mirror of
https://github.com/GreemDev/Ryujinx
synced 2024-11-22 09:53:35 +01:00
2232e4ae87
* 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>
720 lines
30 KiB
C#
720 lines
30 KiB
C#
using Ryujinx.Common.Configuration;
|
|
using Ryujinx.Common.Logging;
|
|
using Ryujinx.Graphics.GAL;
|
|
using Ryujinx.Graphics.Gpu.Engine.Threed;
|
|
using Ryujinx.Graphics.Gpu.Engine.Types;
|
|
using Ryujinx.Graphics.Gpu.Image;
|
|
using Ryujinx.Graphics.Gpu.Memory;
|
|
using Ryujinx.Graphics.Gpu.Shader.DiskCache;
|
|
using Ryujinx.Graphics.Shader;
|
|
using Ryujinx.Graphics.Shader.Translation;
|
|
using System;
|
|
using System.Collections.Generic;
|
|
using System.IO;
|
|
using System.Linq;
|
|
using System.Threading;
|
|
|
|
namespace Ryujinx.Graphics.Gpu.Shader
|
|
{
|
|
/// <summary>
|
|
/// Memory cache of shader code.
|
|
/// </summary>
|
|
class ShaderCache : IDisposable
|
|
{
|
|
/// <summary>
|
|
/// Default flags used on the shader translation process.
|
|
/// </summary>
|
|
public const TranslationFlags DefaultFlags = TranslationFlags.DebugMode;
|
|
|
|
private struct TranslatedShader
|
|
{
|
|
public readonly CachedShaderStage Shader;
|
|
public readonly ShaderProgram Program;
|
|
|
|
public TranslatedShader(CachedShaderStage shader, ShaderProgram program)
|
|
{
|
|
Shader = shader;
|
|
Program = program;
|
|
}
|
|
}
|
|
|
|
private struct TranslatedShaderVertexPair
|
|
{
|
|
public readonly CachedShaderStage VertexA;
|
|
public readonly CachedShaderStage VertexB;
|
|
public readonly ShaderProgram Program;
|
|
|
|
public TranslatedShaderVertexPair(CachedShaderStage vertexA, CachedShaderStage vertexB, ShaderProgram program)
|
|
{
|
|
VertexA = vertexA;
|
|
VertexB = vertexB;
|
|
Program = program;
|
|
}
|
|
}
|
|
|
|
private readonly GpuContext _context;
|
|
|
|
private readonly ShaderDumper _dumper;
|
|
|
|
private readonly Dictionary<ulong, CachedShaderProgram> _cpPrograms;
|
|
private readonly Dictionary<ShaderAddresses, CachedShaderProgram> _gpPrograms;
|
|
|
|
private struct ProgramToSave
|
|
{
|
|
public readonly CachedShaderProgram CachedProgram;
|
|
public readonly IProgram HostProgram;
|
|
public readonly byte[] BinaryCode;
|
|
|
|
public ProgramToSave(CachedShaderProgram cachedProgram, IProgram hostProgram, byte[] binaryCode)
|
|
{
|
|
CachedProgram = cachedProgram;
|
|
HostProgram = hostProgram;
|
|
BinaryCode = binaryCode;
|
|
}
|
|
}
|
|
|
|
private Queue<ProgramToSave> _programsToSaveQueue;
|
|
|
|
private readonly ComputeShaderCacheHashTable _computeShaderCache;
|
|
private readonly ShaderCacheHashTable _graphicsShaderCache;
|
|
private readonly DiskCacheHostStorage _diskCacheHostStorage;
|
|
private readonly BackgroundDiskCacheWriter _cacheWriter;
|
|
|
|
/// <summary>
|
|
/// Event for signalling shader cache loading progress.
|
|
/// </summary>
|
|
public event Action<ShaderCacheState, int, int> ShaderCacheStateChanged;
|
|
|
|
/// <summary>
|
|
/// Creates a new instance of the shader cache.
