EgorBot for EgorBo in #107304

[EgorBot]

Processing dotnet/runtime#107304 (comment) command:

Command

-awsamd -commit 72f9ee0d26c23b3c58ec5af8aeea316095761646 vs 767e4165641583c73918168a920a10513000572c -profiler --envvars DOTNET_JitDisasm:TrailingZeroCount_ulong

using BenchmarkDotNet.Attributes;
using BenchmarkDotNet.Running;
using System.Numerics;
using System.Runtime.CompilerServices;

public class Perf_BitOperations
{
    static T[] Array<T>(int count, int? seed = null)
    {
        var result = new T[count];
        var random = new Random(42);
        if (typeof(T) == typeof(byte) || typeof(T) == typeof(sbyte))
            random.NextBytes(Unsafe.As<byte[]>(result));
        else
            for (int i = 0; i < result.Length; i++)
                result[i] = GenerateValue<T>(random);
        return result;
    }

    static T GenerateValue<T>(Random random)
    {
        if (typeof(T) == typeof(uint))
            return (T)(object)(uint)random.Next();
        if (typeof(T) == typeof(ulong))
            return (T)(object)(ulong)random.Next();
        throw new NotImplementedException();
    }

    static uint[] input_uint = Array<uint>(1000);
    static ulong[] input_ulong = Array<ulong>(1000);

    [Benchmark]
    public int TrailingZeroCount_ulong()
    {
        int sum = 0;
        ulong[] input = input_ulong;
        for (int i = 0; i < input.Length; i++)
        {
            sum += BitOperations.TrailingZeroCount(input[i]);
        }
        return sum;
    }
}

(EgorBot will reply in this issue)

[EgorBot]

Benchmark results on c7a_4xlarge

BenchmarkDotNet v0.14.0, Ubuntu 24.04 LTS (Noble Numbat)
AMD EPYC 9R14, 1 CPU, 16 logical and 16 physical cores
  Job-XAGHSR : .NET 9.0.0 (42.42.42.42424), X64 RyuJIT AVX-512F+CD+BW+DQ+VL+VBMI
  Job-FPFXDN : .NET 9.0.0 (42.42.42.42424), X64 RyuJIT AVX-512F+CD+BW+DQ+VL+VBMI
EnvironmentVariables=DOTNET_JitDisasm=TrailingZeroCount_ulong

Method	Toolchain	Mean	Error	Ratio
TrailingZeroCount_ulong	Before	279.5 ns	0.10 ns	1.00
TrailingZeroCount_ulong	After	278.0 ns	0.22 ns	0.99

BDN_Artifacts.zip

Flame graphs: Main vs PR 🔥
Hot asm: Main vs PR
Hot functions: Main vs PR
Counters: Main vs PR

For clean perf results, make sure you have just one [Benchmark] in your app.

[EgorBot]

cc @EgorBo (logs)

[EgorBo]

@EgorBot -awsamd -commit 72f9ee0d26c23b3c58ec5af8aeea316095761646 vs 767e4165641583c73918168a920a10513000572c -profiler --envvars DOTNET_JitDisasm:TrailingZeroCount_ulong

using BenchmarkDotNet.Attributes;
using BenchmarkDotNet.Running;
using System.Numerics;
using System.Runtime.CompilerServices;

public class Perf_BitOperations
{
    static T[] Array<T>(int count, int? seed = null)
    {
        var result = new T[count];
        var random = new Random(42);
        if (typeof(T) == typeof(byte) || typeof(T) == typeof(sbyte))
            random.NextBytes(Unsafe.As<byte[]>(result));
        else
            for (int i = 0; i < result.Length; i++)
                result[i] = GenerateValue<T>(random);
        return result;
    }

    static T GenerateValue<T>(Random random)
    {
        if (typeof(T) == typeof(uint))
            return (T)(object)(uint)random.Next();
        if (typeof(T) == typeof(ulong))
            return (T)(object)(ulong)random.Next();
        throw new NotImplementedException();
    }

    static uint[] input_uint = Array<uint>(1000);
    static ulong[] input_ulong = Array<ulong>(1000);

    [Benchmark]
    public int TrailingZeroCount_ulong()
    {
        int sum = 0;
        ulong[] input = input_ulong;
        for (int i = 0; i < input.Length; i++)
        {
            sum += BitOperations.TrailingZeroCount(input[i]);
        }
        return sum;
    }
}