0
0
Fork 0
mirror of https://github.com/GreemDev/Ryujinx.git synced 2024-12-28 03:35:47 +00:00
Ryujinx/Ryujinx.Graphics.Gpu/Engine/Threed/ThreedClassState.cs

1049 lines
32 KiB
C#
Raw Normal View History

using Ryujinx.Common.Memory;
using Ryujinx.Graphics.GAL;
using Ryujinx.Graphics.Gpu.Engine.InlineToMemory;
using Ryujinx.Graphics.Gpu.Engine.Types;
using Ryujinx.Graphics.Gpu.Image;
using Ryujinx.Graphics.Shader;
using System;
using System.Runtime.CompilerServices;
namespace Ryujinx.Graphics.Gpu.Engine.Threed
{
/// <summary>
/// Shader stage name.
/// </summary>
enum ShaderType
{
Vertex,
TessellationControl,
TessellationEvaluation,
Geometry,
Fragment
}
/// <summary>
/// Tessellation mode.
/// </summary>
struct TessMode
{
#pragma warning disable CS0649
public uint Packed;
#pragma warning restore CS0649
/// <summary>
/// Unpacks the tessellation abstract patch type.
/// </summary>
/// <returns>Abtract patch type</returns>
public TessPatchType UnpackPatchType()
{
return (TessPatchType)(Packed & 3);
}
/// <summary>
/// Unpacks the spacing between tessellated vertices of the patch.
/// </summary>
/// <returns>Spacing between tessellated vertices</returns>
public TessSpacing UnpackSpacing()
{
return (TessSpacing)((Packed >> 4) & 3);
}
/// <summary>
/// Unpacks the primitive winding order.
/// </summary>
/// <returns>True if clockwise, false if counter-clockwise</returns>
public bool UnpackCw()
{
return (Packed & (1 << 8)) != 0;
}
}
/// <summary>
/// Transform feedback buffer state.
/// </summary>
struct TfBufferState
{
#pragma warning disable CS0649
public Boolean32 Enable;
public GpuVa Address;
public int Size;
public int Offset;
public uint Padding0;
public uint Padding1;
public uint Padding2;
#pragma warning restore CS0649
}
/// <summary>
/// Transform feedback state.
/// </summary>
struct TfState
{
#pragma warning disable CS0649
public int BufferIndex;
public int VaryingsCount;
public int Stride;
public uint Padding;
#pragma warning restore CS0649
}
/// <summary>
/// Render target color buffer state.
/// </summary>
struct RtColorState
{
#pragma warning disable CS0649
public GpuVa Address;
public int WidthOrStride;
public int Height;
public ColorFormat Format;
public MemoryLayout MemoryLayout;
public int Depth;
public int LayerSize;
public int BaseLayer;
public int Unknown0x24;
public int Padding0;
public int Padding1;
public int Padding2;
public int Padding3;
public int Padding4;
public int Padding5;
#pragma warning restore CS0649
}
/// <summary>
/// Viewport transform parameters, for viewport transformation.
/// </summary>
struct ViewportTransform
{
#pragma warning disable CS0649
public float ScaleX;
public float ScaleY;
public float ScaleZ;
public float TranslateX;
public float TranslateY;
public float TranslateZ;
public uint Swizzle;
public uint SubpixelPrecisionBias;
#pragma warning restore CS0649
/// <summary>
/// Unpacks viewport swizzle of the position X component.
/// </summary>
/// <returns>Swizzle enum value</returns>
public ViewportSwizzle UnpackSwizzleX()
{
return (ViewportSwizzle)(Swizzle & 7);
}
/// <summary>
/// Unpacks viewport swizzle of the position Y component.
/// </summary>
/// <returns>Swizzle enum value</returns>
public ViewportSwizzle UnpackSwizzleY()
{
return (ViewportSwizzle)((Swizzle >> 4) & 7);
}
/// <summary>
/// Unpacks viewport swizzle of the position Z component.
/// </summary>
/// <returns>Swizzle enum value</returns>
public ViewportSwizzle UnpackSwizzleZ()
{
return (ViewportSwizzle)((Swizzle >> 8) & 7);
}
/// <summary>
/// Unpacks viewport swizzle of the position W component.
/// </summary>
/// <returns>Swizzle enum value</returns>
public ViewportSwizzle UnpackSwizzleW()
{
return (ViewportSwizzle)((Swizzle >> 12) & 7);
}
}
/// <summary>
/// Viewport extents for viewport clipping, also includes depth range.
/// </summary>
struct ViewportExtents
{
#pragma warning disable CS0649
public ushort X;
public ushort Width;
public ushort Y;
public ushort Height;
public float DepthNear;
public float DepthFar;
#pragma warning restore CS0649
}
/// <summary>
/// Draw state for non-indexed draws.
/// </summary>
struct VertexBufferDrawState
{
#pragma warning disable CS0649
public int First;
public int Count;
#pragma warning restore CS0649
}
/// <summary>
/// Color buffer clear color.
/// </summary>
struct ClearColors
{
#pragma warning disable CS0649
public float Red;
public float Green;
public float Blue;
public float Alpha;
#pragma warning restore CS0649
}
/// <summary>
/// Depth bias (also called polygon offset) parameters.
/// </summary>
struct DepthBiasState
{
#pragma warning disable CS0649
public Boolean32 PointEnable;
public Boolean32 LineEnable;
public Boolean32 FillEnable;
#pragma warning restore CS0649
}
/// <summary>
/// Indicates whenever the blend microcode processes RGB and alpha components.
/// </summary>
enum BlendUcodeEnable
{
Disabled = 0,
EnableRGB = 1,
EnableAlpha = 2,
EnableRGBA = 3
}
/// <summary>
/// Scissor state.
/// </summary>
struct ScissorState
{
#pragma warning disable CS0649
public Boolean32 Enable;
public ushort X1;
public ushort X2;
public ushort Y1;
public ushort Y2;
public uint Padding;
#pragma warning restore CS0649
}
/// <summary>
/// Stencil test masks for back tests.
/// </summary>
struct StencilBackMasks
{
#pragma warning disable CS0649
public int FuncRef;
public int Mask;
public int FuncMask;
#pragma warning restore CS0649
}
/// <summary>
/// Render target depth-stencil buffer state.
/// </summary>
struct RtDepthStencilState
{
#pragma warning disable CS0649
public GpuVa Address;
public ZetaFormat Format;
public MemoryLayout MemoryLayout;
public int LayerSize;
#pragma warning restore CS0649
}
/// <summary>
/// Screen scissor state.
/// </summary>
struct ScreenScissorState
{
#pragma warning disable CS0649
public ushort X;
public ushort Width;
public ushort Y;
public ushort Height;
#pragma warning restore CS0649
}
/// <summary>
/// Vertex attribute vector and component size.
/// </summary>
enum VertexAttribSize
{
Size32x4 = 1,
Size32x3 = 2,
Size16x4 = 3,
Size32x2 = 4,
Size16x3 = 5,
Size8x4 = 0xa,
Size16x2 = 0xf,
Size32 = 0x12,
Size8x3 = 0x13,
Size8x2 = 0x18,
Size16 = 0x1b,
Size8 = 0x1d,
Rgb10A2 = 0x30,
Rg11B10 = 0x31
}
/// <summary>
/// Vertex attribute component type.
/// </summary>
enum VertexAttribType
{
Snorm = 1,
Unorm = 2,
Sint = 3,
Uint = 4,
Uscaled = 5,
Sscaled = 6,
Float = 7
}
/// <summary>
/// Vertex buffer attribute state.
/// </summary>
struct VertexAttribState
{
#pragma warning disable CS0649
public uint Attribute;
#pragma warning restore CS0649
/// <summary>
/// Unpacks the index of the vertex buffer this attribute belongs to.
/// </summary>
/// <returns>Vertex buffer index</returns>
public int UnpackBufferIndex()
{
return (int)(Attribute & 0x1f);
}
/// <summary>
/// Unpacks the attribute constant flag.
/// </summary>
/// <returns>True if the attribute is constant, false otherwise</returns>
public bool UnpackIsConstant()
{
return (Attribute & 0x40) != 0;
}
/// <summary>
/// Unpacks the offset, in bytes, of the attribute on the vertex buffer.
/// </summary>
/// <returns>Attribute offset in bytes</returns>
public int UnpackOffset()
{
return (int)((Attribute >> 7) & 0x3fff);
}
/// <summary>
/// Unpacks the Maxwell attribute format integer.
/// </summary>
/// <returns>Attribute format integer</returns>
public uint UnpackFormat()
{
return Attribute & 0x3fe00000;
}
Vulkan backend (#2518) * WIP Vulkan implementation * No need to initialize attributes on the SPIR-V backend anymore * Allow multithreading shaderc and vkCreateShaderModule You'll only really see the benefit here with threaded-gal or parallel shader cache compile. Fix shaderc multithreaded changes Thread safety for shaderc Options constructor Dunno how they managed to make a constructor not thread safe, but you do you. May avoid some freezes. * Support multiple levels/layers for blit. Fixes MK8D when scaled, maybe a few other games. AMD software "safe" blit not supported right now. * TextureStorage should hold a ref of the foreign storage, otherwise it might be freed while in use * New depth-stencil blit method for AMD * Workaround for AMD driver bug * Fix some tessellation related issues (still doesn't work?) * Submit command buffer before Texture GetData. (UE4 fix) * DrawTexture support * Fix BGRA on OpenGL backend * Fix rebase build break * Support format aliasing on SetImage * Fix uniform buffers being lost when bindings are out of order * Fix storage buffers being lost when bindings are out of order (also avoid allocations when changing bindings) * Use current command buffer for unscaled copy (perf) Avoids flushing commands and renting a command buffer when fulfilling copy dependencies and when games do unscaled copies. * Update to .net6 * Update Silk.NET to version 2.10.1 Somehow, massive performance boost. Seems like their vtable for looking up vulkan methods was really slow before. * Fix PrimitivesGenerated query, disable Transform Feedback queries for now Lets Splatoon 2 work on nvidia. (mostly) * Update counter queue to be similar to the OGL one Fixes softlocks when games had to flush counters. * Don't throw when ending conditional rendering for now This should be re-enabled when conditional rendering is enabled on nvidia etc. * Update findMSB/findLSB to match master's instruction enum * Fix triangle overlay on SMO, Captain Toad, maybe others? * Don't make Intel Mesa pay for Intel Windows bugs * Fix samplers with MinFilter Linear or Nearest (fixes New Super Mario Bros U Deluxe black borders) * Update Spv.Generator * Add alpha test emulation on shader (but no shader specialisation yet...) * Fix R4G4B4A4Unorm texture format permutation * Validation layers should be enabled for any log level other than None * Add barriers around vkCmdCopyImage Write->Read barrier for src image (we want to wait for a write to read it) Write->Read barrier for dst image (we want to wait for the copy to complete before use) * Be a bit more careful with texture access flags, since it can be used for anything * Device local mapping for all buffers May avoid issues with drivers with NVIDIA on linux/older gpus on windows when using large buffers (?) Also some performance things and fixes issues with opengl games loading textures weird. * Cleanup, disable device local buffers for now. * Add single queue support Multiqueue seems to be a bit more responsive on NVIDIA. Should fix texture flush on intel. AMD has been forced to single queue for an experiment. * Fix some validation errors around extended dynamic state * Remove Intel bug workaround, it was fixed on the latest driver * Use circular queue for checking consumption on command buffers Speeds up games that spam command buffers a little. Avoids checking multiple command buffers if multiple are active at once. * Use SupportBufferUpdater, add single layer flush * Fix counter queue leak when game decides to use host conditional rendering * Force device local storage for textures (fixes linux performance) * Port #3019 * Insert barriers around vkCmdBlitImage (may fix some amd flicker) * Fix transform feedback on Intel, gl_Position feedback and clears to inexistent depth buffers * Don't pause transform feedback for multi draw * Fix draw outside of render pass and missing capability * Workaround for wrong last attribute on AMD (affects FFVII, STRIKERS1945, probably more) * Better workaround for AMD vertex buffer size alignment issue * More instructions + fixes on SPIR-V backend * Allow custom aspect ratio on Vulkan * Correct GTK UI status bar positions * SPIR-V: Functions must always end with a return * SPIR-V: Fix ImageQuerySizeLod * SPIR-V: Set DepthReplacing execution mode when FragDepth is modified * SPIR-V: Implement LoopContinue IR instruction * SPIR-V: Geometry shader support * SPIR-V: Use correct binding number on storage buffers array * Reduce allocations for Spir-v serialization Passes BinaryWriter instead of the stream to Write and WriteOperand - Removes creation of BinaryWriter for each instruction - Removes allocations for literal string * Some optimizations to Spv.Generator - Dictionary for lookups of type declarations, constants, extinst - LiteralInteger internal data format -> ushort - Deterministic HashCode implementation to avoid spirv result not being the same between runs - Inline operand list instead of List<T>, falls back to array if many operands. (large performance boost) TODO: improve instruction allocation, structured program creator, ssa? * Pool Spv.Generator resources, cache delegates, spv opts - Pools for Instructions and LiteralIntegers. Can be passed in when creating the generator module. - NewInstruction is called instead of new Instruction() - Ryujinx SpirvGenerator passes in some pools that are static. The idea is for these to be shared between threads eventually. - Estimate code size when creating the output MemoryStream - LiteralInteger pools using ThreadStatic pools that are initialized before and after creation... not sure of a better way since the way these are created is via implicit cast. Also, cache delegates for Spv.Generator for functions that are passed around to GenerateBinary etc, since passing the function raw creates a delegate on each call. TODO: update python spv cs generator to make the coregrammar with NewInstruction and the `params` overloads. * LocalDefMap for Ssa Rewriter Rather than allocating a large array of all registers for each block in the shader, allocate one array of all registers and clear it between blocks. Reduces allocations in the shader translator. * SPIR-V: Transform feedback support * SPIR-V: Fragment shader interlock support (and image coherency) * SPIR-V: Add early fragment tests support * SPIR-V: Implement SwizzleAdd, add missing Triangles ExecutionMode for geometry shaders, remove SamplerType field from TextureMeta * Don't pass depth clip state right now (fix decals) Explicitly disabling it is incorrect. OpenGL currently automatically disables based on depth clamp, which is the behaviour if this state is omitted. * Multisampling support * Multisampling: Use resolve if src samples count > dst samples count * Multisampling: We can only resolve for unscaled copies * SPIR-V: Only add FSI exec mode if used. * SPIR-V: Use ConstantComposite for Texture Offset Vector Fixes a bunch of freezes with SPIR-V on AMD hardware, and validation errors. Note: Obviously assumes input offsets are constant, which they currently are. * SPIR-V: Don't OpReturn if we already OpExit'ed Fixes