ryujinx/Ryujinx.Headless.SDL2/WindowBase.cs

430 lines
14 KiB
C#
Raw Normal View History

using ARMeilleure.Translation;
using Ryujinx.Common.Configuration;
using Ryujinx.Common.Configuration.Hid;
using Ryujinx.Common.Logging;
using Ryujinx.Graphics.GAL;
Add a Multithreading layer for the GAL, multi-thread shader compilation at runtime (#2501) * Initial Implementation About as fast as nvidia GL multithreading, can be improved with faster command queuing. * Struct based command list Speeds up a bit. Still a lot of time lost to resource copy. * Do shader init while the render thread is active. * Introduce circular span pool V1 Ideally should be able to use structs instead of references for storing these spans on commands. Will try that next. * Refactor SpanRef some more Use a struct to represent SpanRef, rather than a reference. * Flush buffers on background thread * Use a span for UpdateRenderScale. Much faster than copying the array. * Calculate command size using reflection * WIP parallel shaders * Some minor optimisation * Only 2 max refs per command now. The command with 3 refs is gone. :relieved: * Don't cast on the GPU side * Remove redundant casts, force sync on window present * Fix Shader Cache * Fix host shader save. * Fixup to work with new renderer stuff * Make command Run static, use array of delegates as lookup Profile says this takes less time than the previous way. * Bring up to date * Add settings toggle. Fix Muiltithreading Off mode. * Fix warning. * Release tracking lock for flushes * Fix Conditional Render fast path with threaded gal * Make handle iteration safe when releasing the lock This is mostly temporary. * Attempt to set backend threading on driver Only really works on nvidia before launching a game. * Fix race condition with BufferModifiedRangeList, exceptions in tracking actions * Update buffer set commands * Some cleanup * Only use stutter workaround when using opengl renderer non-threaded * Add host-conditional reservation of counter events There has always been the possibility that conditional rendering could use a query object just as it is disposed by the counter queue. This change makes it so that when the host decides to use host conditional rendering, the query object is reserved so that it cannot be deleted. Counter events can optionally start reserved, as the threaded implementation can reserve them before the backend creates them, and there would otherwise be a short amount of time where the counter queue could dispose the event before a call to reserve it could be made. * Address Feedback * Make counter flush tracked again. Hopefully does not cause any issues this time. * Wait for FlushTo on the main queue thread. Currently assumes only one thread will want to FlushTo (in this case, the GPU thread) * Add SDL2 headless integration * Add HLE macro commands. Co-authored-by: Mary <mary@mary.zone>
2021-08-26 22:31:29 +00:00
using Ryujinx.Graphics.GAL.Multithreading;
using Ryujinx.HLE.HOS.Applets;
using Ryujinx.HLE.HOS.Services.Am.AppletOE.ApplicationProxyService.ApplicationProxy.Types;
using Ryujinx.HLE.Ui;
using Ryujinx.Input;
using Ryujinx.Input.HLE;
using Ryujinx.SDL2.Common;
using System;
using System.Collections.Generic;
using System.Diagnostics;
using System.Threading;
using static SDL2.SDL;
using Switch = Ryujinx.HLE.Switch;
namespace Ryujinx.Headless.SDL2
{
abstract class WindowBase : IHostUiHandler, IDisposable
{
protected const int DefaultWidth = 1280;
protected const int DefaultHeight = 720;
private const SDL_WindowFlags DefaultFlags = SDL_WindowFlags.SDL_WINDOW_ALLOW_HIGHDPI | SDL_WindowFlags.SDL_WINDOW_RESIZABLE | SDL_WindowFlags.SDL_WINDOW_INPUT_FOCUS | SDL_WindowFlags.SDL_WINDOW_SHOWN;
private const int TargetFps = 60;
public NpadManager NpadManager { get; }
public TouchScreenManager TouchScreenManager { get; }
public Switch Device { get; private set; }
public IRenderer Renderer { get; private set; }
public event EventHandler<StatusUpdatedEventArgs> StatusUpdatedEvent;
protected IntPtr WindowHandle { get; set; }
public IHostUiTheme HostUiTheme { get; }
Avalonia UI - Part 1 (#3270) * avalonia part 1 * remove vulkan ui backend * move ui common files to ui common project * get name for oading screen from device * rebase. * review 1 * review 1.1 * review * cleanup * addressed review * use cancellation token * review * review * rebased * cancel library loading when closing window * remove star image, use fonticon instead * delete render control frame buffer when game ends. change position of fav star * addressed @Thog review * ensure the right ui is downloaded in updates * fix crash when showing not supported dialog during controller request * add prefix to artifact names * Auto-format Avalonia project * Fix input * Fix build, simplify app disposal * remove nv stutter thread * addressed review * add missing change * maintain window size if new size is zero length * add game, handheld, docked to local * reverse scale main window * Update de_DE.json * Update de_DE.json * Update de_DE.json * Update italian json * Update it_IT.json * let render timer poll with no wait * remove unused code * more unused code * enabled tiered compilation and trimming * check if window event is not closed before signaling * fix atmospher case * locale fix * locale fix * remove explicit tiered compilation declarations * Remove ) it_IT.json * Remove ) de_DE.json * Update it_IT.json * Update pt_BR locale with latest strings * Remove ')' * add more strings to locale * update locale * remove extra slash * remove extra slash * set firmware version to 0 if key's not found * fix * revert timer changes * lock on object instead * Update it_IT.json * remove unused method * add load screen text to locale * drop swap event * Update de_DE.json * Update de_DE.json * do null check when stopping emulator * Update de_DE.json * Create tr_TR.json * Add tr_TR * Add tr_TR + Turkish * Update it_IT.json * Update Ryujinx.Ava/Input/AvaloniaMappingHelper.cs Co-authored-by: Ac_K <Acoustik666@gmail.com> * Apply suggestions from code review Co-authored-by: Ac_K <Acoustik666@gmail.com> * Apply suggestions from code review Co-authored-by: Ac_K <Acoustik666@gmail.com> * addressed review * Update Ryujinx.Ava/Ui/Backend/OpenGl/OpenGlRenderTarget.cs Co-authored-by: gdkchan <gab.dark.100@gmail.com> * use avalonia's inbuilt renderer on linux * removed whitespace * workaround for queue render crash with vsync off * drop custom backend * format files * fix not closing issue * remove warnings * rebase * update avalonia library * Reposition the Text and Button on About Page * Assign build version * Remove appveyor text Co-authored-by: gdk <gab.dark.100@gmail.com> Co-authored-by: Niwu34 <67392333+Niwu34@users.noreply.github.com> Co-authored-by: Antonio Brugnolo <36473846+AntoSkate@users.noreply.github.com> Co-authored-by: aegiff <99728970+aegiff@users.noreply.github.com> Co-authored-by: Ac_K <Acoustik666@gmail.com> Co-authored-by: MostlyWhat <78652091+MostlyWhat@users.noreply.github.com>
2022-05-15 11:30:15 +00:00
public int Width { get; private set; }
public int Height { get; private set; }
protected SDL2MouseDriver MouseDriver;
private InputManager _inputManager;
private IKeyboard _keyboardInterface;
private GraphicsDebugLevel _glLogLevel;
private readonly Stopwatch _chrono;
private readonly long _ticksPerFrame;
New shader cache implementation (#3194) * New shader cache implementation * Remove some debug code * Take transform feedback varying count into account * Create shader cache directory if it does not exist + fragment output map related fixes * Remove debug code * Only check texture descriptors if the constant buffer is bound * Also check CPU VA on GetSpanMapped * Remove more unused code and move cache related code * XML docs + remove more unused methods * Better codegen for TransformFeedbackDescriptor.AsSpan * Support migration from old cache format, remove more unused code Shader cache rebuild now also rewrites the shared toc and data files * Fix migration error with BRX shaders * Add a limit to the async translation queue Avoid async translation threads not being able to keep up and the queue growing very large * Re-create specialization state on recompile This might be required if a new version of the shader translator requires more or less state, or if there is a bug related to the GPU state access * Make shader cache more error resilient * Add some missing XML docs and move GpuAccessor docs to the interface/use inheritdoc * Address early PR feedback * Fix rebase * Remove IRenderer.CompileShader and IShader interface, replace with new ShaderSource struct passed to CreateProgram directly * Handle some missing exceptions * Make shader cache purge delete both old and new shader caches * Register textures on new specialization state * Translate and compile shaders in forward order (eliminates diffs due to different binding numbers) * Limit in-flight shader compilation to the maximum number of compilation threads * Replace ParallelDiskCacheLoader state changed event with a callback function * Better handling for invalid constant buffer 1 data length * Do not create the old cache directory structure if the old cache does not exist * Constant buffer use should be per-stage. This change will invalidate existing new caches (file format version was incremented) * Replace rectangle texture with just coordinate normalization * Skip incompatible shaders that are missing texture information, instead of crashing This is required if we, for example, support new texture instruction to the shader translator, and then they allow access to textures that were not accessed before. In this scenario, the old cache entry is no longer usable * Fix coordinates normalization on cubemap textures * Check if title ID is null before combining shader cache path * More robust constant buffer address validation on spec state * More robust constant buffer address validation on spec state (2) * Regenerate shader cache with one stream, rather than one per shader. * Only create shader cache directory during initialization * Logging improvements * Proper shader program disposal * PR feedback, and add a comment on serialized structs * XML docs for RegisterTexture Co-authored-by: riperiperi <rhy3756547@hotmail.com>
