避免C#虚拟调用的开销
我有一些高度优化的数学函数,需要避免C#虚拟调用的开销,c#,virtual-functions,micro-optimization,C#,Virtual Functions,Micro Optimization,我有一些高度优化的数学函数,需要1-2纳秒才能完成。这些函数每秒被调用数亿次,因此尽管性能已经很好,调用开销仍然是一个问题 为了保持程序的可维护性,提供这些方法的类继承了一个IMathFunction接口,以便其他对象可以直接存储特定的数学函数,并在需要时使用它 public interface IMathFunction { double Calculate(double input); double Derivate(double input); } public SomeObje
1-2纳秒才能完成。这些函数每秒被调用数亿次,因此尽管性能已经很好,调用开销仍然是一个问题
为了保持程序的可维护性,提供这些方法的类继承了一个IMathFunction
接口,以便其他对象可以直接存储特定的数学函数,并在需要时使用它
public interface IMathFunction
{
double Calculate(double input);
double Derivate(double input);
}
public SomeObject
{
// Note: There are cases where this is mutable
private readonly IMathFunction mathFunction_;
public double SomeWork(double input, double step)
{
var f = mathFunction_.Calculate(input);
var dv = mathFunction_.Derivate(input);
return f - (dv * step);
}
}
与直接调用相比,这个接口由于使用它的代码如何使用而造成了巨大的开销。直接调用需要1-2ns,而虚拟接口调用需要8-9ns。显然,接口的存在及其虚拟调用的后续转换是该场景的瓶颈
如果可能,我希望保留可维护性和性能在实例化对象时,是否有一种方法可以将虚拟函数解析为直接调用,以便所有后续调用都能够避免开销?我假设这将涉及使用IL创建委托,但是我不知道从哪里开始。因此这有明显的局限性,不应该在任何有接口的地方一直使用,但是如果你有一个地方需要最大化性能,你可以使用泛型:
public SomeObject<TMathFunction> where TMathFunction: struct, IMathFunction
{
private readonly TMathFunction mathFunction_;
public double SomeWork(double input, double step)
{
var f = mathFunction_.Calculate(input);
var dv = mathFunction_.Derivate(input);
return f - (dv * step);
}
}
。。。以及结构版本和抽象版本
下面是界面版本的情况。您可以看到它的效率相对较低,因为它执行两个级别的间接寻址:
return obj.SomeWork(input, step);
sub esp,40h
vzeroupper
vmovaps xmmword ptr [rsp+30h],xmm6
vmovaps xmmword ptr [rsp+20h],xmm7
mov rsi,rcx
vmovsd qword ptr [rsp+60h],xmm2
vmovaps xmm6,xmm1
mov rcx,qword ptr [rsi+8] ; load mathFunction_ into rcx.
vmovaps xmm1,xmm6
mov r11,7FFED7980020h ; load vtable address of the IMathFunction.Calculate function.
cmp dword ptr [rcx],ecx
call qword ptr [r11] ; call IMathFunction.Calculate function which will call the actual Calculate via vtable.
vmovaps xmm7,xmm0
mov rcx,qword ptr [rsi+8] ; load mathFunction_ into rcx.
vmovaps xmm1,xmm6
mov r11,7FFED7980028h ; load vtable address of the IMathFunction.Derivate function.
cmp dword ptr [rcx],ecx
call qword ptr [r11] ; call IMathFunction.Derivate function which will call the actual Derivate via vtable.
vmulsd xmm0,xmm0,mmword ptr [rsp+60h] ; dv * step
vsubsd xmm7,xmm7,xmm0 ; f - (dv * step)
vmovaps xmm0,xmm7
vmovaps xmm6,xmmword ptr [rsp+30h]
vmovaps xmm7,xmmword ptr [rsp+20h]
add rsp,40h
pop rsi
ret
这是一个抽象类。它的效率稍高一些,但只是可以忽略不计:
return obj.SomeWork(input, step);
sub esp,40h
vzeroupper
vmovaps xmmword ptr [rsp+30h],xmm6
vmovaps xmmword ptr [rsp+20h],xmm7
mov rsi,rcx
vmovsd qword ptr [rsp+60h],xmm2
vmovaps xmm6,xmm1
mov rcx,qword ptr [rsi+8] ; load mathFunction_ into rcx.
