ReplacePlusWithSpaceCore_benchmark.cs

using System.Buffers;
using System.Runtime.CompilerServices;
using System.Runtime.InteropServices;
using System.Runtime.Intrinsics;
using System.Runtime.Intrinsics.X86;
using System.Text;
using BenchmarkDotNet.Attributes;
using BenchmarkDotNet.Configs;
using BenchmarkDotNet.Jobs;
using BenchmarkDotNet.Running;
using BenchmarkDotNet.Toolchains.CsProj;
using BenchmarkDotNet.Toolchains.DotNetCli;

BenchmarkRunner.Run<ReplacePlusWithSpaceBenchmark>();

[DisassemblyDiagnoser(printSource: true, maxDepth: 10)]
[MemoryDiagnoser]
[ReturnValueValidator]
[Config(typeof(CustomPathsConfig))]
public class ReplacePlusWithSpaceBenchmark
{
    public class CustomPathsConfig : ManualConfig
    {
        public CustomPathsConfig()
        {
            var dotnetCli64bit = new NetCoreAppSettings("net7.0", null, ".NET 7.0.100-preview.6.22307.20")
                .WithCustomDotNetCliPath(@"C:\Users\mezia\Downloads\dotnet-sdk-7.0.100-preview.6.22307.20-win-x64\dotnet.exe");

            AddJob(Job.RyuJitX64.WithToolchain(CsProjCoreToolchain.From(dotnetCli64bit)));
        }
    }

    [ParamsSource(nameof(ValueSource))]
    public string Value { get; set; } = null!;

    public IEnumerable<string> ValueSource
    {
        get
        {
            for (int i = 0; i < 256; i += 8)
            {
                yield return CreateString(i);
            }

            for (int i = 0; i < 100; i += 3)
            {
                if (i % 8 != 0)
                {
                    yield return CreateString(i);
                }
            }

            static string CreateString(int length)
            {
                var sb = new StringBuilder();
                sb.Append('a', length);
                for (int i = 0; i < length; i += 5)
                {
                    sb[i] = '+';
                }

                return sb.ToString();
            }
        }
    }

    //[Benchmark(Baseline = true)]
    //public string Basic() => BasicHelper.ReplacePlusWithSpace(Value);

    //[Benchmark]
    //public string StringReplace() => Value.Replace('+', ' ');

    [Benchmark(Baseline = true)]
    public string Current() => Vector128Helper_Sse.ReplacePlusWithSpace(Value);

    [Benchmark]
    public string Vector128() => Vector128Helper.ReplacePlusWithSpace(Value);

    [Benchmark]
    public string Vector256() => Vector256Helper.ReplacePlusWithSpace(Value);
}

public static class BasicHelper
{
    private static readonly SpanAction<char, IntPtr> s_replacePlusWithSpace = ReplacePlusWithSpaceCore;

    [MethodImpl(MethodImplOptions.AggressiveInlining)]
    public static unsafe string ReplacePlusWithSpace(ReadOnlySpan<char> span)
    {
        fixed (char* ptr = &MemoryMarshal.GetReference(span))
        {
            return string.Create(span.Length, (IntPtr)ptr, s_replacePlusWithSpace);
        }
    }

    private static unsafe void ReplacePlusWithSpaceCore(Span<char> buffer, IntPtr state)
    {
        fixed (char* ptr = &MemoryMarshal.GetReference(buffer))
        {
            var input = (ushort*)state.ToPointer();
            var output = (ushort*)ptr;
            var i = (nint)0;
            var n = (nint)(uint)buffer.Length;
            for (; i < n; ++i)
            {
                if (input[i] != '+')
                {
                    output[i] = input[i];
                }
                else
                {
                    output[i] = ' ';
                }
            }
        }
    }
}

public static class Vector128Helper_Sse
{
    private static readonly SpanAction<char, IntPtr> s_replacePlusWithSpace = ReplacePlusWithSpaceCore;