spir-v parse failure and stack smashing in RADV (obviously you still need bolist) * SPIR-V: Only use input attribute type for input attributes Output vertex attributes should always be of type float. * Multithreaded Pipeline Compilation * Address some feedback * Make this 32 * Update topology with GpuAccessorState * Cleanup for merge (note: disables spir-v) * Make more robust to shader compilation failure - Don't freeze when GLSL compilation fails - Background SPIR-V pipeline compile failure results in skipped draws, similar to GLSL compilation failure. * Fix Multisampling * Only update fragment scale count if a vertex texture needs a scale. Fixes a performance regression introduced by texture scaling in the vertex stage where support buffer updates would be very frequent, even at 1x, if any textures were used on the vertex stage. This check doesn't exactly look cheap (a flag in the shader stage would probably be preferred), but it is much cheaper than uploading scales in both vulkan and opengl, so it will do for now. * Use a bitmap to do granular tracking for buffer uploads. This path is only taken if the much faster check of "is the buffer rented at all" is triggered, so it doesn't actually end up costing too much, and the time saved by not ending render passes (and on gpu for not waiting on barriers) is probably helpful. Avoids ending render passes to update buffer data (not all the time) - 140-180 to 35-45 in SMO metro kingdom (these updates are in the UI) - Very variable 60-150(!) to 16-25 in mario kart 8 (these updates are in the UI) As well as allowing more data to be preloaded persistently, this will also allow more data to be loaded in the preload buffer, which should be faster as it doesn't need to insert barriers between draws. (and on tbdr, does not need to flush and reload tile memory) Improves performance in GPU limited scenarios. Should notably improve performance on TBDR gpus. Still a lot more to do here. * Copy query results after RP ends, rather than ending to copy We need to end the render pass to get the data (submit command buffer) anyways... Reduces render passes created in games that use queries. * Rework Query stuff a bit to avoid render pass end Tries to reset returned queries in background when possible, rather than ending the render pass. Still ends render pass when resetting a counter after draws, but maybe that can be solved too. (by just pulling an empty object off the pool?) * Remove unnecessary lines Was for testing * Fix validation error for query reset Need to think of a better way to do this. * SPIR-V: Fix SwizzleAdd and some validation errors * SPIR-V: Implement attribute indexing and StoreAttribute * SPIR-V: Fix TextureSize for MS and Buffer sampler types * Fix relaunch issues * SPIR-V: Implement LogicalExclusiveOr * SPIR-V: Constant buffer indexing support * Ignore unsupported attributes rather than throwing (matches current GLSL behaviour) * SPIR-V: Implement tessellation support * SPIR-V: Geometry shader passthrough support * SPIR-V: Implement StoreShader8/16 and StoreStorage8/16 * SPIR-V: Resolution scale support and fix TextureSample multisample with LOD bug * SPIR-V: Fix field index for scale count * SPIR-V: Fix another case of wrong field index * SPIRV/GLSL: More scaling related fixes * SPIR-V: Fix ImageLoad CompositeExtract component type * SPIR-V: Workaround for Intel FrontFacing bug * Enable SPIR-V backend by default * Allow null samplers (samplers are not required when only using texelFetch to access the texture) * Fix some validation errors related to texel block view usage flag and invalid image barrier base level * Use explicit subgroup size if we can (might fix some block flickering on AMD) * Take componentMask and scissor into account when clearing framebuffer attachments * Add missing barriers around CmdFillBuffer (fixes Monster Hunter Rise flickering on NVIDIA) * Use ClampToEdge for Clamp sampler address mode on Vulkan (fixes Hollow Knight) Clamp is unsupported on Vulkan, but ClampToEdge behaves almost the same. ClampToBorder on the other hand (which was being used before) is pretty different * Shader specialization for new Vulkan required state (fixes remaining alpha test issues, vertex stretching on AMD on Crash Bandicoot, etc) * Check if the subgroup size is supported before passing a explicit size * Only enable ShaderFloat64 if the GPU supports it * We don't need to recompile shaders if alpha test state changed but alpha test is disabled * Enable shader cache on Vulkan and implement MultiplyHighS32/U32 on SPIR-V (missed those before) * Fix pipeline state saving before it is updated. This should fix a few warnings and potential stutters due to bad pipeline states being saved in the cache. You may need to clear your guest cache. * Allow null samplers on OpenGL backend * _unit0Sampler should be set only for binding 0 * Remove unused PipelineConverter format variable (was causing IOR) * Raise textures limit to 64 on Vulkan * No need to pack the shader binaries if shader cache is disabled * Fix backbuffer not being cleared and scissor not being re-enabled on OpenGL * Do not clear unbound framebuffer color attachments * Geometry shader passthrough emulation * Consolidate UpdateDepthMode and GetDepthMode implementation * Fix A1B5G5R5 texture format and support R4G4 on Vulkan * Add barrier before use of some modified images * Report 32 bit query result on AMD windows (smo issue) * Add texture recompression support (disabled for now) It recompresses ASTC textures into BC7, which might reduce VRAM usage significantly on games that uses ASTC textures * Do not report R4G4 format as supported on Vulkan It was causing mario head to become white on Super Mario 64 (???) * Improvements to -1 to 1 depth mode. - Transformation is only applied on the last stage in the vertex pipeline. - Should fix some issues with geometry and tessellation (hopefully) - Reading back FragCoord Z on fragment will transform back to -1 to 1. * Geometry Shader index count from ThreadsPerInputPrimitive Generally fixes SPIR-V emitting too many triangles, may change games in OpenGL * Remove gl_FragDepth scaling This is always 0-1; the other two issues were causing the problems. Fixes regression with Xenoblade. * Add Gl StencilOp enum values to Vulkan * Update guest cache to v1.1 (due to specialization state changes) This will explode your shader cache from earlier vulkan build, but it must be done. :pensive: * Vulkan/SPIR-V support for viewport inverse * Fix typo * Don't create query pools for unsupported query types * Return of the Vector Indexing Bug One day, everyone will get this right. * Check for transform feedback query support Sometimes transform feedback is supported without the query type. * Fix gl_FragCoord.z transformation FragCoord.z is always in 0-1, even when the real depth range is -1 to 1. Turns out the only bug was geo and tess stage outputs. Fixes Pokemon Sword/Shield, possibly others. * Fix Avalonia Rebase Vulkan is currently not available on Avalonia, but the build does work and you can use opengl. * Fix headless build * Add support for BC6 and BC7 decompression, decompress all BC formats if they are not supported by the host * Fix BCn 4/5 conversion, GetTextureTarget BCn 4/5 could generate invalid data when a line's size in bytes was not divisible by 4, which both backends expect. GetTextureTarget was not creating a view with the replacement format. * Fix dependency * Fix inverse viewport transform vector type on SPIR-V * Do not require null descriptors support * If MultiViewport is not supported, do not try to set more than one viewport/scissor * Bounds check on bitmap add. * Flush queries on attachment change rather than program change Occlusion queries are usually used in a depth only pass so the attachments changing is a better indication of the query block ending. Write mask changes are also considered since some games do depth only pass by setting 0 write mask on all the colour targets. * Add support for avalonia (#6) * add avalonia support * only lock around skia flush * addressed review * cleanup * add fallback size if avalonia attempts to render but the window size is 0. read desktop scale after enabling dpi check * fix getting window handle on linux. skip render is size is 0 * Combine non-buffer with buffer image descriptor sets * Support multisample texture copy with automatic resolve on Vulkan * Remove old CompileShader methods from the Vulkan backend * Add minimal pipeline layouts that only contains used bindings They are used by helper shaders, the intention is avoiding needing to recompile the shaders (from GLSL to SPIR-V) if the bindings changes on the translated guest shaders * Pre-compile helper shader as SPIR-V, and some fixes * Remove pre-compiled shaderc binary for Windows as its no longer needed by default * Workaround RADV crash Enabling the descriptor indexing extension, even if it is not used, forces the radv driver to use "bolist". * Use RobustBufferAccess on NVIDIA gpus Avoids the SMO waterfall triangle on older NVIDIA gpus. * Implement GPU selector and expose texture recompression on the UI and config * Fix and enable background compute shader compilation Also disables warnings from shader cache pipeline misses. * Fix error due to missing subpass dependency when Attachment Write -> Shader Read barriers are added * If S8D24 is not supported, use D32FS8 * Ensure all fences are destroyed on dispose * Pre-allocate arrays up front on DescriptorSetUpdater, allows the removal of some checks * Add missing clear layer parameter after rebase * Use selected gpu from config for avalonia (#7) * use configured device * address review * Fix D32S8 copy workaround (AMD) Fixes water in Pokemon Legends Arceus on AMD GPUs. Possibly fixes other things. * Use push descriptors for uniform buffer updates (disabled for now) * Push descriptor support check, buffer redundancy checks Should make push descriptors faster, needs more testing though. * Increase light command buffer pool to 2 command buffers, throw rather than returning invalid cbs * Adjust bindings array sizes * Force submit command buffers if memory in use by its resources is high * Add workaround for AMD GCN cubemap view sins `ImageCreateCubeCompatibleBit` seems to generally break 2D array textures with mipmaps... even if they are eventually aliased as a cubemap with mipmaps. Forcing a copy here works around the issue. This could be used in future if enabling this bit reduces performance on certain GPUs. (mobile class is generally a worry) Currently also enabled on Linux as I don't know if they managed to dodge this bug (someone please tell me). Not enabled on Vega at the moment, but easy to add if the issue is there. * Add mobile, non-RX variants to the GCN regex. Also make sure that the 3 digit ones only include numbers starting with 7 or 8. * Increase image limit per stage from 8 to 16 Xenoblade Chronicles 2 was hiting the limit of 8 * Minor code cleanup * Fix NRE caused by SupportBufferUpdater calling pipeline ClearBuffer * Add gpu selector to Avalonia (#8) * Add gpu selector to avalonia settings * show backend label on window * some fixes * address review * Minor changes to the Avalonia UI * Update graphics window UI and locales. (#9) * Update xaml and update locales * locale updates Did my best here but likely needs to be checked by native speakers, especially the use of ampersands in greek, russian and turkish? * Fix locales with more (?) correct translations. * add separator to render widget * fix spanish and portuguese * Add new IdList, replaces buffer list that could not remove elements and had unbounded growth * Don't crash the settings window if Vulkan is not supported * Fix Actions menu not being clickable on GTK UI after relaunch * Rename VulkanGraphicsDevice to VulkanRenderer and Renderer to OpenGLRenderer * Fix IdList and make it not thread safe * Revert useless OpenGL format table changes * Fix headless project build * List throws ArgumentOutOfRangeException * SPIR-V: Fix tessellation * Increase shader cache version due to tessellation fix * Reduce number of Sync objects created (improves perf in some specific titles) * Fix vulkan validation errors for NPOT compressed upload and GCN workaround. * Add timestamp to the shader cache and force rebuild if host cache is outdated * Prefer Mail box present mode for popups (#11) * Prefer Mail box present mode * fix debug * switch present mode when vsync is toggled * only disable vsync on the main window * SPIR-V: Fix geometry shader input load with transform feedback * BC7 Encoder: Prefer more precision on alpha rather than RGB when alpha is 0 * Fix Avalonia build * Address initial PR feedback * Only set transform feedback outputs on last vertex stage * Address riperiperi PR feedback * Remove outdated comment * Remove unused constructor * Only throw for negative results * Throw for QueueSubmit and other errors No point in delaying the inevitable * Transform feedback decorations inside gl_PerVertex struct breaks the NVIDIA compiler * Fix some resolution scale issues * No need for two UpdateScale calls * Fix comments on SPIR-V generator project * Try to fix shader local memory size On DOOM, a shader is using local memory, but both Low and High size are 0, CRS size is 1536, it seems to store on that region? * Remove RectangleF that is now unused * Fix ImageGather with multiple offsets Needs ImageGatherExtended capability, and must use `ConstantComposite` instead of `CompositeConstruct` * Address PR feedback from jD in all projects except Avalonia * Address most of jD PR feedback on Avalonia * Remove unsafe * Fix VulkanSkiaGpu * move present mode request out of Create Swapchain method * split more parts of create swapchain * addressed reviews * addressed review * Address second batch of jD PR feedback * Fix buffer <-> image copy row length and height alignment AlignUp helper does not support NPOT alignment, and ASTC textures can have NPOT block sizes * Better fix for NPOT alignment issue * Use switch expressions on Vulkan EnumConversion Thanks jD * Fix Avalonia build * Add Vulkan selection prompt on startup * Grammar fixes on Vulkan prompt message * Add missing Vulkan migration flag Co-authored-by: riperiperi <rhy3756547@hotmail.com> Co-authored-by: Emmanuel Hansen <emmausssss@gmail.com> Co-authored-by: MutantAura <44103205+MutantAura@users.noreply.github.com>
2022-07-31 21:26:06 +00:00
/// <summary>
/// Unpacks the Maxwell attribute size.