vmovaps xmm1,xmm6
mov rax,qword ptr [rcx] ; load object type data from mathFunction_.
mov rax,qword ptr [rax+40h] ; load address of vtable into rax.
call qword ptr [rax+20h] ; call Calculate via offset 0x20 of vtable.
vmovaps xmm7,xmm0
mov rcx,qword ptr [rsi+8] ; load mathFunction_ into rcx.
vmovaps xmm1,xmm6
mov rax,qword ptr [rcx] ; load object type data from mathFunction_.
mov rax,qword ptr [rax+40h] ; load address of vtable into rax.
call qword ptr [rax+28h] ; call Derivate via offset 0x28 of vtable.
vmulsd xmm0,xmm0,mmword ptr [rsp+60h] ; dv * step
vsubsd xmm7,xmm7,xmm0 ; f - (dv * step)
vmovaps xmm0,xmm7
vmovaps xmm6,xmmword ptr [rsp+30h]
vmovaps xmm7,xmmword ptr [rsp+20h]
add rsp,40h
pop rsi
ret
因此,接口和抽象类都严重依赖分支目标预测来获得可接受的性能。即使这样,你也可以看到还有很多事情要做,所以最好的情况还是相对缓慢,而最坏的情况是由于预测失误导致管道停滞
最后是带有结构的通用版本。您可以看到它的效率大大提高,因为所有内容都已完全内联,因此不涉及分支预测。它还有一个很好的副作用,就是删除了其中的大部分堆栈/参数管理,因此代码变得非常紧凑:
return obj.SomeWork(input, step);
push rax
vzeroupper
movsx rax,byte ptr [rcx+8]
vmovaps xmm0,xmm1
vaddsd xmm0,xmm0,xmm1 ; Calculate - got inlined
vmulsd xmm1,xmm1,xmm1 ; Derivate - got inlined
vmulsd xmm1,xmm1,xmm2 ; dv * step
vsubsd xmm0,xmm0,xmm1 ; f -
add rsp,8
ret
我会将方法分配给代表。这允许您仍然针对接口编程,同时避免接口方法解析
public SomeObject
{
private readonly Func<double, double> _calculate;
private readonly Func<double, double> _derivate;
public SomeObject(IMathFunction mathFunction)
{
_calculate = mathFunction.Calculate;
_derivate = mathFunction.Derivate;
}
public double SomeWork(double input, double step)
{
var f = _calculate(input);
var dv = _derivate(input);
return f - (dv * step);
}
}
公共对象
{
私有只读函数计算;
私有只读函数派生;
公共SomeObject(IMathFunction mathFunction)
{
_计算=数学函数。计算;
_导数=数学函数。导数;
}
公共双工(双输入、双步骤)
{
var f=_计算(输入);
var dv=_导数(输入);
返回f-(dv*步);
}
}
作为对@CoryNelson评论的回应,我进行了测试,以了解真正的影响。我已经密封了function类,但这似乎没有什么区别,因为我的方法不是虚拟的
用大括号减去空方法时间的测试结果(1亿次迭代的平均时间,单位为ns):
空工作方法:1.48
接口:5.69(4.21)
代表:5.78(4.30)
密封等级:2.10(0.62)
类别:2.12(0.64)
委托版本时间与接口版本的时间大致相同(具体时间因测试执行而异)。与类相反的工作速度大约快6.8倍(比较时间减去空的工作方法时间)!这意味着我建议与代表一起工作没有帮助
令我惊讶的是,我期望接口版本的执行时间要长得多。由于这种测试并不代表OP代码的确切上下文,因此其有效性受到限制
static class TimingInterfaceVsDelegateCalls
{
const int N = 100_000_000;
const double msToNs = 1e6 / N;
static SquareFunctionSealed _mathFunctionClassSealed;
static SquareFunction _mathFunctionClass;
static IMathFunction _mathFunctionInterface;
static Func<double, double> _calculate;
static Func<double, double> _derivate;
static TimingInterfaceVsDelegateCalls()
{
_mathFunctionClass = new SquareFunction();
_mathFunctionClassSealed = new SquareFunctionSealed();
_mathFunctionInterface = _mathFunctionClassSealed;
_calculate = _mathFunctionInterface.Calculate;
_derivate = _mathFunctionInterface.Derivate;
}
interface IMathFunction
{
double Calculate(double input);
double Derivate(double input);
}
sealed class SquareFunctionSealed : IMathFunction
{
public double Calculate(double input)
{
return input * input;
}
public double Derivate(double input)
{
return 2 * input;
}
}
class SquareFunction : IMathFunction
{
public double Calculate(double input)
