我曾经认为如果一个方法是内联的，那么理论上它与方法和调用方法的合并是相同的，但基准测试显示性能略有不同
例如，这需要 100 毫秒
public long TestA()
{
long ret = 0;
for (int n = 0; n < testSize; n++)
{
for (int i = 0; i < a; i++)
for (int j = 0; j < b; j++)
{
ret += myArray[i][j];
}
}
return ret;
}
这需要 110 毫秒（如果我强制MethodImplOptions.NoInlining打开，GetIt那么它将是 400 毫秒，所以我假设它是自动内联的）
public long TestB()
{
long ret = 0;
for (int n = 0; n < testSize; n++)
{
for (int i = 0; i < a; i++)
for (int j = 0; j < b; j++)
{
ret += GetIt(i, j);
}
}
return ret;
}
int GetIt(int x, int y)
{
return myArray[x][y];
}
好的，我附上我使用的基准函数片段
public static void RunTests(Func<long> myTest)
{
const int numTrials = 100;
Stopwatch sw = new Stopwatch();
double[] sample = new double[numTrials];
Console.WriteLine("Checksum is {0:N0}", myTest());
sw.Start();
myTest();
sw.Stop();
Console.WriteLine("Estimated time per test is {0:N0} ticks\n", sw.ElapsedTicks);
if (sw.ElapsedTicks < 100)
{
Console.WriteLine("Ticks per test is less than 100 ticks. Suggest increase testSize.");
return;
}
if (sw.ElapsedTicks > 10000)
{
Console.WriteLine("Ticks per test is more than 10,000 ticks. Suggest decrease testSize.");
return;
}
for (int i = 0; i < numTrials / 3; i++)
{
myTest();
}
string testName = myTest.Method.Name;
Console.WriteLine("----> Starting benchmark {0}\n", myTest.Method.Name);
for (int i = 0; i < numTrials; i++)
{
GC.Collect();
GC.WaitForPendingFinalizers();
sw.Restart();
myTest();
sw.Stop();
sample[i] = sw.ElapsedTicks;
}
double testResult = DataSetAnalysis.Report(sample);
DataSetAnalysis.ConsistencyAnalyze(sample, 0.1);
Console.WriteLine();
for (int j = 0; j < numTrials; j = j + 5)
Console.WriteLine("{0,8:N0} {1,8:N0} {2,8:N0} {3,8:N0} {4,8:N0}", sample[j], sample[j + 1], sample[j + 2], sample[j + 3], sample[j + 4]);
Console.WriteLine("\n----> End of benchmark");
}