mirror of
https://github.com/Ryujinx/Ryujinx.git
synced 2024-10-01 12:30:00 +02:00
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>
903 lines
No EOL
38 KiB
C#
903 lines
No EOL
38 KiB
C#
using Ryujinx.Common.Logging;
|
|
using Ryujinx.Graphics.GAL;
|
|
using Ryujinx.Graphics.Gpu.Engine.Types;
|
|
using Ryujinx.Graphics.Gpu.Memory;
|
|
using Ryujinx.Graphics.Gpu.Shader;
|
|
using Ryujinx.Graphics.Shader;
|
|
using System;
|
|
using System.Runtime.CompilerServices;
|
|
using System.Runtime.InteropServices;
|
|
|
|
namespace Ryujinx.Graphics.Gpu.Image
|
|
{
|
|
/// <summary>
|
|
/// Texture bindings manager.
|
|
/// </summary>
|
|
class TextureBindingsManager
|
|
{
|
|
private const int InitialTextureStateSize = 32;
|
|
private const int InitialImageStateSize = 8;
|
|
|
|
private readonly GpuContext _context;
|
|
|
|
private readonly bool _isCompute;
|
|
|
|
private ulong _texturePoolGpuVa;
|
|
private int _texturePoolMaximumId;
|
|
private TexturePool _texturePool;
|
|
private ulong _samplerPoolGpuVa;
|
|
private int _samplerPoolMaximumId;
|
|
private SamplerIndex _samplerIndex;
|
|
private SamplerPool _samplerPool;
|
|
|
|
private readonly GpuChannel _channel;
|
|
private readonly TexturePoolCache _texturePoolCache;
|
|
private readonly SamplerPoolCache _samplerPoolCache;
|
|
|
|
private TexturePool _cachedTexturePool;
|
|
private SamplerPool _cachedSamplerPool;
|
|
|
|
private readonly TextureBindingInfo[][] _textureBindings;
|
|
private readonly TextureBindingInfo[][] _imageBindings;
|
|
|
|
private struct TextureState
|
|
{
|
|
public ITexture Texture;
|
|
public ISampler Sampler;
|
|
|
|
public int TextureHandle;
|
|
public int SamplerHandle;
|
|
public int InvalidatedSequence;
|
|
public Texture CachedTexture;
|
|
public Sampler CachedSampler;
|
|
public int ScaleIndex;
|
|
public TextureUsageFlags UsageFlags;
|
|
}
|
|
|
|
private TextureState[] _textureState;
|
|
private TextureState[] _imageState;
|
|
|
|
private int[] _textureBindingsCount;
|
|
private int[] _imageBindingsCount;
|
|
|
|
private int _texturePoolSequence;
|
|
private int _samplerPoolSequence;
|
|
|
|
private int _textureBufferIndex;
|
|
|
|
private readonly float[] _scales;
|
|
private bool _scaleChanged;
|
|
private int _lastFragmentTotal;
|
|
|
|
/// <summary>
|
|
/// Constructs a new instance of the texture bindings manager.
|
|
/// </summary>
|
|
/// <param name="context">The GPU context that the texture bindings manager belongs to</param>
|
|
/// <param name="channel">The GPU channel that the texture bindings manager belongs to</param>
|
|
/// <param name="texturePoolCache">Texture pools cache used to get texture pools from</param>
|
|
/// <param name="samplerPoolCache">Sampler pools cache used to get sampler pools from</param>
|
|
/// <param name="scales">Array where the scales for the currently bound textures are stored</param>
|
|
/// <param name="isCompute">True if the bindings manager is used for the compute engine</param>
|
|
public TextureBindingsManager(
|
|
GpuContext context,
|
|
GpuChannel channel,
|
|
TexturePoolCache texturePoolCache,
|
|
SamplerPoolCache samplerPoolCache,
|
|
float[] scales,
|
|
bool isCompute)
|
|
{
|
|
_context = context;
|
|
_channel = channel;
|
|
_texturePoolCache = texturePoolCache;
|
|
_samplerPoolCache = samplerPoolCache;
|
|
|
|
_scales = scales;
|
|
_isCompute = isCompute;
|
|
|
|
int stages = isCompute ? 1 : Constants.ShaderStages;
|
|
|
|
_textureBindings = new TextureBindingInfo[stages][];
|
|
_imageBindings = new TextureBindingInfo[stages][];
|
|
|
|
_textureState = new TextureState[InitialTextureStateSize];
|
|
_imageState = new TextureState[InitialImageStateSize];
|
|
|
|
_textureBindingsCount = new int[stages];
|
|
_imageBindingsCount = new int[stages];
|
|
|
|
for (int stage = 0; stage < stages; stage++)
|
|
{
|
|
_textureBindings[stage] = new TextureBindingInfo[InitialTextureStateSize];
|
|
_imageBindings[stage] = new TextureBindingInfo[InitialImageStateSize];
|
|
}
|
|
}
|
|
|
|
/// <summary>
|
|
/// Rents the texture bindings array for a given stage, so that they can be modified.