|
|
/// </summary>
|
|
/// <param name="context">GPU context that the shader cache belongs to</param>
|
|
public ShaderCache(GpuContext context)
|
|
{
|
|
_context = context;
|
|
|
|
_dumper = new ShaderDumper();
|
|
|
|
_cpPrograms = new Dictionary<ulong, CachedShaderProgram>();
|
|
_gpPrograms = new Dictionary<ShaderAddresses, CachedShaderProgram>();
|
|
|
|
_programsToSaveQueue = new Queue<ProgramToSave>();
|
|
|
|
string diskCacheTitleId = GetDiskCachePath();
|
|
|
|
_computeShaderCache = new ComputeShaderCacheHashTable();
|
|
_graphicsShaderCache = new ShaderCacheHashTable();
|
|
_diskCacheHostStorage = new DiskCacheHostStorage(diskCacheTitleId);
|
|
|
|
if (_diskCacheHostStorage.CacheEnabled)
|
|
{
|
|
_cacheWriter = new BackgroundDiskCacheWriter(context, _diskCacheHostStorage);
|
|
}
|
|
}
|
|
|
|
/// <summary>
|
|
/// Gets the path where the disk cache for the current application is stored.
|
|
/// </summary>
|
|
private static string GetDiskCachePath()
|
|
{
|
|
return GraphicsConfig.EnableShaderCache && GraphicsConfig.TitleId != null
|
|
? Path.Combine(AppDataManager.GamesDirPath, GraphicsConfig.TitleId, "cache", "shader")
|
|
: null;
|
|
}
|
|
|
|
/// <summary>
|
|
/// Processes the queue of shaders that must save their binaries to the disk cache.
|
|
/// </summary>
|
|
public void ProcessShaderCacheQueue()
|
|
{
|
|
// Check to see if the binaries for previously compiled shaders are ready, and save them out.
|
|
|
|
while (_programsToSaveQueue.TryPeek(out ProgramToSave programToSave))
|
|
{
|
|
ProgramLinkStatus result = programToSave.HostProgram.CheckProgramLink(false);
|
|
|
|
if (result != ProgramLinkStatus.Incomplete)
|
|
{
|
|
if (result == ProgramLinkStatus.Success)
|
|
{
|
|
_cacheWriter.AddShader(programToSave.CachedProgram, programToSave.BinaryCode ?? programToSave.HostProgram.GetBinary());
|
|
}
|
|
|
|
_programsToSaveQueue.Dequeue();
|
|
}
|
|
else
|
|
{
|
|
break;
|
|
}
|
|
}
|
|
}
|
|
|
|
/// <summary>
|
|
/// Initialize the cache.
|
|
/// </summary>
|
|
/// <param name="cancellationToken">Cancellation token to cancel the shader cache initialization process</param>
|
|
internal void Initialize(CancellationToken cancellationToken)
|
|
{
|
|
if (_diskCacheHostStorage.CacheEnabled)
|
|
{
|
|
ParallelDiskCacheLoader loader = new ParallelDiskCacheLoader(
|
|
_context,
|
|
_graphicsShaderCache,
|
|
_computeShaderCache,
|
|
_diskCacheHostStorage,
|
|
cancellationToken,
|
|
ShaderCacheStateUpdate);
|
|
|
|
loader.LoadShaders();
|
|
|
|
int errorCount = loader.ErrorCount;
|
|
if (errorCount != 0)
|
|
{
|
|
Logger.Warning?.Print(LogClass.Gpu, $"Failed to load {errorCount} shaders from the disk cache.");
|
|
}
|
|
}
|
|
}
|
|
|
|
/// <summary>
|
|
/// Shader cache state update handler.
|
|
/// </summary>
|
|
/// <param name="state">Current state of the shader cache load process</param>
|
|
/// <param name="current">Number of the current shader being processed</param>
|
|
/// <param name="total">Total number of shaders to process</param>
|
|
private void ShaderCacheStateUpdate(ShaderCacheState state, int current, int total)
|
|
{
|
|
ShaderCacheStateChanged?.Invoke(state, current, total);
|
|
}
|
|
|
|
/// <summary>
|
|
/// Gets a compute shader from the cache.
|
|
/// </summary>
|
|
/// <remarks>
|
|
/// This automatically translates, compiles and adds the code to the cache if not present.
