Ryujinx/ARMeilleure/Translation/PTC/PtcProfiler.cs

277 lines
8.1 KiB
C#
Raw Normal View History

Add Profiled Persistent Translation Cache. (#769) * Delete DelegateTypes.cs * Delete DelegateCache.cs * Add files via upload * Update Horizon.cs * Update Program.cs * Update MainWindow.cs * Update Aot.cs * Update RelocEntry.cs * Update Translator.cs * Update MemoryManager.cs * Update InstEmitMemoryHelper.cs * Update Delegates.cs * Nit. * Nit. * Nit. * 10 fewer MSIL bytes for us * Add comment. Nits. * Update Translator.cs * Update Aot.cs * Nits. * Opt.. * Opt.. * Opt.. * Opt.. * Allow to change compression level. * Update MemoryManager.cs * Update Translator.cs * Manage corner cases during the save phase. Nits. * Update Aot.cs * Translator response tweak for Aot disabled. Nit. * Nit. * Nits. * Create DelegateHelpers.cs * Update Delegates.cs * Nit. * Nit. * Nits. * Fix due to #784. * Fixes due to #757 & #841. * Fix due to #846. * Fix due to #847. * Use MethodInfo for managed method calls. Use IR methods instead of managed methods about Max/Min (S/U). Follow-ups & Nits. * Add missing exception messages. Reintroduce slow path for Fmov_Vi. Implement slow path for Fmov_Si. * Switch to the new folder structure. Nits. * Impl. index-based relocation information. Impl. cache file version field. * Nit. * Address gdkchan comments. Mainly: - fixed cache file corruption issue on exit; - exposed a way to disable AOT on the GUI. * Address AcK77 comment. * Address Thealexbarney, jduncanator & emmauss comments. Header magic, CpuId (FI) & Aot -> Ptc. * Adaptation to the new application reloading system. Improvements to the call system of managed methods. Follow-ups. Nits. * Get the same boot times as on master when PTC is disabled. * Profiled Aot. * A32 support (#897). * #975 support (1 of 2). * #975 support (2 of 2). * Rebase fix & nits. * Some fixes and nits (still one bug left). * One fix & nits. * Tests fix (by gdk) & nits. * Support translations not only in high quality and rejit. Nits. * Added possibility to skip translations and continue execution, using `ESC` key. * Update SettingsWindow.cs * Update GLRenderer.cs * Update Ptc.cs * Disabled Profiled PTC by default as requested in the past by gdk. * Fix rejit bug. Increased number of parallel translations. Add stack unwinding stuffs support (1 of 2). Nits. * Add stack unwinding stuffs support (2 of 2). Tuned number of parallel translations. * Restored the ability to assemble jumps with 8-bit offset when Profiled PTC is disabled or during profiling. Modifications due to rebase. Nits. * Limited profiling of the functions to be translated to the addresses belonging to the range of static objects only. * Nits. * Nits. * Update Delegates.cs * Nit. * Update InstEmitSimdArithmetic.cs * Address riperiperi comments. * Fixed the issue of unjustifiably longer boot times at the second boot than at the first boot, measured at the same time or reference point and with the same number of translated functions. * Implemented a simple redundant load/save mechanism. Halved the value of Decoder.MaxInstsPerFunction more appropriate for the current performance of the Translator. Replaced by Logger.PrintError to Logger.PrintDebug in TexturePool.cs about the supposed invalid texture format to avoid the spawn of the log. Nits. * Nit. Improved Logger.PrintError in TexturePool.cs to avoid log spawn. Added missing code for FZ handling (in output) for fp max/min instructions (slow paths). * Add configuration migration for PTC Co-authored-by: Thog <me@thog.eu>
2020-06-16 20:28:02 +02:00
using ARMeilleure.State;
using System;
using System.Collections.Generic;
using System.Diagnostics;
using System.IO;
using System.IO.Compression;
using System.Runtime.Serialization.Formatters.Binary;
using System.Security.Cryptography;
using System.Threading;
namespace ARMeilleure.Translation.PTC
{
public static class PtcProfiler
{
private const int SaveInterval = 30; // Seconds.
private const CompressionLevel SaveCompressionLevel = CompressionLevel.Fastest;
private static readonly BinaryFormatter _binaryFormatter;
private static readonly System.Timers.Timer _timer;
private static readonly ManualResetEvent _waitEvent;
private static readonly object _lock;
private static bool _disposed;
internal static Dictionary<ulong, (ExecutionMode mode, bool highCq)> ProfiledFuncs { get; private set; } //! Not to be modified.