|
|
/// </summary>
|
|
/// <param name="stage">Shader stage number, or 0 for compute shaders</param>
|
|
/// <param name="count">The number of bindings needed</param>
|
|
/// <returns>The texture bindings array</returns>
|
|
public TextureBindingInfo[] RentTextureBindings(int stage, int count)
|
|
{
|
|
if (count > _textureBindings[stage].Length)
|
|
{
|
|
Array.Resize(ref _textureBindings[stage], count);
|
|
}
|
|
|
|
_textureBindingsCount[stage] = count;
|
|
|
|
return _textureBindings[stage];
|
|
}
|
|
|
|
/// <summary>
|
|
/// Rents the image bindings array for a given stage, so that they can be modified.
|
|
/// </summary>
|
|
/// <param name="stage">Shader stage number, or 0 for compute shaders</param>
|
|
/// <param name="count">The number of bindings needed</param>
|
|
/// <returns>The image bindings array</returns>
|
|
public TextureBindingInfo[] RentImageBindings(int stage, int count)
|
|
{
|
|
if (count > _imageBindings[stage].Length)
|
|
{
|
|
Array.Resize(ref _imageBindings[stage], count);
|
|
}
|
|
|
|
_imageBindingsCount[stage] = count;
|
|
|
|
return _imageBindings[stage];
|
|
}
|
|
|
|
/// <summary>
|
|
/// Sets the max binding indexes for textures and images.
|
|
/// </summary>
|
|
/// <param name="maxTextureBinding">The maximum texture binding</param>
|
|
/// <param name="maxImageBinding">The maximum image binding</param>
|
|
public void SetMaxBindings(int maxTextureBinding, int maxImageBinding)
|
|
{
|
|
if (maxTextureBinding >= _textureState.Length)
|
|
{
|
|
Array.Resize(ref _textureState, maxTextureBinding + 1);
|
|
}
|
|
|
|
if (maxImageBinding >= _imageState.Length)
|
|
{
|
|
Array.Resize(ref _imageState, maxImageBinding + 1);
|
|
}
|
|
}
|
|
|
|
/// <summary>
|
|
/// Sets the textures constant buffer index.
|
|
/// The constant buffer specified holds the texture handles.
|
|
/// </summary>
|
|
/// <param name="index">Constant buffer index</param>
|
|
public void SetTextureBufferIndex(int index)
|
|
{
|
|
_textureBufferIndex = index;
|
|
}
|
|
|
|
/// <summary>
|
|
/// Sets the current texture sampler pool to be used.
|
|
/// </summary>
|
|
/// <param name="gpuVa">Start GPU virtual address of the pool</param>
|
|
/// <param name="maximumId">Maximum ID of the pool (total count minus one)</param>
|
|
/// <param name="samplerIndex">Type of the sampler pool indexing used for bound samplers</param>
|
|
public void SetSamplerPool(ulong gpuVa, int maximumId, SamplerIndex samplerIndex)
|
|
{
|
|
_samplerPoolGpuVa = gpuVa;
|
|
_samplerPoolMaximumId = maximumId;
|
|
_samplerIndex = samplerIndex;
|
|
_samplerPool = null;
|
|
}
|
|
|
|
/// <summary>
|
|
/// Sets the current texture pool to be used.
|
|
/// </summary>
|
|
/// <param name="gpuVa">Start GPU virtual address of the pool</param>
|
|
/// <param name="maximumId">Maximum ID of the pool (total count minus one)</param>
|
|
public void SetTexturePool(ulong gpuVa, int maximumId)
|
|
{
|
|
_texturePoolGpuVa = gpuVa;
|
|
_texturePoolMaximumId = maximumId;
|
|
_texturePool = null;
|
|
}
|
|
|
|
/// <summary>
|
|
/// Gets a texture and a sampler from their respective pools from a texture ID and a sampler ID.
|
|
/// </summary>
|
|
/// <param name="textureId">ID of the texture</param>
|
|
/// <param name="samplerId">ID of the sampler</param>
|
|
public (Texture, Sampler) GetTextureAndSampler(int textureId, int samplerId)
|
|
{
|
|
(TexturePool texturePool, SamplerPool samplerPool) = GetPools();
|
|
|
|
return (texturePool.Get(textureId), samplerPool.Get(samplerId));
|
|
}
|
|
|
|
/// <summary>
|
|
/// Updates the texture scale for a given texture or image.