2022-04-10 13:49:44 +00:00
private readonly CancellationTokenSource _gpuCancellationTokenSource;
private readonly ManualResetEvent _exitEvent;
private long _ticks;
private bool _isActive;
private bool _isStopped;
private uint _windowId;
private string _gpuVendorName;
private AspectRatio _aspectRatio;
private bool _enableMouse;
public WindowBase(InputManager inputManager, GraphicsDebugLevel glLogLevel, AspectRatio aspectRatio, bool enableMouse)
{
MouseDriver = new SDL2MouseDriver();
_inputManager = inputManager;
_inputManager.SetMouseDriver(MouseDriver);
NpadManager = _inputManager.CreateNpadManager();
TouchScreenManager = _inputManager.CreateTouchScreenManager();
_keyboardInterface = (IKeyboard)_inputManager.KeyboardDriver.GetGamepad("0");
_glLogLevel = glLogLevel;
_chrono = new Stopwatch();
_ticksPerFrame = Stopwatch.Frequency / TargetFps;
New shader cache implementation (#3194) * New shader cache implementation * Remove some debug code * Take transform feedback varying count into account * Create shader cache directory if it does not exist + fragment output map related fixes * Remove debug code * Only check texture descriptors if the constant buffer is bound * Also check CPU VA on GetSpanMapped * Remove more unused code and move cache related code * XML docs + remove more unused methods * Better codegen for TransformFeedbackDescriptor.AsSpan * Support migration from old cache format, remove more unused code Shader cache rebuild now also rewrites the shared toc and data files * Fix migration error with BRX shaders * Add a limit to the async translation queue Avoid async translation threads not being able to keep up and the queue growing very large * Re-create specialization state on recompile This might be required if a new version of the shader translator requires more or less state, or if there is a bug related to the GPU state access * Make shader cache more error resilient * Add some missing XML docs and move GpuAccessor docs to the interface/use inheritdoc * Address early PR feedback * Fix rebase * Remove IRenderer.CompileShader and IShader interface, replace with new ShaderSource struct passed to CreateProgram directly * Handle some missing exceptions * Make shader cache purge delete both old and new shader caches * Register textures on new specialization state * Translate and compile shaders in forward order (eliminates diffs due to different binding numbers) * Limit in-flight shader compilation to the maximum number of compilation threads * Replace ParallelDiskCacheLoader state changed event with a callback function * Better handling for invalid constant buffer 1 data length * Do not create the old cache directory structure if the old cache does not exist * Constant buffer use should be per-stage. This change will invalidate existing new caches (file format version was incremented) * Replace rectangle texture with just coordinate normalization * Skip incompatible shaders that are missing texture information, instead of crashing This is required if we, for example, support new texture instruction to the shader translator, and then they allow access to textures that were not accessed before. In this scenario, the old cache entry is no longer usable * Fix coordinates normalization on cubemap textures * Check if title ID is null before combining shader cache path * More robust constant buffer address validation on spec state * More robust constant buffer address validation on spec state (2) * Regenerate shader cache with one stream, rather than one per shader. * Only create shader cache directory during initialization * Logging improvements * Proper shader program disposal * PR feedback, and add a comment on serialized structs * XML docs for RegisterTexture Co-authored-by: riperiperi <rhy3756547@hotmail.com>
2022-04-10 13:49:44 +00:00
_gpuCancellationTokenSource = new CancellationTokenSource();
_exitEvent = new ManualResetEvent(false);
_aspectRatio = aspectRatio;
_enableMouse = enableMouse;
HostUiTheme = new HeadlessHostUiTheme();
SDL2Driver.Instance.Initialize();
}
public void Initialize(Switch device, List<InputConfig> inputConfigs, bool enableKeyboard, bool enableMouse)
{
Device = device;
Add a Multithreading layer for the GAL, multi-thread shader compilation at runtime (#2501) * Initial Implementation About as fast as nvidia GL multithreading, can be improved with faster command queuing. * Struct based command list Speeds up a bit. Still a lot of time lost to resource copy. * Do shader init while the render thread is active. * Introduce circular span pool V1 Ideally should be able to use structs instead of references for storing these spans on commands. Will try that next. * Refactor SpanRef some more Use a struct to represent SpanRef, rather than a reference. * Flush buffers on background thread * Use a span for UpdateRenderScale. Much faster than copying the array. * Calculate command size using reflection * WIP parallel shaders * Some minor optimisation * Only 2 max refs per command now. The command with 3 refs is gone. :relieved: * Don't cast on the GPU side * Remove redundant casts, force sync on window present * Fix Shader Cache * Fix host shader save. * Fixup to work with new renderer stuff * Make command Run static, use array of delegates as lookup Profile says this takes less time than the previous way. * Bring up to date * Add settings toggle. Fix Muiltithreading Off mode. * Fix warning. * Release tracking lock for flushes * Fix Conditional Render fast path with threaded gal * Make handle iteration safe when releasing the lock This is mostly temporary. * Attempt to set backend threading on driver Only really works on nvidia before launching a game. * Fix race condition with BufferModifiedRangeList, exceptions in tracking actions * Update buffer set commands * Some cleanup * Only use stutter workaround when using opengl renderer non-threaded * Add host-conditional reservation of counter events There has always been the possibility that conditional rendering could use a query object just as it is disposed by the counter queue. This change makes it so that when the host decides to use host conditional rendering, the query object is reserved so that it cannot be deleted. Counter events can optionally start reserved, as the threaded implementation can reserve them before the backend creates them, and there would otherwise be a short amount of time where the counter queue could dispose the event before a call to reserve it could be made. * Address Feedback * Make counter flush tracked again. Hopefully does not cause any issues this time. * Wait for FlushTo on the main queue thread. Currently assumes only one thread will want to FlushTo (in this case, the GPU thread) * Add SDL2 headless integration * Add HLE macro commands. Co-authored-by: Mary <mary@mary.zone>
2021-08-26 22:31:29 +00:00
IRenderer renderer = Device.Gpu.Renderer;
if (renderer is ThreadedRenderer tr)
{
renderer = tr.BaseRenderer;
}
Renderer = renderer;
NpadManager.Initialize(device, inputConfigs, enableKeyboard, enableMouse);
TouchScreenManager.Initialize(device);
}
private void InitializeWindow()
{
string titleNameSection = string.IsNullOrWhiteSpace(Device.Application.TitleName) ? string.Empty
: $" - {Device.Application.TitleName}";
string titleVersionSection = string.IsNullOrWhiteSpace(Device.Application.DisplayVersion) ? string.Empty
: $" v{Device.Application.DisplayVersion}";
string titleIdSection = string.IsNullOrWhiteSpace(Device.Application.TitleIdText) ? string.Empty
: $" ({Device.Application.TitleIdText.ToUpper()})";
string titleArchSection = Device.Application.TitleIs64Bit ? " (64-bit)" : " (32-bit)";
WindowHandle = SDL_CreateWindow($"Ryujinx {Program.Version}{titleNameSection}{titleVersionSection}{titleIdSection}{titleArchSection}", SDL_WINDOWPOS_UNDEFINED, SDL_WINDOWPOS_UNDEFINED, DefaultWidth, DefaultHeight, DefaultFlags | GetWindowFlags());
if (WindowHandle == IntPtr.Zero)
{
string errorMessage = $"SDL_CreateWindow failed with error \"{SDL_GetError()}\"";
Logger.Error?.Print(LogClass.Application, errorMessage);
throw new Exception(errorMessage);
}
_windowId = SDL_GetWindowID(WindowHandle);
SDL2Driver.Instance.RegisterWindow(_windowId, HandleWindowEvent);
Avalonia UI - Part 1 (#3270) * avalonia part 1 * remove vulkan ui backend * move ui common files to ui common project * get name for oading screen from device * rebase. * review 1 * review 1.1 * review * cleanup * addressed review * use cancellation token * review * review * rebased * cancel library loading when closing window * remove star image, use fonticon instead * delete render control frame buffer when game ends. change position of fav star * addressed @Thog review * ensure the right ui is downloaded in updates * fix crash when showing not supported dialog during controller request * add prefix to artifact names * Auto-format Avalonia project * Fix input * Fix build, simplify app disposal * remove nv stutter thread * addressed review * add missing change * maintain window size if new size is zero length * add game, handheld, docked to local * reverse scale main window * Update de_DE.json * Update de_DE.json * Update de_DE.json * Update italian json * Update it_IT.json * let render timer poll with no wait * remove unused code * more unused code * enabled tiered compilation and trimming * check if window event is not closed before signaling * fix atmospher case * locale fix * locale fix * remove explicit tiered compilation declarations * Remove ) it_IT.json * Remove ) de_DE.json * Update it_IT.json * Update pt_BR locale with latest strings * Remove ')' * add more strings to locale * update locale * remove extra slash * remove extra slash * set firmware version to 0 if key's not found * fix * revert timer changes * lock on object instead * Update it_IT.json * remove unused method * add load screen text to locale * drop swap event * Update de_DE.json * Update de_DE.json * do null check when stopping emulator * Update de_DE.json * Create tr_TR.json * Add tr_TR * Add tr_TR + Turkish * Update it_IT.json * Update Ryujinx.Ava/Input/AvaloniaMappingHelper.cs Co-authored-by: Ac_K <Acoustik666@gmail.com> * Apply suggestions from code review Co-authored-by: Ac_K <Acoustik666@gmail.com> * Apply suggestions from code review Co-authored-by: Ac_K <Acoustik666@gmail.com> * addressed review * Update Ryujinx.Ava/Ui/Backend/OpenGl/OpenGlRenderTarget.cs Co-authored-by: gdkchan <gab.dark.100@gmail.com> * use avalonia's inbuilt renderer on linux * removed whitespace * workaround for queue render crash with vsync off * drop custom backend * format files * fix not closing issue * remove warnings * rebase * update avalonia library * Reposition the Text and Button on About Page * Assign build version * Remove appveyor text Co-authored-by: gdk <gab.dark.100@gmail.com> Co-authored-by: Niwu34 <67392333+Niwu34@users.noreply.github.com> Co-authored-by: Antonio Brugnolo <36473846+AntoSkate@users.noreply.github.com> Co-authored-by: aegiff <99728970+aegiff@users.noreply.github.com> Co-authored-by: Ac_K <Acoustik666@gmail.com> Co-authored-by: MostlyWhat <78652091+MostlyWhat@users.noreply.github.com>
