mirror of
https://github.com/ryujinx-mirror/ryujinx.git
synced 2024-11-22 18:15:11 +00:00
e20abbf9cc
* Vulkan: Don't flush commands when creating most sync When the WaitForIdle method is called, we create sync as some internal GPU method may read back written buffer data. Some games randomly intersperse compute dispatch into their render passes, which result in this happening an unbounded number of times depending on how many times they run compute. Creating sync in Vulkan is expensive, as we need to flush the current command buffer so that it can be waited on. We have a limited number of active command buffers due to how we track resource usage, so submitting too many command buffers will force us to wait for them to return to the pool. This PR allows less "important" sync (things which are less likely to be waited on) to wait on a command buffer's result without submitting it, instead relying on AutoFlush or another, more important sync to flush it later on. Because of the possibility of us waiting for a command buffer that hasn't submitted yet, any thread needs to be able to force the active command buffer to submit. The ability to do this has been added to the backend multithreading via an "Interrupt", though it is not supported without multithreading. OpenGL drivers should already be doing something similar so they don't blow up when creating lots of sync, which is why this hasn't been a problem for these games over there. Improves Vulkan performance on Xenoblade DE, Pokemon Scarlet/Violet, and Zelda BOTW (still another large issue here) * Add strict argument This is technically a separate concern from whether the sync is a host syncpoint. * Remove _interrupted variable * Actually wait for the invoke This is required by AMD GPUs, and also may have caused some issues on other GPUs. * Remove unused using. * I don't know why it added these ones. * Address Feedback * Fix typo
397 lines
No EOL
14 KiB
C#
397 lines
No EOL
14 KiB
C#
using Ryujinx.Common;
|
|
using Ryujinx.Graphics.GAL;
|
|
using Ryujinx.Graphics.Gpu.Engine.GPFifo;
|
|
using Ryujinx.Graphics.Gpu.Memory;
|
|
using Ryujinx.Graphics.Gpu.Shader;
|
|
using Ryujinx.Graphics.Gpu.Synchronization;
|
|
using System;
|
|
using System.Collections.Concurrent;
|
|
using System.Collections.Generic;
|
|
using System.Threading;
|
|
|
|
namespace Ryujinx.Graphics.Gpu
|
|
{
|
|
/// <summary>
|
|
/// GPU emulation context.
|
|
/// </summary>
|
|
public sealed class GpuContext : IDisposable
|
|
{
|
|
private const int NsToTicksFractionNumerator = 384;
|
|
private const int NsToTicksFractionDenominator = 625;
|
|
|
|
/// <summary>
|
|
/// Event signaled when the host emulation context is ready to be used by the gpu context.
|
|
/// </summary>
|
|
public ManualResetEvent HostInitalized { get; }
|
|
|
|
/// <summary>
|
|
/// Host renderer.
|
|
/// </summary>
|
|
public IRenderer Renderer { get; }
|
|
|
|
/// <summary>
|
|
/// GPU General Purpose FIFO queue.
|
|
/// </summary>
|
|
public GPFifoDevice GPFifo { get; }
|
|
|
|
/// <summary>
|
|
/// GPU synchronization manager.
|
|
/// </summary>
|
|
public SynchronizationManager Synchronization { get; }
|
|
|
|
/// <summary>
|
|
/// Presentation window.
|
|
/// </summary>
|
|
public Window Window { get; }
|
|
|
|
/// <summary>
|
|
/// Internal sequence number, used to avoid needless resource data updates
|
|
/// in the middle of a command buffer before synchronizations.
|
|
/// </summary>
|
|
internal int SequenceNumber { get; private set; }
|
|
|
|
/// <summary>
|
|
/// Internal sync number, used to denote points at which host synchronization can be requested.
|
|
/// </summary>
|
|
internal ulong SyncNumber { get; private set; }
|
|
|
|
/// <summary>
|
|
/// Actions to be performed when a CPU waiting syncpoint or barrier is triggered.
|
|
/// If there are more than 0 items when this happens, a host sync object will be generated for the given <see cref="SyncNumber"/>,
|
|
/// and the SyncNumber will be incremented.
|
|
/// </summary>
|
|
internal List<Action> SyncActions { get; }
|
|
|
|
/// <summary>
|
|
/// Actions to be performed when a CPU waiting syncpoint is triggered.