|
|
/// </summary>
|
|
/// <param name="texture">Start GPU virtual address of the pool</param>
|
|
/// <param name="usageFlags">The related texture usage flags</param>
|
|
/// <param name="index">The texture/image binding index</param>
|
|
/// <param name="stage">The active shader stage</param>
|
|
/// <returns>True if the given texture has become blacklisted, indicating that its host texture may have changed.</returns>
|
|
private bool UpdateScale(Texture texture, TextureUsageFlags usageFlags, int index, ShaderStage stage)
|
|
{
|
|
float result = 1f;
|
|
bool changed = false;
|
|
|
|
if ((usageFlags & TextureUsageFlags.NeedsScaleValue) != 0 && texture != null)
|
|
{
|
|
if ((usageFlags & TextureUsageFlags.ResScaleUnsupported) != 0)
|
|
{
|
|
changed = texture.ScaleMode != TextureScaleMode.Blacklisted;
|
|
texture.BlacklistScale();
|
|
}
|
|
else
|
|
{
|
|
switch (stage)
|
|
{
|
|
case ShaderStage.Fragment:
|
|
float scale = texture.ScaleFactor;
|
|
|
|
if (scale != 1)
|
|
{
|
|
Texture activeTarget = _channel.TextureManager.GetAnyRenderTarget();
|
|
|
|
if (activeTarget != null && (activeTarget.Info.Width / (float)texture.Info.Width) == (activeTarget.Info.Height / (float)texture.Info.Height))
|
|
{
|
|
// If the texture's size is a multiple of the sampler size, enable interpolation using gl_FragCoord. (helps "invent" new integer values between scaled pixels)
|
|
result = -scale;
|
|
break;
|
|
}
|
|
}
|
|
|
|
result = scale;
|
|
break;
|
|
|
|
case ShaderStage.Vertex:
|
|
int fragmentIndex = (int)ShaderStage.Fragment - 1;
|
|
index += _textureBindingsCount[fragmentIndex] + _imageBindingsCount[fragmentIndex];
|
|
|
|
result = texture.ScaleFactor;
|
|
break;
|
|
|
|
case ShaderStage.Compute:
|
|
result = texture.ScaleFactor;
|
|
break;
|
|
}
|
|
}
|
|
}
|
|
|
|
if (result != _scales[index])
|
|
{
|
|
_scaleChanged = true;
|
|
|
|
_scales[index] = result;
|
|
}
|
|
|
|
return changed;
|
|
}
|
|
|
|
/// <summary>
|
|
/// Determines if the vertex stage requires a scale value.
|
|
/// </summary>
|
|
private bool VertexRequiresScale()
|
|
{
|
|
for (int i = 0; i < _textureBindingsCount[0]; i++)
|
|
{
|
|
if ((_textureBindings[0][i].Flags & TextureUsageFlags.NeedsScaleValue) != 0)
|
|
{
|
|
return true;
|
|
}
|
|
}
|
|
|
|
for (int i = 0; i < _imageBindingsCount[0]; i++)
|
|
{
|
|
if ((_imageBindings[0][i].Flags & TextureUsageFlags.NeedsScaleValue) != 0)
|
|
{
|
|
return true;
|
|
}
|
|
}
|
|
|
|
return false;
|
|
}
|
|
|
|
/// <summary>
|
|
/// Uploads texture and image scales to the backend when they are used.
|
|
/// </summary>
|
|
private void CommitRenderScale()
|
|
{
|
|
// Stage 0 total: Compute or Vertex.
|
|
int total = _textureBindingsCount[0] + _imageBindingsCount[0];
|
|
|
|
int fragmentIndex = (int)ShaderStage.Fragment - 1;
|
|
int fragmentTotal = _isCompute ? 0 : (_textureBindingsCount[fragmentIndex] + _imageBindingsCount[fragmentIndex]);
|
|
|
|
if (total != 0 && fragmentTotal != _lastFragmentTotal && VertexRequiresScale())
|
|
{
|
|
// Must update scales in the support buffer if:
|
|
// - Vertex stage has bindings that require scale.
|
|
// - Fragment stage binding count has been updated since last render scale update.
|
|
|
|
_scaleChanged = true;
|
|
}
|
|
|
|
if (_scaleChanged)
|
|
{
|
|
if (!_isCompute)
|
|
{
|
|
total += fragmentTotal; // Add the fragment bindings to the total.
|
|
}
|
|
|
|
_lastFragmentTotal = fragmentTotal;
|
|
|
|
_context.Renderer.Pipeline.UpdateRenderScale(_scales, total, fragmentTotal);
|
|
|
|
_scaleChanged = false;
|
|
}
|
|
}
|
|
|
|
/// <summary>
|
|
/// Ensures that the bindings are visible to the host GPU.
|
|
/// Note: this actually performs the binding using the host graphics API.
|
|
/// </summary>
|
|
/// <param name="specState">Specialization state for the bound shader</param>
|
|
/// <returns>True if all bound textures match the current shader specialiation state, false otherwise</returns>
|
|
public bool CommitBindings(ShaderSpecializationState specState)
|
|
{
|
|
(TexturePool texturePool, SamplerPool samplerPool) = GetPools();
|
|
|
|
// Check if the texture pool has been modified since bindings were last committed.
