBuffer,
ref cachedSamplerBuffer,
ref cachedStageIndex,
textureBufferIndex,
samplerBufferIndex,
textureKey.StageIndex);
int packedId = TextureHandle.ReadPackedId(textureKey.Handle, cachedTextureBuffer, cachedSamplerBuffer);
int textureId = TextureHandle.UnpackTextureId(packedId);
if (pool.IsValidId(textureId))
{
ref readonly Image.TextureDescriptor descriptor = ref pool.GetDescriptorRef(textureId);
if (!MatchesTexture(kv.Value, descriptor))
{
return false;
}
}
}
}
return true;
}
/// <summary>
/// Checks if the recorded texture state matches the given texture descriptor.
/// </summary>
/// <param name="specializationState">Texture specialization state</param>
/// <param name="descriptor">Texture descriptor</param>
/// <returns>True if the state matches, false otherwise</returns>
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private bool MatchesTexture(Box<TextureSpecializationState> specializationState, in Image.TextureDescriptor descriptor)
{
if (specializationState != null)
{
if (specializationState.Value.QueriedFlags.HasFlag(QueriedTextureStateFlags.CoordNormalized) &&
specializationState.Value.CoordNormalized != descriptor.UnpackTextureCoordNormalized())
{
return false;
}
}
return true;
}
/// <summary>
/// Checks if the recorded texture state for a given texture binding matches a texture descriptor.
/// </summary>
/// <param name="stage">The shader stage</param>
/// <param name="index">The texture index</param>
/// <param name="descriptor">Texture descriptor</param>
/// <returns>True if the state matches, false otherwise</returns>
public bool MatchesTexture(ShaderStage stage, int index, in Image.TextureDescriptor descriptor)
{
Box<TextureSpecializationState> specializationState = _textureByBinding[(int)stage][index];
return MatchesTexture(specializationState, descriptor);
}
/// <summary>
/// Checks if the recorded texture state for a given image binding matches a texture descriptor.
/// </summary>
/// <param name="stage">The shader stage</param>
/// <param name="index">The texture index</param>
/// <param name="descriptor">Texture descriptor</param>
/// <returns>True if the state matches, false otherwise</returns>
public bool MatchesImage(ShaderStage stage, int index, in Image.TextureDescriptor descriptor)
{
Box<TextureSpecializationState> specializationState = _imageByBinding[(int)stage][index];
return MatchesTexture(specializationState, descriptor);
}
/// <summary>
/// Reads shader specialization state that has been serialized.
/// </summary>
/// <param name="dataReader">Data reader</param>
/// <returns>Shader specialization state</returns>
public static ShaderSpecializationState Read(ref BinarySerializer dataReader)
{
ShaderSpecializationState specState = new ShaderSpecializationState();
dataReader.Read(ref specState._queriedState);
dataReader.Read(ref specState._compute);
if (specState._compute)
{
dataReader.ReadWithMagicAndSize(ref specState.ComputeState, ComsMagic);
}
else
{
dataReader.ReadWithMagicAndSize(ref specState.GraphicsState, GfxsMagic);
}
dataReader.Read(ref specState._constantBufferUsePerStage);
int constantBufferUsePerStageMask = specState._constantBufferUsePerStage;
while (constantBufferUsePerStageMask != 0)
{
int index = BitOperations.TrailingZeroCount(constantBufferUsePerStageMask);
dataReader.Read(ref specState.ConstantBufferUse[index]);
constantBufferUsePerStageMask &= ~(1 << index);
}
bool hasPipelineState = false;
dataReader.Read(ref hasPipelineState);
if (hasPipelineState)
{
ProgramPipelineState pipelineState = default;
dataReader.ReadWithMagicAndSize(ref pipelineState, PgpsMagic);
specState.PipelineState = pipelineState;
}
if (specState._queriedState.HasFlag(QueriedStateFlags.TransformFeedback))
{
ushort tfCount = 0;
dataReader.Read(ref tfCount);
specState.TransformFeedbackDescriptors = new TransformFeedbackDescriptor[tfCount];
for (int index = 0; index < tfCount; index++)
{
dataReader.ReadWithMagicAndSize(ref specState.TransformFeedbackDescriptors[index], TfbdMagic);
}
}
ushort count = 0;
dataReader.Read(ref count);
for (int index = 0; index < count; index++)
{
TextureKey textureKey = default;
Box<TextureSpecializationState> textureState = new Box<TextureSpecializationState>();
dataReader.ReadWithMagicAndSize(ref textureKey, TexkMagic);
dataReader.ReadWithMagicAndSize(ref textureState.Value, TexsMagic);
specState._textureSpecialization[textureKey] = textureState;
}
return specState;
}
/// <summary>
/// Serializes the shader specialization state.
/// </summary>
/// <param name="dataWriter">Data writer</param>
public void Write(ref BinarySerializer dataWriter)
{
dataWriter.Write(ref _queriedState);
dataWriter.Write(ref _compute);
if (_compute)
{
dataWriter.WriteWithMagicAndSize(ref ComputeState, ComsMagic);
}
else
{
dataWriter.WriteWithMagicAndSize(ref GraphicsState, GfxsMagic);
}
dataWriter.Write(ref _constantBufferUsePerStage);
int constantBufferUsePerStageMask = _constantBufferUsePerStage;
while (constantBufferUsePerStageMask != 0)
{
int index = BitOperations.TrailingZeroCount(constantBufferUsePerStageMask);
dataWriter.Write(ref ConstantBufferUse[index]);
constantBufferUsePerStageMask &= ~(1 << index);
}
bool hasPipelineState = PipelineState.HasValue;
dataWriter.Write(ref hasPipelineState);
if (hasPipelineState)
{
ProgramPipelineState pipelineState = PipelineState.Value;
dataWriter.WriteWithMagicAndSize(ref pipelineState, PgpsMagic);
}
if (_queriedState.HasFlag(QueriedStateFlags.TransformFeedback))
{
ushort tfCount = (ushort)TransformFeedbackDescriptors.Length;
dataWriter.Write(ref tfCount);
for (int index = 0; index < TransformFeedbackDescriptors.Length; index++)
{
dataWriter.WriteWithMagicAndSize(ref TransformFeedbackDescriptors[index], TfbdMagic);
}
}
ushort count = (ushort)_textureSpecialization.Count;
dataWriter.Write(ref count);
foreach (var kv in _textureSpecialization)
{
var textureKey = kv.Key;
var textureState = kv.Value;
dataWriter.WriteWithMagicAndSize(ref textureKey, TexkMagic);
dataWriter.WriteWithMagicAndSize(ref textureState.Value, TexsMagic);
}
}
}
}