internal static bool Enabled { get; private set; }
public static ulong StaticCodeStart { internal get; set; }
public static int StaticCodeSize { internal get; set; }
static PtcProfiler()
{
_binaryFormatter = new BinaryFormatter();
_timer = new System.Timers.Timer((double)SaveInterval * 1000d);
_timer.Elapsed += PreSave;
_waitEvent = new ManualResetEvent(true);
_lock = new object();
_disposed = false;
ProfiledFuncs = new Dictionary<ulong, (ExecutionMode, bool)>();
Enabled = false;
}
internal static void AddEntry(ulong address, ExecutionMode mode, bool highCq)
{
if (IsAddressInStaticCodeRange(address))
{
lock (_lock)
{
Debug.Assert(!highCq && !ProfiledFuncs.ContainsKey(address));
ProfiledFuncs.TryAdd(address, (mode, highCq));
}
}
}
internal static void UpdateEntry(ulong address, ExecutionMode mode, bool highCq)
{
if (IsAddressInStaticCodeRange(address))
{
lock (_lock)
{
Debug.Assert(highCq && ProfiledFuncs.ContainsKey(address));
ProfiledFuncs[address] = (mode, highCq);
}
}
}
internal static bool IsAddressInStaticCodeRange(ulong address)
{
return address >= StaticCodeStart && address < StaticCodeStart + (ulong)StaticCodeSize;
}
internal static void ClearEntries()
{
ProfiledFuncs.Clear();
}
internal static void PreLoad()
{
string fileNameActual = String.Concat(Ptc.CachePathActual, ".info");
string fileNameBackup = String.Concat(Ptc.CachePathBackup, ".info");
FileInfo fileInfoActual = new FileInfo(fileNameActual);
FileInfo fileInfoBackup = new FileInfo(fileNameBackup);
if (fileInfoActual.Exists && fileInfoActual.Length != 0L)
{
if (!Load(fileNameActual))
{
if (fileInfoBackup.Exists && fileInfoBackup.Length != 0L)
{
Load(fileNameBackup);
}
}
}
else if (fileInfoBackup.Exists && fileInfoBackup.Length != 0L)
{
Load(fileNameBackup);
}
}
private static bool Load(string fileName)
{
using (FileStream compressedStream = new FileStream(fileName, FileMode.Open))
using (DeflateStream deflateStream = new DeflateStream(compressedStream, CompressionMode.Decompress, true))
using (MemoryStream stream = new MemoryStream())
using (MD5 md5 = MD5.Create())
{
int hashSize = md5.HashSize / 8;
try
{
deflateStream.CopyTo(stream);
}
catch
{
InvalidateCompressedStream(compressedStream);
return false;
}
Add Profiled Persistent Translation Cache. (#769) * Delete DelegateTypes.cs * Delete DelegateCache.cs * Add files via upload * Update Horizon.cs * Update Program.cs * Update MainWindow.cs * Update Aot.cs * Update RelocEntry.cs * Update Translator.cs * Update MemoryManager.cs * Update InstEmitMemoryHelper.cs * Update Delegates.cs * Nit. * Nit. * Nit. * 10 fewer MSIL bytes for us * Add comment. Nits. * Update Translator.cs * Update Aot.cs * Nits. * Opt.. * Opt.. * Opt.. * Opt.. * Allow to change compression level. * Update MemoryManager.cs * Update Translator.cs * Manage corner cases during the save phase. Nits. * Update Aot.cs * Translator response tweak for Aot disabled. Nit. * Nit. * Nits. * Create DelegateHelpers.cs * Update Delegates.cs * Nit. * Nit. * Nits. * Fix due to #784. * Fixes due to #757 & #841. * Fix due to #846. * Fix due to #847. * Use MethodInfo for managed method calls. Use IR methods instead of managed methods about Max/Min (S/U). Follow-ups & Nits. * Add missing exception messages. Reintroduce slow path for Fmov_Vi. Implement slow path for Fmov_Si. * Switch to the new folder structure. Nits. * Impl. index-based relocation information. Impl. cache file version field. * Nit. * Address gdkchan comments. Mainly: - fixed cache file corruption issue on exit; - exposed a way to disable AOT on the GUI. * Address AcK77 comment. * Address Thealexbarney, jduncanator & emmauss comments. Header magic, CpuId (FI) & Aot -> Ptc. * Adaptation to the new application reloading system. Improvements to the call system of managed methods. Follow-ups. Nits. * Get the same boot times as on master when PTC is disabled. * Profiled Aot. * A32 support (#897). * #975 support (1 of 2). * #975 support (2 of 2). * Rebase fix & nits. * Some fixes and nits (still one bug left). * One fix & nits. * Tests fix (by gdk) & nits. * Support translations not only in high quality and