|
|
// If it wasn't, then it's possible to avoid looking up textures again when the handle remains the same.
|
|
bool poolModified = _cachedTexturePool != texturePool || _cachedSamplerPool != samplerPool;
|
|
|
|
_cachedTexturePool = texturePool;
|
|
_cachedSamplerPool = samplerPool;
|
|
|
|
if (texturePool != null)
|
|
{
|
|
int texturePoolSequence = texturePool.CheckModified();
|
|
|
|
if (_texturePoolSequence != texturePoolSequence)
|
|
{
|
|
poolModified = true;
|
|
_texturePoolSequence = texturePoolSequence;
|
|
}
|
|
}
|
|
|
|
if (samplerPool != null)
|
|
{
|
|
int samplerPoolSequence = samplerPool.CheckModified();
|
|
|
|
if (_samplerPoolSequence != samplerPoolSequence)
|
|
{
|
|
poolModified = true;
|
|
_samplerPoolSequence = samplerPoolSequence;
|
|
}
|
|
}
|
|
|
|
bool specStateMatches = true;
|
|
|
|
if (_isCompute)
|
|
{
|
|
specStateMatches &= CommitTextureBindings(texturePool, samplerPool, ShaderStage.Compute, 0, poolModified, specState);
|
|
specStateMatches &= CommitImageBindings(texturePool, ShaderStage.Compute, 0, poolModified, specState);
|
|
}
|
|
else
|
|
{
|
|
for (ShaderStage stage = ShaderStage.Vertex; stage <= ShaderStage.Fragment; stage++)
|
|
{
|
|
int stageIndex = (int)stage - 1;
|
|
|
|
specStateMatches &= CommitTextureBindings(texturePool, samplerPool, stage, stageIndex, poolModified, specState);
|
|
specStateMatches &= CommitImageBindings(texturePool, stage, stageIndex, poolModified, specState);
|
|
}
|
|
}
|
|
|
|
CommitRenderScale();
|
|
|
|
return specStateMatches;
|
|
}
|
|
|
|
/// <summary>
|
|
/// Fetch the constant buffers used for a texture to cache.
|
|
/// </summary>
|
|
/// <param name="stageIndex">Stage index of the constant buffer</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="textureBufferIndex">The new texture buffer index</param>
|
|
/// <param name="samplerBufferIndex">The new sampler buffer index</param>
|
|
[MethodImpl(MethodImplOptions.AggressiveInlining)]
|
|
private void UpdateCachedBuffer(
|
|
int stageIndex,
|
|
ref int cachedTextureBufferIndex,
|
|
ref int cachedSamplerBufferIndex,
|
|
ref ReadOnlySpan<int> cachedTextureBuffer,
|
|
ref ReadOnlySpan<int> cachedSamplerBuffer,
|
|
int textureBufferIndex,
|
|
int samplerBufferIndex)
|
|
{
|
|
if (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 (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;
|
|
}
|
|
}
|
|
|
|
/// <summary>
|
|
/// Counts the total number of texture bindings used by all shader stages.
|
|
/// </summary>
|
|
/// <returns>The total amount of textures used</returns>
|
|
private int GetTextureBindingsCount()
|
|
{
|
|
int count = 0;
|
|
|
|
for (int i = 0; i < _textureBindings.Length; i++)
|
|
{
|
|
if (_textureBindings[i] != null)
|
|
{
|
|
count += _textureBindings[i].Length;
|
|
}
|
|
}
|
|
|
|
return count;
|
|
}
|
|
|
|
/// <summary>
|
|
/// Ensures that the texture bindings are visible to the host GPU.
|
|
/// Note: this actually performs the binding using the host graphics API.
