Posts about JIT

LegacyJIT-x86 and first method call



Today I tell you about one of my favorite benchmarks (this method doesn't return a useful value, we need it only as an example):

[Benchmark]
public string Sum()
{
    double a = 1, b = 1;
    var sw = new Stopwatch();
    for (int i = 0; i < 10001; i++)
        a = a + b;
    return string.Format("{0}{1}", a, sw.ElapsedMilliseconds);
}

An interesting fact: if you call Stopwatch.GetTimestamp() before the first call of the Sum method, you improve Sum performance several times (works only with LegacyJIT-x86).

Read more    Comments


RyuJIT RC and constant folding



Update: The below results are valid for the release version of RyuJIT.

The challenge of the day: which method is faster?

public double Sqrt13()
{
    return Math.Sqrt(1) + Math.Sqrt(2) + Math.Sqrt(3) + Math.Sqrt(4) + Math.Sqrt(5) + 
           Math.Sqrt(6) + Math.Sqrt(7) + Math.Sqrt(8) + Math.Sqrt(9) + Math.Sqrt(10) + 
           Math.Sqrt(11) + Math.Sqrt(12) + Math.Sqrt(13);
}
public double Sqrt14()
{
    return Math.Sqrt(1) + Math.Sqrt(2) + Math.Sqrt(3) + Math.Sqrt(4) + Math.Sqrt(5) + 
           Math.Sqrt(6) + Math.Sqrt(7) + Math.Sqrt(8) + Math.Sqrt(9) + Math.Sqrt(10) + 
           Math.Sqrt(11) + Math.Sqrt(12) + Math.Sqrt(13) + Math.Sqrt(14);
}

I have measured the methods performance with help of BenchmarkDotNet for RyuJIT RC (a part of .NET Framework 4.6 RC) and received the following results:

// BenchmarkDotNet=v0.7.4.0
// OS=Microsoft Windows NT 6.2.9200.0
// Processor=Intel(R) Core(TM) i7-4702MQ CPU @ 2.20GHz, ProcessorCount=8
// CLR=MS.NET 4.0.30319.0, Arch=64-bit  [RyuJIT]
Common:  Type=Math_DoubleSqrtAvx  Mode=Throughput  Platform=X64  Jit=RyuJit  .NET=Current  

 Method |  AvrTime |    StdDev |         op/s |
------- |--------- |---------- |------------- |
 Sqrt13 | 55.40 ns |  0.571 ns |  18050993.06 |
 Sqrt14 |  1.43 ns | 0.0224 ns | 697125029.18 |

How so? If I add one more Math.Sqrt to the expression, the method starts work 40 times faster! Let's examine the situation..

Read more    Comments


Unrolling of small loops in different JIT versions



Challenge of the day: what will the following code display?

struct Point
{
    public int X;
    public int Y;
}
static void Print(Point p)
{
    Console.WriteLine(p.X + " " + p.Y);
}
static void Main()
{
    var p = new Point();
    for (p.X = 0; p.X < 2; p.X++)
        Print(p);
}

The right answer: it depends. There is a bug in CLR2 JIT-x86 which spoil this wonderful program. This story is about optimization that called unrolling of small loops. This is a very interesting theme, let's discuss it in detail.

Read more    Comments


RyuJIT CTP5 and loop unrolling



RyuJIT will be available soon. It is a next generation JIT-compiler for .NET-applications. Microsoft likes to tell us about the benefits of SIMD using and JIT-compilation time reducing. But what about basic code optimization which is usually applying by a compiler? Today we talk about the loop unrolling (unwinding) optimization. In general, in this type of code optimization, the code

for (int i = 0; i < 1024; i++)
    Foo(i);

transforms to

for (int i = 0; i < 1024; i += 4)
{
    Foo(i);
    Foo(i + 1);
    Foo(i + 2);
    Foo(i + 3);
}

Such approach can significantly increase performance of your code. So, what's about loop unrolling in .NET?

Read more    Comments


JIT version determining in runtime



Sometimes I want to know used JIT compiler version in my little C# experiments. It is clear that it is possible to determine the version in advance based on the environment. However, sometimes I want to know it in runtime to perform specific code for the current JIT compiler. More formally, I want to get the value from the following enum:

public enum JitVersion
{
    Mono, MsX86, MsX64, RyuJit
}

It is easy to detect Mono by existing of the Mono.Runtime class. Otherwise, we can assume that we work with Microsoft JIT implementation. It is easy to detect JIT-x86 with help of IntPtr.Size == 4. The challenge is to distinguish JIT-x64 and RyuJIT. Next, I will show how you can do it with help of the bug from my previous post.

Read more    Comments


A bug story about JIT-x64



Can you say, what will the following code display for step=1?

public void Foo(int step)
{
    for (int i = 0; i < step; i++)
    {
        bar = i + 10;
        for (int j = 0; j < 2 * step; j += step)
            Console.WriteLine(j + 10);
    }
}

If you think about specific numbers, you are wrong. The right answer: it depends. The post title suggests to us, the program can has a strange behavior for x64.

Read more    Comments