/// </summary>
/// <returns>Attribute size</returns>
public VertexAttribSize UnpackSize()
{
return (VertexAttribSize)((Attribute >> 21) & 0x3f);
}
/// <summary>
Vulkan backend (#2518) * WIP Vulkan implementation * No need to initialize attributes on the SPIR-V backend anymore * Allow multithreading shaderc and vkCreateShaderModule You'll only really see the benefit here with threaded-gal or parallel shader cache compile. Fix shaderc multithreaded changes Thread safety for shaderc Options constructor Dunno how they managed to make a constructor not thread safe, but you do you. May avoid some freezes. * Support multiple levels/layers for blit. Fixes MK8D when scaled, maybe a few other games. AMD software "safe" blit not supported right now. * TextureStorage should hold a ref of the foreign storage, otherwise it might be freed while in use * New depth-stencil blit method for AMD * Workaround for AMD driver bug * Fix some tessellation related issues (still doesn't work?) * Submit command buffer before Texture GetData. (UE4 fix) * DrawTexture support * Fix BGRA on OpenGL backend * Fix rebase build break * Support format aliasing on SetImage * Fix uniform buffers being lost when bindings are out of order * Fix storage buffers being lost when bindings are out of order (also avoid allocations when changing bindings) * Use current command buffer for unscaled copy (perf) Avoids flushing commands and renting a command buffer when fulfilling copy dependencies and when games do unscaled copies. * Update to .net6 * Update Silk.NET to version 2.10.1 Somehow, massive performance boost. Seems like their vtable for looking up vulkan methods was really slow before. * Fix PrimitivesGenerated query, disable Transform Feedback queries for now Lets Splatoon 2 work on nvidia. (mostly) * Update counter queue to be similar to the OGL one Fixes softlocks when games had to flush counters. * Don't throw when ending conditional rendering for now This should be re-enabled when conditional rendering is enabled on nvidia etc. * Update findMSB/findLSB to match master's instruction enum * Fix triangle overlay on SMO, Captain Toad, maybe others? * Don't make Intel Mesa pay for Intel Windows bugs * Fix samplers with MinFilter Linear or Nearest (fixes New Super Mario Bros U Deluxe black borders) * Update Spv.Generator * Add alpha test emulation on shader (but no shader specialisation yet...) * Fix R4G4B4A4Unorm texture format permutation * Validation layers should be enabled for any log level other than None * Add barriers around vkCmdCopyImage Write->Read barrier for src image (we want to wait for a write to read it) Write->Read barrier for dst image (we want to wait for the copy to complete before use) * Be a bit more careful with texture access flags, since it can be used for anything * Device local mapping for all buffers May avoid issues with drivers with NVIDIA on linux/older gpus on windows when using large buffers (?) Also some performance things and fixes issues with opengl games loading textures weird. * Cleanup, disable device local buffers for now. * Add single queue support Multiqueue seems to be a bit more responsive on NVIDIA. Should fix texture flush on intel. AMD has been forced to single queue for an experiment. * Fix some validation errors around extended dynamic state * Remove Intel bug workaround, it was fixed on the latest driver * Use circular queue for checking consumption on command buffers Speeds up games that spam command buffers a little. Avoids checking multiple command buffers if multiple are active at once. * Use SupportBufferUpdater, add single layer flush * Fix counter queue leak when game decides to use host conditional rendering * Force device local storage for textures (fixes linux performance) * Port #3019 * Insert barriers around vkCmdBlitImage (may fix some amd flicker) * Fix transform feedback on Intel, gl_Position feedback and clears to inexistent depth buffers * Don't pause transform feedback for multi draw * Fix draw outside of render pass and missing capability * Workaround for wrong last attribute on AMD (affects FFVII, STRIKERS1945, probably more) * Better workaround for AMD vertex buffer size alignment issue * More instructions + fixes on SPIR-V backend * Allow custom aspect ratio on Vulkan * Correct GTK UI status bar positions * SPIR-V: Functions must always end with a return * SPIR-V: Fix ImageQuerySizeLod * SPIR-V: Set DepthReplacing execution mode when FragDepth is modified * SPIR-V: Implement LoopContinue IR instruction * SPIR-V: Geometry shader support * SPIR-V: Use correct binding number on storage buffers array * Reduce allocations for Spir-v serialization Passes BinaryWriter instead of the stream to Write and WriteOperand - Removes creation of BinaryWriter for each instruction - Removes allocations for literal string * Some optimizations to Spv.Generator - Dictionary for lookups of type declarations, constants, extinst - LiteralInteger internal data format -> ushort - Deterministic HashCode implementation to avoid spirv result not being the same between runs - Inline operand list instead of List<T>, falls back to array if many operands. (large performance boost) TODO: improve instruction allocation, structured program creator, ssa? * Pool Spv.Generator resources, cache delegates, spv opts - Pools for Instructions and LiteralIntegers. Can be passed in when creating the generator module. - NewInstruction is called instead of new Instruction() - Ryujinx SpirvGenerator passes in some pools that are static. The idea is for these to be shared between threads eventually. - Estimate code size when creating the output MemoryStream - LiteralInteger pools using ThreadStatic pools that are initialized before and after creation... not sure of a better way since the way these are created is via implicit cast. Also, cache delegates for Spv.Generator for functions that are passed around to GenerateBinary etc, since passing the function raw creates a delegate on each call. TODO: update python spv cs generator to make the coregrammar with NewInstruction and the `params` overloads. * LocalDefMap for Ssa Rewriter Rather than allocating a large array of all registers for each block in the shader, allocate one array of all registers and clear it between blocks. Reduces allocations in the shader translator. * SPIR-V: Transform feedback support * SPIR-V: Fragment shader interlock support (and image coherency) * SPIR-V: Add early fragment tests support * SPIR-V: Implement SwizzleAdd, add missing Triangles ExecutionMode for geometry shaders, remove SamplerType field from TextureMeta * Don't pass depth clip state right now (fix decals) Explicitly disabling it is incorrect. OpenGL currently automatically disables based on depth clamp, which is the behaviour if this state is omitted. * Multisampling support * Multisampling: Use resolve if src samples count > dst samples count * Multisampling: We can only resolve for unscaled copies * SPIR-V: Only add FSI exec mode if used. * SPIR-V: Use ConstantComposite for Texture Offset Vector Fixes a bunch of freezes with SPIR-V on AMD hardware, and validation errors. Note: Obviously assumes input offsets are constant, which they currently are. * SPIR-V: Don't OpReturn if we already OpExit'ed Fixes spir-v parse failure and stack smashing in RADV (obviously you still need bolist) * SPIR-V: Only use input attribute type for input attributes Output vertex attributes should always be of type float. * Multithreaded Pipeline Compilation * Address some feedback * Make this 32 * Update topology with GpuAccessorState * Cleanup for merge (note: disables spir-v) * Make more robust to shader compilation failure - Don't freeze when GLSL compilation fails - Background SPIR-V pipeline compile failure results in skipped draws, similar to GLSL compilation failure. * Fix Multisampling * Only update fragment scale count if a vertex texture needs a scale. Fixes a performance regression introduced by texture scaling in the vertex stage where support buffer updates would be very frequent, even at 1x, if any textures were used on the vertex stage. This check doesn't exactly look cheap (a flag in the shader stage would probably be preferred), but it is much cheaper than uploading scales in both vulkan and opengl, so it will do for now. * Use a bitmap to do granular tracking for buffer uploads. This path is only taken if the much faster check of "is the buffer rented at all" is triggered, so it doesn't actually end up costing too much, and the time saved by not ending render passes (and on gpu for not waiting on barriers) is probably helpful. Avoids ending render passes to update buffer data (not all the time) - 140-180 to 35-45 in SMO metro kingdom (these updates are in the UI) - Very variable 60-150(!) to 16-25 in mario kart 8 (these updates are in the UI) As well as allowing more data to be preloaded persistently, this will also allow more data to be loaded in the preload buffer, which should be faster as it doesn't need to insert barriers between draws. (and on tbdr, does not need to flush and reload tile memory) Improves performance in GPU limited scenarios. Should notably improve performance on TBDR gpus. Still a lot more to do here. * Copy query results after RP ends, rather than ending to copy We need to end the render pass to get the data (submit command buffer) anyways... Reduces render passes created in games that use queries. * Rework Query stuff a bit to avoid render pass end Tries to reset returned queries in background when possible, rather than ending the render pass. Still ends render pass when resetting a counter after draws, but maybe that can be solved too. (by just pulling an empty object off the pool?) * Remove unnecessary lines Was for testing * Fix validation error for query reset Need to think of a better way to do this. * SPIR-V: Fix SwizzleAdd and some validation errors * SPIR-V: Implement attribute indexing and StoreAttribute * SPIR-V: Fix TextureSize for MS and Buffer sampler types * Fix relaunch issues * SPIR-V: Implement LogicalExclusiveOr * SPIR-V: Constant buffer indexing support * Ignore unsupported attributes rather than throwing (matches current GLSL behaviour) * SPIR-V: Implement tessellation support * SPIR-V: Geometry shader passthrough support * SPIR-V: Implement StoreShader8/16 and StoreStorage8/16 * SPIR-V: Resolution scale support and fix TextureSample multisample with LOD bug * SPIR-V: Fix field index for scale count * SPIR-V: Fix another case of wrong field index * SPIRV/GLSL: More scaling related fixes * SPIR-V: Fix ImageLoad CompositeExtract component type * SPIR-V: Workaround for Intel FrontFacing bug * Enable SPIR-V backend by default * Allow null samplers (samplers are not required when only using texelFetch to access the texture) * Fix some validation errors related to texel block view usage flag and invalid image barrier base level * Use explicit subgroup size if we can (might fix some block flickering on AMD) * Take componentMask and scissor into account when clearing framebuffer attachments * Add missing barriers around CmdFillBuffer (fixes Monster Hunter Rise flickering on NVIDIA) * Use ClampToEdge for Clamp sampler address mode on Vulkan (fixes Hollow Knight) Clamp is unsupported on Vulkan, but ClampToEdge behaves almost the same. ClampToBorder on the other hand (which was being used before) is pretty different * Shader specialization for new Vulkan required state (fixes remaining alpha test issues, vertex stretching on AMD on Crash Bandicoot, etc) * Check if the subgroup size is supported before passing a explicit size * Only enable ShaderFloat64 if the GPU supports it * We don't need to recompile shaders if alpha test state changed but alpha test is disabled * Enable shader cache on Vulkan and implement MultiplyHighS32/U32 on SPIR-V (missed those before) * Fix pipeline state saving before it is updated. This should fix a few warnings and potential stutters due to bad pipeline states being saved in the cache. You may need to clear your guest cache. * Allow null samplers on OpenGL backend * _unit0Sampler should be set only for binding 0 * Remove unused PipelineConverter format variable (was causing IOR) * Raise textures limit to 64 on Vulkan * No need to pack the shader binaries if shader cache is disabled * Fix backbuffer not being cleared and scissor not being re-enabled on OpenGL * Do not clear unbound framebuffer color attachments * Geometry shader passthrough emulation * Consolidate UpdateDepthMode and GetDepthMode implementation * Fix A1B5G5R5 texture format and support R4G4 on Vulkan * Add barrier before use of some modified images * Report 32 bit query result on AMD windows (smo issue) * Add texture recompression support (disabled for now) It recompresses ASTC textures into BC7, which might reduce VRAM usage significantly on games that uses ASTC textures * Do not report R4G4 format as supported on Vulkan It was causing mario head to become white on Super Mario 64 (???) * Improvements to -1 to 1 depth mode. - Transformation is only applied on the last stage in the vertex pipeline. - Should fix some issues with geometry and tessellation (hopefully) - Reading back FragCoord Z on fragment will transform back to -1 to 1. * Geometry Shader index count from ThreadsPerInputPrimitive Generally fixes SPIR-V emitting too many triangles, may change games in OpenGL * Remove gl_FragDepth scaling This is always 0-1; the other two issues were causing the problems. Fixes regression with Xenoblade. * Add Gl StencilOp enum values to Vulkan * Update guest cache to v1.1 (due to specialization state changes) This will explode your shader cache from earlier vulkan build, but it must be done. :pensive: * Vulkan/SPIR-V support for viewport inverse * Fix typo * Don't create query pools for unsupported query types * Return of the Vector Indexing Bug One day, everyone will get this right. * Check for transform feedback query support Sometimes transform feedback is supported without the query type. * Fix gl_FragCoord.z transformation FragCoord.z is always in 0-1, even when the real depth range is -1 to 1. Turns out the only bug was geo and tess stage outputs. Fixes Pokemon Sword/Shield, possibly others. * Fix Avalonia Rebase Vulkan is currently not available on Avalonia, but the build does work and you can use opengl. * Fix headless build * Add support for BC6 and BC7 decompression, decompress all BC formats if they are not supported by the host * Fix BCn 4/5 conversion, GetTextureTarget BCn 4/5 could generate invalid data when a line's size in bytes was not divisible by 4, which both backends expect. GetTextureTarget was not creating a view with the replacement format. * Fix dependency * Fix inverse viewport transform vector type on SPIR-V * Do not require null descriptors support * If MultiViewport is not supported, do not try to set more than one viewport/scissor * Bounds check on bitmap add. * Flush queries on attachment change rather than program change Occlusion queries are usually used in a depth only pass so the attachments changing is a better indication of the query block ending. Write mask changes are also considered since some games do depth only pass by setting 0 write mask on all the colour targets. * Add support for avalonia (#6) * add avalonia support * only lock around skia flush * addressed review * cleanup * add fallback size if avalonia attempts to render but the window size is 0. read desktop scale after enabling dpi check * fix getting window handle on linux. skip render is size is 0 * Combine non-buffer with buffer image descriptor sets * Support multisample texture copy with automatic resolve on Vulkan * Remove old CompileShader methods from the Vulkan backend * Add minimal pipeline layouts that only contains used bindings They are used by helper shaders, the intention is avoiding needing to recompile the shaders (from GLSL to SPIR-V) if the bindings changes on the translated guest shaders * Pre-compile helper shader as SPIR-V, and some fixes * Remove pre-compiled shaderc binary for Windows as its no longer needed by default * Workaround RADV crash Enabling the descriptor indexing extension, even if it is not used, forces the radv driver to use "bolist". * Use RobustBufferAccess on NVIDIA gpus Avoids the SMO waterfall triangle on older NVIDIA gpus. * Implement GPU selector and expose texture recompression on the UI and config * Fix and enable background compute shader compilation Also disables warnings from shader cache pipeline misses. * Fix error due to missing subpass dependency when Attachment Write -> Shader Read barriers are added * If S8D24 is not supported, use D32FS8 * Ensure all fences are destroyed on dispose * Pre-allocate arrays up front on DescriptorSetUpdater, allows the removal of some checks * Add missing clear layer parameter after rebase * Use selected gpu from config for avalonia (#7) * use configured device * address review * Fix D32S8 copy workaround (AMD) Fixes water in Pokemon Legends Arceus on AMD GPUs. Possibly fixes other things. * Use push descriptors for uniform buffer updates (disabled for now) * Push descriptor support check, buffer redundancy checks Should make push descriptors faster, needs more testing though. * Increase light command buffer pool to 2 command buffers, throw rather than returning invalid cbs * Adjust bindings array sizes * Force submit command buffers if memory in use by its resources is high * Add workaround for AMD GCN cubemap view sins `ImageCreateCubeCompatibleBit` seems to generally break 2D array textures with mipmaps... even if they are eventually aliased as a cubemap with mipmaps. Forcing a copy here works around the issue. This could be used in future if enabling this bit reduces performance on certain GPUs. (mobile class is generally a worry) Currently also enabled on Linux as I don't know if they managed to dodge this bug (someone please tell me). Not enabled on Vega at the moment, but easy to add if the issue is there. * Add mobile, non-RX variants to the GCN regex. Also make sure that the 3 digit ones only include numbers starting with 7 or 8. * Increase image limit per stage from 8 to 16 Xenoblade Chronicles 2 was hiting the limit of 8 * Minor code cleanup * Fix NRE caused by SupportBufferUpdater calling pipeline ClearBuffer * Add gpu selector to Avalonia (#8) * Add gpu selector to avalonia settings * show backend label on window * some fixes * address review * Minor changes to the Avalonia UI * Update graphics window UI and locales. (#9) * Update xaml and update locales * locale updates Did my best here but likely needs to be checked by native speakers, especially the use of ampersands in greek, russian and turkish? * Fix locales with more (?) correct translations. * add separator to render widget * fix spanish and portuguese * Add new IdList, replaces buffer list that could not remove elements and had unbounded growth * Don't crash the settings window if Vulkan is not supported * Fix Actions menu not being clickable on GTK UI after relaunch * Rename VulkanGraphicsDevice to VulkanRenderer and Renderer to OpenGLRenderer * Fix IdList and make it not thread safe * Revert useless OpenGL format table changes * Fix headless project build * List throws ArgumentOutOfRangeException * SPIR-V: Fix tessellation * Increase shader cache version due to tessellation fix * Reduce number of Sync objects created (improves perf in some specific titles) * Fix vulkan validation errors for NPOT compressed upload and GCN workaround. * Add timestamp to the shader cache and force rebuild if host cache is outdated * Prefer Mail box present mode for popups (#11) * Prefer Mail box present mode * fix debug * switch present mode when vsync is toggled * only disable vsync on the main window * SPIR-V: Fix geometry shader input load with transform feedback * BC7 Encoder: Prefer more precision on alpha rather than RGB when alpha is 0 * Fix Avalonia build * Address initial PR feedback * Only set transform feedback outputs on last vertex stage * Address riperiperi PR feedback * Remove outdated comment * Remove unused constructor * Only throw for negative results * Throw for QueueSubmit and other errors No point in delaying the inevitable * Transform feedback decorations inside gl_PerVertex struct breaks the NVIDIA compiler * Fix some resolution scale issues * No need for two UpdateScale calls * Fix comments on SPIR-V generator project * Try to fix shader local memory size On DOOM, a shader is using local memory, but both Low and High size are 0, CRS size is 1536, it seems to store on that region? * Remove RectangleF that is now unused * Fix ImageGather with multiple offsets Needs ImageGatherExtended capability, and must use `ConstantComposite` instead of `CompositeConstruct` * Address PR feedback from jD in all projects except Avalonia * Address most of jD PR feedback on Avalonia * Remove unsafe * Fix VulkanSkiaGpu * move present mode request out of Create Swapchain method * split more parts of create swapchain * addressed reviews * addressed review * Address second batch of jD PR feedback * Fix buffer <-> image copy row length and height alignment AlignUp helper does not support NPOT alignment, and ASTC textures can have NPOT block sizes * Better fix for NPOT alignment issue * Use switch expressions on Vulkan EnumConversion Thanks jD * Fix Avalonia build * Add Vulkan selection prompt on startup * Grammar fixes on Vulkan prompt message * Add missing Vulkan migration flag Co-authored-by: riperiperi <rhy3756547@hotmail.com> Co-authored-by: Emmanuel Hansen <emmausssss@gmail.com> Co-authored-by: MutantAura <44103205+MutantAura@users.noreply.github.com>
2022-07-31 21:26:06 +00:00
/// Unpacks the Maxwell attribute component type.