|
|
/// If there are more than 0 items when this happens, a host sync object will be generated for the given <see cref="SyncNumber"/>,
|
|
/// and the SyncNumber will be incremented.
|
|
/// </summary>
|
|
internal List<Action> SyncpointActions { get; }
|
|
|
|
/// <summary>
|
|
/// Buffer migrations that are currently in-flight. These are checked whenever sync is created to determine if buffer migration
|
|
/// copies have completed on the GPU, and their data can be freed.
|
|
/// </summary>
|
|
internal List<BufferMigration> BufferMigrations { get; }
|
|
|
|
/// <summary>
|
|
/// Queue with deferred actions that must run on the render thread.
|
|
/// </summary>
|
|
internal Queue<Action> DeferredActions { get; }
|
|
|
|
/// <summary>
|
|
/// Registry with physical memories that can be used with this GPU context, keyed by owner process ID.
|
|
/// </summary>
|
|
internal ConcurrentDictionary<ulong, PhysicalMemory> PhysicalMemoryRegistry { get; }
|
|
|
|
/// <summary>
|
|
/// Host hardware capabilities.
|
|
/// </summary>
|
|
internal Capabilities Capabilities;
|
|
|
|
/// <summary>
|
|
/// Event for signalling shader cache loading progress.
|
|
/// </summary>
|
|
public event Action<ShaderCacheState, int, int> ShaderCacheStateChanged;
|
|
|
|
private Thread _gpuThread;
|
|
private bool _pendingSync;
|
|
|
|
/// <summary>
|
|
/// Creates a new instance of the GPU emulation context.
|
|
/// </summary>
|
|
/// <param name="renderer">Host renderer</param>
|
|
public GpuContext(IRenderer renderer)
|
|
{
|
|
Renderer = renderer;
|
|
|
|
GPFifo = new GPFifoDevice(this);
|
|
|
|
Synchronization = new SynchronizationManager();
|
|
|
|
Window = new Window(this);
|
|
|
|
HostInitalized = new ManualResetEvent(false);
|
|
|
|
SyncActions = new List<Action>();
|
|
SyncpointActions = new List<Action>();
|
|
BufferMigrations = new List<BufferMigration>();
|
|
|
|
DeferredActions = new Queue<Action>();
|
|
|
|
PhysicalMemoryRegistry = new ConcurrentDictionary<ulong, PhysicalMemory>();
|
|
}
|
|
|
|
/// <summary>
|
|
/// Creates a new GPU channel.
|
|
/// </summary>
|
|
/// <returns>The GPU channel</returns>
|
|
public GpuChannel CreateChannel()
|
|
{
|
|
return new GpuChannel(this);
|
|
}
|
|
|
|
/// <summary>
|
|
/// Creates a new GPU memory manager.
|
|
/// </summary>
|
|
/// <param name="pid">ID of the process that owns the memory manager</param>
|
|
/// <returns>The memory manager</returns>
|
|
/// <exception cref="ArgumentException">Thrown when <paramref name="pid"/> is invalid</exception>
|
|
public MemoryManager CreateMemoryManager(ulong pid)
|
|
{
|
|
if (!PhysicalMemoryRegistry.TryGetValue(pid, out var physicalMemory))
|
|
{
|
|
throw new ArgumentException("The PID is invalid or the process was not registered", nameof(pid));
|
|
}
|
|
|
|
return new MemoryManager(physicalMemory);
|
|
}
|
|
|
|
/// <summary>
|
|
/// Registers virtual memory used by a process for GPU memory access, caching and read/write tracking.
|
|
/// </summary>
|
|
/// <param name="pid">ID of the process that owns <paramref name="cpuMemory"/></param>
|
|
/// <param name="cpuMemory">Virtual memory owned by the process</param>
|
|
/// <exception cref="ArgumentException">Thrown if <paramref name="pid"/> was already registered</exception>
|
|
public void RegisterProcess(ulong pid, Cpu.IVirtualMemoryManagerTracked cpuMemory)
|
|
{
|
|
var physicalMemory = new PhysicalMemory(this, cpuMemory);
|
|
if (!PhysicalMemoryRegistry.TryAdd(pid, physicalMemory))
|
|
{
|
|
throw new ArgumentException("The PID was already registered", nameof(pid));
|
|
}
|
|
|
|
physicalMemory.ShaderCache.ShaderCacheStateChanged += ShaderCacheStateUpdate;
|
|
}
|
|
|
|
/// <summary>
|
|
/// Unregisters a process, indicating that its memory will no longer be used, and that caches can be freed.
