为什么通过 Pointer 转换结构很慢,而 Unsafe.As 很快?

Why is casting a struct via Pointer slow, while Unsafe.As is fast?

背景

我想制作一些整数大小的 structs(即 32 位和 64 位),它们很容易转换 to/from 相同大小的原始非托管类型(即 Int32UInt32 尤其适用于 32 位大小的结构)。

然后,这些结构将公开用于位操作/索引的其他功能,这些功能在整数类型上不直接可用。基本上,作为一种语法糖,提高可读性和易用性。

然而,重要的部分是性能,因为这个额外的抽象基本上应该有 0 成本(在一天结束时 CPU 应该 "see" 相同的位,就好像它正在处理原始整数)。

示例结构

下面只是我想出的最基本的 struct。它没有所有的功能,但足以说明我的问题:

[StructLayout(LayoutKind.Explicit, Pack = 1, Size = 4)]
public struct Mask32 {
  [FieldOffset(3)]
  public byte Byte1;
  [FieldOffset(2)]
  public ushort UShort1;
  [FieldOffset(2)]
  public byte Byte2;
  [FieldOffset(1)]
  public byte Byte3;
  [FieldOffset(0)]
  public ushort UShort2;
  [FieldOffset(0)]
  public byte Byte4;

  [DebuggerStepThrough, MethodImpl(MethodImplOptions.AggressiveInlining)]
  public static unsafe implicit operator Mask32(int i) => *(Mask32*)&i;
  [DebuggerStepThrough, MethodImpl(MethodImplOptions.AggressiveInlining)]
  public static unsafe implicit operator Mask32(uint i) => *(Mask32*)&i;
}

测试

我想测试这个结构的性能。特别是我想看看如果我使用常规的按位算术:(i >> 8) & 0xFF(例如获取第 3 个字节),它是否可以让我得到单个字节).

下面你会看到我想出的一个基准:

public unsafe class MyBenchmark {

  const int count = 50000;

  [Benchmark(Baseline = true)]
  public static void Direct() {
    var j = 0;
    for (int i = 0; i < count; i++) {
      //var b1 = i.Byte1();
      //var b2 = i.Byte2();
      var b3 = i.Byte3();
      //var b4 = i.Byte4();
      j += b3;
    }
  }


  [Benchmark]
  public static void ViaStructPointer() {
    var j = 0;
    int i = 0;
    var s = (Mask32*)&i;
    for (; i < count; i++) {
      //var b1 = s->Byte1;
      //var b2 = s->Byte2;
      var b3 = s->Byte3;
      //var b4 = s->Byte4;
      j += b3;
    }
  }

  [Benchmark]
  public static void ViaStructPointer2() {
    var j = 0;
    int i = 0;
    for (; i < count; i++) {
      var s = *(Mask32*)&i;
      //var b1 = s.Byte1;
      //var b2 = s.Byte2;
      var b3 = s.Byte3;
      //var b4 = s.Byte4;
      j += b3;
    }
  }

  [Benchmark]
  public static void ViaStructCast() {
    var j = 0;
    for (int i = 0; i < count; i++) {
      Mask32 m = i;
      //var b1 = m.Byte1;
      //var b2 = m.Byte2;
      var b3 = m.Byte3;
      //var b4 = m.Byte4;
      j += b3;
    }
  }

  [Benchmark]
  public static void ViaUnsafeAs() {
    var j = 0;
    for (int i = 0; i < count; i++) {
      var m = Unsafe.As<int, Mask32>(ref i);
      //var b1 = m.Byte1;
      //var b2 = m.Byte2;
      var b3 = m.Byte3;
      //var b4 = m.Byte4;
      j += b3;
    }
  }

}

Byte1()Byte2()Byte3()Byte4() 只是 内联的扩展方法 和通过按位运算和转换简单地获得第 n 个字节:

[DebuggerStepThrough, MethodImpl(MethodImplOptions.AggressiveInlining)]
public static byte Byte1(this int it) => (byte)(it >> 24);
[DebuggerStepThrough, MethodImpl(MethodImplOptions.AggressiveInlining)]
public static byte Byte2(this int it) => (byte)((it >> 16) & 0xFF);
[DebuggerStepThrough, MethodImpl(MethodImplOptions.AggressiveInlining)]
public static byte Byte3(this int it) => (byte)((it >> 8) & 0xFF);
[DebuggerStepThrough, MethodImpl(MethodImplOptions.AggressiveInlining)]
public static byte Byte4(this int it) => (byte)it;