/// </summary>
/// <returns>Attribute component type</returns>
public VertexAttribType UnpackType()
Vulkan backend (#2518) * WIP Vulkan implementation * No need to initialize attributes on the SPIR-V backend anymore * Allow multithreading shaderc and vkCreateShaderModule You'll only really see the benefit here with threaded-gal or parallel shader cache compile. Fix shaderc multithreaded changes Thread safety for shaderc Options constructor Dunno how they managed to make a constructor not thread safe, but you do you. May avoid some freezes. * Support multiple levels/layers for blit. Fixes MK8D when scaled, maybe a few other games. AMD software "safe" blit not supported right now. * TextureStorage should hold a ref of the foreign storage, otherwise it might be freed while in use * New depth-stencil blit method for AMD * Workaround for AMD driver bug * Fix some tessellation related issues (still doesn't work?) * Submit command buffer before Texture GetData. (UE4 fix) * DrawTexture support * Fix BGRA on OpenGL backend * Fix rebase build break * Support format aliasing on SetImage * Fix uniform buffers being lost when bindings are out of order * Fix storage buffers being lost when bindings are out of order (also avoid allocations when changing bindings) * Use current command buffer for unscaled copy (perf) Avoids flushing commands and renting a command buffer when fulfilling copy dependencies and when games do unscaled copies. * Update to .net6 * Update Silk.NET to version 2.10.1 Somehow, massive performance boost. Seems like their vtable for looking up vulkan methods was really slow before. * Fix PrimitivesGenerated query, disable Transform Feedback queries for now Lets Splatoon 2 work on nvidia. (mostly) * Update counter queue to be similar to the OGL one Fixes softlocks when games had to flush counters. * Don't throw when ending conditional rendering for now This should be re-enabled when conditional rendering is enabled on nvidia etc. * Update findMSB/findLSB to match master's instruction enum * Fix triangle overlay on SMO, Captain Toad, maybe others? * Don't make Intel Mesa pay for Intel Windows bugs * Fix samplers with MinFilter Linear or Nearest (fixes New Super Mario Bros U Deluxe black borders) * Update Spv.Generator * Add alpha test emulation on shader (but no shader specialisation yet...) * Fix R4G4B4A4Unorm texture format permutation * Validation layers should be enabled for any log level other than None * Add barriers around vkCmdCopyImage Write->Read barrier for src image (we want to wait for a write to read it) Write->Read barrier for dst image (we want to wait for the copy to complete before use) * Be a bit more careful with texture access flags, since it can be used for anything * Device local mapping for all buffers May avoid issues with drivers with NVIDIA on linux/older gpus on windows when using large buffers (?) Also some performance things and fixes issues with opengl games loading textures weird. * Cleanup, disable device local buffers for now. * Add single queue support Multiqueue seems to be a bit more responsive on NVIDIA. Should fix texture flush on intel. AMD has been forced to single queue for an experiment. * Fix some validation errors around extended dynamic state * Remove Intel bug workaround, it was fixed on the latest driver * Use circular queue for checking consumption on command buffers Speeds up games that spam command buffers a little. Avoids checking multiple command buffers if multiple are active at once. * Use SupportBufferUpdater, add single layer flush * Fix counter queue leak when game decides to use host conditional rendering * Force device local storage for textures (fixes linux performance) * Port #3019 * Insert barriers around vkCmdBlitImage (may fix some amd flicker) * Fix transform feedback on Intel, gl_Position feedback and clears to inexistent depth buffers * Don't pause transform feedback for multi draw * Fix draw outside of render pass and missing capability * Workaround for wrong last attribute on AMD (affects FFVII, STRIKERS1945, probably more) * Better workaround for AMD vertex buffer size alignment issue * More instructions + fixes on SPIR-V backend * Allow custom aspect ratio on Vulkan * Correct GTK UI status bar positions * SPIR-V: Functions must always end with a return * SPIR-V: Fix ImageQuerySizeLod * SPIR-V: Set DepthReplacing execution mode when FragDepth is modified * SPIR-V: Implement LoopContinue IR instruction * SPIR-V: Geometry shader support * SPIR-V: Use correct binding number on storage buffers array * Reduce allocations for Spir-v serialization Passes BinaryWriter instead of the stream to Write and WriteOperand - Removes creation of BinaryWriter for each instruction - Removes allocations for literal string * Some optimizations to Spv.Generator - Dictionary for lookups of type declarations, constants, extinst - LiteralInteger internal data format -> ushort - Deterministic HashCode implementation to avoid spirv result not being the same between runs - Inline operand list instead of List<T>, falls back to array if many operands. (large performance boost) TODO: improve instruction allocation, structured program creator, ssa? * Pool Spv.Generator resources, cache delegates, spv opts - Pools for Instructions and LiteralIntegers. Can be passed in when creating the generator module. - NewInstruction is called instead of new Instruction() - Ryujinx SpirvGenerator passes in some pools that are static. The idea is for these to be shared between threads eventually. - Estimate code size when creating the output MemoryStream - LiteralInteger pools using ThreadStatic pools that are initialized before and after creation... not sure of a better way since the way these are created is via implicit cast. Also, cache delegates for Spv.Generator for functions that are passed around to GenerateBinary etc, since passing the function raw creates a delegate on each call. TODO: update python spv cs generator to make the coregrammar with NewInstruction and the `params` overloads. * LocalDefMap for Ssa Rewriter Rather than allocating a large array of all registers for each block in the shader, allocate one array of all registers and clear it between blocks. Reduces allocations in the shader translator. * SPIR-V: Transform feedback support * SPIR-V: Fragment shader interlock support (and image coherency) * SPIR-V: Add early fragment tests support * SPIR-V: Implement SwizzleAdd, add missing Triangles ExecutionMode for geometry shaders, remove SamplerType field from TextureMeta * Don't pass depth clip state right now (fix decals) Explicitly disabling it is incorrect. OpenGL currently automatically disables based on depth clamp, which is the behaviour if this state is omitted. * Multisampling support * Multisampling: Use resolve if src samples count > dst samples count * Multisampling: We can only resolve for unscaled copies * SPIR-V: Only add FSI exec mode if used. * SPIR-V: Use ConstantComposite for Texture Offset Vector Fixes a bunch of freezes with SPIR-V on AMD hardware, and validation errors. Note: Obviously assumes input offsets are constant, which they currently are. * SPIR-V: Don't OpReturn if we already OpExit'ed Fixes spir-v parse failure and stack smashing in RADV (obviously you still need bolist) * SPIR-V: Only use input attribute type for input attributes Output vertex attributes should always be of type float. * Multithreaded Pipeline Compilation * Address some feedback * Make this 32 * Update topology with GpuAccessorState * Cleanup for merge (note: disables spir-v) * Make more robust to shader compilation failure - Don't freeze when GLSL compilation fails - Background SPIR-V pipeline compile failure results in skipped draws, similar to GLSL compilation failure. * Fix Multisampling * Only update fragment scale count if a vertex texture needs a scale. Fixes a performance regression introduced by texture scaling in the vertex stage where support buffer updates would be very frequent, even at 1x, if any textures were used on the vertex stage. This check doesn't exactly look cheap (a flag in the shader stage would probably be preferred), but it is much cheaper than uploading scales in both vulkan and opengl, so it will do for now. * Use a bitmap to do granular tracking for buffer uploads. This path is only taken if the much faster check of "is the buffer rented at all" is triggered, so it doesn't actually end up costing too much, and the time saved by not ending render passes (and on gpu for not waiting on barriers) is probably helpful. Avoids ending render passes to update buffer data (not all the time) - 140-180 to 35-45 in SMO metro kingdom (these updates are in the UI) - Very variable 60-150(!) to 16-25 in mario kart 8 (these updates are in the UI) As well as allowing more data to be preloaded persistently, this will also allow more data to be loaded in the preload buffer, which should be faster as it doesn't need to insert barriers between draws. (and on tbdr, does not need to flush and reload tile memory) Improves performance in GPU limited scenarios. Should notably improve performance on TBDR gpus. Still a lot more to do here. * Copy query results after RP ends, rather than ending to copy We need to end the render pass to get the data (submit command buffer) anyways... Reduces render passes created in games that use queries. * Rework Query stuff a bit to avoid render pass end Tries to reset returned queries in background when possible, rather than ending the render pass. Still ends render pass when resetting a counter after draws, but maybe that can be solved too. (by just pulling an empty object off the pool?) * Remove unnecessary lines Was for testing * Fix validation error for query reset Need to think of a better way to do this. * SPIR-V: Fix SwizzleAdd and some validation errors * SPIR-V: Implement attribute indexing and StoreAttribute * SPIR-V: Fix TextureSize for MS and Buffer sampler types * Fix relaunch issues * SPIR-V: Implement LogicalExclusiveOr * SPIR-V: Constant buffer indexing support * Ignore unsupported attributes rather than throwing (matches current GLSL behaviour) * SPIR-V: Implement tessellation support * SPIR-V: Geometry shader passthrough support * SPIR-V: Implement StoreShader8/16 and StoreStorage8/16 * SPIR-V: Resolution scale support and fix TextureSample multisample with LOD bug * SPIR-V: Fix field index for scale count * SPIR-V: Fix another case of wrong field index * SPIRV/GLSL: More scaling related fixes * SPIR-V: Fix ImageLoad CompositeExtract component type * SPIR-V: Workaround for Intel FrontFacing bug * Enable SPIR-V backend by default * Allow null samplers (samplers are not required when only using texelFetch to access the texture) * Fix some validation errors related to texel block view usage flag and invalid image barrier base level * Use explicit subgroup size if we can (might fix some block flickering on AMD) * Take componentMask and scissor into account when clearing framebuffer attachments * Add missing barriers around CmdFillBuffer (fixes Monster Hunter Rise flickering on NVIDIA) * Use ClampToEdge for Clamp sampler address mode on Vulkan (fixes Hollow Knight) Clamp is unsupported on Vulkan, but ClampToEdge behaves almost the same. ClampToBorder on the other hand (which was being used before) is pretty different * Shader specialization for new Vulkan required state (fixes remaining alpha test issues, vertex stretching on AMD on Crash Bandicoot, etc) * Check if the subgroup size is supported before passing a explicit size * Only enable ShaderFloat64 if the GPU supports it * We don't need to recompile shaders if alpha test state changed but alpha test is disabled * Enable shader cache on Vulkan and implement MultiplyHighS32/U32 on SPIR-V (missed those before) * Fix pipeline state saving before it is updated. This should fix a few warnings and potential stutters due to bad pipeline states being saved in the cache. You may need to clear your guest cache. * Allow null samplers on OpenGL backend * _unit0Sampler should be set only for binding 0 * Remove unused PipelineConverter format variable (was causing IOR) * Raise textures limit to 64 on Vulkan * No need to pack the shader binaries if shader cache is disabled * Fix backbuffer not being cleared and scissor not being re-enabled on OpenGL * Do not clear unbound framebuffer color attachments * Geometry shader passthrough emulation * Consolidate UpdateDepthMode and GetDepthMode implementation * Fix A1B5G5R5 texture format and support R4G4 on Vulkan * Add barrier before use of some modified images * Report 32 bit query result on AMD windows (smo issue) * Add texture recompression support (disabled for now) It recompresses ASTC textures into BC7, which might reduce VRAM usage significantly on games that uses ASTC textures * Do not report R4G4 format as supported on Vulkan It was causing mario head to become white on Super Mario 64 (???) * Improvements to -1 to 1 depth mode. - Transformation is only applied on the last stage in the vertex pipeline. - Should fix some issues with geometry and tessellation (hopefully) - Reading back FragCoord Z on fragment will transform back to -1 to 1. * Geometry Shader index count from ThreadsPerInputPrimitive Generally fixes SPIR-V emitting too many triangles, may change games in OpenGL * Remove gl_FragDepth scaling This is always 0-1; the other two issues were causing the problems. Fixes regression with Xenoblade. * Add Gl StencilOp enum values to Vulkan * Update guest cache to v1.1 (due to specialization state changes) This will explode your shader cache from earlier vulkan build, but it must be done. :pensive: * Vulkan/SPIR-V support for viewport inverse * Fix typo * Don't create query pools for unsupported query types * Return of the Vector Indexing Bug One day, everyone will get this right. * Check for transform feedback query support Sometimes transform feedback is supported without the query type. * Fix gl_FragCoord.z transformation FragCoord.z is always in 0-1, even when the real depth range is -1 to 1. Turns out the only bug was geo and tess stage outputs. Fixes Pokemon Sword/Shield, possibly others. * Fix Avalonia Rebase Vulkan is currently not available on Avalonia, but the build does work and you can use opengl. * Fix headless build * Add support for BC6 and BC7 decompression, decompress all BC formats if they are not supported by the host * Fix BCn 4/5 conversion, GetTextureTarget BCn 4/5 could generate invalid data when a line's size in bytes was not divisible by 4, which both backends expect. GetTextureTarget was not creating a view with the replacement format. * Fix dependency * Fix inverse viewport transform vector type on SPIR-V * Do not require null descriptors support * If MultiViewport is not supported, do not try to set more than one viewport/scissor * Bounds check on bitmap add. * Flush queries on attachment change rather than program change Occlusion queries are usually used in a depth only pass so the attachments changing is a better indication of the query block ending. Write mask changes are also considered since some games do depth only pass by setting 0 write mask on all the colour targets. * Add support for avalonia (#6) * add avalonia support * only lock around skia flush * addressed review * cleanup * add fallback size if avalonia attempts to render but the window size is 0. read desktop scale after enabling dpi check * fix getting window handle on linux. skip render is size is 0 * Combine non-buffer with buffer image descriptor sets * Support multisample texture copy with automatic resolve on Vulkan * Remove old CompileShader methods from the Vulkan backend * Add minimal pipeline layouts that only contains used bindings They are used by helper shaders, the intention is avoiding needing to recompile the shaders (from GLSL to SPIR-V) if the bindings changes on the translated guest shaders * Pre-compile helper shader as SPIR-V, and some fixes * Remove pre-compiled shaderc binary for Windows as its no longer needed by default * Workaround RADV crash Enabling the descriptor indexing extension, even if it is not used, forces the radv driver to use "bolist". * Use RobustBufferAccess on NVIDIA gpus Avoids the SMO waterfall triangle on older NVIDIA gpus. * Implement GPU selector and expose texture recompression on the UI and config * Fix and enable background compute shader compilation Also disables warnings from shader cache pipeline misses. * Fix error due to missing subpass dependency when Attachment Write -> Shader Read barriers are added * If S8D24 is not supported, use D32FS8 * Ensure all fences are destroyed on dispose * Pre-allocate arrays up front on DescriptorSetUpdater, allows the removal of some checks * Add missing clear layer parameter after rebase * Use selected gpu from config for avalonia (#7) * use configured device * address