|
|
/// </summary>
|
|
/// <param name="pid">ID of the process</param>
|
|
public void UnregisterProcess(ulong pid)
|
|
{
|
|
if (PhysicalMemoryRegistry.TryRemove(pid, out var physicalMemory))
|
|
{
|
|
physicalMemory.ShaderCache.ShaderCacheStateChanged -= ShaderCacheStateUpdate;
|
|
physicalMemory.Dispose();
|
|
}
|
|
}
|
|
|
|
/// <summary>
|
|
/// Converts a nanoseconds timestamp value to Maxwell time ticks.
|
|
/// </summary>
|
|
/// <remarks>
|
|
/// The frequency is 614400000 Hz.
|
|
/// </remarks>
|
|
/// <param name="nanoseconds">Timestamp in nanoseconds</param>
|
|
/// <returns>Maxwell ticks</returns>
|
|
private static ulong ConvertNanosecondsToTicks(ulong nanoseconds)
|
|
{
|
|
// We need to divide first to avoid overflows.
|
|
// We fix up the result later by calculating the difference and adding
|
|
// that to the result.
|
|
ulong divided = nanoseconds / NsToTicksFractionDenominator;
|
|
|
|
ulong rounded = divided * NsToTicksFractionDenominator;
|
|
|
|
ulong errorBias = (nanoseconds - rounded) * NsToTicksFractionNumerator / NsToTicksFractionDenominator;
|
|
|
|
return divided * NsToTicksFractionNumerator + errorBias;
|
|
}
|
|
|
|
/// <summary>
|
|
/// Gets the value of the GPU timer.
|
|
/// </summary>
|
|
/// <returns>The current GPU timestamp</returns>
|
|
public ulong GetTimestamp()
|
|
{
|
|
ulong ticks = ConvertNanosecondsToTicks((ulong)PerformanceCounter.ElapsedNanoseconds);
|
|
|
|
if (GraphicsConfig.FastGpuTime)
|
|
{
|
|
// Divide by some amount to report time as if operations were performed faster than they really are.
|
|
// This can prevent some games from switching to a lower resolution because rendering is too slow.
|
|
ticks /= 256;
|
|
}
|
|
|
|
return ticks;
|
|
}
|
|
|
|
/// <summary>
|
|
/// Shader cache state update handler.
|
|
/// </summary>
|
|
/// <param name="state">Current state of the shader cache load process</param>
|
|
/// <param name="current">Number of the current shader being processed</param>
|
|
/// <param name="total">Total number of shaders to process</param>
|
|
private void ShaderCacheStateUpdate(ShaderCacheState state, int current, int total)
|
|
{
|
|
ShaderCacheStateChanged?.Invoke(state, current, total);
|
|
}
|
|
|
|
/// <summary>
|
|
/// Initialize the GPU shader cache.
|
|
/// </summary>
|
|
public void InitializeShaderCache(CancellationToken cancellationToken)
|
|
{
|
|
HostInitalized.WaitOne();
|
|
|
|
foreach (var physicalMemory in PhysicalMemoryRegistry.Values)
|
|
{
|
|
physicalMemory.ShaderCache.Initialize(cancellationToken);
|
|
}
|
|
}
|
|
|
|
/// <summary>
|
|
/// Sets the current thread as the main GPU thread.
|
|
/// </summary>
|
|
public void SetGpuThread()
|
|
{
|
|
_gpuThread = Thread.CurrentThread;
|
|
|
|
Capabilities = Renderer.GetCapabilities();
|
|
}
|
|
|
|
/// <summary>
|
|
/// Checks if the current thread is the GPU thread.
|
|
/// </summary>
|
|
/// <returns>True if the thread is the GPU thread, false otherwise</returns>
|
|
public bool IsGpuThread()
|
|
{
|
|
return _gpuThread == Thread.CurrentThread;
|
|
}
|
|
|
|
/// <summary>
|
|
/// Processes the queue of shaders that must save their binaries to the disk cache.
|
|
/// </summary>
|
|
public void ProcessShaderCacheQueue()
|
|
{
|
|
foreach (var physicalMemory in PhysicalMemoryRegistry.Values)
|
|
{
|
|
physicalMemory.ShaderCache.ProcessShaderCacheQueue();
|
|
}
|
|
}
|
|
|
|
/// <summary>
|
|
/// Advances internal sequence number.