|
|
/// </remarks>
|
|
/// <param name="channel">GPU channel</param>
|
|
/// <param name="poolState">Texture pool state</param>
|
|
/// <param name="computeState">Compute engine state</param>
|
|
/// <param name="gpuVa">GPU virtual address of the binary shader code</param>
|
|
/// <returns>Compiled compute shader code</returns>
|
|
public CachedShaderProgram GetComputeShader(
|
|
GpuChannel channel,
|
|
GpuChannelPoolState poolState,
|
|
GpuChannelComputeState computeState,
|
|
ulong gpuVa)
|
|
{
|
|
if (_cpPrograms.TryGetValue(gpuVa, out var cpShader) && IsShaderEqual(channel, poolState, cpShader, gpuVa))
|
|
{
|
|
return cpShader;
|
|
}
|
|
|
|
if (_computeShaderCache.TryFind(channel, poolState, gpuVa, out cpShader, out byte[] cachedGuestCode))
|
|
{
|
|
_cpPrograms[gpuVa] = cpShader;
|
|
return cpShader;
|
|
}
|
|
|
|
ShaderSpecializationState specState = new ShaderSpecializationState(ref computeState);
|
|
GpuAccessorState gpuAccessorState = new GpuAccessorState(poolState, computeState, default, specState);
|
|
GpuAccessor gpuAccessor = new GpuAccessor(_context, channel, gpuAccessorState);
|
|
|
|
TranslatorContext translatorContext = DecodeComputeShader(gpuAccessor, _context.Capabilities.Api, gpuVa);
|
|
|
|
TranslatedShader translatedShader = TranslateShader(_dumper, channel, translatorContext, cachedGuestCode);
|
|
|
|
ShaderSource[] shaderSourcesArray = new ShaderSource[] { CreateShaderSource(translatedShader.Program) };
|
|
|
|
IProgram hostProgram = _context.Renderer.CreateProgram(shaderSourcesArray, new ShaderInfo(-1));
|
|
|
|
cpShader = new CachedShaderProgram(hostProgram, specState, translatedShader.Shader);
|
|
|
|
_computeShaderCache.Add(cpShader);
|
|
EnqueueProgramToSave(cpShader, hostProgram, shaderSourcesArray);
|
|
_cpPrograms[gpuVa] = cpShader;
|
|
|
|
return cpShader;
|
|
}
|
|
|
|
/// <summary>
|
|
/// Updates the shader pipeline state based on the current GPU state.
|
|
/// </summary>
|
|
/// <param name="state">Current GPU 3D engine state</param>
|
|
/// <param name="pipeline">Shader pipeline state to be updated</param>
|
|
/// <param name="graphicsState">Current graphics state</param>
|
|
/// <param name="channel">Current GPU channel</param>
|
|
private void UpdatePipelineInfo(
|
|
ref ThreedClassState state,
|
|
ref ProgramPipelineState pipeline,
|
|
GpuChannelGraphicsState graphicsState,
|
|
GpuChannel channel)
|
|
{
|
|
channel.TextureManager.UpdateRenderTargets();
|
|
|
|
var rtControl = state.RtControl;
|
|
var msaaMode = state.RtMsaaMode;
|
|
|
|
pipeline.SamplesCount = msaaMode.SamplesInX() * msaaMode.SamplesInY();
|
|
|
|
int count = rtControl.UnpackCount();
|
|
|
|
for (int index = 0; index < Constants.TotalRenderTargets; index++)
|
|
{
|
|
int rtIndex = rtControl.UnpackPermutationIndex(index);
|
|
|
|
var colorState = state.RtColorState[rtIndex];
|
|
|
|
if (index >= count || colorState.Format == 0 || colorState.WidthOrStride == 0)
|
|
{
|
|
pipeline.AttachmentEnable[index] = false;
|
|
pipeline.AttachmentFormats[index] = Format.R8G8B8A8Unorm;
|
|
}
|
|
else
|
|
{
|
|
pipeline.AttachmentEnable[index] = true;
|
|
pipeline.AttachmentFormats[index] = colorState.Format.Convert().Format;
|
|
}
|
|
}
|
|
|
|
pipeline.DepthStencilEnable = state.RtDepthStencilEnable;
|
|
pipeline.DepthStencilFormat = pipeline.DepthStencilEnable ? state.RtDepthStencilState.Format.Convert().Format : Format.D24UnormS8Uint;
|
|
|
|
pipeline.VertexBufferCount = Constants.TotalVertexBuffers;
|
|
pipeline.Topology = graphicsState.Topology;
|
|
}
|
|
|
|
/// <summary>
|
|
/// Gets a graphics shader program from the shader cache.