|
|
/// </summary>
|
|
/// <param name="texturePool">The current texture pool</param>
|
|
/// <param name="samplerPool">The current sampler pool</param>
|
|
/// <param name="stage">The shader stage using the textures to be bound</param>
|
|
/// <param name="stageIndex">The stage number of the specified shader stage</param
|
|
/// <param name="poolModified">True if either the texture or sampler pool was modified, false otherwise</param>
|
|
/// <param name="specState">Specialization state for the bound shader</param>
|
|
/// <returns>True if all bound textures match the current shader specialiation state, false otherwise</returns>
|
|
private bool CommitTextureBindings(
|
|
TexturePool texturePool,
|
|
SamplerPool samplerPool,
|
|
ShaderStage stage,
|
|
int stageIndex,
|
|
bool poolModified,
|
|
ShaderSpecializationState specState)
|
|
{
|
|
int textureCount = _textureBindingsCount[stageIndex];
|
|
if (textureCount == 0)
|
|
{
|
|
return true;
|
|
}
|
|
|
|
if (texturePool == null)
|
|
{
|
|
Logger.Error?.Print(LogClass.Gpu, $"Shader stage \"{stage}\" uses textures, but texture pool was not set.");
|
|
return true;
|
|
}
|
|
|
|
bool specStateMatches = true;
|
|
|
|
int cachedTextureBufferIndex = -1;
|
|
int cachedSamplerBufferIndex = -1;
|
|
ReadOnlySpan<int> cachedTextureBuffer = Span<int>.Empty;
|
|
ReadOnlySpan<int> cachedSamplerBuffer = Span<int>.Empty;
|
|
|
|
for (int index = 0; index < textureCount; index++)
|
|
{
|
|
TextureBindingInfo bindingInfo = _textureBindings[stageIndex][index];
|
|
TextureUsageFlags usageFlags = bindingInfo.Flags;
|
|
|
|
(int textureBufferIndex, int samplerBufferIndex) = TextureHandle.UnpackSlots(bindingInfo.CbufSlot, _textureBufferIndex);
|
|
|
|
UpdateCachedBuffer(stageIndex, ref cachedTextureBufferIndex, ref cachedSamplerBufferIndex, ref cachedTextureBuffer, ref cachedSamplerBuffer, textureBufferIndex, samplerBufferIndex);
|
|
|
|
int packedId = TextureHandle.ReadPackedId(bindingInfo.Handle, cachedTextureBuffer, cachedSamplerBuffer);
|
|
int textureId = TextureHandle.UnpackTextureId(packedId);
|
|
int samplerId;
|
|
|
|
if (_samplerIndex == SamplerIndex.ViaHeaderIndex)
|
|
{
|
|
samplerId = textureId;
|
|
}
|
|
else
|
|
{
|
|
samplerId = TextureHandle.UnpackSamplerId(packedId);
|
|
}
|
|
|
|
ref TextureState state = ref _textureState[bindingInfo.Binding];
|
|
|
|
if (!poolModified &&
|
|
state.TextureHandle == textureId &&
|
|
state.SamplerHandle == samplerId &&
|
|
state.CachedTexture != null &&
|
|
state.CachedTexture.InvalidatedSequence == state.InvalidatedSequence &&
|
|
state.CachedSampler?.IsDisposed != true)
|
|
{
|
|
// The texture is already bound.
|
|
state.CachedTexture.SynchronizeMemory();
|
|
|
|
if ((state.ScaleIndex != index || state.UsageFlags != usageFlags) &&
|
|
UpdateScale(state.CachedTexture, usageFlags, index, stage))
|
|
{
|
|
ITexture hostTextureRebind = state.CachedTexture.GetTargetTexture(bindingInfo.Target);
|
|
|
|
state.Texture = hostTextureRebind;
|
|
state.ScaleIndex = index;
|
|
state.UsageFlags = usageFlags;
|
|
|
|
_context.Renderer.Pipeline.SetTextureAndSampler(stage, bindingInfo.Binding, hostTextureRebind, state.Sampler);
|
|
}
|
|
|
|
continue;
|
|
}
|
|
|
|
state.TextureHandle = textureId;
|
|
state.SamplerHandle = samplerId;
|
|
|
|
ref readonly TextureDescriptor descriptor = ref texturePool.GetForBinding(textureId, out Texture texture);
|
|
|
|
specStateMatches &= specState.MatchesTexture(stage, index, descriptor);
|
|
|
|
Sampler sampler = _samplerPool?.Get(samplerId);
|
|
|
|
ITexture hostTexture = texture?.GetTargetTexture(bindingInfo.Target);
|
|
ISampler hostSampler = sampler?.GetHostSampler(texture);
|
|
|
|
if (hostTexture != null && texture.Target == Target.TextureBuffer)
|
|
{
|
|
// Ensure that the buffer texture is using the correct buffer as storage.
|
|
// Buffers are frequently re-created to accomodate larger data, so we need to re-bind
|
|
// to ensure we're not using a old buffer that was already deleted.
|
|
_channel.BufferManager.SetBufferTextureStorage(stage, hostTexture, texture.Range.GetSubRange(0).Address, texture.Size, bindingInfo, bindingInfo.Format, false);
|
|
}
|
|
else
|
|
{
|
|
bool textureOrSamplerChanged = state.Texture != hostTexture || state.Sampler != hostSampler;
|
|
|
|
if ((state.ScaleIndex != index || state.UsageFlags != usageFlags || textureOrSamplerChanged) &&
|
|
UpdateScale(texture, usageFlags, index, stage))
|
|
{
|
|
hostTexture = texture?.GetTargetTexture(bindingInfo.Target);
|
|
textureOrSamplerChanged = true;
|
|
}
|
|
|
|
if (textureOrSamplerChanged)
|
|
{
|
|
state.Texture = hostTexture;
|
|
state.ScaleIndex = index;
|
|
state.UsageFlags = usageFlags;
|
|
|
|
state.Sampler = hostSampler;
|
|
|
|
_context.Renderer.Pipeline.SetTextureAndSampler(stage, bindingInfo.Binding, hostTexture, hostSampler);
|
|
}
|
|
|
|
state.CachedTexture = texture;
|
|
state.CachedSampler = sampler;
|
|
state.InvalidatedSequence = texture?.InvalidatedSequence ?? 0;
|
|
}
|
|
}
|
|
|
|
return specStateMatches;
|
|
}
|
|
|
|
/// <summary>
|
|
/// Ensures that the image bindings are visible to the host GPU.