|
|
/// This forces the update of any modified GPU resource.
|
|
/// </summary>
|
|
internal void AdvanceSequence()
|
|
{
|
|
SequenceNumber++;
|
|
}
|
|
|
|
/// <summary>
|
|
/// Registers a buffer migration. These are checked to see if they can be disposed when the sync number increases,
|
|
/// and the migration copy has completed.
|
|
/// </summary>
|
|
/// <param name="migration">The buffer migration</param>
|
|
internal void RegisterBufferMigration(BufferMigration migration)
|
|
{
|
|
BufferMigrations.Add(migration);
|
|
_pendingSync = true;
|
|
}
|
|
|
|
/// <summary>
|
|
/// Registers an action to be performed the next time a syncpoint is incremented.
|
|
/// This will also ensure a host sync object is created, and <see cref="SyncNumber"/> is incremented.
|
|
/// </summary>
|
|
/// <param name="action">The action to be performed on sync object creation</param>
|
|
/// <param name="syncpointOnly">True if the sync action should only run when syncpoints are incremented</param>
|
|
public void RegisterSyncAction(Action action, bool syncpointOnly = false)
|
|
{
|
|
if (syncpointOnly)
|
|
{
|
|
SyncpointActions.Add(action);
|
|
}
|
|
else
|
|
{
|
|
SyncActions.Add(action);
|
|
_pendingSync = true;
|
|
}
|
|
}
|
|
|
|
/// <summary>
|
|
/// Creates a host sync object if there are any pending sync actions. The actions will then be called.
|
|
/// If no actions are present, a host sync object is not created.
|
|
/// </summary>
|
|
/// <param name="syncpoint">True if host sync is being created by a syncpoint</param>
|
|
/// <param name="strict">True if the sync should signal as soon as possible</param>
|
|
public void CreateHostSyncIfNeeded(bool syncpoint, bool strict)
|
|
{
|
|
if (BufferMigrations.Count > 0)
|
|
{
|
|
ulong currentSyncNumber = Renderer.GetCurrentSync();
|
|
|
|
for (int i = 0; i < BufferMigrations.Count; i++)
|
|
{
|
|
BufferMigration migration = BufferMigrations[i];
|
|
long diff = (long)(currentSyncNumber - migration.SyncNumber);
|
|
|
|
if (diff >= 0)
|
|
{
|
|
migration.Dispose();
|
|
BufferMigrations.RemoveAt(i--);
|
|
}
|
|
}
|
|
}
|
|
|
|
if (_pendingSync || (syncpoint && SyncpointActions.Count > 0))
|
|
{
|
|
Renderer.CreateSync(SyncNumber, strict);
|
|
|
|
SyncNumber++;
|
|
|
|
foreach (Action action in SyncActions)
|
|
{
|
|
action();
|
|
}
|
|
|
|
foreach (Action action in SyncpointActions)
|
|
{
|
|
action();
|
|
}
|
|
|
|
SyncActions.Clear();
|
|
SyncpointActions.Clear();
|
|
}
|
|
|
|
_pendingSync = false;
|
|
}
|
|
|
|
/// <summary>
|
|
/// Performs deferred actions.
|
|
/// This is useful for actions that must run on the render thread, such as resource disposal.
|
|
/// </summary>
|
|
internal void RunDeferredActions()
|
|
{
|
|
while (DeferredActions.TryDequeue(out Action action))
|
|
{
|
|
action();
|
|
}
|
|
}
|
|
|
|
/// <summary>
|
|
/// Disposes all GPU resources currently cached.
|
|
/// It's an error to push any GPU commands after disposal.
|
|
/// Additionally, the GPU commands FIFO must be empty for disposal,
|
|
/// and processing of all commands must have finished.
|
|
/// </summary>
|
|
public void Dispose()
|
|
{
|
|
Renderer.Dispose();
|
|
GPFifo.Dispose();
|
|
HostInitalized.Dispose();
|
|
|
|
// Has to be disposed before processing deferred actions, as it will produce some.
|
|
foreach (var physicalMemory in PhysicalMemoryRegistry.Values)
|
|
{
|
|
physicalMemory.Dispose();
|
|
}
|
|
|
|
PhysicalMemoryRegistry.Clear();
|
|
|
|
RunDeferredActions();
|
|
}
|
|
}
|
|
} |