    [MethodImpl(MethodImplOptions.AggressiveInlining)]
    public static unsafe string ReplacePlusWithSpace(ReadOnlySpan<char> span)
    {
        fixed (char* ptr = &MemoryMarshal.GetReference(span))
        {
            return string.Create(span.Length, (IntPtr)ptr, s_replacePlusWithSpace);
        }
    }

    private static unsafe void ReplacePlusWithSpaceCore(Span<char> buffer, IntPtr state)
    {
        fixed (char* ptr = &MemoryMarshal.GetReference(buffer))
        {
            var input = (ushort*)state.ToPointer();
            var output = (ushort*)ptr;

            var i = (nint)0;
            var n = (nint)(uint)buffer.Length;

            if (Sse41.IsSupported && n >= Vector128<ushort>.Count)
            {
                var vecPlus = Vector128.Create((ushort)'+');
                var vecSpace = Vector128.Create((ushort)' ');

                do
                {
                    var vec = Sse2.LoadVector128(input + i);
                    var mask = Sse2.CompareEqual(vec, vecPlus);
                    var res = Sse41.BlendVariable(vec, vecSpace, mask);
                    Sse2.Store(output + i, res);
                    i += Vector128<ushort>.Count;

                } while (i <= n - Vector128<ushort>.Count);
            }

            for (; i < n; ++i)
            {
                if (input[i] != '+')
                {
                    output[i] = input[i];
                }
                else
                {
                    output[i] = ' ';
                }
            }
        }
    }
}

public static class Vector128Helper
{
    private static readonly SpanAction<char, IntPtr> s_replacePlusWithSpace = ReplacePlusWithSpaceCore;

    [MethodImpl(MethodImplOptions.AggressiveInlining)]
    public static unsafe string ReplacePlusWithSpace(ReadOnlySpan<char> span)
    {
        fixed (char* ptr = &MemoryMarshal.GetReference(span))
        {
            return string.Create(span.Length, (IntPtr)ptr, s_replacePlusWithSpace);
        }
    }

    public static unsafe void ReplacePlusWithSpaceCore(Span<char> buffer, IntPtr state)
    {
        fixed (char* ptr = &MemoryMarshal.GetReference(buffer))
        {
            var input = (ushort*)state.ToPointer();
            var output = (ushort*)ptr;
            var i = (nint)0;
            var n = (nint)(uint)buffer.Length;

            if (n >= Vector128<ushort>.Count)
            {
                var vecPlus = Vector128.Create((ushort)'+');
                var vecSpace = Vector128.Create((ushort)' ');

                do
                {
                    var vec = Vector128.Load(input + i);
                    var mask = Vector128.Equals(vec, vecPlus);
                    var res = Vector128.ConditionalSelect(mask, vecSpace, vec);
                    res.Store(output + i);
                    i += Vector128<ushort>.Count;

                } while (i <= n - Vector128<ushort>.Count);
            }

            for (; i < n; ++i)
            {
                if (input[i] != '+')
                {
                    output[i] = input[i];
                }
                else
                {
                    output[i] = ' ';
                }
            }
        }
    }
}

public static class Vector256Helper
{
    private static readonly SpanAction<char, IntPtr> s_replacePlusWithSpace = ReplacePlusWithSpaceCore;

    [MethodImpl(MethodImplOptions.AggressiveInlining)]
    public static unsafe string ReplacePlusWithSpace(ReadOnlySpan<char> span)
    {
        fixed (char* ptr = &MemoryMarshal.GetReference(span))
        {
            return string.Create(span.Length, (IntPtr)ptr, s_replacePlusWithSpace);
        }
    }

    private static unsafe void ReplacePlusWithSpaceCore(Span<char> buffer, IntPtr state)
    {
        fixed (char* ptr = &MemoryMarshal.GetReference(buffer))
        {
            var input = (ushort*)state.ToPointer();
            var output = (ushort*)ptr;

            var i = (nint)0;
            var n = (nint)(uint)buffer.Length;

            if (Vector256.IsHardwareAccelerated && n >= Vector256<ushort>.Count)
            {
                var vecPlus = Vector256.Create((ushort)'+');
                var vecSpace = Vector256.Create((ushort)' ');

                do
                {
                    var vec = Vector256.Load(input + i);
                    var mask = Vector256.Equals(vec, vecPlus);
                    var res = Vector256.ConditionalSelect(mask, vecSpace, vec);
                    res.Store(output + i);
                    i += Vector256<ushort>.Count;
                } while (i <= n - Vector256<ushort>.Count);
            }

            if (Vector128.IsHardwareAccelerated && n - i >= Vector128<ushort>.Count)
            {
                var vecPlus = Vector128.Create((ushort)'+');
                var vecSpace = Vector128.Create((ushort)' ');