review * Fix D32S8 copy workaround (AMD) Fixes water in Pokemon Legends Arceus on AMD GPUs. Possibly fixes other things. * Use push descriptors for uniform buffer updates (disabled for now) * Push descriptor support check, buffer redundancy checks Should make push descriptors faster, needs more testing though. * Increase light command buffer pool to 2 command buffers, throw rather than returning invalid cbs * Adjust bindings array sizes * Force submit command buffers if memory in use by its resources is high * Add workaround for AMD GCN cubemap view sins `ImageCreateCubeCompatibleBit` seems to generally break 2D array textures with mipmaps... even if they are eventually aliased as a cubemap with mipmaps. Forcing a copy here works around the issue. This could be used in future if enabling this bit reduces performance on certain GPUs. (mobile class is generally a worry) Currently also enabled on Linux as I don't know if they managed to dodge this bug (someone please tell me). Not enabled on Vega at the moment, but easy to add if the issue is there. * Add mobile, non-RX variants to the GCN regex. Also make sure that the 3 digit ones only include numbers starting with 7 or 8. * Increase image limit per stage from 8 to 16 Xenoblade Chronicles 2 was hiting the limit of 8 * Minor code cleanup * Fix NRE caused by SupportBufferUpdater calling pipeline ClearBuffer * Add gpu selector to Avalonia (#8) * Add gpu selector to avalonia settings * show backend label on window * some fixes * address review * Minor changes to the Avalonia UI * Update graphics window UI and locales. (#9) * Update xaml and update locales * locale updates Did my best here but likely needs to be checked by native speakers, especially the use of ampersands in greek, russian and turkish? * Fix locales with more (?) correct translations. * add separator to render widget * fix spanish and portuguese * Add new IdList, replaces buffer list that could not remove elements and had unbounded growth * Don't crash the settings window if Vulkan is not supported * Fix Actions menu not being clickable on GTK UI after relaunch * Rename VulkanGraphicsDevice to VulkanRenderer and Renderer to OpenGLRenderer * Fix IdList and make it not thread safe * Revert useless OpenGL format table changes * Fix headless project build * List throws ArgumentOutOfRangeException * SPIR-V: Fix tessellation * Increase shader cache version due to tessellation fix * Reduce number of Sync objects created (improves perf in some specific titles) * Fix vulkan validation errors for NPOT compressed upload and GCN workaround. * Add timestamp to the shader cache and force rebuild if host cache is outdated * Prefer Mail box present mode for popups (#11) * Prefer Mail box present mode * fix debug * switch present mode when vsync is toggled * only disable vsync on the main window * SPIR-V: Fix geometry shader input load with transform feedback * BC7 Encoder: Prefer more precision on alpha rather than RGB when alpha is 0 * Fix Avalonia build * Address initial PR feedback * Only set transform feedback outputs on last vertex stage * Address riperiperi PR feedback * Remove outdated comment * Remove unused constructor * Only throw for negative results * Throw for QueueSubmit and other errors No point in delaying the inevitable * Transform feedback decorations inside gl_PerVertex struct breaks the NVIDIA compiler * Fix some resolution scale issues * No need for two UpdateScale calls * Fix comments on SPIR-V generator project * Try to fix shader local memory size On DOOM, a shader is using local memory, but both Low and High size are 0, CRS size is 1536, it seems to store on that region? * Remove RectangleF that is now unused * Fix ImageGather with multiple offsets Needs ImageGatherExtended capability, and must use `ConstantComposite` instead of `CompositeConstruct` * Address PR feedback from jD in all projects except Avalonia * Address most of jD PR feedback on Avalonia * Remove unsafe * Fix VulkanSkiaGpu * move present mode request out of Create Swapchain method * split more parts of create swapchain * addressed reviews * addressed review * Address second batch of jD PR feedback * Fix buffer <-> image copy row length and height alignment AlignUp helper does not support NPOT alignment, and ASTC textures can have NPOT block sizes * Better fix for NPOT alignment issue * Use switch expressions on Vulkan EnumConversion Thanks jD * Fix Avalonia build * Add Vulkan selection prompt on startup * Grammar fixes on Vulkan prompt message * Add missing Vulkan migration flag Co-authored-by: riperiperi <rhy3756547@hotmail.com> Co-authored-by: Emmanuel Hansen <emmausssss@gmail.com> Co-authored-by: MutantAura <44103205+MutantAura@users.noreply.github.com>
2022-07-31 21:26:06 +00:00
{
return (VertexAttribType)((Attribute >> 27) & 7);
Vulkan backend (#2518) * WIP Vulkan implementation * No need to initialize attributes on the SPIR-V backend anymore * Allow multithreading shaderc and vkCreateShaderModule You'll only really see the benefit here with threaded-gal or parallel shader cache compile. Fix shaderc multithreaded changes Thread safety for shaderc Options constructor Dunno how they managed to make a constructor not thread safe, but you do you. May avoid some freezes. * Support multiple levels/layers for blit. Fixes MK8D when scaled, maybe a few other games. AMD software "safe" blit not supported right now. * TextureStorage should hold a ref of the foreign storage, otherwise it might be freed while in use * New depth-stencil blit method for AMD * Workaround for AMD driver bug * Fix some tessellation related issues (still doesn't work?) * Submit command buffer before Texture GetData. (UE4 fix) * DrawTexture support * Fix BGRA on OpenGL backend * Fix rebase build break * Support format aliasing on SetImage * Fix uniform buffers being lost when bindings are out of order * Fix storage buffers being lost when bindings are out of order (also avoid allocations when changing bindings) * Use current command buffer for unscaled copy (perf) Avoids flushing commands and renting a command buffer when fulfilling copy dependencies and when games do unscaled copies. * Update to .net6 * Update Silk.NET to version 2.10.1 Somehow, massive performance boost. Seems like their vtable for looking up vulkan methods was really slow before. * Fix PrimitivesGenerated query, disable Transform Feedback queries for now Lets Splatoon 2 work on nvidia. (mostly) * Update counter queue to be similar to the OGL one Fixes softlocks when games had to flush counters. * Don't throw when ending conditional rendering for now This should be re-enabled when conditional rendering is enabled on nvidia etc. * Update findMSB/findLSB to match master's instruction enum * Fix triangle overlay on SMO, Captain Toad, maybe others? * Don't make Intel Mesa pay for Intel Windows bugs * Fix samplers with MinFilter Linear or Nearest (fixes New Super Mario Bros U Deluxe black borders) * Update Spv.Generator * Add alpha test emulation on shader (but no shader specialisation yet...) * Fix R4G4B4A4Unorm texture format permutation * Validation layers should be enabled for any log level other than None * Add barriers around vkCmdCopyImage Write->Read barrier for src image (we want to wait for a write to read it) Write->Read barrier for dst image (we want to wait for the copy to complete before use) * Be a bit more careful with texture access flags, since it can be used for anything * Device local mapping for all buffers May avoid issues with drivers with NVIDIA on linux/older gpus on windows when using large buffers (?) Also some performance things and fixes issues with opengl games loading textures weird. * Cleanup, disable device local buffers for now. * Add single queue support Multiqueue seems to be a bit more responsive on NVIDIA. Should fix texture flush on intel. AMD has been forced to single queue for an experiment. * Fix some validation errors around extended dynamic state * Remove Intel bug workaround, it was fixed on the latest driver * Use circular queue for checking consumption on command buffers Speeds up games that spam command buffers a little. Avoids checking multiple command buffers if multiple are active at once. * Use SupportBufferUpdater, add single layer flush * Fix counter queue leak when game decides to use host conditional rendering * Force device local storage for textures (fixes linux performance) * Port #3019 * Insert barriers around vkCmdBlitImage (may fix some amd flicker) * Fix transform feedback on Intel, gl_Position feedback and clears to inexistent depth buffers * Don't pause transform feedback for multi draw * Fix draw outside of render pass and missing capability * Workaround for wrong last attribute on AMD (affects FFVII, STRIKERS1945, probably more) * Better workaround for AMD vertex buffer size alignment issue * More instructions + fixes on SPIR-V backend * Allow custom aspect ratio on Vulkan * Correct GTK UI status bar positions * SPIR-V: Functions must always end with a return * SPIR-V: Fix ImageQuerySizeLod * SPIR-V: Set DepthReplacing execution mode when FragDepth is modified * SPIR-V: Implement LoopContinue IR instruction * SPIR-V: Geometry shader support * SPIR-V: Use correct binding number on storage buffers array * Reduce allocations for Spir-v serialization Passes BinaryWriter instead of the stream to Write and WriteOperand - Removes creation of BinaryWriter for each instruction - Removes allocations for literal string * Some optimizations to Spv.Generator - Dictionary for lookups of type declarations, constants, extinst - LiteralInteger internal data format -> ushort - Deterministic HashCode implementation to avoid spirv result not being the same between runs - Inline operand list instead of List<T>, falls back to array if many operands. (large performance boost) TODO: improve instruction allocation, structured program creator, ssa? * Pool Spv.Generator resources, cache delegates, spv opts - Pools for Instructions and LiteralIntegers. Can be passed in when creating the generator module. - NewInstruction is called instead of new Instruction() - Ryujinx SpirvGenerator passes in some pools that are static. The idea is for these to be shared between threads eventually. - Estimate code size when creating the output MemoryStream - LiteralInteger pools using ThreadStatic pools that are initialized before and after creation... not sure of a better way since the way these are created is via implicit cast. Also, cache delegates for Spv.Generator for functions that are passed around to GenerateBinary etc, since passing the function raw creates a delegate on each call. TODO: update python spv cs generator to make the coregrammar with NewInstruction and the `params` overloads. * LocalDefMap for Ssa Rewriter Rather than allocating a large array of all registers for each block in the shader, allocate one array of all registers and clear it between blocks. Reduces allocations in the shader translator. * SPIR-V: Transform feedback support * SPIR-V: Fragment shader interlock support (and image coherency) * SPIR-V: Add early fragment tests support * SPIR-V: Implement SwizzleAdd, add missing Triangles ExecutionMode for geometry shaders, remove SamplerType field from TextureMeta * Don't pass depth clip state right now (fix decals) Explicitly disabling it is incorrect. OpenGL currently automatically disables based on depth clamp, which is the behaviour if this state is omitted. * Multisampling support * Multisampling: Use resolve if src samples count > dst samples count * Multisampling: We can only resolve for unscaled copies * SPIR-V: Only add FSI exec mode if used. * SPIR-V: Use ConstantComposite for Texture Offset Vector Fixes a bunch of freezes with SPIR-V on AMD hardware, and validation errors. Note: Obviously assumes input offsets are constant, which they currently are. * SPIR-V: Don't OpReturn if we already OpExit'ed Fixes spir-v parse failure and stack smashing in RADV (obviously you still need bolist) * SPIR-V: Only use input attribute type for input attributes Output vertex attributes should always be of type float. * Multithreaded Pipeline Compilation * Address some feedback * Make this 32 * Update topology with GpuAccessorState * Cleanup for merge (note: disables spir-v) * Make more robust to shader compilation failure - Don't freeze when GLSL compilation fails - Background SPIR-V pipeline compile failure results in skipped draws, similar to GLSL compilation failure. * Fix Multisampling * Only update fragment scale count if a vertex texture needs a scale. Fixes a performance regression introduced by texture scaling in the vertex stage where support buffer updates would be very frequent, even at 1x, if any textures were used on the vertex stage. This check doesn't exactly look cheap (a flag in the shader stage would probably be preferred), but it is much cheaper than uploading scales in both vulkan and opengl, so it will do for now. * Use a bitmap to do granular tracking for buffer uploads. This path is only taken if the much faster check of "is the buffer rented at all" is triggered, so it doesn't actually end up costing too much, and the time saved by not ending render passes (and on gpu for not waiting on barriers) is probably helpful. Avoids ending render passes to update buffer data (not all the time) - 140-180 to 35-45 in SMO metro kingdom (these updates are in the UI) - Very variable 60-150(!) to 16-25 in mario kart 8 (these updates are in the UI) As well as allowing more data to be preloaded persistently, this will also allow more data to be loaded in the preload buffer, which should be faster as it doesn't need to insert barriers between draws. (and on tbdr, does not need to flush and reload tile memory) Improves performance in GPU limited scenarios. Should notably improve performance on TBDR gpus. Still a lot more to do here. * Copy query results after RP ends, rather than ending to copy We need to end the render pass to get the data (submit command buffer) anyways... Reduces render passes created in games that use queries. * Rework Query stuff a bit to avoid render pass end Tries to reset returned queries in background when possible, rather than ending the render pass. Still ends render pass when resetting a counter after draws, but maybe that can be solved too. (by just pulling an empty object off the pool?) * Remove unnecessary lines Was for testing * Fix validation error for query reset Need to think of a better way to do this. * SPIR-V: Fix SwizzleAdd and some validation errors * SPIR-V: Implement attribute indexing and StoreAttribute * SPIR-V: Fix TextureSize for MS and Buffer sampler types * Fix relaunch issues * SPIR-V: Implement LogicalExclusiveOr * SPIR-V: Constant buffer indexing support * Ignore unsupported attributes rather than throwing (matches current GLSL behaviour) * SPIR-V: Implement tessellation support * SPIR-V: Geometry shader passthrough support * SPIR-V: Implement StoreShader8/16 and StoreStorage8/16 * SPIR-V: Resolution scale support and fix TextureSample multisample with LOD bug * SPIR-V: Fix field index for scale count * SPIR-V: Fix another case of wrong field index * SPIRV/GLSL: More scaling related fixes * SPIR-V: Fix ImageLoad CompositeExtract component type * SPIR-V: Workaround for Intel FrontFacing bug * Enable SPIR-V backend by default * Allow null samplers (samplers are not required when only using texelFetch to access the texture) * Fix some validation errors related to texel block view usage flag and invalid image barrier base level * Use explicit subgroup size if we can (might fix some block flickering on AMD) * Take componentMask and scissor into account when clearing framebuffer attachments * Add missing barriers around CmdFillBuffer (fixes Monster Hunter Rise flickering on NVIDIA) * Use ClampToEdge for Clamp sampler address mode on Vulkan (fixes Hollow Knight) Clamp is unsupported on Vulkan, but ClampToEdge behaves almost the same. ClampToBorder on the other hand (which was being used before) is pretty different * Shader specialization for new Vulkan required state (fixes remaining alpha test issues, vertex stretching on AMD on Crash Bandicoot, etc) * Check if the subgroup size is supported before passing a explicit size * Only enable ShaderFloat64 if the GPU supports it * We don't need to recompile shaders if alpha test state changed but alpha test is disabled * Enable shader cache on Vulkan and implement MultiplyHighS32/U32 on SPIR-V (missed those before) * Fix pipeline state saving before it is updated. This should fix a few warnings and potential stutters due to bad pipeline states being saved in the cache. You may need to clear your guest cache. * Allow null samplers on OpenGL backend * _unit0Sampler should be set only for binding 0 * Remove unused PipelineConverter format variable (was causing IOR) * Raise textures