2022-05-15 11:30:15 +00:00
Width = DefaultWidth;
Height = DefaultHeight;
}
private void HandleWindowEvent(SDL_Event evnt)
{
if (evnt.type == SDL_EventType.SDL_WINDOWEVENT)
{
switch (evnt.window.windowEvent)
{
case SDL_WindowEventID.SDL_WINDOWEVENT_SIZE_CHANGED:
Avalonia UI - Part 1 (#3270) * avalonia part 1 * remove vulkan ui backend * move ui common files to ui common project * get name for oading screen from device * rebase. * review 1 * review 1.1 * review * cleanup * addressed review * use cancellation token * review * review * rebased * cancel library loading when closing window * remove star image, use fonticon instead * delete render control frame buffer when game ends. change position of fav star * addressed @Thog review * ensure the right ui is downloaded in updates * fix crash when showing not supported dialog during controller request * add prefix to artifact names * Auto-format Avalonia project * Fix input * Fix build, simplify app disposal * remove nv stutter thread * addressed review * add missing change * maintain window size if new size is zero length * add game, handheld, docked to local * reverse scale main window * Update de_DE.json * Update de_DE.json * Update de_DE.json * Update italian json * Update it_IT.json * let render timer poll with no wait * remove unused code * more unused code * enabled tiered compilation and trimming * check if window event is not closed before signaling * fix atmospher case * locale fix * locale fix * remove explicit tiered compilation declarations * Remove ) it_IT.json * Remove ) de_DE.json * Update it_IT.json * Update pt_BR locale with latest strings * Remove ')' * add more strings to locale * update locale * remove extra slash * remove extra slash * set firmware version to 0 if key's not found * fix * revert timer changes * lock on object instead * Update it_IT.json * remove unused method * add load screen text to locale * drop swap event * Update de_DE.json * Update de_DE.json * do null check when stopping emulator * Update de_DE.json * Create tr_TR.json * Add tr_TR * Add tr_TR + Turkish * Update it_IT.json * Update Ryujinx.Ava/Input/AvaloniaMappingHelper.cs Co-authored-by: Ac_K <Acoustik666@gmail.com> * Apply suggestions from code review Co-authored-by: Ac_K <Acoustik666@gmail.com> * Apply suggestions from code review Co-authored-by: Ac_K <Acoustik666@gmail.com> * addressed review * Update Ryujinx.Ava/Ui/Backend/OpenGl/OpenGlRenderTarget.cs Co-authored-by: gdkchan <gab.dark.100@gmail.com> * use avalonia's inbuilt renderer on linux * removed whitespace * workaround for queue render crash with vsync off * drop custom backend * format files * fix not closing issue * remove warnings * rebase * update avalonia library * Reposition the Text and Button on About Page * Assign build version * Remove appveyor text Co-authored-by: gdk <gab.dark.100@gmail.com> Co-authored-by: Niwu34 <67392333+Niwu34@users.noreply.github.com> Co-authored-by: Antonio Brugnolo <36473846+AntoSkate@users.noreply.github.com> Co-authored-by: aegiff <99728970+aegiff@users.noreply.github.com> Co-authored-by: Ac_K <Acoustik666@gmail.com> Co-authored-by: MostlyWhat <78652091+MostlyWhat@users.noreply.github.com>
2022-05-15 11:30:15 +00:00
Width = evnt.window.data1;
Height = evnt.window.data2;
Renderer?.Window.SetSize(Width, Height);
MouseDriver.SetClientSize(Width, Height);
break;
case SDL_WindowEventID.SDL_WINDOWEVENT_CLOSE:
Exit();
break;
default:
break;
}
}
else
{
MouseDriver.Update(evnt);
}
}
protected abstract void InitializeRenderer();
protected abstract void FinalizeRenderer();
Avalonia UI - Part 1 (#3270) * avalonia part 1 * remove vulkan ui backend * move ui common files to ui common project * get name for oading screen from device * rebase. * review 1 * review 1.1 * review * cleanup * addressed review * use cancellation token * review * review * rebased * cancel library loading when closing window * remove star image, use fonticon instead * delete render control frame buffer when game ends. change position of fav star * addressed @Thog review * ensure the right ui is downloaded in updates * fix crash when showing not supported dialog during controller request * add prefix to artifact names * Auto-format Avalonia project * Fix input * Fix build, simplify app disposal * remove nv stutter thread * addressed review * add missing change * maintain window size if new size is zero length * add game, handheld, docked to local * reverse scale main window * Update de_DE.json * Update de_DE.json * Update de_DE.json * Update italian json * Update it_IT.json * let render timer poll with no wait * remove unused code * more unused code * enabled tiered compilation and trimming * check if window event is not closed before signaling * fix atmospher case * locale fix * locale fix * remove explicit tiered compilation declarations * Remove ) it_IT.json * Remove ) de_DE.json * Update it_IT.json * Update pt_BR locale with latest strings * Remove ')' * add more strings to locale * update locale * remove extra slash * remove extra slash * set firmware version to 0 if key's not found * fix * revert timer changes * lock on object instead * Update it_IT.json * remove unused method * add load screen text to locale * drop swap event * Update de_DE.json * Update de_DE.json * do null check when stopping emulator * Update de_DE.json * Create tr_TR.json * Add tr_TR * Add tr_TR + Turkish * Update it_IT.json * Update Ryujinx.Ava/Input/AvaloniaMappingHelper.cs Co-authored-by: Ac_K <Acoustik666@gmail.com> * Apply suggestions from code review Co-authored-by: Ac_K <Acoustik666@gmail.com> * Apply suggestions from code review Co-authored-by: Ac_K <Acoustik666@gmail.com> * addressed review * Update Ryujinx.Ava/Ui/Backend/OpenGl/OpenGlRenderTarget.cs Co-authored-by: gdkchan <gab.dark.100@gmail.com> * use avalonia's inbuilt renderer on linux * removed whitespace * workaround for queue render crash with vsync off * drop custom backend * format files * fix not closing issue * remove warnings * rebase * update avalonia library * Reposition the Text and Button on About Page * Assign build version * Remove appveyor text Co-authored-by: gdk <gab.dark.100@gmail.com> Co-authored-by: Niwu34 <67392333+Niwu34@users.noreply.github.com> Co-authored-by: Antonio Brugnolo <36473846+AntoSkate@users.noreply.github.com> Co-authored-by: aegiff <99728970+aegiff@users.noreply.github.com> Co-authored-by: Ac_K <Acoustik666@gmail.com> Co-authored-by: MostlyWhat <78652091+MostlyWhat@users.noreply.github.com>
2022-05-15 11:30:15 +00:00
protected abstract void SwapBuffers(object image);
protected abstract string GetGpuVendorName();
public abstract SDL_WindowFlags GetWindowFlags();
public void Render()
{
InitializeRenderer();
Device.Gpu.Renderer.Initialize(_glLogLevel);
_gpuVendorName = GetGpuVendorName();
Add a Multithreading layer for the GAL, multi-thread shader compilation at runtime (#2501) * Initial Implementation About as fast as nvidia GL multithreading, can be improved with faster command queuing. * Struct based command list Speeds up a bit. Still a lot of time lost to resource copy. * Do shader init while the render thread is active. * Introduce circular span pool V1 Ideally should be able to use structs instead of references for storing these spans on commands. Will try that next. * Refactor SpanRef some more Use a struct to represent SpanRef, rather than a reference. * Flush buffers on background thread * Use a span for UpdateRenderScale. Much faster than copying the array. * Calculate command size using reflection * WIP parallel shaders * Some minor optimisation * Only 2 max refs per command now. The command with 3 refs is gone. :relieved: * Don't cast on the GPU side * Remove redundant casts, force sync on window present * Fix Shader Cache * Fix host shader save. * Fixup to work with new renderer stuff * Make command Run static, use array of delegates as lookup Profile says this takes less time than the previous way. * Bring up to date * Add settings toggle. Fix Muiltithreading Off mode. * Fix warning. * Release tracking lock for flushes * Fix Conditional Render fast path with threaded gal * Make handle iteration safe when releasing the lock This is mostly temporary. * Attempt to set backend threading on driver Only really works on nvidia before launching a game. * Fix race condition with BufferModifiedRangeList, exceptions in tracking actions * Update buffer set commands * Some cleanup * Only use stutter workaround when using opengl renderer non-threaded * Add host-conditional reservation of counter events There has always been the possibility that conditional rendering could use a query object just as it is disposed by the counter queue. This change makes it so that when the host decides to use host conditional rendering, the query object is reserved so that it cannot be deleted. Counter events can optionally start reserved, as the threaded implementation can reserve them before the backend creates them, and there would otherwise be a short amount of time where the counter queue could dispose the event before a call to reserve it could be made. * Address Feedback * Make counter flush tracked again. Hopefully does not cause any issues this time. * Wait for FlushTo on the main queue thread. Currently assumes only one thread will want to FlushTo (in this case, the GPU thread) * Add SDL2 headless integration * Add HLE macro commands. Co-authored-by: Mary <mary@mary.zone>