                do
                {
                    var vec = Vector128.Load(input + i);
                    var mask = Vector128.Equals(vec, vecPlus);
                    var res = Vector128.ConditionalSelect(mask, vecSpace, vec);
                    res.Store(output + i);
                    i += Vector128<ushort>.Count;
                } while (i <= n - Vector128<ushort>.Count);
            }

            for (; i < n; ++i)
            {
                if (input[i] != '+')
                {
                    output[i] = input[i];
                }
                else
                {
                    output[i] = ' ';
                }
            }
        }
    }
}

result.md

BenchmarkDotNet=v0.13.1, OS=Windows 10.0.22621
AMD Ryzen 7 5800X, 1 CPU, 16 logical and 8 physical cores
.NET SDK=7.0.100-preview.4.22252.9
  [Host]    : .NET 7.0.0 (7.0.22.22904), X64 RyuJIT
  RyuJitX64 : .NET 7.0.0 (7.0.22.30504), X64 RyuJIT

Job=RyuJitX64  Jit=RyuJit  Platform=X64  
Toolchain=.NET 7.0.100-preview.6.22307.20  

Method	Value	Mean	Error	StdDev	Median	Ratio	RatioSD	Code Size	Gen 0	Gen 1	Allocated
Current	****	1.317 ns	0.0165 ns	0.0138 ns	1.319 ns	1.00	0.00	268 B	-	-	-
Vector128		1.379 ns	0.0266 ns	0.0208 ns	1.375 ns	1.05	0.03	268 B	-	-	-
Vector256		1.310 ns	0.0389 ns	0.0364 ns	1.294 ns	1.00	0.03	268 B	-	-	-
Current	+aa	6.731 ns	0.1773 ns	0.3106 ns	6.705 ns	1.00	0.00	268 B	0.0019	-	32 B
Vector128	+aa	6.698 ns	0.1804 ns	0.2644 ns	6.645 ns	1.00	0.06	268 B	0.0019	-	32 B
Vector256	+aa	6.723 ns	0.1790 ns	0.1915 ns	6.734 ns	1.01	0.06	268 B	0.0019	-	32 B
Current	+aaaa+	8.237 ns	0.1365 ns	0.1139 ns	8.214 ns	1.00	0.00	268 B	0.0024	-	40 B
Vector128	+aaaa+	8.109 ns	0.1052 ns	0.0933 ns	8.114 ns	0.99	0.02	268 B	0.0024	-	40 B
Vector256	+aaaa+	8.713 ns	0.2150 ns	0.3765 ns	8.721 ns	1.07	0.05	268 B	0.0024	-	40 B
Current	+aaaa+aa	5.837 ns	0.1348 ns	0.1125 ns	5.808 ns	1.00	0.00	268 B	0.0024	-	40 B
Vector128	+aaaa+aa	5.711 ns	0.1591 ns	0.2068 ns	5.698 ns	0.98	0.05	268 B	0.0024	-	40 B
Vector256	+aaaa+aa	5.875 ns	0.0769 ns	0.0719 ns	5.878 ns	1.01	0.02	268 B	0.0024	-	40 B
Current	+aaaa+aaa	5.998 ns	0.1526 ns	0.3568 ns	5.842 ns	1.00	0.00	268 B	0.0024	-	40 B
Vector128	+aaaa+aaa	5.775 ns	0.1323 ns	0.1238 ns	5.778 ns	0.91	0.05	268 B	0.0024	-	40 B
Vector256	+aaaa+aaa	6.034 ns	0.1181 ns	0.1047 ns	6.032 ns	0.95	0.07	268 B	0.0024	-	40 B
Current	+aaaa+aaaa+a	7.784 ns	0.1768 ns	0.1654 ns	7.804 ns	1.00	0.00	268 B	0.0029	-	48 B
Vector128	+aaaa+aaaa+a	7.667 ns	0.1610 ns	0.1427 ns	7.639 ns	0.99	0.03	268 B	0.0029	-	48 B