limit to 64 on Vulkan * No need to pack the shader binaries if shader cache is disabled * Fix backbuffer not being cleared and scissor not being re-enabled on OpenGL * Do not clear unbound framebuffer color attachments * Geometry shader passthrough emulation * Consolidate UpdateDepthMode and GetDepthMode implementation * Fix A1B5G5R5 texture format and support R4G4 on Vulkan * Add barrier before use of some modified images * Report 32 bit query result on AMD windows (smo issue) * Add texture recompression support (disabled for now) It recompresses ASTC textures into BC7, which might reduce VRAM usage significantly on games that uses ASTC textures * Do not report R4G4 format as supported on Vulkan It was causing mario head to become white on Super Mario 64 (???) * Improvements to -1 to 1 depth mode. - Transformation is only applied on the last stage in the vertex pipeline. - Should fix some issues with geometry and tessellation (hopefully) - Reading back FragCoord Z on fragment will transform back to -1 to 1. * Geometry Shader index count from ThreadsPerInputPrimitive Generally fixes SPIR-V emitting too many triangles, may change games in OpenGL * Remove gl_FragDepth scaling This is always 0-1; the other two issues were causing the problems. Fixes regression with Xenoblade. * Add Gl StencilOp enum values to Vulkan * Update guest cache to v1.1 (due to specialization state changes) This will explode your shader cache from earlier vulkan build, but it must be done. :pensive: * Vulkan/SPIR-V support for viewport inverse * Fix typo * Don't create query pools for unsupported query types * Return of the Vector Indexing Bug One day, everyone will get this right. * Check for transform feedback query support Sometimes transform feedback is supported without the query type. * Fix gl_FragCoord.z transformation FragCoord.z is always in 0-1, even when the real depth range is -1 to 1. Turns out the only bug was geo and tess stage outputs. Fixes Pokemon Sword/Shield, possibly others. * Fix Avalonia Rebase Vulkan is currently not available on Avalonia, but the build does work and you can use opengl. * Fix headless build * Add support for BC6 and BC7 decompression, decompress all BC formats if they are not supported by the host * Fix BCn 4/5 conversion, GetTextureTarget BCn 4/5 could generate invalid data when a line's size in bytes was not divisible by 4, which both backends expect. GetTextureTarget was not creating a view with the replacement format. * Fix dependency * Fix inverse viewport transform vector type on SPIR-V * Do not require null descriptors support * If MultiViewport is not supported, do not try to set more than one viewport/scissor * Bounds check on bitmap add. * Flush queries on attachment change rather than program change Occlusion queries are usually used in a depth only pass so the attachments changing is a better indication of the query block ending. Write mask changes are also considered since some games do depth only pass by setting 0 write mask on all the colour targets. * Add support for avalonia (#6) * add avalonia support * only lock around skia flush * addressed review * cleanup * add fallback size if avalonia attempts to render but the window size is 0. read desktop scale after enabling dpi check * fix getting window handle on linux. skip render is size is 0 * Combine non-buffer with buffer image descriptor sets * Support multisample texture copy with automatic resolve on Vulkan * Remove old CompileShader methods from the Vulkan backend * Add minimal pipeline layouts that only contains used bindings They are used by helper shaders, the intention is avoiding needing to recompile the shaders (from GLSL to SPIR-V) if the bindings changes on the translated guest shaders * Pre-compile helper shader as SPIR-V, and some fixes * Remove pre-compiled shaderc binary for Windows as its no longer needed by default * Workaround RADV crash Enabling the descriptor indexing extension, even if it is not used, forces the radv driver to use "bolist". * Use RobustBufferAccess on NVIDIA gpus Avoids the SMO waterfall triangle on older NVIDIA gpus. * Implement GPU selector and expose texture recompression on the UI and config * Fix and enable background compute shader compilation Also disables warnings from shader cache pipeline misses. * Fix error due to missing subpass dependency when Attachment Write -> Shader Read barriers are added * If S8D24 is not supported, use D32FS8 * Ensure all fences are destroyed on dispose * Pre-allocate arrays up front on DescriptorSetUpdater, allows the removal of some checks * Add missing clear layer parameter after rebase * Use selected gpu from config for avalonia (#7) * use configured device * address review * Fix D32S8 copy workaround (AMD) Fixes water in Pokemon Legends Arceus on AMD GPUs. Possibly fixes other things. * Use push descriptors for uniform buffer updates (disabled for now) * Push descriptor support check, buffer redundancy checks Should make push descriptors faster, needs more testing though. * Increase light command buffer pool to 2 command buffers, throw rather than returning invalid cbs * Adjust bindings array sizes * Force submit command buffers if memory in use by its resources is high * Add workaround for AMD GCN cubemap view sins `ImageCreateCubeCompatibleBit` seems to generally break 2D array textures with mipmaps... even if they are eventually aliased as a cubemap with mipmaps. Forcing a copy here works around the issue. This could be used in future if enabling this bit reduces performance on certain GPUs. (mobile class is generally a worry) Currently also enabled on Linux as I don't know if they managed to dodge this bug (someone please tell me). Not enabled on Vega at the moment, but easy to add if the issue is there. * Add mobile, non-RX variants to the GCN regex. Also make sure that the 3 digit ones only include numbers starting with 7 or 8. * Increase image limit per stage from 8 to 16 Xenoblade Chronicles 2 was hiting the limit of 8 * Minor code cleanup * Fix NRE caused by SupportBufferUpdater calling pipeline ClearBuffer * Add gpu selector to Avalonia (#8) * Add gpu selector to avalonia settings * show backend label on window * some fixes * address review * Minor changes to the Avalonia UI * Update graphics window UI and locales. (#9) * Update xaml and update locales * locale updates Did my best here but likely needs to be checked by native speakers, especially the use of ampersands in greek, russian and turkish? * Fix locales with more (?) correct translations. * add separator to render widget * fix spanish and portuguese * Add new IdList, replaces buffer list that could not remove elements and had unbounded growth * Don't crash the settings window if Vulkan is not supported * Fix Actions menu not being clickable on GTK UI after relaunch * Rename VulkanGraphicsDevice to VulkanRenderer and Renderer to OpenGLRenderer * Fix IdList and make it not thread safe * Revert useless OpenGL format table changes * Fix headless project build * List throws ArgumentOutOfRangeException * SPIR-V: Fix tessellation * Increase shader cache version due to tessellation fix * Reduce number of Sync objects created (improves perf in some specific titles) * Fix vulkan validation errors for NPOT compressed upload and GCN workaround. * Add timestamp to the shader cache and force rebuild if host cache is outdated * Prefer Mail box present mode for popups (#11) * Prefer Mail box present mode * fix debug * switch present mode when vsync is toggled * only disable vsync on the main window * SPIR-V: Fix geometry shader input load with transform feedback * BC7 Encoder: Prefer more precision on alpha rather than RGB when alpha is 0 * Fix Avalonia build * Address initial PR feedback * Only set transform feedback outputs on last vertex stage * Address riperiperi PR feedback * Remove outdated comment * Remove unused constructor * Only throw for negative results * Throw for QueueSubmit and other errors No point in delaying the inevitable * Transform feedback decorations inside gl_PerVertex struct breaks the NVIDIA compiler * Fix some resolution scale issues * No need for two UpdateScale calls * Fix comments on SPIR-V generator project * Try to fix shader local memory size On DOOM, a shader is using local memory, but both Low and High size are 0, CRS size is 1536, it seems to store on that region? * Remove RectangleF that is now unused * Fix ImageGather with multiple offsets Needs ImageGatherExtended capability, and must use `ConstantComposite` instead of `CompositeConstruct` * Address PR feedback from jD in all projects except Avalonia * Address most of jD PR feedback on Avalonia * Remove unsafe * Fix VulkanSkiaGpu * move present mode request out of Create Swapchain method * split more parts of create swapchain * addressed reviews * addressed review * Address second batch of jD PR feedback * Fix buffer <-> image copy row length and height alignment AlignUp helper does not support NPOT alignment, and ASTC textures can have NPOT block sizes * Better fix for NPOT alignment issue * Use switch expressions on Vulkan EnumConversion Thanks jD * Fix Avalonia build * Add Vulkan selection prompt on startup * Grammar fixes on Vulkan prompt message * Add missing Vulkan migration flag Co-authored-by: riperiperi <rhy3756547@hotmail.com> Co-authored-by: Emmanuel Hansen <emmausssss@gmail.com> Co-authored-by: MutantAura <44103205+MutantAura@users.noreply.github.com>
2022-07-31 21:26:06 +00:00
}
}
/// <summary>
/// Render target draw buffers control.
/// </summary>
struct RtControl
{
#pragma warning disable CS0649
public uint Packed;
#pragma warning restore CS0649
/// <summary>
/// Unpacks the number of active draw buffers.
/// </summary>
/// <returns>Number of active draw buffers</returns>
public int UnpackCount()
{
return (int)(Packed & 0xf);
}
/// <summary>
/// Unpacks the color attachment index for a given draw buffer.
/// </summary>
/// <param name="index">Index of the draw buffer</param>
/// <returns>Attachment index</returns>
public int UnpackPermutationIndex(int index)
{
return (int)((Packed >> (4 + index * 3)) & 7);
}
}
/// <summary>
/// 3D, 2D or 1D texture size.
/// </summary>
struct Size3D
{
#pragma warning disable CS0649
public int Width;
public int Height;
public int Depth;
#pragma warning restore CS0649
}
/// <summary>
/// Stencil front test state and masks.
/// </summary>
struct StencilTestState
{
#pragma warning disable CS0649
public Boolean32 Enable;
public StencilOp FrontSFail;
public StencilOp FrontDpFail;
public StencilOp FrontDpPass;
public CompareOp FrontFunc;
public int FrontFuncRef;
public int FrontFuncMask;
public int FrontMask;
#pragma warning restore CS0649
}
/// <summary>
/// Screen Y control register.
/// </summary>
[Flags]
enum YControl
{
NegateY = 1 << 0,
TriangleRastFlip = 1 << 4
}
/// <summary>
/// RGB color components packed as 16-bit float values.
/// </summary>
struct RgbHalf
{
#pragma warning disable CS0649
public uint R;
public uint G;
public uint B;
public uint Padding;
#pragma warning restore CS0649
/// <summary>
/// Unpacks the red color component as a 16-bit float value.
/// </summary>
/// <returns>The component value</returns>
public Half UnpackR()
{
ushort value = (ushort)R;
return Unsafe.As<ushort, Half>(ref value);
}
/// <summary>
/// Unpacks the green color component as a 16-bit float value.
/// </summary>
/// <returns>The component value</returns>
public Half UnpackG()
{
ushort value = (ushort)G;
return Unsafe.As<ushort, Half>(ref value);
}
/// <summary>
/// Unpacks the blue color component as a 16-bit float value.
/// </summary>
/// <returns>The component value</returns>
public Half UnpackB()
{
ushort value = (ushort)B;
return Unsafe.As<ushort, Half>(ref value);
}
}
/// <summary>
/// Condition for conditional rendering.
/// </summary>
enum Condition
{
Never,
Always,
ResultNonZero,
Equal,
NotEqual
}
/// <summary>
/// Texture or sampler pool state.
/// </summary>
struct PoolState
{
#pragma warning disable CS0649
public GpuVa Address;
public int MaximumId;
#pragma warning restore CS0649
}
/// <summary>
/// Stencil back test state.
/// </summary>
struct StencilBackTestState
{
#pragma warning disable CS0649
public Boolean32 TwoSided;
public StencilOp BackSFail;
public StencilOp BackDpFail;
public StencilOp BackDpPass;
public CompareOp BackFunc;
#pragma warning restore CS0649
}
/// <summary>
/// Primitive restart state.
/// </summary>
struct PrimitiveRestartState
{
#pragma warning disable CS0649
public Boolean32 Enable;
public int Index;
#pragma warning restore CS0649
}
/// <summary>
/// GPU index buffer state.
/// This is used on indexed draws.
/// </summary>
struct IndexBufferState
{
#pragma warning disable CS0649
public GpuVa Address;
public GpuVa EndAddress;
public IndexType Type;
public int First;
#pragma warning restore CS0649
}
/// <summary>
/// Face culling and orientation parameters.
/// </summary>
struct FaceState
{
#pragma warning disable CS0649
public Boolean32 CullEnable;
public FrontFace FrontFace;
public Face CullFace;
#pragma warning restore CS0649
}
/// <summary>
/// View volume clip control.
/// </summary>
[Flags]
enum ViewVolumeClipControl
{
ForceDepthRangeZeroToOne = 1 << 0,
DepthClampDisabled = 1 << 11
}
/// <summary>
/// Logical operation state.
/// </summary>
struct LogicalOpState
{
#pragma warning disable CS0649
public Boolean32 Enable;
public LogicalOp LogicalOp;
#pragma warning restore CS0649
}
/// <summary>
/// Render target color buffer mask.
/// This defines which color channels are written to the color buffer.
/// </summary>
struct RtColorMask
{
#pragma warning disable CS0649
public uint Packed;
#pragma warning restore CS0649
/// <summary>
/// Unpacks red channel enable.
/// </summary>
/// <returns>True to write the new red channel color, false to keep the old value</returns>
public bool UnpackRed()
{
return (Packed & 0x1) != 0;
}
/// <summary>
/// Unpacks green channel enable.
/// </summary>
/// <returns>True to write the new green channel color, false to keep the old value</returns>
public bool UnpackGreen()
{
return (Packed & 0x10) != 0;
}
/// <summary>
/// Unpacks blue channel enable.
/// </summary>
/// <returns>True to write the new blue channel color, false to keep the old value</returns>
public bool UnpackBlue()
{
return (Packed & 0x100) != 0;
}
/// <summary>
/// Unpacks alpha channel enable.
/// </summary>
/// <returns>True to write the new alpha channel color, false to keep the old value</returns>
public bool UnpackAlpha()
{
return (Packed & 0x1000) != 0;
}
}
/// <summary>
/// Vertex buffer state.
/// </summary>
struct VertexBufferState
{
#pragma warning disable CS0649
public uint Control;
public GpuVa Address;
public int Divisor;
#pragma warning restore CS0649
/// <summary>
/// Vertex buffer stride, defined as the number of bytes occupied by each vertex in memory.
/// </summary>
/// <returns>Vertex buffer stride</returns>
public int UnpackStride()
{
return (int)(Control & 0xfff);
}
/// <summary>
/// Vertex buffer enable.
/// </summary>
/// <returns>True if the vertex buffer is enabled, false otherwise</returns>
public bool UnpackEnable()
{
return (Control & (1 << 12)) != 0;
}
}
/// <summary>
/// Color buffer blending parameters, shared by all color buffers.
/// </summary>
struct BlendStateCommon
{
#pragma warning disable CS0649
public Boolean32 SeparateAlpha;
public BlendOp ColorOp;
public BlendFactor ColorSrcFactor;
public BlendFactor ColorDstFactor;
public BlendOp AlphaOp;
public BlendFactor AlphaSrcFactor;
public uint Unknown0x1354;
public BlendFactor AlphaDstFactor;
#pragma warning restore CS0649
}
/// <summary>
/// Color buffer blending parameters.
/// </summary>
struct BlendState
{
#pragma warning disable CS0649
public Boolean32 SeparateAlpha;
public BlendOp ColorOp;
public BlendFactor ColorSrcFactor;
public BlendFactor ColorDstFactor;
public BlendOp AlphaOp;
public BlendFactor AlphaSrcFactor;
public BlendFactor AlphaDstFactor;
public uint Padding;
#pragma warning restore CS0649
}
/// <summary>
/// Graphics shader stage state.
/// </summary>
struct ShaderState
{
#pragma warning disable CS0649
public uint Control;
public uint Offset;
public uint Unknown0x8;
public int MaxRegisters;
public ShaderType Type;
public uint Unknown0x14;
public uint Unknown0x18;
public uint Unknown0x1c;
public uint Unknown0x20;
public uint Unknown0x24;
public uint Unknown0x28;
public uint Unknown0x2c;
public uint Unknown0x30;
public uint Unknown0x34;
public uint Unknown0x38;
public uint Unknown0x3c;
#pragma warning restore CS0649
/// <summary>
/// Unpacks shader enable information.
/// Must be ignored for vertex shaders, those are always enabled.
/// </summary>
/// <returns>True if the stage is enabled, false otherwise</returns>
public bool UnpackEnable()
{
return (Control & 1) != 0;
}
}
/// <summary>
/// Uniform buffer state for the uniform buffer currently being modified.