|
|
/// This includes all the specified shader stages.
|
|
/// </summary>
|
|
/// <remarks>
|
|
/// This automatically translates, compiles and adds the code to the cache if not present.
|
|
/// </remarks>
|
|
/// <param name="state">GPU state</param>
|
|
/// <param name="pipeline">Pipeline state</param>
|
|
/// <param name="channel">GPU channel</param>
|
|
/// <param name="poolState">Texture pool state</param>
|
|
/// <param name="graphicsState">3D engine state</param>
|
|
/// <param name="addresses">Addresses of the shaders for each stage</param>
|
|
/// <returns>Compiled graphics shader code</returns>
|
|
public CachedShaderProgram GetGraphicsShader(
|
|
ref ThreedClassState state,
|
|
ref ProgramPipelineState pipeline,
|
|
GpuChannel channel,
|
|
GpuChannelPoolState poolState,
|
|
GpuChannelGraphicsState graphicsState,
|
|
ShaderAddresses addresses)
|
|
{
|
|
if (_gpPrograms.TryGetValue(addresses, out var gpShaders) && IsShaderEqual(channel, poolState, graphicsState, gpShaders, addresses))
|
|
{
|
|
return gpShaders;
|
|
}
|
|
|
|
if (_graphicsShaderCache.TryFind(channel, poolState, graphicsState, addresses, out gpShaders, out var cachedGuestCode))
|
|
{
|
|
_gpPrograms[addresses] = gpShaders;
|
|
return gpShaders;
|
|
}
|
|
|
|
TransformFeedbackDescriptor[] transformFeedbackDescriptors = GetTransformFeedbackDescriptors(ref state);
|
|
|
|
UpdatePipelineInfo(ref state, ref pipeline, graphicsState, channel);
|
|
|
|
ShaderSpecializationState specState = new ShaderSpecializationState(ref graphicsState, ref pipeline, transformFeedbackDescriptors);
|
|
GpuAccessorState gpuAccessorState = new GpuAccessorState(poolState, default, graphicsState, specState, transformFeedbackDescriptors);
|
|
|
|
ReadOnlySpan<ulong> addressesSpan = addresses.AsSpan();
|
|
|
|
TranslatorContext[] translatorContexts = new TranslatorContext[Constants.ShaderStages + 1];
|
|
TranslatorContext nextStage = null;
|
|
|
|
TargetApi api = _context.Capabilities.Api;
|
|
|
|
for (int stageIndex = Constants.ShaderStages - 1; stageIndex >= 0; stageIndex--)
|
|
{
|
|
ulong gpuVa = addressesSpan[stageIndex + 1];
|
|
|
|
if (gpuVa != 0)
|
|
{
|
|
GpuAccessor gpuAccessor = new GpuAccessor(_context, channel, gpuAccessorState, stageIndex);
|
|
TranslatorContext currentStage = DecodeGraphicsShader(gpuAccessor, api, DefaultFlags, gpuVa);
|
|
|
|
if (nextStage != null)
|
|
{
|
|
currentStage.SetNextStage(nextStage);
|
|
}
|
|
|
|
if (stageIndex == 0 && addresses.VertexA != 0)
|
|
{
|
|
translatorContexts[0] = DecodeGraphicsShader(gpuAccessor, api, DefaultFlags | TranslationFlags.VertexA, addresses.VertexA);
|
|
}
|
|
|
|
translatorContexts[stageIndex + 1] = currentStage;
|
|
nextStage = currentStage;
|
|
}
|
|
}
|
|
|
|
CachedShaderStage[] shaders = new CachedShaderStage[Constants.ShaderStages + 1];
|
|
List<ShaderSource> shaderSources = new List<ShaderSource>();
|
|
|
|
for (int stageIndex = 0; stageIndex < Constants.ShaderStages; stageIndex++)
|
|
{
|
|
TranslatorContext currentStage = translatorContexts[stageIndex + 1];
|
|
|
|
if (currentStage != null)
|
|
{
|
|
ShaderProgram program;
|
|
|
|
if (stageIndex == 0 && translatorContexts[0] != null)
|
|
{
|
|
TranslatedShaderVertexPair translatedShader = TranslateShader(
|
|
_dumper,
|
|
channel,
|
|
currentStage,
|
|
translatorContexts[0],
|
|
cachedGuestCode.VertexACode,
|
|