编辑: 修复代码以确保实际使用变量。还注释掉了 4 个变量中的 3 个来真正测试结构转换/成员访问而不是实际使用变量。

结果

我 运行 这些在发布版本中对 x64 进行了优化。

Intel Core i7-3770K CPU 3.50GHz (Ivy Bridge), 1 CPU, 8 logical cores and 4 physical cores
Frequency=3410223 Hz, Resolution=293.2360 ns, Timer=TSC
  [Host]     : .NET Framework 4.6.1 (CLR 4.0.30319.42000), 64bit RyuJIT-v4.6.1086.0
  DefaultJob : .NET Framework 4.6.1 (CLR 4.0.30319.42000), 64bit RyuJIT-v4.6.1086.0


            Method |      Mean |     Error |    StdDev | Scaled | ScaledSD |
------------------ |----------:|----------:|----------:|-------:|---------:|
            Direct |  14.47 us | 0.3314 us | 0.2938 us |   1.00 |     0.00 |
  ViaStructPointer | 111.32 us | 0.6481 us | 0.6062 us |   7.70 |     0.15 |
 ViaStructPointer2 | 102.31 us | 0.7632 us | 0.7139 us |   7.07 |     0.14 |
     ViaStructCast |  29.00 us | 0.3159 us | 0.2800 us |   2.01 |     0.04 |
       ViaUnsafeAs |  14.32 us | 0.0955 us | 0.0894 us |   0.99 |     0.02 |

编辑: 修复代码后的新结果:

            Method |      Mean |     Error |    StdDev | Scaled | ScaledSD |
------------------ |----------:|----------:|----------:|-------:|---------:|
            Direct |  57.51 us | 1.1070 us | 1.0355 us |   1.00 |     0.00 |
  ViaStructPointer | 203.20 us | 3.9830 us | 3.5308 us |   3.53 |     0.08 |
 ViaStructPointer2 | 198.08 us | 1.8411 us | 1.6321 us |   3.45 |     0.06 |
     ViaStructCast |  79.68 us | 1.5478 us | 1.7824 us |   1.39 |     0.04 |
       ViaUnsafeAs |  57.01 us | 0.8266 us | 0.6902 us |   0.99 |     0.02 |

问题

基准测试结果让我感到惊讶,这就是为什么我有几个问题:

编辑: 更改代码后剩下的问题更少,以便实际使用变量。

  1. 为什么指针的东西那么慢?
  2. 为什么演员表花费的时间是基准案例的两倍? implicit/explicit 运算符不是内联的吗?
  3. 为什么新的 System.Runtime.CompilerServices.Unsafe 包 (v. 4.5.0) 这么快?我认为它至少会涉及一个方法调用...
  4. 更一般地说,我怎样才能本质上制作一个零成本结构,它可以简单地充当"window"到一些内存或像[=这样的大原始类型26=] 以便我可以更有效地操作/读取该内存?这里的最佳做法是什么?

答案似乎是当您使用 Unsafe.As() 时,JIT 编译器可以更好地进行某些优化。

Unsafe.As() 的实现非常简单,如下所示:

public static ref TTo As<TFrom, TTo>(ref TFrom source)
{
    return ref source;
}

就是这样!

这是我写的一个测试程序,用于与转换进行比较:

using System;
using System.Diagnostics;
using System.Runtime.CompilerServices;
using System.Runtime.InteropServices;

namespace Demo
{
    [StructLayout(LayoutKind.Explicit, Pack = 1, Size = 4)]
    public struct Mask32
    {
        [FieldOffset(3)]
        public byte Byte1;
        [FieldOffset(2)]
        public ushort UShort1;
        [FieldOffset(2)]
        public byte Byte2;
        [FieldOffset(1)]
        public byte Byte3;
        [FieldOffset(0)]
        public ushort UShort2;
        [FieldOffset(0)]
        public byte Byte4;
    }

    public static unsafe class Program
    {
        static int count = 50000000;

        public static int ViaStructPointer()
        {
            int total = 0;

            for (int i = 0; i < count; i++)
            {
                var s = (Mask32*)&i;
                total += s->Byte1;
            }

            return total;
        }

        public static int ViaUnsafeAs()
        {
            int total = 0;

            for (int i = 0; i < count; i++)
            {
                var m = Unsafe.As<int, Mask32>(ref i);
                total += m.Byte1;
            }

            return total;
        }

        public static void Main(string[] args)
        {
            var sw = new Stopwatch();

            sw.Restart();
            ViaStructPointer();
            Console.WriteLine("ViaStructPointer took " + sw.Elapsed);

            sw.Restart();
            ViaUnsafeAs();
            Console.WriteLine("ViaUnsafeAs took " + sw.Elapsed);
        }
    }
}

我在 PC(x64 发布版本)上得到的结果如下:

ViaStructPointer took 00:00:00.1314279
ViaUnsafeAs took 00:00:00.0249446

如你所见,ViaUnsafeAs确实快多了。

那么让我们看看编译器生成了什么:

public static unsafe int ViaStructPointer()
{
    int total = 0;
    for (int i = 0; i < Program.count; i++)
    {
        total += (*(Mask32*)(&i)).Byte1;
    }
    return total;
}

public static int ViaUnsafeAs()
{
    int total = 0;
    for (int i = 0; i < Program.count; i++)
    {
        total += (Unsafe.As<int, Mask32>(ref i)).Byte1;
    }
    return total;
}   

好的,那里没有什么明显的。但是 IL 呢?