/// </summary>
struct UniformBufferState
{
#pragma warning disable CS0649
public int Size;
public GpuVa Address;
public int Offset;
#pragma warning restore CS0649
}
unsafe struct ThreedClassState : IShadowState
{
#pragma warning disable CS0649
public uint SetObject;
public int SetObjectClassId => (int)((SetObject >> 0) & 0xFFFF);
public int SetObjectEngineId => (int)((SetObject >> 16) & 0x1F);
public fixed uint Reserved04[63];
public uint NoOperation;
public uint SetNotifyA;
public int SetNotifyAAddressUpper => (int)((SetNotifyA >> 0) & 0xFF);
public uint SetNotifyB;
public uint Notify;
public NotifyType NotifyType => (NotifyType)(Notify);
public uint WaitForIdle;
public uint LoadMmeInstructionRamPointer;
public uint LoadMmeInstructionRam;
public uint LoadMmeStartAddressRamPointer;
public uint LoadMmeStartAddressRam;
public uint SetMmeShadowRamControl;
public SetMmeShadowRamControlMode SetMmeShadowRamControlMode => (SetMmeShadowRamControlMode)((SetMmeShadowRamControl >> 0) & 0x3);
public fixed uint Reserved128[2];
public uint SetGlobalRenderEnableA;
public int SetGlobalRenderEnableAOffsetUpper => (int)((SetGlobalRenderEnableA >> 0) & 0xFF);
public uint SetGlobalRenderEnableB;
public uint SetGlobalRenderEnableC;
public int SetGlobalRenderEnableCMode => (int)((SetGlobalRenderEnableC >> 0) & 0x7);
public uint SendGoIdle;
public uint PmTrigger;
public uint PmTriggerWfi;
public fixed uint Reserved148[2];
public uint SetInstrumentationMethodHeader;
public uint SetInstrumentationMethodData;
public fixed uint Reserved158[10];
public uint LineLengthIn;
public uint LineCount;
public uint OffsetOutUpper;
public int OffsetOutUpperValue => (int)((OffsetOutUpper >> 0) & 0xFF);
public uint OffsetOut;
public uint PitchOut;
public uint SetDstBlockSize;
public SetDstBlockSizeWidth SetDstBlockSizeWidth => (SetDstBlockSizeWidth)((SetDstBlockSize >> 0) & 0xF);
public SetDstBlockSizeHeight SetDstBlockSizeHeight => (SetDstBlockSizeHeight)((SetDstBlockSize >> 4) & 0xF);
public SetDstBlockSizeDepth SetDstBlockSizeDepth => (SetDstBlockSizeDepth)((SetDstBlockSize >> 8) & 0xF);
public uint SetDstWidth;
public uint SetDstHeight;
public uint SetDstDepth;
public uint SetDstLayer;
public uint SetDstOriginBytesX;
public int SetDstOriginBytesXV => (int)((SetDstOriginBytesX >> 0) & 0xFFFFF);
public uint SetDstOriginSamplesY;
public int SetDstOriginSamplesYV => (int)((SetDstOriginSamplesY >> 0) & 0xFFFF);
public uint LaunchDma;
public LaunchDmaDstMemoryLayout LaunchDmaDstMemoryLayout => (LaunchDmaDstMemoryLayout)((LaunchDma >> 0) & 0x1);
public LaunchDmaCompletionType LaunchDmaCompletionType => (LaunchDmaCompletionType)((LaunchDma >> 4) & 0x3);
public LaunchDmaInterruptType LaunchDmaInterruptType => (LaunchDmaInterruptType)((LaunchDma >> 8) & 0x3);
public LaunchDmaSemaphoreStructSize LaunchDmaSemaphoreStructSize => (LaunchDmaSemaphoreStructSize)((LaunchDma >> 12) & 0x1);
public bool LaunchDmaReductionEnable => (LaunchDma & 0x2) != 0;
public LaunchDmaReductionOp LaunchDmaReductionOp => (LaunchDmaReductionOp)((LaunchDma >> 13) & 0x7);
public LaunchDmaReductionFormat LaunchDmaReductionFormat => (LaunchDmaReductionFormat)((LaunchDma >> 2) & 0x3);
public bool LaunchDmaSysmembarDisable => (LaunchDma & 0x40) != 0;
public uint LoadInlineData;
public fixed uint Reserved1B8[22];
public Boolean32 EarlyZForce;
public fixed uint Reserved214[45];
public uint SyncpointAction;
public fixed uint Reserved2CC[10];
public uint BlendUcodeNormalizedDst;
public fixed uint Reserved2F8[10];
public TessMode TessMode;
public Array4<float> TessOuterLevel;
public Array2<float> TessInnerLevel;
public fixed uint Reserved33C[16];
public Boolean32 RasterizeEnable;
public Array4<TfBufferState> TfBufferState;
public fixed uint Reserved400[192];
public Array4<TfState> TfState;
public fixed uint Reserved740[1];
public Boolean32 TfEnable;
public fixed uint Reserved748[46];
public Array8<RtColorState> RtColorState;
public Array16<ViewportTransform> ViewportTransform;
public Array16<ViewportExtents> ViewportExtents;
public fixed uint ReservedD00[29];
public VertexBufferDrawState VertexBufferDrawState;
public uint DepthMode;
public ClearColors ClearColors;
public float ClearDepthValue;
public fixed uint ReservedD94[3];
public uint ClearStencilValue;
public fixed uint ReservedDA4[2];
public PolygonMode PolygonModeFront;
public PolygonMode PolygonModeBack;
public Boolean32 PolygonSmoothEnable;
public fixed uint ReservedDB8[2];
public DepthBiasState DepthBiasState;
public int PatchVertices;
public BlendUcodeEnable BlendUcodeEnable;
public uint BlendUcodeSize;
public fixed uint ReservedDD8[2];
public uint TextureBarrier;
public uint WatchdogTimer;
public Boolean32 PrimitiveRestartDrawArrays;
public uint ReservedDEC;
public uint LoadBlendUcodeStart;
public uint LoadBlendUcodeInstruction;
public fixed uint ReservedDF8[2];
public Array16<ScissorState> ScissorState;
public fixed uint ReservedF00[21];
public StencilBackMasks StencilBackMasks;
public fixed uint ReservedF60[5];
public uint InvalidateTextures;
public fixed uint ReservedF78[1];
public uint TextureBarrierTiled;
public fixed uint ReservedF80[4];
public Boolean32 RtColorMaskShared;
public fixed uint ReservedF94[19];
public RtDepthStencilState RtDepthStencilState;
public ScreenScissorState ScreenScissorState;
public fixed uint ReservedFFC[33];
public int DrawTextureDstX;
public int DrawTextureDstY;
public int DrawTextureDstWidth;
public int DrawTextureDstHeight;
public long DrawTextureDuDx;
public long DrawTextureDvDy;
public int DrawTextureSamplerId;
public int DrawTextureTextureId;
public int DrawTextureSrcX;
public int DrawTextureSrcY;
public fixed uint Reserved10B0[18];
public uint ClearFlags;
public fixed uint Reserved10FC[25];
Vulkan backend (#2518) * WIP Vulkan implementation * No need to initialize attributes on the SPIR-V backend anymore * Allow multithreading shaderc and vkCreateShaderModule You'll only really see the benefit here with threaded-gal or parallel shader cache compile. Fix shaderc multithreaded changes Thread safety for shaderc Options constructor Dunno how they managed to make a constructor not thread safe, but you do you. May avoid some freezes. * Support multiple levels/layers for blit. Fixes MK8D when scaled, maybe a few other games. AMD software "safe" blit not supported right now. * TextureStorage should hold a ref of the foreign storage, otherwise it might be freed while in use * New depth-stencil blit method for AMD * Workaround for AMD driver bug * Fix some tessellation related issues (still doesn't work?) * Submit command buffer before Texture GetData. (UE4 fix) * DrawTexture support * Fix BGRA on OpenGL backend * Fix rebase build break * Support format aliasing on SetImage * Fix uniform buffers being lost when bindings are out of order * Fix storage buffers being lost when bindings are out of order (also avoid allocations when changing bindings) * Use current command buffer for unscaled copy (perf) Avoids flushing commands and renting a command buffer when fulfilling copy dependencies and when games do unscaled copies. * Update to .net6 * Update Silk.NET to version 2.10.1 Somehow, massive performance boost. Seems like their vtable for looking up vulkan methods was really slow before. * Fix PrimitivesGenerated query, disable Transform Feedback queries for now Lets Splatoon 2 work on nvidia. (mostly) * Update counter queue to be similar to the OGL one Fixes softlocks when games had to flush counters. * Don't throw when ending conditional rendering for now This should be re-enabled when conditional rendering is enabled on nvidia etc. * Update findMSB/findLSB to match master's instruction enum * Fix triangle overlay on SMO, Captain Toad, maybe others? * Don't make Intel Mesa pay for Intel Windows bugs * Fix samplers with MinFilter Linear or Nearest (fixes New Super Mario Bros U Deluxe black borders) * Update Spv.Generator * Add alpha test emulation on shader (but no shader specialisation yet...) * Fix R4G4B4A4Unorm texture format permutation * Validation layers should be enabled for any log level other than None * Add barriers around vkCmdCopyImage Write->Read barrier for src image (we want to wait for a write to read it) Write->Read barrier for dst image (we want to wait for the copy to complete before use) * Be a bit more careful with texture access flags, since it can be used for anything * Device local mapping for all buffers May avoid issues with drivers with NVIDIA on linux/older gpus on windows when using large buffers (?) Also some performance things and fixes issues with opengl games loading textures weird. * Cleanup, disable device local buffers for now. * Add single queue support Multiqueue seems to be a bit more responsive on NVIDIA. Should fix texture flush on intel. AMD has been forced to single queue for an experiment. * Fix some validation errors around extended dynamic state * Remove Intel bug workaround, it was fixed on the latest driver * Use circular queue for checking consumption on command buffers Speeds up games that spam command buffers a little. Avoids checking multiple command buffers if multiple are active at once. * Use SupportBufferUpdater, add single layer flush * Fix counter queue leak when game decides to use host conditional rendering * Force device local storage for textures (fixes linux performance) * Port #3019 * Insert barriers around vkCmdBlitImage (may fix some amd flicker) * Fix transform feedback on Intel, gl_Position feedback and clears to inexistent depth buffers * Don't pause transform feedback for multi draw * Fix draw outside of render pass and missing capability * Workaround for wrong last attribute on AMD (affects FFVII, STRIKERS1945, probably more) * Better workaround for AMD vertex buffer size alignment issue * More instructions + fixes on SPIR-V backend * Allow custom aspect ratio on Vulkan * Correct GTK UI status bar positions * SPIR-V: Functions must always end with a return * SPIR-V: Fix ImageQuerySizeLod * SPIR-V: Set DepthReplacing execution mode when FragDepth is modified * SPIR-V: Implement LoopContinue IR instruction * SPIR-V: Geometry shader support * SPIR-V: Use correct binding number on storage buffers array * Reduce allocations for Spir-v serialization Passes BinaryWriter instead of the stream to Write and WriteOperand - Removes creation of BinaryWriter for each instruction - Removes allocations for literal string * Some optimizations to Spv.Generator - Dictionary for lookups of type declarations, constants, extinst - LiteralInteger internal data format -> ushort - Deterministic HashCode implementation to avoid spirv result not being the same between runs - Inline operand list instead of List<T>, falls back to array if many operands. (large performance boost) TODO: improve instruction allocation, structured program creator, ssa? * Pool Spv.Generator resources, cache delegates, spv opts - Pools for Instructions and LiteralIntegers. Can be passed in when creating the generator module. - NewInstruction is called instead of new Instruction() - Ryujinx SpirvGenerator passes in some pools that are static. The idea is for these to be shared between threads eventually. - Estimate code size when creating the output MemoryStream - LiteralInteger pools using ThreadStatic pools that are initialized before and after creation... not sure of a better way since the way these are created is via implicit cast. Also, cache delegates for Spv.Generator for functions that are passed around to GenerateBinary etc, since passing the function raw creates a delegate on each call. TODO: update python spv cs generator to make the coregrammar with NewInstruction and the `params` overloads. * LocalDefMap for Ssa Rewriter Rather than allocating a large array of all registers for each block in the shader, allocate one array of all registers and clear it between blocks. Reduces allocations in the shader translator. * SPIR-V: Transform feedback support * SPIR-V: Fragment shader interlock support (and image coherency) * SPIR-V: Add early fragment tests support * SPIR-V: Implement SwizzleAdd, add missing Triangles ExecutionMode for geometry shaders, remove SamplerType field from TextureMeta * Don't pass depth clip state right now (fix decals) Explicitly disabling it is incorrect. OpenGL currently automatically disables based on depth clamp, which is the behaviour if this state is omitted. * Multisampling support * Multisampling: Use resolve if src samples count > dst samples count * Multisampling: We can only resolve for unscaled copies * SPIR-V: Only add FSI exec mode if used. * SPIR-V: Use ConstantComposite for Texture Offset Vector Fixes a bunch of freezes with SPIR-V on AMD hardware, and validation errors. Note: Obviously assumes input offsets are constant, which they currently are. * SPIR-V: Don't OpReturn if we already OpExit'ed Fixes spir-v parse failure and stack smashing in RADV (obviously you still need bolist) * SPIR-V: Only use input attribute type for input attributes Output vertex attributes should always be of type float. * Multithreaded Pipeline Compilation * Address some feedback * Make this 32 * Update topology with GpuAccessorState * Cleanup for merge (note: disables spir-v) * Make more robust to shader compilation failure - Don't freeze when GLSL compilation fails - Background SPIR-V pipeline compile failure results in skipped draws, similar to GLSL compilation failure. * Fix Multisampling * Only update fragment scale count if a vertex texture needs a scale. Fixes a performance regression introduced by texture scaling in the vertex stage where support buffer updates would be very frequent, even at 1x, if any textures were used on the vertex stage. This check doesn't exactly look cheap (a flag in the shader stage would probably be preferred), but it is much cheaper than uploading scales in both vulkan and opengl, so it will do for now. * Use a bitmap to do granular tracking for buffer uploads. This path is only taken if the much faster check of "is the buffer rented at all" is triggered, so it doesn't actually end up costing too much, and the time saved by not ending render passes (and on gpu for not waiting on barriers) is probably helpful. Avoids ending render passes to update buffer data (not all the time) - 140-180 to 35-45 in SMO metro kingdom (these updates are in the UI) - Very variable 60-150(!) to 16-25 in mario kart 8 (these updates are in the UI) As well as allowing more data to be preloaded persistently, this will also allow more data to be loaded in the preload buffer, which should be faster as it doesn't need to insert barriers between draws. (and on tbdr, does not need to flush and reload tile memory) Improves performance in GPU limited scenarios. Should notably improve performance on TBDR gpus. Still a lot more to do here. * Copy query results after RP ends, rather than ending to copy We need to end the render pass to get the data (submit command buffer) anyways... Reduces render passes created in games that use queries. * Rework Query stuff a bit to avoid render pass end Tries to reset returned queries in background when possible, rather than ending the render pass. Still ends render pass when resetting a counter after draws, but maybe that can be solved too. (by just pulling an empty object off the pool?) * Remove unnecessary lines Was for testing * Fix validation error for query reset Need to think of a better way to do this. * SPIR-V: Fix SwizzleAdd and some validation errors * SPIR-V: Implement attribute indexing and StoreAttribute * SPIR-V: Fix TextureSize for MS and Buffer sampler types * Fix relaunch issues * SPIR-V: Implement LogicalExclusiveOr * SPIR-V: Constant buffer indexing support * Ignore unsupported attributes rather than throwing (matches current GLSL behaviour) * SPIR-V: Implement tessellation support * SPIR-V: Geometry shader passthrough support * SPIR-V: Implement StoreShader8/16 and StoreStorage8/16 * SPIR-V: Resolution scale support and fix TextureSample multisample with LOD bug * SPIR-V: Fix field index for scale count * SPIR-V: Fix another case of wrong field index * SPIRV/GLSL: More scaling related fixes * SPIR-V: Fix ImageLoad CompositeExtract component type * SPIR-V: Workaround for Intel FrontFacing bug * Enable SPIR-V backend by default * Allow null samplers (samplers are not required when only using texelFetch to access the texture) * Fix some validation errors related to texel block view usage flag and invalid image barrier base level * Use explicit subgroup size if we can (might fix some block flickering on