cachedGuestCode.VertexBCode);
|
|
|
|
shaders[0] = translatedShader.VertexA;
|
|
shaders[1] = translatedShader.VertexB;
|
|
program = translatedShader.Program;
|
|
}
|
|
else
|
|
{
|
|
byte[] code = cachedGuestCode.GetByIndex(stageIndex);
|
|
|
|
TranslatedShader translatedShader = TranslateShader(_dumper, channel, currentStage, code);
|
|
|
|
shaders[stageIndex + 1] = translatedShader.Shader;
|
|
program = translatedShader.Program;
|
|
}
|
|
|
|
if (program != null)
|
|
{
|
|
shaderSources.Add(CreateShaderSource(program));
|
|
}
|
|
}
|
|
}
|
|
|
|
ShaderSource[] shaderSourcesArray = shaderSources.ToArray();
|
|
|
|
int fragmentOutputMap = shaders[5]?.Info.FragmentOutputMap ?? -1;
|
|
IProgram hostProgram = _context.Renderer.CreateProgram(shaderSourcesArray, new ShaderInfo(fragmentOutputMap, pipeline));
|
|
|
|
gpShaders = new CachedShaderProgram(hostProgram, specState, shaders);
|
|
|
|
_graphicsShaderCache.Add(gpShaders);
|
|
EnqueueProgramToSave(gpShaders, hostProgram, shaderSourcesArray);
|
|
_gpPrograms[addresses] = gpShaders;
|
|
|
|
return gpShaders;
|
|
}
|
|
|
|
/// <summary>
|
|
/// Creates a shader source for use with the backend from a translated shader program.
|
|
/// </summary>
|
|
/// <param name="program">Translated shader program</param>
|
|
/// <returns>Shader source</returns>
|
|
public static ShaderSource CreateShaderSource(ShaderProgram program)
|
|
{
|
|
return new ShaderSource(program.Code, program.BinaryCode, GetBindings(program.Info), program.Info.Stage, program.Language);
|
|
}
|
|
|
|
/// <summary>
|
|
/// Puts a program on the queue of programs to be saved on the disk cache.
|
|
/// </summary>
|
|
/// <remarks>
|
|
/// This will not do anything if disk shader cache is disabled.
|
|
/// </remarks>
|
|
/// <param name="program">Cached shader program</param>
|
|
/// <param name="hostProgram">Host program</param>
|
|
/// <param name="sources">Source for each shader stage</param>
|
|
private void EnqueueProgramToSave(CachedShaderProgram program, IProgram hostProgram, ShaderSource[] sources)
|
|
{
|
|
if (_diskCacheHostStorage.CacheEnabled)
|
|
{
|
|
byte[] binaryCode = _context.Capabilities.Api == TargetApi.Vulkan ? ShaderBinarySerializer.Pack(sources) : null;
|
|
ProgramToSave programToSave = new ProgramToSave(program, hostProgram, binaryCode);
|
|
|
|
_programsToSaveQueue.Enqueue(programToSave);
|
|
}
|
|
}
|
|
|
|
/// <summary>
|
|
/// Gets transform feedback state from the current GPU state.
|
|
/// </summary>
|
|
/// <param name="state">Current GPU state</param>
|
|
/// <returns>Four transform feedback descriptors for the enabled TFBs, or null if TFB is disabled</returns>
|
|
private static TransformFeedbackDescriptor[] GetTransformFeedbackDescriptors(ref ThreedClassState state)
|
|
{
|
|
bool tfEnable = state.TfEnable;
|
|
if (!tfEnable)
|
|
{
|
|
return null;
|
|
}
|
|
|
|
TransformFeedbackDescriptor[] descs = new TransformFeedbackDescriptor[Constants.TotalTransformFeedbackBuffers];
|
|
|
|
for (int i = 0; i < Constants.TotalTransformFeedbackBuffers; i++)
|
|
{
|
|
var tf = state.TfState[i];
|
|
|
|
descs[i] = new TransformFeedbackDescriptor(
|
|
tf.BufferIndex,
|
|
tf.Stride,
|
|
tf.VaryingsCount,
|
|
ref state.TfVaryingLocations[i]);
|
|
}
|
|
|
|
return descs;
|
|
}
|
|
|
|
/// <summary>
|
|
/// Checks if compute shader code in memory is equal to the cached shader.