2021-08-26 22:31:29 +00:00
Device.Gpu.Renderer.RunLoop(() =>
{
Device.Gpu.SetGpuThread();
New shader cache implementation (#3194) * New shader cache implementation * Remove some debug code * Take transform feedback varying count into account * Create shader cache directory if it does not exist + fragment output map related fixes * Remove debug code * Only check texture descriptors if the constant buffer is bound * Also check CPU VA on GetSpanMapped * Remove more unused code and move cache related code * XML docs + remove more unused methods * Better codegen for TransformFeedbackDescriptor.AsSpan * Support migration from old cache format, remove more unused code Shader cache rebuild now also rewrites the shared toc and data files * Fix migration error with BRX shaders * Add a limit to the async translation queue Avoid async translation threads not being able to keep up and the queue growing very large * Re-create specialization state on recompile This might be required if a new version of the shader translator requires more or less state, or if there is a bug related to the GPU state access * Make shader cache more error resilient * Add some missing XML docs and move GpuAccessor docs to the interface/use inheritdoc * Address early PR feedback * Fix rebase * Remove IRenderer.CompileShader and IShader interface, replace with new ShaderSource struct passed to CreateProgram directly * Handle some missing exceptions * Make shader cache purge delete both old and new shader caches * Register textures on new specialization state * Translate and compile shaders in forward order (eliminates diffs due to different binding numbers) * Limit in-flight shader compilation to the maximum number of compilation threads * Replace ParallelDiskCacheLoader state changed event with a callback function * Better handling for invalid constant buffer 1 data length * Do not create the old cache directory structure if the old cache does not exist * Constant buffer use should be per-stage. This change will invalidate existing new caches (file format version was incremented) * Replace rectangle texture with just coordinate normalization * Skip incompatible shaders that are missing texture information, instead of crashing This is required if we, for example, support new texture instruction to the shader translator, and then they allow access to textures that were not accessed before. In this scenario, the old cache entry is no longer usable * Fix coordinates normalization on cubemap textures * Check if title ID is null before combining shader cache path * More robust constant buffer address validation on spec state * More robust constant buffer address validation on spec state (2) * Regenerate shader cache with one stream, rather than one per shader. * Only create shader cache directory during initialization * Logging improvements * Proper shader program disposal * PR feedback, and add a comment on serialized structs * XML docs for RegisterTexture Co-authored-by: riperiperi <rhy3756547@hotmail.com>
2022-04-10 13:49:44 +00:00
Device.Gpu.InitializeShaderCache(_gpuCancellationTokenSource.Token);
Add a Multithreading layer for the GAL, multi-thread shader compilation at runtime (#2501) * Initial Implementation About as fast as nvidia GL multithreading, can be improved with faster command queuing. * Struct based command list Speeds up a bit. Still a lot of time lost to resource copy. * Do shader init while the render thread is active. * Introduce circular span pool V1 Ideally should be able to use structs instead of references for storing these spans on commands. Will try that next. * Refactor SpanRef some more Use a struct to represent SpanRef, rather than a reference. * Flush buffers on background thread * Use a span for UpdateRenderScale. Much faster than copying the array. * Calculate command size using reflection * WIP parallel shaders * Some minor optimisation * Only 2 max refs per command now. The command with 3 refs is gone. :relieved: * Don't cast on the GPU side * Remove redundant casts, force sync on window present * Fix Shader Cache * Fix host shader save. * Fixup to work with new renderer stuff * Make command Run static, use array of delegates as lookup Profile says this takes less time than the previous way. * Bring up to date * Add settings toggle. Fix Muiltithreading Off mode. * Fix warning. * Release tracking lock for flushes * Fix Conditional Render fast path with threaded gal * Make handle iteration safe when releasing the lock This is mostly temporary. * Attempt to set backend threading on driver Only really works on nvidia before launching a game. * Fix race condition with BufferModifiedRangeList, exceptions in tracking actions * Update buffer set commands * Some cleanup * Only use stutter workaround when using opengl renderer non-threaded * Add host-conditional reservation of counter events There has always been the possibility that conditional rendering could use a query object just as it is disposed by the counter queue. This change makes it so that when the host decides to use host conditional rendering, the query object is reserved so that it cannot be deleted. Counter events can optionally start reserved, as the threaded implementation can reserve them before the backend creates them, and there would otherwise be a short amount of time where the counter queue could dispose the event before a call to reserve it could be made. * Address Feedback * Make counter flush tracked again. Hopefully does not cause any issues this time. * Wait for FlushTo on the main queue thread. Currently assumes only one thread will want to FlushTo (in this case, the GPU thread) * Add SDL2 headless integration * Add HLE macro commands. Co-authored-by: Mary <mary@mary.zone>
2021-08-26 22:31:29 +00:00
Translator.IsReadyForTranslation.Set();
Add a Multithreading layer for the GAL, multi-thread shader compilation at runtime (#2501) * Initial Implementation About as fast as nvidia GL multithreading, can be improved with faster command queuing. * Struct based command list Speeds up a bit. Still a lot of time lost to resource copy. * Do shader init while the render thread is active. * Introduce circular span pool V1 Ideally should be able to use structs instead of references for storing these spans on commands. Will try that next. * Refactor SpanRef some more Use a struct to represent SpanRef, rather than a reference. * Flush buffers on background thread * Use a span for UpdateRenderScale. Much faster than copying the array. * Calculate command size using reflection * WIP parallel shaders * Some minor optimisation * Only 2 max refs per command now. The command with 3 refs is gone. :relieved: * Don't cast on the GPU side * Remove redundant casts, force sync on window present * Fix Shader Cache * Fix host shader save. * Fixup to work with new renderer stuff * Make command Run static, use array of delegates as lookup Profile says this takes less time than the previous way. * Bring up to date * Add settings toggle. Fix Muiltithreading Off mode. * Fix warning. * Release tracking lock for flushes * Fix Conditional Render fast path with threaded gal * Make handle iteration safe when releasing the lock This is mostly temporary. * Attempt to set backend threading on driver Only really works on nvidia before launching a game. * Fix race condition with BufferModifiedRangeList, exceptions in tracking actions * Update buffer set commands * Some cleanup * Only use stutter workaround when using opengl renderer non-threaded * Add host-conditional reservation of counter events There has always been the possibility that conditional rendering could use a query object just as it is disposed by the counter queue. This change makes it so that when the host decides to use host conditional rendering, the query object is reserved so that it cannot be deleted. Counter events can optionally start reserved, as the threaded implementation can reserve them before the backend creates them, and there would otherwise be a short amount of time where the counter queue could dispose the event before a call to reserve it could be made. * Address Feedback * Make counter flush tracked again. Hopefully does not cause any issues this time. * Wait for FlushTo on the main queue thread. Currently assumes only one thread will want to FlushTo (in this case, the GPU thread) * Add SDL2 headless integration * Add HLE macro commands. Co-authored-by: Mary <mary@mary.zone>
2021-08-26 22:31:29 +00:00
while (_isActive)
{
Add a Multithreading layer for the GAL, multi-thread shader compilation at runtime (#2501) * Initial Implementation About as fast as nvidia GL multithreading, can be improved with faster command queuing. * Struct based command list Speeds up a bit. Still a lot of time lost to resource copy. * Do shader init while the render thread is active. * Introduce circular span pool V1 Ideally should be able to use structs instead of references for storing these spans on commands. Will try that next. * Refactor SpanRef some more Use a struct to represent SpanRef, rather than a reference. * Flush buffers on background thread * Use a span for UpdateRenderScale. Much faster than copying the array. * Calculate command size using reflection * WIP parallel shaders * Some minor optimisation * Only 2 max refs per command now. The command with 3 refs is gone. :relieved: * Don't cast on the GPU side * Remove redundant casts, force sync on window present * Fix Shader Cache * Fix host shader save. * Fixup to work with new renderer stuff * Make command Run static, use array of delegates as lookup Profile says this takes less time than the previous way. * Bring up to date * Add settings toggle. Fix Muiltithreading Off mode. * Fix warning. * Release tracking lock for flushes * Fix Conditional Render fast path with threaded gal * Make handle iteration safe when releasing the lock This is mostly temporary. * Attempt to set backend threading on driver Only really works on nvidia before launching a game. * Fix race condition with BufferModifiedRangeList, exceptions in tracking actions * Update buffer set commands * Some cleanup * Only use stutter workaround when using opengl renderer non-threaded * Add host-conditional reservation of counter events There has always been the possibility that conditional rendering could use a query object just as it is disposed by the counter queue. This change makes it so that when the host decides to use host conditional rendering, the query object is reserved so that it cannot be deleted. Counter events can optionally start reserved, as the threaded implementation can reserve them before the backend creates them, and there would otherwise be a short amount of time where the counter queue could dispose the event before a call to reserve it could be made. * Address Feedback * Make counter flush tracked again. Hopefully does not cause any issues this time. * Wait for FlushTo on the main queue thread. Currently assumes only one thread will want to FlushTo (in this case, the GPU thread) * Add SDL2 headless integration * Add HLE macro commands. Co-authored-by: Mary <mary@mary.zone>