AMD) * Take componentMask and scissor into account when clearing framebuffer attachments * Add missing barriers around CmdFillBuffer (fixes Monster Hunter Rise flickering on NVIDIA) * Use ClampToEdge for Clamp sampler address mode on Vulkan (fixes Hollow Knight) Clamp is unsupported on Vulkan, but ClampToEdge behaves almost the same. ClampToBorder on the other hand (which was being used before) is pretty different * Shader specialization for new Vulkan required state (fixes remaining alpha test issues, vertex stretching on AMD on Crash Bandicoot, etc) * Check if the subgroup size is supported before passing a explicit size * Only enable ShaderFloat64 if the GPU supports it * We don't need to recompile shaders if alpha test state changed but alpha test is disabled * Enable shader cache on Vulkan and implement MultiplyHighS32/U32 on SPIR-V (missed those before) * Fix pipeline state saving before it is updated. This should fix a few warnings and potential stutters due to bad pipeline states being saved in the cache. You may need to clear your guest cache. * Allow null samplers on OpenGL backend * _unit0Sampler should be set only for binding 0 * Remove unused PipelineConverter format variable (was causing IOR) * Raise textures limit to 64 on Vulkan * No need to pack the shader binaries if shader cache is disabled * Fix backbuffer not being cleared and scissor not being re-enabled on OpenGL * Do not clear unbound framebuffer color attachments * Geometry shader passthrough emulation * Consolidate UpdateDepthMode and GetDepthMode implementation * Fix A1B5G5R5 texture format and support R4G4 on Vulkan * Add barrier before use of some modified images * Report 32 bit query result on AMD windows (smo issue) * Add texture recompression support (disabled for now) It recompresses ASTC textures into BC7, which might reduce VRAM usage significantly on games that uses ASTC textures * Do not report R4G4 format as supported on Vulkan It was causing mario head to become white on Super Mario 64 (???) * Improvements to -1 to 1 depth mode. - Transformation is only applied on the last stage in the vertex pipeline. - Should fix some issues with geometry and tessellation (hopefully) - Reading back FragCoord Z on fragment will transform back to -1 to 1. * Geometry Shader index count from ThreadsPerInputPrimitive Generally fixes SPIR-V emitting too many triangles, may change games in OpenGL * Remove gl_FragDepth scaling This is always 0-1; the other two issues were causing the problems. Fixes regression with Xenoblade. * Add Gl StencilOp enum values to Vulkan * Update guest cache to v1.1 (due to specialization state changes) This will explode your shader cache from earlier vulkan build, but it must be done. :pensive: * Vulkan/SPIR-V support for viewport inverse * Fix typo * Don't create query pools for unsupported query types * Return of the Vector Indexing Bug One day, everyone will get this right. * Check for transform feedback query support Sometimes transform feedback is supported without the query type. * Fix gl_FragCoord.z transformation FragCoord.z is always in 0-1, even when the real depth range is -1 to 1. Turns out the only bug was geo and tess stage outputs. Fixes Pokemon Sword/Shield, possibly others. * Fix Avalonia Rebase Vulkan is currently not available on Avalonia, but the build does work and you can use opengl. * Fix headless build * Add support for BC6 and BC7 decompression, decompress all BC formats if they are not supported by the host * Fix BCn 4/5 conversion, GetTextureTarget BCn 4/5 could generate invalid data when a line's size in bytes was not divisible by 4, which both backends expect. GetTextureTarget was not creating a view with the replacement format. * Fix dependency * Fix inverse viewport transform vector type on SPIR-V * Do not require null descriptors support * If MultiViewport is not supported, do not try to set more than one viewport/scissor * Bounds check on bitmap add. * Flush queries on attachment change rather than program change Occlusion queries are usually used in a depth only pass so the attachments changing is a better indication of the query block ending. Write mask changes are also considered since some games do depth only pass by setting 0 write mask on all the colour targets. * Add support for avalonia (#6) * add avalonia support * only lock around skia flush * addressed review * cleanup * add fallback size if avalonia attempts to render but the window size is 0. read desktop scale after enabling dpi check * fix getting window handle on linux. skip render is size is 0 * Combine non-buffer with buffer image descriptor sets * Support multisample texture copy with automatic resolve on Vulkan * Remove old CompileShader methods from the Vulkan backend * Add minimal pipeline layouts that only contains used bindings They are used by helper shaders, the intention is avoiding needing to recompile the shaders (from GLSL to SPIR-V) if the bindings changes on the translated guest shaders * Pre-compile helper shader as SPIR-V, and some fixes * Remove pre-compiled shaderc binary for Windows as its no longer needed by default * Workaround RADV crash Enabling the descriptor indexing extension, even if it is not used, forces the radv driver to use "bolist". * Use RobustBufferAccess on NVIDIA gpus Avoids the SMO waterfall triangle on older NVIDIA gpus. * Implement GPU selector and expose texture recompression on the UI and config * Fix and enable background compute shader compilation Also disables warnings from shader cache pipeline misses. * Fix error due to missing subpass dependency when Attachment Write -> Shader Read barriers are added * If S8D24 is not supported, use D32FS8 * Ensure all fences are destroyed on dispose * Pre-allocate arrays up front on DescriptorSetUpdater, allows the removal of some checks * Add missing clear layer parameter after rebase * Use selected gpu from config for avalonia (#7) * use configured device * address review * Fix D32S8 copy workaround (AMD) Fixes water in Pokemon Legends Arceus on AMD GPUs. Possibly fixes other things. * Use push descriptors for uniform buffer updates (disabled for now) * Push descriptor support check, buffer redundancy checks Should make push descriptors faster, needs more testing though. * Increase light command buffer pool to 2 command buffers, throw rather than returning invalid cbs * Adjust bindings array sizes * Force submit command buffers if memory in use by its resources is high * Add workaround for AMD GCN cubemap view sins `ImageCreateCubeCompatibleBit` seems to generally break 2D array textures with mipmaps... even if they are eventually aliased as a cubemap with mipmaps. Forcing a copy here works around the issue. This could be used in future if enabling this bit reduces performance on certain GPUs. (mobile class is generally a worry) Currently also enabled on Linux as I don't know if they managed to dodge this bug (someone please tell me). Not enabled on Vega at the moment, but easy to add if the issue is there. * Add mobile, non-RX variants to the GCN regex. Also make sure that the 3 digit ones only include numbers starting with 7 or 8. * Increase image limit per stage from 8 to 16 Xenoblade Chronicles 2 was hiting the limit of 8 * Minor code cleanup * Fix NRE caused by SupportBufferUpdater calling pipeline ClearBuffer * Add gpu selector to Avalonia (#8) * Add gpu selector to avalonia settings * show backend label on window * some fixes * address review * Minor changes to the Avalonia UI * Update graphics window UI and locales. (#9) * Update xaml and update locales * locale updates Did my best here but likely needs to be checked by native speakers, especially the use of ampersands in greek, russian and turkish? * Fix locales with more (?) correct translations. * add separator to render widget * fix spanish and portuguese * Add new IdList, replaces buffer list that could not remove elements and had unbounded growth * Don't crash the settings window if Vulkan is not supported * Fix Actions menu not being clickable on GTK UI after relaunch * Rename VulkanGraphicsDevice to VulkanRenderer and Renderer to OpenGLRenderer * Fix IdList and make it not thread safe * Revert useless OpenGL format table changes * Fix headless project build * List throws ArgumentOutOfRangeException * SPIR-V: Fix tessellation * Increase shader cache version due to tessellation fix * Reduce number of Sync objects created (improves perf in some specific titles) * Fix vulkan validation errors for NPOT compressed upload and GCN workaround. * Add timestamp to the shader cache and force rebuild if host cache is outdated * Prefer Mail box present mode for popups (#11) * Prefer Mail box present mode * fix debug * switch present mode when vsync is toggled * only disable vsync on the main window * SPIR-V: Fix geometry shader input load with transform feedback * BC7 Encoder: Prefer more precision on alpha rather than RGB when alpha is 0 * Fix Avalonia build * Address initial PR feedback * Only set transform feedback outputs on last vertex stage * Address riperiperi PR feedback * Remove outdated comment * Remove unused constructor * Only throw for negative results * Throw for QueueSubmit and other errors No point in delaying the inevitable * Transform feedback decorations inside gl_PerVertex struct breaks the NVIDIA compiler * Fix some resolution scale issues * No need for two UpdateScale calls * Fix comments on SPIR-V generator project * Try to fix shader local memory size On DOOM, a shader is using local memory, but both Low and High size are 0, CRS size is 1536, it seems to store on that region? * Remove RectangleF that is now unused * Fix ImageGather with multiple offsets Needs ImageGatherExtended capability, and must use `ConstantComposite` instead of `CompositeConstruct` * Address PR feedback from jD in all projects except Avalonia * Address most of jD PR feedback on Avalonia * Remove unsafe * Fix VulkanSkiaGpu * move present mode request out of Create Swapchain method * split more parts of create swapchain * addressed reviews * addressed review * Address second batch of jD PR feedback * Fix buffer <-> image copy row length and height alignment AlignUp helper does not support NPOT alignment, and ASTC textures can have NPOT block sizes * Better fix for NPOT alignment issue * Use switch expressions on Vulkan EnumConversion Thanks jD * Fix Avalonia build * Add Vulkan selection prompt on startup * Grammar fixes on Vulkan prompt message * Add missing Vulkan migration flag Co-authored-by: riperiperi <rhy3756547@hotmail.com> Co-authored-by: Emmanuel Hansen <emmausssss@gmail.com> Co-authored-by: MutantAura <44103205+MutantAura@users.noreply.github.com>
2022-07-31 21:26:06 +00:00
public Array32<VertexAttribState> VertexAttribState;
public fixed uint Reserved11E0[13];
public uint DrawVertexArrayBeginEndInstanceFirst;
public uint DrawVertexArrayBeginEndInstanceSubsequent;
public RtControl RtControl;
public fixed uint Reserved1220[2];
public Size3D RtDepthStencilSize;
public SamplerIndex SamplerIndex;
public fixed uint Reserved1238[37];
public Boolean32 DepthTestEnable;
public fixed uint Reserved12D0[4];
public Boolean32 AlphaToCoverageDitherEnable;
public Boolean32 BlendIndependent;
public Boolean32 DepthWriteEnable;
public Boolean32 AlphaTestEnable;
public fixed uint Reserved12F0[5];
public uint VbElementU8;
public uint Reserved1308;
public CompareOp DepthTestFunc;
public float AlphaTestRef;
public CompareOp AlphaTestFunc;
public uint Reserved1318;
public ColorF BlendConstant;
public fixed uint Reserved132C[4];
public BlendStateCommon BlendStateCommon;
public Boolean32 BlendEnableCommon;
public Array8<Boolean32> BlendEnable;
public StencilTestState StencilTestState;
public fixed uint Reserved13A0[3];
public YControl YControl;
public float LineWidthSmooth;
public float LineWidthAliased;
public fixed uint Reserved13B8[27];
public uint InvalidateSamplerCacheNoWfi;
public uint InvalidateTextureHeaderCacheNoWfi;
public fixed uint Reserved142C[2];
public uint FirstVertex;
public uint FirstInstance;
public fixed uint Reserved143C[17];
public Array8<RgbHalf> BlendUcodeConstants;
public fixed uint Reserved1500[4];
public uint ClipDistanceEnable;
public uint Reserved1514;
public float PointSize;
public uint Reserved151C;
public Boolean32 PointSpriteEnable;
public fixed uint Reserved1524[3];
public uint ResetCounter;
public Boolean32 MultisampleEnable;
public Boolean32 RtDepthStencilEnable;
public uint MultisampleControl;
public fixed uint Reserved1540[4];
public GpuVa RenderEnableAddress;
public Condition RenderEnableCondition;
public PoolState SamplerPoolState;
public uint Reserved1568;
public float DepthBiasFactor;
public Boolean32 LineSmoothEnable;
public PoolState TexturePoolState;
public fixed uint Reserved1580[5];
public StencilBackTestState StencilBackTestState;
public fixed uint Reserved15A8[5];
public float DepthBiasUnits;
public fixed uint Reserved15C0[4];
public TextureMsaaMode RtMsaaMode;
public fixed uint Reserved15D4[5];
public uint VbElementU32;
public uint Reserved15EC;
public uint VbElementU16;
public fixed uint Reserved15F4[4];
public uint PointCoordReplace;
public GpuVa ShaderBaseAddress;
public uint Reserved1610;
public uint DrawEnd;
public uint DrawBegin;
public fixed uint Reserved161C[10];
public PrimitiveRestartState PrimitiveRestartState;
public fixed uint Reserved164C[95];
public IndexBufferState IndexBufferState;
public uint IndexBufferCount;
public uint DrawIndexBuffer32BeginEndInstanceFirst;
public uint DrawIndexBuffer16BeginEndInstanceFirst;
public uint DrawIndexBuffer8BeginEndInstanceFirst;
public uint DrawIndexBuffer32BeginEndInstanceSubsequent;
public uint DrawIndexBuffer16BeginEndInstanceSubsequent;
public uint DrawIndexBuffer8BeginEndInstanceSubsequent;
public fixed uint Reserved17FC[32];
public float DepthBiasClamp;
public Array16<Boolean32> VertexBufferInstanced;
public fixed uint Reserved18C0[20];
public Boolean32 VertexProgramPointSize;
public uint Reserved1914;
public FaceState FaceState;
public fixed uint Reserved1924[2];
public uint ViewportTransformEnable;
public fixed uint Reserved1930[3];
public ViewVolumeClipControl ViewVolumeClipControl;
public fixed uint Reserved1940[2];
public Boolean32 PrimitiveTypeOverrideEnable;
public fixed uint Reserved194C[9];
public PrimitiveTypeOverride PrimitiveTypeOverride;
public fixed uint Reserved1974[20];
public LogicalOpState LogicOpState;
public uint Reserved19CC;
public uint Clear;
public fixed uint Reserved19D4[11];
public Array8<RtColorMask> RtColorMask;
public fixed uint Reserved1A20[56];
public GpuVa SemaphoreAddress;
public int SemaphorePayload;
public uint SemaphoreControl;
public fixed uint Reserved1B10[60];
public Array16<VertexBufferState> VertexBufferState;
public fixed uint Reserved1D00[64];
public Array8<BlendState> BlendState;
public Array16<GpuVa> VertexBufferEndAddress;
public fixed uint Reserved1F80[32];
public Array6<ShaderState> ShaderState;
public fixed uint Reserved2180[96];
public uint SetFalcon00;
public uint SetFalcon01;
public uint SetFalcon02;
public uint SetFalcon03;
public uint SetFalcon04;
public uint SetFalcon05;
public uint SetFalcon06;
public uint SetFalcon07;
public uint SetFalcon08;
public uint SetFalcon09;
public uint SetFalcon10;
public uint SetFalcon11;
public uint SetFalcon12;
public uint SetFalcon13;
public uint SetFalcon14;
public uint SetFalcon15;
public uint SetFalcon16;
public uint SetFalcon17;
public uint SetFalcon18;
public uint SetFalcon19;
public uint SetFalcon20;
public uint SetFalcon21;
public uint SetFalcon22;
public uint SetFalcon23;
public uint SetFalcon24;
public uint SetFalcon25;
public uint SetFalcon26;
public uint SetFalcon27;
public uint SetFalcon28;
public uint SetFalcon29;
public uint SetFalcon30;
public uint SetFalcon31;
public UniformBufferState UniformBufferState;
public Array16<uint> UniformBufferUpdateData;
public fixed uint Reserved23D0[16];
public uint UniformBufferBindVertex;
public fixed uint Reserved2414[7];
public uint UniformBufferBindTessControl;
public fixed uint Reserved2434[7];
public uint UniformBufferBindTessEvaluation;
public fixed uint Reserved2454[7];
public uint UniformBufferBindGeometry;
public fixed uint Reserved2474[7];
public uint UniformBufferBindFragment;
public fixed uint Reserved2494[93];
public uint TextureBufferIndex;
public fixed uint Reserved260C[125];
public Array4<Array32<uint>> TfVaryingLocations;
public fixed uint Reserved2A00[640];
public MmeShadowScratch SetMmeShadowScratch;
#pragma warning restore CS0649
}
}