|
|
/// </summary>
|
|
/// <param name="channel">GPU channel using the shader</param>
|
|
/// <param name="poolState">GPU channel state to verify shader compatibility</param>
|
|
/// <param name="cpShader">Cached compute shader</param>
|
|
/// <param name="gpuVa">GPU virtual address of the shader code in memory</param>
|
|
/// <returns>True if the code is different, false otherwise</returns>
|
|
private static bool IsShaderEqual(
|
|
GpuChannel channel,
|
|
GpuChannelPoolState poolState,
|
|
CachedShaderProgram cpShader,
|
|
ulong gpuVa)
|
|
{
|
|
if (IsShaderEqual(channel.MemoryManager, cpShader.Shaders[0], gpuVa))
|
|
{
|
|
return cpShader.SpecializationState.MatchesCompute(channel, poolState, true);
|
|
}
|
|
|
|
return false;
|
|
}
|
|
|
|
/// <summary>
|
|
/// Checks if graphics shader code from all stages in memory are equal to the cached shaders.
|
|
/// </summary>
|
|
/// <param name="channel">GPU channel using the shader</param>
|
|
/// <param name="poolState">GPU channel state to verify shader compatibility</param>
|
|
/// <param name="graphicsState">GPU channel graphics state to verify shader compatibility</param>
|
|
/// <param name="gpShaders">Cached graphics shaders</param>
|
|
/// <param name="addresses">GPU virtual addresses of all enabled shader stages</param>
|
|
/// <returns>True if the code is different, false otherwise</returns>
|
|
private static bool IsShaderEqual(
|
|
GpuChannel channel,
|
|
GpuChannelPoolState poolState,
|
|
GpuChannelGraphicsState graphicsState,
|
|
CachedShaderProgram gpShaders,
|
|
ShaderAddresses addresses)
|
|
{
|
|
ReadOnlySpan<ulong> addressesSpan = addresses.AsSpan();
|
|
|
|
for (int stageIndex = 0; stageIndex < gpShaders.Shaders.Length; stageIndex++)
|
|
{
|
|
CachedShaderStage shader = gpShaders.Shaders[stageIndex];
|
|
|
|
ulong gpuVa = addressesSpan[stageIndex];
|
|
|
|
if (!IsShaderEqual(channel.MemoryManager, shader, gpuVa))
|
|
{
|
|
return false;
|
|
}
|
|
}
|
|
|
|
return gpShaders.SpecializationState.MatchesGraphics(channel, poolState, graphicsState, true);
|
|
}
|
|
|
|
/// <summary>
|
|
/// Checks if the code of the specified cached shader is different from the code in memory.
|
|
/// </summary>
|
|
/// <param name="memoryManager">Memory manager used to access the GPU memory where the shader is located</param>
|
|
/// <param name="shader">Cached shader to compare with</param>
|
|
/// <param name="gpuVa">GPU virtual address of the binary shader code</param>
|
|
/// <returns>True if the code is different, false otherwise</returns>
|
|
private static bool IsShaderEqual(MemoryManager memoryManager, CachedShaderStage shader, ulong gpuVa)
|
|
{
|
|
if (shader == null)
|
|
{
|
|
return true;
|
|
}
|
|
|
|
ReadOnlySpan<byte> memoryCode = memoryManager.GetSpan(gpuVa, shader.Code.Length);
|
|
|
|
return memoryCode.SequenceEqual(shader.Code);
|
|
}
|
|
|
|
/// <summary>
|
|
/// Decode the binary Maxwell shader code to a translator context.
|
|
/// </summary>
|
|
/// <param name="gpuAccessor">GPU state accessor</param>
|
|
/// <param name="api">Graphics API that will be used with the shader</param>
|
|
/// <param name="gpuVa">GPU virtual address of the binary shader code</param>
|
|
/// <returns>The generated translator context</returns>
|
|
public static TranslatorContext DecodeComputeShader(IGpuAccessor gpuAccessor, TargetApi api, ulong gpuVa)
|
|
{
|
|
var options = CreateTranslationOptions(api, DefaultFlags | TranslationFlags.Compute);
|
|
return Translator.CreateContext(gpuVa, gpuAccessor, options);
|
|
}
|
|
|
|
/// <summary>
|
|
/// Decode the binary Maxwell shader code to a translator context.