rejit. Nits. * Added possibility to skip translations and continue execution, using `ESC` key. * Update SettingsWindow.cs * Update GLRenderer.cs * Update Ptc.cs * Disabled Profiled PTC by default as requested in the past by gdk. * Fix rejit bug. Increased number of parallel translations. Add stack unwinding stuffs support (1 of 2). Nits. * Add stack unwinding stuffs support (2 of 2). Tuned number of parallel translations. * Restored the ability to assemble jumps with 8-bit offset when Profiled PTC is disabled or during profiling. Modifications due to rebase. Nits. * Limited profiling of the functions to be translated to the addresses belonging to the range of static objects only. * Nits. * Nits. * Update Delegates.cs * Nit. * Update InstEmitSimdArithmetic.cs * Address riperiperi comments. * Fixed the issue of unjustifiably longer boot times at the second boot than at the first boot, measured at the same time or reference point and with the same number of translated functions. * Implemented a simple redundant load/save mechanism. Halved the value of Decoder.MaxInstsPerFunction more appropriate for the current performance of the Translator. Replaced by Logger.PrintError to Logger.PrintDebug in TexturePool.cs about the supposed invalid texture format to avoid the spawn of the log. Nits. * Nit. Improved Logger.PrintError in TexturePool.cs to avoid log spawn. Added missing code for FZ handling (in output) for fp max/min instructions (slow paths). * Add configuration migration for PTC Co-authored-by: Thog <me@thog.eu>
2020-06-16 20:28:02 +02:00
stream.Seek(0L, SeekOrigin.Begin);
byte[] currentHash = new byte[hashSize];
stream.Read(currentHash, 0, hashSize);
byte[] expectedHash = md5.ComputeHash(stream);
if (!CompareHash(currentHash, expectedHash))
{
InvalidateCompressedStream(compressedStream);
return false;
}
stream.Seek((long)hashSize, SeekOrigin.Begin);
try
{
ProfiledFuncs = (Dictionary<ulong, (ExecutionMode, bool)>)_binaryFormatter.Deserialize(stream);
}
catch
{
ProfiledFuncs = new Dictionary<ulong, (ExecutionMode, bool)>();
InvalidateCompressedStream(compressedStream);
return false;
}
return true;
}
}
private static bool CompareHash(ReadOnlySpan<byte> currentHash, ReadOnlySpan<byte> expectedHash)
{
return currentHash.SequenceEqual(expectedHash);
}
private static void InvalidateCompressedStream(FileStream compressedStream)
{
compressedStream.SetLength(0L);
}
private static void PreSave(object source, System.Timers.ElapsedEventArgs e)
{
_waitEvent.Reset();
string fileNameActual = String.Concat(Ptc.CachePathActual, ".info");
string fileNameBackup = String.Concat(Ptc.CachePathBackup, ".info");
FileInfo fileInfoActual = new FileInfo(fileNameActual);
if (fileInfoActual.Exists && fileInfoActual.Length != 0L)
{
File.Copy(fileNameActual, fileNameBackup, true);
}
Save(fileNameActual);
_waitEvent.Set();
}
private static void Save(string fileName)
{
using (MemoryStream stream = new MemoryStream())
using (MD5 md5 = MD5.Create())
{
int hashSize = md5.HashSize / 8;
stream.Seek((long)hashSize, SeekOrigin.Begin);
lock (_lock)
{
_binaryFormatter.Serialize(stream, ProfiledFuncs);
}
stream.Seek((long)hashSize, SeekOrigin.Begin);
byte[] hash = md5.ComputeHash(stream);
stream.Seek(0L, SeekOrigin.Begin);
stream.Write(hash, 0, hashSize);
using (FileStream compressedStream = new FileStream(fileName, FileMode.OpenOrCreate))
using (DeflateStream deflateStream = new DeflateStream(compressedStream, SaveCompressionLevel, true))
{
try
{
stream.WriteTo(deflateStream);
}
catch
{
compressedStream.Position = 0L;
}
if (compressedStream.Position < compressedStream.Length)
{
compressedStream.SetLength(compressedStream.Position);
}
}
}
}
internal static void Start()
{
if (Ptc.State == PtcState.Enabled ||
Ptc.State == PtcState.Continuing)
{
Enabled = true;
_timer.Enabled = true;
}
}
public static void Stop()
{
Enabled = false;
if (!_disposed)
{
_timer.Enabled = false;
}
}
internal static void Wait()
{
_waitEvent.WaitOne();
}
public static void Dispose()
{
if (!_disposed)
{
_disposed = true;
_timer.Elapsed -= PreSave;
_timer.Dispose();
Wait();
_waitEvent.Dispose();
}
}
}
}