|
|
/// Note: this actually performs the binding using the host graphics API.
|
|
/// </summary>
|
|
/// <param name="pool">The current texture pool</param>
|
|
/// <param name="stage">The shader stage using the textures to be bound</param>
|
|
/// <param name="stageIndex">The stage number of the specified shader stage</param>
|
|
/// <param name="poolModified">True if either the texture or sampler pool was modified, false otherwise</param>
|
|
/// <param name="specState">Specialization state for the bound shader</param>
|
|
/// <returns>True if all bound images match the current shader specialiation state, false otherwise</returns>
|
|
private bool CommitImageBindings(TexturePool pool, ShaderStage stage, int stageIndex, bool poolModified, ShaderSpecializationState specState)
|
|
{
|
|
int imageCount = _imageBindingsCount[stageIndex];
|
|
if (imageCount == 0)
|
|
{
|
|
return true;
|
|
}
|
|
|
|
if (pool == null)
|
|
{
|
|
Logger.Error?.Print(LogClass.Gpu, $"Shader stage \"{stage}\" uses images, but texture pool was not set.");
|
|
return true;
|
|
}
|
|
|
|
// Scales for images appear after the texture ones.
|
|
int baseScaleIndex = _textureBindingsCount[stageIndex];
|
|
|
|
int cachedTextureBufferIndex = -1;
|
|
int cachedSamplerBufferIndex = -1;
|
|
ReadOnlySpan<int> cachedTextureBuffer = Span<int>.Empty;
|
|
ReadOnlySpan<int> cachedSamplerBuffer = Span<int>.Empty;
|
|
|
|
bool specStateMatches = true;
|
|
|
|
for (int index = 0; index < imageCount; index++)
|
|
{
|
|
TextureBindingInfo bindingInfo = _imageBindings[stageIndex][index];
|
|
TextureUsageFlags usageFlags = bindingInfo.Flags;
|
|
int scaleIndex = baseScaleIndex + index;
|
|
|
|
(int textureBufferIndex, int samplerBufferIndex) = TextureHandle.UnpackSlots(bindingInfo.CbufSlot, _textureBufferIndex);
|
|
|
|
UpdateCachedBuffer(stageIndex, ref cachedTextureBufferIndex, ref cachedSamplerBufferIndex, ref cachedTextureBuffer, ref cachedSamplerBuffer, textureBufferIndex, samplerBufferIndex);
|
|
|
|
int packedId = TextureHandle.ReadPackedId(bindingInfo.Handle, cachedTextureBuffer, cachedSamplerBuffer);
|
|
int textureId = TextureHandle.UnpackTextureId(packedId);
|
|
|
|
ref TextureState state = ref _imageState[bindingInfo.Binding];
|
|
|
|
bool isStore = bindingInfo.Flags.HasFlag(TextureUsageFlags.ImageStore);
|
|
|
|
if (!poolModified &&
|
|
state.TextureHandle == textureId &&
|
|
state.CachedTexture != null &&
|
|
state.CachedTexture.InvalidatedSequence == state.InvalidatedSequence)
|
|
{
|
|
Texture cachedTexture = state.CachedTexture;
|
|
|
|
// The texture is already bound.
|
|
cachedTexture.SynchronizeMemory();
|
|
|
|
if (isStore)
|
|
{
|
|
cachedTexture?.SignalModified();
|
|
}
|
|
|
|
if ((state.ScaleIndex != scaleIndex || state.UsageFlags != usageFlags) &&
|
|
UpdateScale(state.CachedTexture, usageFlags, scaleIndex, stage))
|
|
{
|
|
ITexture hostTextureRebind = state.CachedTexture.GetTargetTexture(bindingInfo.Target);
|
|
|
|
Format format = bindingInfo.Format == 0 ? cachedTexture.Format : bindingInfo.Format;
|
|
|
|
state.Texture = hostTextureRebind;
|
|
state.ScaleIndex = scaleIndex;
|
|
state.UsageFlags = usageFlags;
|
|
|
|
_context.Renderer.Pipeline.SetImage(bindingInfo.Binding, hostTextureRebind, format);
|
|
}
|
|
|
|
continue;
|
|
}
|
|
|
|
state.TextureHandle = textureId;
|
|
|
|
ref readonly TextureDescriptor descriptor = ref pool.GetForBinding(textureId, out Texture texture);
|
|
|
|
specStateMatches &= specState.MatchesImage(stage, index, descriptor);
|
|
|
|
ITexture hostTexture = texture?.GetTargetTexture(bindingInfo.Target);
|
|
|
|
if (hostTexture != null && texture.Target == Target.TextureBuffer)
|
|
{
|
|
// Ensure that the buffer texture is using the correct buffer as storage.