|
|
/// </summary>
|
|
/// <remarks>
|
|
/// This will combine the "Vertex A" and "Vertex B" shader stages, if specified, into one shader.
|
|
/// </remarks>
|
|
/// <param name="gpuAccessor">GPU state accessor</param>
|
|
/// <param name="api">Graphics API that will be used with the shader</param>
|
|
/// <param name="flags">Flags that controls shader translation</param>
|
|
/// <param name="gpuVa">GPU virtual address of the shader code</param>
|
|
/// <returns>The generated translator context</returns>
|
|
public static TranslatorContext DecodeGraphicsShader(IGpuAccessor gpuAccessor, TargetApi api, TranslationFlags flags, ulong gpuVa)
|
|
{
|
|
var options = CreateTranslationOptions(api, flags);
|
|
return Translator.CreateContext(gpuVa, gpuAccessor, options);
|
|
}
|
|
|
|
/// <summary>
|
|
/// Translates a previously generated translator context to something that the host API accepts.
|
|
/// </summary>
|
|
/// <param name="dumper">Optional shader code dumper</param>
|
|
/// <param name="channel">GPU channel using the shader</param>
|
|
/// <param name="currentStage">Translator context of the stage to be translated</param>
|
|
/// <param name="vertexA">Optional translator context of the shader that should be combined</param>
|
|
/// <param name="codeA">Optional Maxwell binary code of the Vertex A shader, if present</param>
|
|
/// <param name="codeB">Optional Maxwell binary code of the Vertex B or current stage shader, if present on cache</param>
|
|
/// <returns>Compiled graphics shader code</returns>
|
|
private static TranslatedShaderVertexPair TranslateShader(
|
|
ShaderDumper dumper,
|
|
GpuChannel channel,
|
|
TranslatorContext currentStage,
|
|
TranslatorContext vertexA,
|
|
byte[] codeA,
|
|
byte[] codeB)
|
|
{
|
|
ulong cb1DataAddress = channel.BufferManager.GetGraphicsUniformBufferAddress(0, 1);
|
|
|
|
var memoryManager = channel.MemoryManager;
|
|
|
|
codeA ??= memoryManager.GetSpan(vertexA.Address, vertexA.Size).ToArray();
|
|
codeB ??= memoryManager.GetSpan(currentStage.Address, currentStage.Size).ToArray();
|
|
byte[] cb1DataA = memoryManager.Physical.GetSpan(cb1DataAddress, vertexA.Cb1DataSize).ToArray();
|
|
byte[] cb1DataB = memoryManager.Physical.GetSpan(cb1DataAddress, currentStage.Cb1DataSize).ToArray();
|
|
|
|
ShaderDumpPaths pathsA = default;
|
|
ShaderDumpPaths pathsB = default;
|
|
|
|
if (dumper != null)
|
|
{
|
|
pathsA = dumper.Dump(codeA, compute: false);
|
|
pathsB = dumper.Dump(codeB, compute: false);
|
|
}
|
|
|
|
ShaderProgram program = currentStage.Translate(vertexA);
|
|
|
|
pathsB.Prepend(program);
|
|
pathsA.Prepend(program);
|
|
|
|
CachedShaderStage vertexAStage = new CachedShaderStage(null, codeA, cb1DataA);
|
|
CachedShaderStage vertexBStage = new CachedShaderStage(program.Info, codeB, cb1DataB);
|
|
|
|
return new TranslatedShaderVertexPair(vertexAStage, vertexBStage, program);
|
|
}
|
|
|
|
/// <summary>
|
|
/// Translates a previously generated translator context to something that the host API accepts.