2021-08-26 22:31:29 +00:00
if (_isStopped)
{
return;
}
Add a Multithreading layer for the GAL, multi-thread shader compilation at runtime (#2501) * Initial Implementation About as fast as nvidia GL multithreading, can be improved with faster command queuing. * Struct based command list Speeds up a bit. Still a lot of time lost to resource copy. * Do shader init while the render thread is active. * Introduce circular span pool V1 Ideally should be able to use structs instead of references for storing these spans on commands. Will try that next. * Refactor SpanRef some more Use a struct to represent SpanRef, rather than a reference. * Flush buffers on background thread * Use a span for UpdateRenderScale. Much faster than copying the array. * Calculate command size using reflection * WIP parallel shaders * Some minor optimisation * Only 2 max refs per command now. The command with 3 refs is gone. :relieved: * Don't cast on the GPU side * Remove redundant casts, force sync on window present * Fix Shader Cache * Fix host shader save. * Fixup to work with new renderer stuff * Make command Run static, use array of delegates as lookup Profile says this takes less time than the previous way. * Bring up to date * Add settings toggle. Fix Muiltithreading Off mode. * Fix warning. * Release tracking lock for flushes * Fix Conditional Render fast path with threaded gal * Make handle iteration safe when releasing the lock This is mostly temporary. * Attempt to set backend threading on driver Only really works on nvidia before launching a game. * Fix race condition with BufferModifiedRangeList, exceptions in tracking actions * Update buffer set commands * Some cleanup * Only use stutter workaround when using opengl renderer non-threaded * Add host-conditional reservation of counter events There has always been the possibility that conditional rendering could use a query object just as it is disposed by the counter queue. This change makes it so that when the host decides to use host conditional rendering, the query object is reserved so that it cannot be deleted. Counter events can optionally start reserved, as the threaded implementation can reserve them before the backend creates them, and there would otherwise be a short amount of time where the counter queue could dispose the event before a call to reserve it could be made. * Address Feedback * Make counter flush tracked again. Hopefully does not cause any issues this time. * Wait for FlushTo on the main queue thread. Currently assumes only one thread will want to FlushTo (in this case, the GPU thread) * Add SDL2 headless integration * Add HLE macro commands. Co-authored-by: Mary <mary@mary.zone>
2021-08-26 22:31:29 +00:00
_ticks += _chrono.ElapsedTicks;
Add a Multithreading layer for the GAL, multi-thread shader compilation at runtime (#2501) * Initial Implementation About as fast as nvidia GL multithreading, can be improved with faster command queuing. * Struct based command list Speeds up a bit. Still a lot of time lost to resource copy. * Do shader init while the render thread is active. * Introduce circular span pool V1 Ideally should be able to use structs instead of references for storing these spans on commands. Will try that next. * Refactor SpanRef some more Use a struct to represent SpanRef, rather than a reference. * Flush buffers on background thread * Use a span for UpdateRenderScale. Much faster than copying the array. * Calculate command size using reflection * WIP parallel shaders * Some minor optimisation * Only 2 max refs per command now. The command with 3 refs is gone. :relieved: * Don't cast on the GPU side * Remove redundant casts, force sync on window present * Fix Shader Cache * Fix host shader save. * Fixup to work with new renderer stuff * Make command Run static, use array of delegates as lookup Profile says this takes less time than the previous way. * Bring up to date * Add settings toggle. Fix Muiltithreading Off mode. * Fix warning. * Release tracking lock for flushes * Fix Conditional Render fast path with threaded gal * Make handle iteration safe when releasing the lock This is mostly temporary. * Attempt to set backend threading on driver Only really works on nvidia before launching a game. * Fix race condition with BufferModifiedRangeList, exceptions in tracking actions * Update buffer set commands * Some cleanup * Only use stutter workaround when using opengl renderer non-threaded * Add host-conditional reservation of counter events There has always been the possibility that conditional rendering could use a query object just as it is disposed by the counter queue. This change makes it so that when the host decides to use host conditional rendering, the query object is reserved so that it cannot be deleted. Counter events can optionally start reserved, as the threaded implementation can reserve them before the backend creates them, and there would otherwise be a short amount of time where the counter queue could dispose the event before a call to reserve it could be made. * Address Feedback * Make counter flush tracked again. Hopefully does not cause any issues this time. * Wait for FlushTo on the main queue thread. Currently assumes only one thread will want to FlushTo (in this case, the GPU thread) * Add SDL2 headless integration * Add HLE macro commands. Co-authored-by: Mary <mary@mary.zone>
2021-08-26 22:31:29 +00:00
_chrono.Restart();
if (Device.WaitFifo())
{
Add a Multithreading layer for the GAL, multi-thread shader compilation at runtime (#2501) * Initial Implementation About as fast as nvidia GL multithreading, can be improved with faster command queuing. * Struct based command list Speeds up a bit. Still a lot of time lost to resource copy. * Do shader init while the render thread is active. * Introduce circular span pool V1 Ideally should be able to use structs instead of references for storing these spans on commands. Will try that next. * Refactor SpanRef some more Use a struct to represent SpanRef, rather than a reference. * Flush buffers on background thread * Use a span for UpdateRenderScale. Much faster than copying the array. * Calculate command size using reflection * WIP parallel shaders * Some minor optimisation * Only 2 max refs per command now. The command with 3 refs is gone. :relieved: * Don't cast on the GPU side * Remove redundant casts, force sync on window present * Fix Shader Cache * Fix host shader save. * Fixup to work with new renderer stuff * Make command Run static, use array of delegates as lookup Profile says this takes less time than the previous way. * Bring up to date * Add settings toggle. Fix Muiltithreading Off mode. * Fix warning. * Release tracking lock for flushes * Fix Conditional Render fast path with threaded gal * Make handle iteration safe when releasing the lock This is mostly temporary. * Attempt to set backend threading on driver Only really works on nvidia before launching a game. * Fix race condition with BufferModifiedRangeList, exceptions in tracking actions * Update buffer set commands * Some cleanup * Only use stutter workaround when using opengl renderer non-threaded * Add host-conditional reservation of counter events There has always been the possibility that conditional rendering could use a query object just as it is disposed by the counter queue. This change makes it so that when the host decides to use host conditional rendering, the query object is reserved so that it cannot be deleted. Counter events can optionally start reserved, as the threaded implementation can reserve them before the backend creates them, and there would otherwise be a short amount of time where the counter queue could dispose the event before a call to reserve it could be made. * Address Feedback * Make counter flush tracked again. Hopefully does not cause any issues this time. * Wait for FlushTo on the main queue thread. Currently assumes only one thread will want to FlushTo (in this case, the GPU thread) * Add SDL2 headless integration * Add HLE macro commands. Co-authored-by: Mary <mary@mary.zone>
2021-08-26 22:31:29 +00:00
Device.Statistics.RecordFifoStart();
Device.ProcessFrame();
Device.Statistics.RecordFifoEnd();
}