|
|
// Buffers are frequently re-created to accomodate larger data, so we need to re-bind
|
|
// to ensure we're not using a old buffer that was already deleted.
|
|
|
|
Format format = bindingInfo.Format;
|
|
|
|
if (format == 0 && texture != null)
|
|
{
|
|
format = texture.Format;
|
|
}
|
|
|
|
_channel.BufferManager.SetBufferTextureStorage(stage, hostTexture, texture.Range.GetSubRange(0).Address, texture.Size, bindingInfo, format, true);
|
|
}
|
|
else
|
|
{
|
|
if (isStore)
|
|
{
|
|
texture?.SignalModified();
|
|
}
|
|
|
|
if ((state.ScaleIndex != scaleIndex || state.UsageFlags != usageFlags || state.Texture != hostTexture) &&
|
|
UpdateScale(texture, usageFlags, scaleIndex, stage))
|
|
{
|
|
hostTexture = texture?.GetTargetTexture(bindingInfo.Target);
|
|
}
|
|
|
|
if (state.Texture != hostTexture)
|
|
{
|
|
state.Texture = hostTexture;
|
|
state.ScaleIndex = scaleIndex;
|
|
state.UsageFlags = usageFlags;
|
|
|
|
Format format = bindingInfo.Format;
|
|
|
|
if (format == 0 && texture != null)
|
|
{
|
|
format = texture.Format;
|
|
}
|
|
|
|
_context.Renderer.Pipeline.SetImage(bindingInfo.Binding, hostTexture, format);
|
|
}
|
|
|
|
state.CachedTexture = texture;
|
|
state.InvalidatedSequence = texture?.InvalidatedSequence ?? 0;
|
|
}
|
|
}
|
|
|
|
return specStateMatches;
|
|
}
|
|
|
|
/// <summary>
|
|
/// Gets the texture descriptor for a given texture handle.
|
|
/// </summary>
|
|
/// <param name="poolGpuVa">GPU virtual address of the texture pool</param>
|
|
/// <param name="bufferIndex">Index of the constant buffer with texture handles</param>
|
|
/// <param name="maximumId">Maximum ID of the texture pool</param>
|
|
/// <param name="stageIndex">The stage number where the texture is bound</param>
|
|
/// <param name="handle">The texture handle</param>
|
|
/// <param name="cbufSlot">The texture handle's constant buffer slot</param>
|
|
/// <returns>The texture descriptor for the specified texture</returns>
|
|
public TextureDescriptor GetTextureDescriptor(
|
|
ulong poolGpuVa,
|
|
int bufferIndex,
|
|
int maximumId,
|
|
int stageIndex,
|
|
int handle,
|
|
int cbufSlot)
|
|
{
|
|
(int textureBufferIndex, int samplerBufferIndex) = TextureHandle.UnpackSlots(cbufSlot, bufferIndex);
|
|
|
|
int packedId = ReadPackedId(stageIndex, handle, textureBufferIndex, samplerBufferIndex);
|
|
int textureId = TextureHandle.UnpackTextureId(packedId);
|
|
|
|
ulong poolAddress = _channel.MemoryManager.Translate(poolGpuVa);
|
|
|
|
TexturePool texturePool = _texturePoolCache.FindOrCreate(_channel, poolAddress, maximumId);
|
|
|
|
TextureDescriptor descriptor;
|
|
|
|
if (texturePool.IsValidId(textureId))
|
|
{
|
|
descriptor = texturePool.GetDescriptor(textureId);
|
|
}
|
|
else
|
|
{
|
|
// If the ID is not valid, we just return a default descriptor with the most common state.
|
|
// Since this is used for shader specialization, doing so might avoid the need for recompilations.
|
|
descriptor = new TextureDescriptor();
|
|
descriptor.Word4 |= (uint)TextureTarget.Texture2D << 23;
|
|
descriptor.Word5 |= 1u << 31; // Coords normalized.
|
|
}
|
|
|
|
return descriptor;
|
|
}
|
|
|
|
/// <summary>
|
|
/// Reads a packed texture and sampler ID (basically, the real texture handle)
|
|
/// from the texture constant buffer.