{
return input * input;
}
public double Derivate(double input)
{
return 2 * input;
}
}
public static void Test()
{
var stopWatch = new Stopwatch();
stopWatch.Start();
for (int i = 0; i < N; i++) {
double result = SomeWorkEmpty(i);
}
stopWatch.Stop();
double emptyTime = stopWatch.ElapsedMilliseconds * msToNs;
Console.WriteLine($"Empty Work method: {emptyTime:n2}");
stopWatch.Restart();
for (int i = 0; i < N; i++) {
double result = SomeWorkInterface(i);
}
stopWatch.Stop();
PrintResult("Interface", stopWatch.ElapsedMilliseconds, emptyTime);
stopWatch.Restart();
for (int i = 0; i < N; i++) {
double result = SomeWorkDelegate(i);
}
stopWatch.Stop();
PrintResult("Delegates", stopWatch.ElapsedMilliseconds, emptyTime);
stopWatch.Restart();
for (int i = 0; i < N; i++) {
double result = SomeWorkClassSealed(i);
}
stopWatch.Stop();
PrintResult("Sealed Class", stopWatch.ElapsedMilliseconds, emptyTime);
stopWatch.Restart();
for (int i = 0; i < N; i++) {
double result = SomeWorkClass(i);
}
stopWatch.Stop();
PrintResult("Class", stopWatch.ElapsedMilliseconds, emptyTime);
}
private static void PrintResult(string text, long elapsed, double emptyTime)
{
Console.WriteLine($"{text}: {elapsed * msToNs:n2} ({elapsed * msToNs - emptyTime:n2})");
}
[MethodImpl(MethodImplOptions.NoInlining)]
private static double SomeWorkEmpty(int i)
{
return 0.0;
}
[MethodImpl(MethodImplOptions.NoInlining)]
private static double SomeWorkInterface(int i)
{
double f = _mathFunctionInterface.Calculate(i);
double dv = _mathFunctionInterface.Derivate(i);
return f - (dv * 12.34534);
}
[MethodImpl(MethodImplOptions.NoInlining)]
private static double SomeWorkDelegate(int i)
{
double f = _calculate(i);
double dv = _derivate(i);
return f - (dv * 12.34534);
}
[MethodImpl(MethodImplOptions.NoInlining)]
private static double SomeWorkClassSealed(int i)
{
double f = _mathFunctionClassSealed.Calculate(i);
double dv = _mathFunctionClassSealed.Derivate(i);
return f - (dv * 12.34534);
}
[MethodImpl(MethodImplOptions.NoInlining)]
private static double SomeWorkClass(int i)
{
double f = _mathFunctionClass.Calculate(i);
double dv = _mathFunctionClass.Derivate(i);
return f - (dv * 12.34534);
}
}
静态类计时interfacevsdelegatecalls
{
常数int N=100_000_000;
常数双mston=1e6/N;
静态SquareFunctionSealed _mathFunctionClassSealed;
静态平方函数mathFunctionClass;
静态IMathFunction\u mathFunctionInterface;
静态函数计算;
静态函数导数;
静态计时interfacevsdelegatecalls()
{
_mathFunctionClass=新的平方函数();
_mathFunctionClassSealed=新的SquareFunctionSealed();
_mathFunctionInterface=\u mathFunctionClassSealed;
_calculate=\u mathFunctionInterface.calculate;
_派生=_mathFunctionInterface.derivate;
}
接口IMathFunction
{
双计算(双输入);
双导数(双输入);
}
密封类SquareFunction密封:IMathFunction
{
公共双计算(双输入)
{
返回输入*输入;
}
公共双导数(双输入)
{
返回2*输入;
}
}
类SquareFunction:IMathFunction
{
公共双计算(双输入)
{
返回输入*输入;
}
公共双导数(双输入)
{
返回2*输入;
}
}
公共静态无效测试()
{
var stopWatch=新秒表();
秒表。开始();
对于(int i=0;istatic class TimingInterfaceVsDelegateCalls
{
const int N = 100_000_000;
const double msToNs = 1e6 / N;