Add a Multithreading layer for the GAL, multi-thread shader compilation at runtime (#2501) * Initial Implementation About as fast as nvidia GL multithreading, can be improved with faster command queuing. * Struct based command list Speeds up a bit. Still a lot of time lost to resource copy. * Do shader init while the render thread is active. * Introduce circular span pool V1 Ideally should be able to use structs instead of references for storing these spans on commands. Will try that next. * Refactor SpanRef some more Use a struct to represent SpanRef, rather than a reference. * Flush buffers on background thread * Use a span for UpdateRenderScale. Much faster than copying the array. * Calculate command size using reflection * WIP parallel shaders * Some minor optimisation * Only 2 max refs per command now. The command with 3 refs is gone. :relieved: * Don't cast on the GPU side * Remove redundant casts, force sync on window present * Fix Shader Cache * Fix host shader save. * Fixup to work with new renderer stuff * Make command Run static, use array of delegates as lookup Profile says this takes less time than the previous way. * Bring up to date * Add settings toggle. Fix Muiltithreading Off mode. * Fix warning. * Release tracking lock for flushes * Fix Conditional Render fast path with threaded gal * Make handle iteration safe when releasing the lock This is mostly temporary. * Attempt to set backend threading on driver Only really works on nvidia before launching a game. * Fix race condition with BufferModifiedRangeList, exceptions in tracking actions * Update buffer set commands * Some cleanup * Only use stutter workaround when using opengl renderer non-threaded * Add host-conditional reservation of counter events There has always been the possibility that conditional rendering could use a query object just as it is disposed by the counter queue. This change makes it so that when the host decides to use host conditional rendering, the query object is reserved so that it cannot be deleted. Counter events can optionally start reserved, as the threaded implementation can reserve them before the backend creates them, and there would otherwise be a short amount of time where the counter queue could dispose the event before a call to reserve it could be made. * Address Feedback * Make counter flush tracked again. Hopefully does not cause any issues this time. * Wait for FlushTo on the main queue thread. Currently assumes only one thread will want to FlushTo (in this case, the GPU thread) * Add SDL2 headless integration * Add HLE macro commands. Co-authored-by: Mary <mary@mary.zone>
2021-08-26 22:31:29 +00:00
while (Device.ConsumeFrameAvailable())
{
Avalonia UI - Part 1 (#3270) * avalonia part 1 * remove vulkan ui backend * move ui common files to ui common project * get name for oading screen from device * rebase. * review 1 * review 1.1 * review * cleanup * addressed review * use cancellation token * review * review * rebased * cancel library loading when closing window * remove star image, use fonticon instead * delete render control frame buffer when game ends. change position of fav star * addressed @Thog review * ensure the right ui is downloaded in updates * fix crash when showing not supported dialog during controller request * add prefix to artifact names * Auto-format Avalonia project * Fix input * Fix build, simplify app disposal * remove nv stutter thread * addressed review * add missing change * maintain window size if new size is zero length * add game, handheld, docked to local * reverse scale main window * Update de_DE.json * Update de_DE.json * Update de_DE.json * Update italian json * Update it_IT.json * let render timer poll with no wait * remove unused code * more unused code * enabled tiered compilation and trimming * check if window event is not closed before signaling * fix atmospher case * locale fix * locale fix * remove explicit tiered compilation declarations * Remove ) it_IT.json * Remove ) de_DE.json * Update it_IT.json * Update pt_BR locale with latest strings * Remove ')' * add more strings to locale * update locale * remove extra slash * remove extra slash * set firmware version to 0 if key's not found * fix * revert timer changes * lock on object instead * Update it_IT.json * remove unused method * add load screen text to locale * drop swap event * Update de_DE.json * Update de_DE.json * do null check when stopping emulator * Update de_DE.json * Create tr_TR.json * Add tr_TR * Add tr_TR + Turkish * Update it_IT.json * Update Ryujinx.Ava/Input/AvaloniaMappingHelper.cs Co-authored-by: Ac_K <Acoustik666@gmail.com> * Apply suggestions from code review Co-authored-by: Ac_K <Acoustik666@gmail.com> * Apply suggestions from code review Co-authored-by: Ac_K <Acoustik666@gmail.com> * addressed review * Update Ryujinx.Ava/Ui/Backend/OpenGl/OpenGlRenderTarget.cs Co-authored-by: gdkchan <gab.dark.100@gmail.com> * use avalonia's inbuilt renderer on linux * removed whitespace * workaround for queue render crash with vsync off * drop custom backend * format files * fix not closing issue * remove warnings * rebase * update avalonia library * Reposition the Text and Button on About Page * Assign build version * Remove appveyor text Co-authored-by: gdk <gab.dark.100@gmail.com> Co-authored-by: Niwu34 <67392333+Niwu34@users.noreply.github.com> Co-authored-by: Antonio Brugnolo <36473846+AntoSkate@users.noreply.github.com> Co-authored-by: aegiff <99728970+aegiff@users.noreply.github.com> Co-authored-by: Ac_K <Acoustik666@gmail.com> Co-authored-by: MostlyWhat <78652091+MostlyWhat@users.noreply.github.com>
2022-05-15 11:30:15 +00:00
Device.PresentFrame((texture) => { SwapBuffers(texture); });
Add a Multithreading layer for the GAL, multi-thread shader compilation at runtime (#2501) * Initial Implementation About as fast as nvidia GL multithreading, can be improved with faster command queuing. * Struct based command list Speeds up a bit. Still a lot of time lost to resource copy. * Do shader init while the render thread is active. * Introduce circular span pool V1 Ideally should be able to use structs instead of references for storing these spans on commands. Will try that next. * Refactor SpanRef some more Use a struct to represent SpanRef, rather than a reference. * Flush buffers on background thread * Use a span for UpdateRenderScale. Much faster than copying the array. * Calculate command size using reflection * WIP parallel shaders * Some minor optimisation * Only 2 max refs per command now. The command with 3 refs is gone. :relieved: * Don't cast on the GPU side * Remove redundant casts, force sync on window present * Fix Shader Cache * Fix host shader save. * Fixup to work with new renderer stuff * Make command Run static, use array of delegates as lookup Profile says this takes less time than the previous way. * Bring up to date * Add settings toggle. Fix Muiltithreading Off mode. * Fix warning. * Release tracking lock for flushes * Fix Conditional Render fast path with threaded gal * Make handle iteration safe when releasing the lock This is mostly temporary. * Attempt to set backend threading on driver Only really works on nvidia before launching a game. * Fix race condition with BufferModifiedRangeList, exceptions in tracking actions * Update buffer set commands * Some cleanup * Only use stutter workaround when using opengl renderer non-threaded * Add host-conditional reservation of counter events There has always been the possibility that conditional rendering could use a query object just as it is disposed by the counter queue. This change makes it so that when the host decides to use host conditional rendering, the query object is reserved so that it cannot be deleted. Counter events can optionally start reserved, as the threaded implementation can reserve them before the backend creates them, and there would otherwise be a short amount of time where the counter queue could dispose the event before a call to reserve it could be made. * Address Feedback * Make counter flush tracked again. Hopefully does not cause any issues this time. * Wait for FlushTo on the main queue thread. Currently assumes only one thread will want to FlushTo (in this case, the GPU thread) * Add SDL2 headless integration * Add HLE macro commands. Co-authored-by: Mary <mary@mary.zone>
2021-08-26 22:31:29 +00:00
}
Add a Multithreading layer for the GAL, multi-thread shader compilation at runtime (#2501) * Initial Implementation About as fast as nvidia GL multithreading, can be improved with faster command queuing. * Struct based command list Speeds up a bit. Still a lot of time lost to resource copy. * Do shader init while the render thread is active. * Introduce circular span pool V1 Ideally should be able to use structs instead of references for storing these spans on commands. Will try that next. * Refactor SpanRef some more Use a struct to represent SpanRef, rather than a reference. * Flush buffers on background thread * Use a span for UpdateRenderScale. Much faster than copying the array. * Calculate command size using reflection * WIP parallel shaders * Some minor optimisation * Only 2 max refs per command now. The command with 3 refs is gone. :relieved: * Don't cast on the GPU side * Remove redundant casts, force sync on window present * Fix Shader Cache * Fix host shader save. * Fixup to work with new renderer stuff * Make command Run static, use array of delegates as lookup Profile says this takes less time than the previous way. * Bring up to date * Add settings toggle. Fix Muiltithreading Off mode. * Fix warning. * Release tracking lock for flushes * Fix Conditional Render fast path with threaded gal * Make handle iteration safe when releasing the lock This is mostly temporary. * Attempt to set backend threading on driver Only really works on nvidia before launching a game. * Fix race condition with BufferModifiedRangeList, exceptions in tracking actions * Update buffer set commands * Some cleanup * Only use stutter workaround when using opengl renderer non-threaded * Add host-conditional reservation of counter events There has always been the possibility that conditional rendering could use a query object just as it is disposed by the counter queue. This change makes it so that when the host decides to use host conditional rendering, the query object is reserved so that it cannot be deleted. Counter events can optionally start reserved, as the threaded implementation can reserve them before the backend creates them, and there would otherwise be a short amount of time where the counter queue could dispose the event before a call to reserve it could be made. * Address Feedback * Make counter flush tracked again. Hopefully does not cause any issues this time. * Wait for FlushTo on the main queue thread. Currently assumes only one thread will want to FlushTo (in this case, the GPU thread) * Add SDL2 headless integration * Add HLE macro commands. Co-authored-by: Mary <mary@mary.zone>