|
|
/// </summary>
|
|
/// <param name="stageIndex">The number of the shader stage where the texture is bound</param>
|
|
/// <param name="wordOffset">A word offset of the handle on the buffer (the "fake" shader handle)</param>
|
|
/// <param name="textureBufferIndex">Index of the constant buffer holding the texture handles</param>
|
|
/// <param name="samplerBufferIndex">Index of the constant buffer holding the sampler handles</param>
|
|
/// <returns>The packed texture and sampler ID (the real texture handle)</returns>
|
|
[MethodImpl(MethodImplOptions.AggressiveInlining)]
|
|
private int ReadPackedId(int stageIndex, int wordOffset, int textureBufferIndex, int samplerBufferIndex)
|
|
{
|
|
(int textureWordOffset, int samplerWordOffset, TextureHandleType handleType) = TextureHandle.UnpackOffsets(wordOffset);
|
|
|
|
ulong textureBufferAddress = _isCompute
|
|
? _channel.BufferManager.GetComputeUniformBufferAddress(textureBufferIndex)
|
|
: _channel.BufferManager.GetGraphicsUniformBufferAddress(stageIndex, textureBufferIndex);
|
|
|
|
int handle = _channel.MemoryManager.Physical.Read<int>(textureBufferAddress + (uint)textureWordOffset * 4);
|
|
|
|
// The "wordOffset" (which is really the immediate value used on texture instructions on the shader)
|
|
// is a 13-bit value. However, in order to also support separate samplers and textures (which uses
|
|
// bindless textures on the shader), we extend it with another value on the higher 16 bits with
|
|
// another offset for the sampler.
|
|
// The shader translator has code to detect separate texture and sampler uses with a bindless texture,
|
|
// turn that into a regular texture access and produce those special handles with values on the higher 16 bits.
|
|
if (handleType != TextureHandleType.CombinedSampler)
|
|
{
|
|
int samplerHandle;
|
|
|
|
if (handleType != TextureHandleType.SeparateConstantSamplerHandle)
|
|
{
|
|
ulong samplerBufferAddress = _isCompute
|
|
? _channel.BufferManager.GetComputeUniformBufferAddress(samplerBufferIndex)
|
|
: _channel.BufferManager.GetGraphicsUniformBufferAddress(stageIndex, samplerBufferIndex);
|
|
|
|
samplerHandle = _channel.MemoryManager.Physical.Read<int>(samplerBufferAddress + (uint)samplerWordOffset * 4);
|
|
}
|
|
else
|
|
{
|
|
samplerHandle = samplerWordOffset;
|
|
}
|
|
|
|
if (handleType == TextureHandleType.SeparateSamplerId ||
|
|
handleType == TextureHandleType.SeparateConstantSamplerHandle)
|
|
{
|
|
samplerHandle <<= 20;
|
|
}
|
|
|
|
handle |= samplerHandle;
|
|
}
|
|
|
|
return handle;
|
|
}
|
|
|
|
/// <summary>
|
|
/// Gets the texture and sampler pool for the GPU virtual address that are currently set.
|
|
/// </summary>
|
|
/// <returns>The texture and sampler pools</returns>
|
|
private (TexturePool, SamplerPool) GetPools()
|
|
{
|
|
MemoryManager memoryManager = _channel.MemoryManager;
|
|
|
|
TexturePool texturePool = _texturePool;
|
|
SamplerPool samplerPool = _samplerPool;
|
|
|
|
if (texturePool == null)
|
|
{
|
|
ulong poolAddress = memoryManager.Translate(_texturePoolGpuVa);
|
|
|
|
if (poolAddress != MemoryManager.PteUnmapped)
|
|
{
|
|
texturePool = _texturePoolCache.FindOrCreate(_channel, poolAddress, _texturePoolMaximumId);
|
|
_texturePool = texturePool;
|
|
}
|
|
}
|
|
|
|
if (samplerPool == null)
|
|
{
|
|
ulong poolAddress = memoryManager.Translate(_samplerPoolGpuVa);
|
|
|
|
if (poolAddress != MemoryManager.PteUnmapped)
|
|
{
|
|
samplerPool = _samplerPoolCache.FindOrCreate(_channel, poolAddress, _samplerPoolMaximumId);
|
|
_samplerPool = samplerPool;
|
|
}
|
|
}
|
|
|
|
return (texturePool, samplerPool);
|
|
}
|
|
|
|
/// <summary>
|
|
/// Forces the texture and sampler pools to be re-loaded from the cache on next use.
|
|
/// </summary>
|
|
/// <remarks>
|
|
/// This should be called if the memory mappings change, to ensure the correct pools are being used.
|
|
/// </remarks>
|
|
public void ReloadPools()
|
|
{
|
|
_samplerPool = null;
|
|
_texturePool = null;
|
|
}
|
|
|
|
/// <summary>
|
|
/// Force all bound textures and images to be rebound the next time CommitBindings is called.
|
|
/// </summary>
|
|
public void Rebind()
|
|
{
|
|
Array.Clear(_textureState);
|
|
Array.Clear(_imageState);
|
|
}
|
|
}
|
|
} |