static SquareFunctionSealed _mathFunctionClassSealed;
static SquareFunction _mathFunctionClass;
static IMathFunction _mathFunctionInterface;
static Func<double, double> _calculate;
static Func<double, double> _derivate;
static TimingInterfaceVsDelegateCalls()
{
_mathFunctionClass = new SquareFunction();
_mathFunctionClassSealed = new SquareFunctionSealed();
_mathFunctionInterface = _mathFunctionClassSealed;
_calculate = _mathFunctionInterface.Calculate;
_derivate = _mathFunctionInterface.Derivate;
}
interface IMathFunction
{
double Calculate(double input);
double Derivate(double input);
}
sealed class SquareFunctionSealed : IMathFunction
{
public double Calculate(double input)
{
return input * input;
}
public double Derivate(double input)
{
return 2 * input;
}
}
class SquareFunction : IMathFunction
{
public double Calculate(double input)
{
return input * input;
}
public double Derivate(double input)
{
return 2 * input;
}
}
public static void Test()
{
var stopWatch = new Stopwatch();
stopWatch.Start();
for (int i = 0; i < N; i++) {
double result = SomeWorkEmpty(i);
}
stopWatch.Stop();
double emptyTime = stopWatch.ElapsedMilliseconds * msToNs;
Console.WriteLine($"Empty Work method: {emptyTime:n2}");
stopWatch.Restart();
for (int i = 0; i < N; i++) {
double result = SomeWorkInterface(i);
}
stopWatch.Stop();
PrintResult("Interface", stopWatch.ElapsedMilliseconds, emptyTime);
stopWatch.Restart();
for (int i = 0; i < N; i++) {
double result = SomeWorkDelegate(i);
}
stopWatch.Stop();
PrintResult("Delegates", stopWatch.ElapsedMilliseconds, emptyTime);
stopWatch.Restart();
for (int i = 0; i < N; i++) {
double result = SomeWorkClassSealed(i);
}
stopWatch.Stop();
PrintResult("Sealed Class", stopWatch.ElapsedMilliseconds, emptyTime);
stopWatch.Restart();
for (int i = 0; i < N; i++) {
double result = SomeWorkClass(i);
}
stopWatch.Stop();
PrintResult("Class", stopWatch.ElapsedMilliseconds, emptyTime);
}
private static void PrintResult(string text, long elapsed, double emptyTime)
{
Console.WriteLine($"{text}: {elapsed * msToNs:n2} ({elapsed * msToNs - emptyTime:n2})");
}
[MethodImpl(MethodImplOptions.NoInlining)]
private static double SomeWorkEmpty(int i)
{
return 0.0;
}
[MethodImpl(MethodImplOptions.NoInlining)]
private static double SomeWorkInterface(int i)
{
double f = _mathFunctionInterface.Calculate(i);
double dv = _mathFunctionInterface.Derivate(i);
return f - (dv * 12.34534);
}
[MethodImpl(MethodImplOptions.NoInlining)]
private static double SomeWorkDelegate(int i)
{
double f = _calculate(i);
double dv = _derivate(i);
return f - (dv * 12.34534);
}
[MethodImpl(MethodImplOptions.NoInlining)]
private static double SomeWorkClassSealed(int i)
{
double f = _mathFunctionClassSealed.Calculate(i);
double dv = _mathFunctionClassSealed.Derivate(i);
return f - (dv * 12.34534);
}
[MethodImpl(MethodImplOptions.NoInlining)]
private static double SomeWorkClass(int i)
{
double f = _mathFunctionClass.Calculate(i);
double dv = _mathFunctionClass.Derivate(i);
return f - (dv * 12.34534);
}
}