2021-08-26 22:31:29 +00:00
if (_ticks >= _ticksPerFrame)
{
string dockedMode = Device.System.State.DockedMode ? "Docked" : "Handheld";
float scale = Graphics.Gpu.GraphicsConfig.ResScale;
if (scale != 1)
{
dockedMode += $" ({scale}x)";
}
StatusUpdatedEvent?.Invoke(this, new StatusUpdatedEventArgs(
Device.EnableDeviceVsync,
dockedMode,
Device.Configuration.AspectRatio.ToText(),
$"Game: {Device.Statistics.GetGameFrameRate():00.00} FPS ({Device.Statistics.GetGameFrameTime():00.00} ms)",
Add a Multithreading layer for the GAL, multi-thread shader compilation at runtime (#2501) * Initial Implementation About as fast as nvidia GL multithreading, can be improved with faster command queuing. * Struct based command list Speeds up a bit. Still a lot of time lost to resource copy. * Do shader init while the render thread is active. * Introduce circular span pool V1 Ideally should be able to use structs instead of references for storing these spans on commands. Will try that next. * Refactor SpanRef some more Use a struct to represent SpanRef, rather than a reference. * Flush buffers on background thread * Use a span for UpdateRenderScale. Much faster than copying the array. * Calculate command size using reflection * WIP parallel shaders * Some minor optimisation * Only 2 max refs per command now. The command with 3 refs is gone. :relieved: * Don't cast on the GPU side * Remove redundant casts, force sync on window present * Fix Shader Cache * Fix host shader save. * Fixup to work with new renderer stuff * Make command Run static, use array of delegates as lookup Profile says this takes less time than the previous way. * Bring up to date * Add settings toggle. Fix Muiltithreading Off mode. * Fix warning. * Release tracking lock for flushes * Fix Conditional Render fast path with threaded gal * Make handle iteration safe when releasing the lock This is mostly temporary. * Attempt to set backend threading on driver Only really works on nvidia before launching a game. * Fix race condition with BufferModifiedRangeList, exceptions in tracking actions * Update buffer set commands * Some cleanup * Only use stutter workaround when using opengl renderer non-threaded * Add host-conditional reservation of counter events There has always been the possibility that conditional rendering could use a query object just as it is disposed by the counter queue. This change makes it so that when the host decides to use host conditional rendering, the query object is reserved so that it cannot be deleted. Counter events can optionally start reserved, as the threaded implementation can reserve them before the backend creates them, and there would otherwise be a short amount of time where the counter queue could dispose the event before a call to reserve it could be made. * Address Feedback * Make counter flush tracked again. Hopefully does not cause any issues this time. * Wait for FlushTo on the main queue thread. Currently assumes only one thread will want to FlushTo (in this case, the GPU thread) * Add SDL2 headless integration * Add HLE macro commands. Co-authored-by: Mary <mary@mary.zone>
2021-08-26 22:31:29 +00:00
$"FIFO: {Device.Statistics.GetFifoPercent():0.00} %",
$"GPU: {_gpuVendorName}"));
_ticks = Math.Min(_ticks - _ticksPerFrame, _ticksPerFrame);
}
}
Add a Multithreading layer for the GAL, multi-thread shader compilation at runtime (#2501) * Initial Implementation About as fast as nvidia GL multithreading, can be improved with faster command queuing. * Struct based command list Speeds up a bit. Still a lot of time lost to resource copy. * Do shader init while the render thread is active. * Introduce circular span pool V1 Ideally should be able to use structs instead of references for storing these spans on commands. Will try that next. * Refactor SpanRef some more Use a struct to represent SpanRef, rather than a reference. * Flush buffers on background thread * Use a span for UpdateRenderScale. Much faster than copying the array. * Calculate command size using reflection * WIP parallel shaders * Some minor optimisation * Only 2 max refs per command now. The command with 3 refs is gone. :relieved: * Don't cast on the GPU side * Remove redundant casts, force sync on window present * Fix Shader Cache * Fix host shader save. * Fixup to work with new renderer stuff * Make command Run static, use array of delegates as lookup Profile says this takes less time than the previous way. * Bring up to date * Add settings toggle. Fix Muiltithreading Off mode. * Fix warning. * Release tracking lock for flushes * Fix Conditional Render fast path with threaded gal * Make handle iteration safe when releasing the lock This is mostly temporary. * Attempt to set backend threading on driver Only really works on nvidia before launching a game. * Fix race condition with BufferModifiedRangeList, exceptions in tracking actions * Update buffer set commands * Some cleanup * Only use stutter workaround when using opengl renderer non-threaded * Add host-conditional reservation of counter events There has always been the possibility that conditional rendering could use a query object just as it is disposed by the counter queue. This change makes it so that when the host decides to use host conditional rendering, the query object is reserved so that it cannot be deleted. Counter events can optionally start reserved, as the threaded implementation can reserve them before the backend creates them, and there would otherwise be a short amount of time where the counter queue could dispose the event before a call to reserve it could be made. * Address Feedback * Make counter flush tracked again. Hopefully does not cause any issues this time. * Wait for FlushTo on the main queue thread. Currently assumes only one thread will want to FlushTo (in this case, the GPU thread) * Add SDL2 headless integration * Add HLE macro commands. Co-authored-by: Mary <mary@mary.zone>
2021-08-26 22:31:29 +00:00
});
FinalizeRenderer();
}
public void Exit()
{
TouchScreenManager?.Dispose();
NpadManager?.Dispose();
if (_isStopped)
{
return;
}
New shader cache implementation (#3194) * New shader cache implementation * Remove some debug code * Take transform feedback varying count into account * Create shader cache directory if it does not exist + fragment output map related fixes * Remove debug code * Only check texture descriptors if the constant buffer is bound * Also check CPU VA on GetSpanMapped * Remove more unused code and move cache related code * XML docs + remove more unused methods * Better codegen for TransformFeedbackDescriptor.AsSpan * Support migration from old cache format, remove more unused code Shader cache rebuild now also rewrites the shared toc and data files * Fix migration error with BRX shaders * Add a limit to the async translation queue Avoid async translation threads not being able to keep up and the queue growing very large * Re-create specialization state on recompile This might be required if a new version of the shader translator requires more or less state, or if there is a bug related to the GPU state access * Make shader cache more error resilient * Add some missing XML docs and move GpuAccessor docs to the interface/use inheritdoc * Address early PR feedback * Fix rebase * Remove IRenderer.CompileShader and IShader interface, replace with new ShaderSource struct passed to CreateProgram directly * Handle some missing exceptions * Make shader cache purge delete both old and new shader caches * Register textures on new specialization state * Translate and compile shaders in forward order (eliminates diffs due to different binding numbers) * Limit in-flight shader compilation to the maximum number of compilation threads * Replace ParallelDiskCacheLoader state changed event with a callback function * Better handling for invalid constant buffer 1 data length * Do not create the old cache directory structure if the old cache does not exist * Constant buffer use should be per-stage. This change will invalidate existing new caches (file format version was incremented) * Replace rectangle texture with just coordinate normalization * Skip incompatible shaders that are missing texture information, instead of crashing This is required if we, for example, support new texture instruction to the shader translator, and then they allow access to textures that were not accessed before. In this scenario, the old cache entry is no longer usable * Fix coordinates normalization on cubemap textures * Check if title ID is null before combining shader cache path * More robust constant buffer address validation on spec state * More robust constant buffer address validation on spec state (2) * Regenerate shader cache with one stream, rather than one per shader. * Only create shader cache directory during initialization * Logging improvements * Proper shader program disposal * PR feedback, and add a comment on serialized structs * XML docs for RegisterTexture Co-authored-by: riperiperi <rhy3756547@hotmail.com>
2022-04-10 13:49:44 +00:00
_gpuCancellationTokenSource.Cancel();
_isStopped = true;
_isActive = false;
_exitEvent.WaitOne();
_exitEvent.Dispose();
}
public void MainLoop()
{
while (_isActive)
{
UpdateFrame();
SDL_PumpEvents();
// Polling becomes expensive if it's not slept
Thread.Sleep(1);
}
_exitEvent.Set();
}
private void NVStutterWorkaround()
{
while (_isActive)
{
// When NVIDIA Threaded Optimization is on, the driver will snapshot all threads in the system whenever the application creates any new ones.
// The ThreadPool has something called a "GateThread" which terminates itself after some inactivity.
// However, it immediately starts up again, since the rules regarding when to terminate and when to start differ.
// This creates a new thread every second or so.
// The main problem with this is that the thread snapshot can take 70ms, is on the OpenGL thread and will delay rendering any graphics.
// This is a little over budget on a frame time of 16ms, so creates a large stutter.
// The solution is to keep the ThreadPool active so that it never has a reason to terminate the GateThread.
// TODO: This should be removed when the issue with the GateThread is resolved.