.method public hidebysig static int32 ViaStructPointer () cil managed 
{
    .locals init (
        [0] int32 total,
        [1] int32 i,
        [2] valuetype Demo.Mask32* s
    )

    IL_0000: ldc.i4.0
    IL_0001: stloc.0
    IL_0002: ldc.i4.0
    IL_0003: stloc.1
    IL_0004: br.s IL_0017
    .loop
    {
        IL_0006: ldloca.s i
        IL_0008: conv.u
        IL_0009: stloc.2
        IL_000a: ldloc.0
        IL_000b: ldloc.2
        IL_000c: ldfld uint8 Demo.Mask32::Byte1
        IL_0011: add
        IL_0012: stloc.0
        IL_0013: ldloc.1
        IL_0014: ldc.i4.1
        IL_0015: add
        IL_0016: stloc.1

        IL_0017: ldloc.1
        IL_0018: ldsfld int32 Demo.Program::count
        IL_001d: blt.s IL_0006
    }

    IL_001f: ldloc.0
    IL_0020: ret
}

.method public hidebysig static int32 ViaUnsafeAs () cil managed 
{
    .locals init (
        [0] int32 total,
        [1] int32 i,
        [2] valuetype Demo.Mask32 m
    )

    IL_0000: ldc.i4.0
    IL_0001: stloc.0
    IL_0002: ldc.i4.0
    IL_0003: stloc.1
    IL_0004: br.s IL_0020
    .loop
    {
        IL_0006: ldloca.s i
        IL_0008: call valuetype Demo.Mask32& [System.Runtime.CompilerServices.Unsafe]System.Runtime.CompilerServices.Unsafe::As<int32, valuetype Demo.Mask32>(!!0&)
        IL_000d: ldobj Demo.Mask32
        IL_0012: stloc.2
        IL_0013: ldloc.0
        IL_0014: ldloc.2
        IL_0015: ldfld uint8 Demo.Mask32::Byte1
        IL_001a: add
        IL_001b: stloc.0
        IL_001c: ldloc.1
        IL_001d: ldc.i4.1
        IL_001e: add
        IL_001f: stloc.1

        IL_0020: ldloc.1
        IL_0021: ldsfld int32 Demo.Program::count
        IL_0026: blt.s IL_0006
    }

    IL_0028: ldloc.0
    IL_0029: ret
}

啊哈!这里唯一的区别是:

ViaStructPointer: conv.u
ViaUnsafeAs:      call valuetype Demo.Mask32& [System.Runtime.CompilerServices.Unsafe]System.Runtime.CompilerServices.Unsafe::As<int32, valuetype Demo.Mask32>(!!0&)
                  ldobj Demo.Mask32

从表面上看,您会期望 conv.u 比用于 Unsafe.As 的两条指令更快。但是,JIT 编译器似乎能够比单个 conv.u.

更好地优化这两条指令。

为什么 是合理的 - 不幸的是我还没有答案!我几乎可以肯定 JITTER 正在内联对 Unsafe::As<>() 的调用,并且 JIT 正在进一步优化它。

There is some information about the Unsafe class' optimisations here.

请注意,为 Unsafe.As<> 生成的 IL 很简单:

.method public hidebysig static !!TTo& As<TFrom, TTo> (
        !!TFrom& source
    ) cil managed aggressiveinlining 
{
    .custom instance void System.Runtime.Versioning.NonVersionableAttribute::.ctor() = (
        01 00 00 00
    )
    IL_0000: ldarg.0
    IL_0001: ret
}

现在我想更清楚为什么 JITTER 可以将其优化得如此好。

当您获取本地地址时,jit 通常必须将该本地地址保存在堆栈中。这里就是这种情况。在 ViaPointer 版本中,i 保存在堆栈中。在 ViaUnsafe 中,i 被复制到一个临时文件中,临时文件保存在堆栈中。前者比较慢,因为i也是用来控制循环的迭代次数。

您可以使用以下明确复制的代码获得非常接近 ViaUnsafe 的性能:

    public static int ViaStructPointer2()
    {
        int total = 0;

        for (int i = 0; i < count; i++)
        {
            int j = i;
            var s = (Mask32*)&j;
            total += s->Byte1;
        }

        return total;
    }

ViaStructPointer  took 00:00:00.1147793
ViaUnsafeAs       took 00:00:00.0282828
ViaStructPointer2 took 00:00:00.0257589