Ryujinx-uplift/Ryujinx.Graphics.OpenGL/Queries/BufferedQuery.cs

121 lines
3.6 KiB
C#
Raw Normal View History

using OpenTK.Graphics.OpenGL;
using Ryujinx.Common.Logging;
using System;
using System.Runtime.InteropServices;
using System.Threading;
namespace Ryujinx.Graphics.OpenGL.Queries
{
class BufferedQuery : IDisposable
{
private const int MaxQueryRetries = 5000;
private const long DefaultValue = -1;
private const ulong HighMask = 0xFFFFFFFF00000000;
public int Query { get; }
private int _buffer;
private IntPtr _bufferMap;
private QueryTarget _type;
public BufferedQuery(QueryTarget type)
{
_buffer = GL.GenBuffer();
Query = GL.GenQuery();
_type = type;
GL.BindBuffer(BufferTarget.QueryBuffer, _buffer);
unsafe
{
long defaultValue = DefaultValue;
GL.BufferStorage(BufferTarget.QueryBuffer, sizeof(long), (IntPtr)(&defaultValue), BufferStorageFlags.MapReadBit | BufferStorageFlags.MapWriteBit | BufferStorageFlags.MapPersistentBit);
}
_bufferMap = GL.MapBufferRange(BufferTarget.QueryBuffer, IntPtr.Zero, sizeof(long), BufferAccessMask.MapReadBit | BufferAccessMask.MapWriteBit | BufferAccessMask.MapPersistentBit);
}
public void Reset()
{
GL.EndQuery(_type);
GL.BeginQuery(_type, Query);
}
public void Begin()
{
GL.BeginQuery(_type, Query);
}
public unsafe void End(bool withResult)
{
GL.EndQuery(_type);
if (withResult)
{
GL.BindBuffer(BufferTarget.QueryBuffer, _buffer);
Marshal.WriteInt64(_bufferMap, -1L);
GL.GetQueryObject(Query, GetQueryObjectParam.QueryResult, (long*)0);
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>
2021-08-27 00:31:29 +02:00
GL.MemoryBarrier(MemoryBarrierFlags.QueryBufferBarrierBit | MemoryBarrierFlags.ClientMappedBufferBarrierBit);
}
else
{
// Dummy result, just return 0.
Marshal.WriteInt64(_bufferMap, 0L);
}
}
private bool WaitingForValue(long data)
{
return data == DefaultValue ||
((ulong)data & HighMask) == (unchecked((ulong)DefaultValue) & HighMask);
}
public bool TryGetResult(out long result)
{
result = Marshal.ReadInt64(_bufferMap);
return !WaitingForValue(result);
}
public long AwaitResult(AutoResetEvent wakeSignal = null)
{
long data = DefaultValue;
if (wakeSignal == null)
{
while (WaitingForValue(data))
{
data = Marshal.ReadInt64(_bufferMap);
}
}
else
{
int iterations = 0;
while (WaitingForValue(data) && iterations++ < MaxQueryRetries)
{
data = Marshal.ReadInt64(_bufferMap);
if (WaitingForValue(data))
{
wakeSignal.WaitOne(1);
}
}
if (iterations >= MaxQueryRetries)
{
Logger.Error?.Print(LogClass.Gpu, $"Error: Query result timed out. Took more than {MaxQueryRetries} tries.");
}
}
return data;
}
public void Dispose()
{
GL.BindBuffer(BufferTarget.QueryBuffer, _buffer);
GL.UnmapBuffer(BufferTarget.QueryBuffer);
GL.DeleteBuffer(_buffer);
GL.DeleteQuery(Query);
}
}
}