ThreadPool.QueueUserWorkItem((state) => { });
Thread.Sleep(300);
}
}
private bool UpdateFrame()
{
if (!_isActive)
{
return true;
}
if (_isStopped)
{
return false;
}
NpadManager.Update();
// Touchscreen
bool hasTouch = false;
// Get screen touch position
if (!_enableMouse)
{
hasTouch = TouchScreenManager.Update(true, (_inputManager.MouseDriver as SDL2MouseDriver).IsButtonPressed(MouseButton.Button1), _aspectRatio.ToFloat());
}
if (!hasTouch)
{
TouchScreenManager.Update(false);
}
Device.Hid.DebugPad.Update();
return true;
}
public void Execute()
{
_chrono.Restart();
_isActive = true;
InitializeWindow();
Thread renderLoopThread = new Thread(Render)
{
Name = "GUI.RenderLoop"
};
renderLoopThread.Start();
Add a Multithreading layer for the GAL, multi-thread shader compilation at runtime (#2501) * Initial Implementation About as fast as nvidia GL multithreading, can be improved with faster command queuing. * Struct based command list Speeds up a bit. Still a lot of time lost to resource copy. * Do shader init while the render thread is active. * Introduce circular span pool V1 Ideally should be able to use structs instead of references for storing these spans on commands. Will try that next. * Refactor SpanRef some more Use a struct to represent SpanRef, rather than a reference. * Flush buffers on background thread * Use a span for UpdateRenderScale. Much faster than copying the array. * Calculate command size using reflection * WIP parallel shaders * Some minor optimisation * Only 2 max refs per command now. The command with 3 refs is gone. :relieved: * Don't cast on the GPU side * Remove redundant casts, force sync on window present * Fix Shader Cache * Fix host shader save. * Fixup to work with new renderer stuff * Make command Run static, use array of delegates as lookup Profile says this takes less time than the previous way. * Bring up to date * Add settings toggle. Fix Muiltithreading Off mode. * Fix warning. * Release tracking lock for flushes * Fix Conditional Render fast path with threaded gal * Make handle iteration safe when releasing the lock This is mostly temporary. * Attempt to set backend threading on driver Only really works on nvidia before launching a game. * Fix race condition with BufferModifiedRangeList, exceptions in tracking actions * Update buffer set commands * Some cleanup * Only use stutter workaround when using opengl renderer non-threaded * Add host-conditional reservation of counter events There has always been the possibility that conditional rendering could use a query object just as it is disposed by the counter queue. This change makes it so that when the host decides to use host conditional rendering, the query object is reserved so that it cannot be deleted. Counter events can optionally start reserved, as the threaded implementation can reserve them before the backend creates them, and there would otherwise be a short amount of time where the counter queue could dispose the event before a call to reserve it could be made. * Address Feedback * Make counter flush tracked again. Hopefully does not cause any issues this time. * Wait for FlushTo on the main queue thread. Currently assumes only one thread will want to FlushTo (in this case, the GPU thread) * Add SDL2 headless integration * Add HLE macro commands. Co-authored-by: Mary <mary@mary.zone>
2021-08-26 22:31:29 +00:00
Thread nvStutterWorkaround = null;
if (Renderer is Graphics.OpenGL.Renderer)
{
Add a Multithreading layer for the GAL, multi-thread shader compilation at runtime (#2501) * Initial Implementation About as fast as nvidia GL multithreading, can be improved with faster command queuing. * Struct based command list Speeds up a bit. Still a lot of time lost to resource copy. * Do shader init while the render thread is active. * Introduce circular span pool V1 Ideally should be able to use structs instead of references for storing these spans on commands. Will try that next. * Refactor SpanRef some more Use a struct to represent SpanRef, rather than a reference. * Flush buffers on background thread * Use a span for UpdateRenderScale. Much faster than copying the array. * Calculate command size using reflection * WIP parallel shaders * Some minor optimisation * Only 2 max refs per command now. The command with 3 refs is gone. :relieved: * Don't cast on the GPU side * Remove redundant casts, force sync on window present * Fix Shader Cache * Fix host shader save. * Fixup to work with new renderer stuff * Make command Run static, use array of delegates as lookup Profile says this takes less time than the previous way. * Bring up to date * Add settings toggle. Fix Muiltithreading Off mode. * Fix warning. * Release tracking lock for flushes * Fix Conditional Render fast path with threaded gal * Make handle iteration safe when releasing the lock This is mostly temporary. * Attempt to set backend threading on driver Only really works on nvidia before launching a game. * Fix race condition with BufferModifiedRangeList, exceptions in tracking actions * Update buffer set commands * Some cleanup * Only use stutter workaround when using opengl renderer non-threaded * Add host-conditional reservation of counter events There has always been the possibility that conditional rendering could use a query object just as it is disposed by the counter queue. This change makes it so that when the host decides to use host conditional rendering, the query object is reserved so that it cannot be deleted. Counter events can optionally start reserved, as the threaded implementation can reserve them before the backend creates them, and there would otherwise be a short amount of time where the counter queue could dispose the event before a call to reserve it could be made. * Address Feedback * Make counter flush tracked again. Hopefully does not cause any issues this time. * Wait for FlushTo on the main queue thread. Currently assumes only one thread will want to FlushTo (in this case, the GPU thread) * Add SDL2 headless integration * Add HLE macro commands. Co-authored-by: Mary <mary@mary.zone>
2021-08-26 22:31:29 +00:00
nvStutterWorkaround = new Thread(NVStutterWorkaround)
{
Name = "GUI.NVStutterWorkaround"
};
nvStutterWorkaround.Start();
}
MainLoop();
renderLoopThread.Join();
Add a Multithreading layer for the GAL, multi-thread shader compilation at runtime (#2501) * Initial Implementation About as fast as nvidia GL multithreading, can be improved with faster command queuing. * Struct based command list Speeds up a bit. Still a lot of time lost to resource copy. * Do shader init while the render thread is active. * Introduce circular span pool V1 Ideally should be able to use structs instead of references for storing these spans on commands. Will try that next. * Refactor SpanRef some more Use a struct to represent SpanRef, rather than a reference. * Flush buffers on background thread * Use a span for UpdateRenderScale. Much faster than copying the array. * Calculate command size using reflection * WIP parallel shaders * Some minor optimisation * Only 2 max refs per command now. The command with 3 refs is gone. :relieved: * Don't cast on the GPU side * Remove redundant casts, force sync on window present * Fix Shader Cache * Fix host shader save. * Fixup to work with new renderer stuff * Make command Run static, use array of delegates as lookup Profile says this takes less time than the previous way. * Bring up to date * Add settings toggle. Fix Muiltithreading Off mode. * Fix warning. * Release tracking lock for flushes * Fix Conditional Render fast path with threaded gal * Make handle iteration safe when releasing the lock This is mostly temporary. * Attempt to set backend threading on driver Only really works on nvidia before launching a game. * Fix race condition with BufferModifiedRangeList, exceptions in tracking actions * Update buffer set commands * Some cleanup * Only use stutter workaround when using opengl renderer non-threaded * Add host-conditional reservation of counter events There has always been the possibility that conditional rendering could use a query object just as it is disposed by the counter queue. This change makes it so that when the host decides to use host conditional rendering, the query object is reserved so that it cannot be deleted. Counter events can optionally start reserved, as the threaded implementation can reserve them before the backend creates them, and there would otherwise be a short amount of time where the counter queue could dispose the event before a call to reserve it could be made. * Address Feedback * Make counter flush tracked again. Hopefully does not cause any issues this time. * Wait for FlushTo on the main queue thread. Currently assumes only one thread will want to FlushTo (in this case, the GPU thread) * Add SDL2 headless integration * Add HLE macro commands. Co-authored-by: Mary <mary@mary.zone>
2021-08-26 22:31:29 +00:00
nvStutterWorkaround?.Join();
Exit();
}
public bool DisplayInputDialog(SoftwareKeyboardUiArgs args, out string userText)
{
// SDL2 doesn't support input dialogs
userText = "Ryujinx";
return true;
}
public bool DisplayMessageDialog(string title, string message)
{
SDL_ShowSimpleMessageBox(SDL_MessageBoxFlags.SDL_MESSAGEBOX_INFORMATION, title, message, WindowHandle);
return true;
}
public bool DisplayMessageDialog(ControllerAppletUiArgs args)
{
string playerCount = args.PlayerCountMin == args.PlayerCountMax ? $"exactly {args.PlayerCountMin}" : $"{args.PlayerCountMin}-{args.PlayerCountMax}";
string message = $"Application requests {playerCount} player(s) with:\n\n"
+ $"TYPES: {args.SupportedStyles}\n\n"
+ $"PLAYERS: {string.Join(", ", args.SupportedPlayers)}\n\n"
+ (args.IsDocked ? "Docked mode set. Handheld is also invalid.\n\n" : "")
+ "Please reconfigure Input now and then press OK.";
return DisplayMessageDialog("Controller Applet", message);
}
public IDynamicTextInputHandler CreateDynamicTextInputHandler()
{
return new HeadlessDynamicTextInputHandler();
}
public void ExecuteProgram(Switch device, ProgramSpecifyKind kind, ulong value)
{
device.Configuration.UserChannelPersistence.ExecuteProgram(kind, value);
Exit();
}
public bool DisplayErrorAppletDialog(string title, string message, string[] buttonsText)
{
SDL_MessageBoxData data = new SDL_MessageBoxData
{
title = title,
message = message,
buttons = new SDL_MessageBoxButtonData[buttonsText.Length],
numbuttons = buttonsText.Length,
window = WindowHandle
};
for (int i = 0; i < buttonsText.Length; i++)
{
data.buttons[i] = new SDL_MessageBoxButtonData
{
buttonid = i,
text = buttonsText[i]
};
}
SDL_ShowMessageBox(ref data, out int _);
return true;
}
public void Dispose()
{
Dispose(true);
}
protected virtual void Dispose(bool disposing)
{
if (disposing)
{
_isActive = false;
TouchScreenManager?.Dispose();
NpadManager.Dispose();
SDL2Driver.Instance.UnregisterWindow(_windowId);
SDL_DestroyWindow(WindowHandle);
SDL2Driver.Instance.Dispose();
}
}
}
}