|
|
/// </summary>
|
|
/// <param name="dumper">Optional shader code dumper</param>
|
|
/// <param name="channel">GPU channel using the shader</param>
|
|
/// <param name="context">Translator context of the stage to be translated</param>
|
|
/// <param name="code">Optional Maxwell binary code of the current stage shader, if present on cache</param>
|
|
/// <returns>Compiled graphics shader code</returns>
|
|
private static TranslatedShader TranslateShader(ShaderDumper dumper, GpuChannel channel, TranslatorContext context, byte[] code)
|
|
{
|
|
var memoryManager = channel.MemoryManager;
|
|
|
|
ulong cb1DataAddress = context.Stage == ShaderStage.Compute
|
|
? channel.BufferManager.GetComputeUniformBufferAddress(1)
|
|
: channel.BufferManager.GetGraphicsUniformBufferAddress(StageToStageIndex(context.Stage), 1);
|
|
|
|
byte[] cb1Data = memoryManager.Physical.GetSpan(cb1DataAddress, context.Cb1DataSize).ToArray();
|
|
code ??= memoryManager.GetSpan(context.Address, context.Size).ToArray();
|
|
|
|
ShaderDumpPaths paths = dumper?.Dump(code, context.Stage == ShaderStage.Compute) ?? default;
|
|
ShaderProgram program = context.Translate();
|
|
|
|
paths.Prepend(program);
|
|
|
|
return new TranslatedShader(new CachedShaderStage(program.Info, code, cb1Data), program);
|
|
}
|
|
|
|
/// <summary>
|
|
/// Gets the index of a stage from a <see cref="ShaderStage"/>.
|
|
/// </summary>
|
|
/// <param name="stage">Stage to get the index from</param>
|
|
/// <returns>Stage index</returns>
|
|
private static int StageToStageIndex(ShaderStage stage)
|
|
{
|
|
return stage switch
|
|
{
|
|
ShaderStage.TessellationControl => 1,
|
|
ShaderStage.TessellationEvaluation => 2,
|
|
ShaderStage.Geometry => 3,
|
|
ShaderStage.Fragment => 4,
|
|
_ => 0
|
|
};
|
|
}
|
|
|
|
/// <summary>
|
|
/// Gets information about the bindings used by a shader program.
|
|
/// </summary>
|
|
/// <param name="info">Shader program information to get the information from</param>
|
|
/// <returns>Shader bindings</returns>
|
|
public static ShaderBindings GetBindings(ShaderProgramInfo info)
|
|
{
|
|
var uniformBufferBindings = info.CBuffers.Select(x => x.Binding).ToArray();
|
|
var storageBufferBindings = info.SBuffers.Select(x => x.Binding).ToArray();
|
|
var textureBindings = info.Textures.Select(x => x.Binding).ToArray();
|
|
var imageBindings = info.Images.Select(x => x.Binding).ToArray();
|
|
|
|
return new ShaderBindings(
|
|
uniformBufferBindings,
|
|
storageBufferBindings,
|
|
textureBindings,
|
|
imageBindings);
|
|
}
|
|
|
|
/// <summary>
|
|
/// Creates shader translation options with the requested graphics API and flags.
|
|
/// The shader language is choosen based on the current configuration and graphics API.
|
|
/// </summary>
|
|
/// <param name="api">Target graphics API</param>
|
|
/// <param name="flags">Translation flags</param>
|
|
/// <returns>Translation options</returns>
|
|
private static TranslationOptions CreateTranslationOptions(TargetApi api, TranslationFlags flags)
|
|
{
|
|
TargetLanguage lang = GraphicsConfig.EnableSpirvCompilationOnVulkan && api == TargetApi.Vulkan
|
|
? TargetLanguage.Spirv
|
|
: TargetLanguage.Glsl;
|
|
|
|
return new TranslationOptions(lang, api, flags);
|
|
}
|
|
|
|
/// <summary>
|
|
/// Disposes the shader cache, deleting all the cached shaders.
|
|
/// It's an error to use the shader cache after disposal.
|
|
/// </summary>
|
|
public void Dispose()
|
|
{
|
|
foreach (CachedShaderProgram program in _graphicsShaderCache.GetPrograms())
|
|
{
|
|
program.Dispose();
|
|
}
|
|
|
|
foreach (CachedShaderProgram program in _computeShaderCache.GetPrograms())
|
|
{
|
|
program.Dispose();
|
|
}
|
|
|
|
_cacheWriter?.Dispose();
|
|
}
|
|
}
|
|
}
|