Vector256	+aaaa+aaaa+a	7.859 ns	0.1180 ns	0.0921 ns	7.879 ns	1.01	0.02	268 B	0.0029	-	48 B
Current	+aaaa+aaaa+aaaa	9.351 ns	0.2320 ns	0.3252 ns	9.347 ns	1.00	0.00	268 B	0.0033	-	56 B
Vector128	+aaaa+aaaa+aaaa	9.617 ns	0.2375 ns	0.5409 ns	9.608 ns	1.07	0.07	268 B	0.0033	-	56 B
Vector256	+aaaa+aaaa+aaaa	9.842 ns	0.2407 ns	0.5077 ns	9.868 ns	1.08	0.06	268 B	0.0033	-	56 B
Current	+aaaa+aaaa+aaaa+	6.934 ns	0.1839 ns	0.4335 ns	6.952 ns	1.00	0.00	268 B	0.0033	-	56 B
Vector128	+aaaa+aaaa+aaaa+	6.356 ns	0.1703 ns	0.1749 ns	6.329 ns	0.97	0.05	268 B	0.0033	-	56 B
Vector256	+aaaa+aaaa+aaaa+	6.093 ns	0.1166 ns	0.1033 ns	6.106 ns	0.93	0.05	268 B	0.0033	-	56 B
Current	+aaaa+aaaa+aaaa+aa	6.991 ns	0.1710 ns	0.1599 ns	6.935 ns	1.00	0.00	268 B	0.0038	-	64 B
Vector128	+aaaa+aaaa+aaaa+aa	6.927 ns	0.1248 ns	0.1106 ns	6.922 ns	0.99	0.02	268 B	0.0038	-	64 B
Vector256	+aaaa+aaaa+aaaa+aa	6.686 ns	0.0994 ns	0.0881 ns	6.668 ns	0.96	0.02	268 B	0.0038	-	64 B
Current	+aaaa(...)aaaa+ [21]	8.598 ns	0.2152 ns	0.2392 ns	8.574 ns	1.00	0.00	268 B	0.0038	-	64 B
Vector128	+aaaa(...)aaaa+ [21]	8.152 ns	0.1098 ns	0.0973 ns	8.135 ns	0.96	0.02	268 B	0.0038	-	64 B
Vector256	+aaaa(...)aaaa+ [21]	8.179 ns	0.0743 ns	0.0659 ns	8.177 ns	0.96	0.03	268 B	0.0038	-	64 B
Current	+aaaa(...)a+aaa [24]	7.728 ns	0.1500 ns	0.1330 ns	7.735 ns	1.00	0.00	268 B	0.0043	-	72 B
Vector128	+aaaa(...)a+aaa [24]	7.360 ns	0.1153 ns	0.1022 ns	7.391 ns	0.95	0.02	268 B	0.0043	-	72 B
Vector256	+aaaa(...)a+aaa [24]	6.574 ns	0.0694 ns	0.0615 ns	6.581 ns	0.85	0.02	268 B	0.0043	-	72 B
Current	+aaaa(...)aaa+a [27]	8.214 ns	0.1025 ns	0.0856 ns	8.241 ns	1.00	0.00	268 B	0.0048	-	80 B
Vector128	+aaaa(...)aaa+a [27]	8.175 ns	0.1227 ns	0.1088 ns	8.194 ns	1.00	0.01	268 B	0.0048	-	80 B
Vector256	+aaaa(...)aaa+a [27]	8.225 ns	0.1926 ns	0.1802 ns	8.230 ns	1.00	0.03	268 B	0.0048	-	80 B
Current	+aaaa(...)+aaaa [30]	10.011 ns	0.2441 ns	0.6724 ns	9.770 ns	1.00	0.00	268 B	0.0053	-	88 B
Vector128	+aaaa(...)+aaaa [30]	10.134 ns	0.2466 ns	0.5309 ns	9.963 ns	0.99	0.08	268 B	0.0053	-	88 B
Vector256	+aaaa(...)+aaaa [30]	9.812 ns	0.2400 ns	0.5513 ns	9.594 ns	0.97	0.08	268 B	0.0053	-	88 B
Current	+aaaa(...)aaa+a [32]	8.690 ns	0.2142 ns	0.2292 ns	8.622 ns	1.00	0.00	268 B	0.0053	-	88 B
Vector128	+aaaa(...)aaa+a [32]	8.404 ns	0.1444 ns	0.1350 ns	8.409 ns	0.97	0.03	268 B	0.0053	-	88 B
Vector256	+aaaa(...)aaa+a [32]	7.214 ns	0.1387 ns	0.1158 ns	7.208 ns	0.83	0.02	268 B	0.0053	-	88 B
Current	+aaaa(...)aa+aa [33]	9.056 ns	0.2239 ns	0.5009 ns	8.924 ns	1.00	0.00	268 B	0.0053	-	88 B
Vector128	+aaaa(...)aa+aa [33]	8.357 ns	0.0891 ns	0.0744 ns	8.352 ns	0.87	0.04	268 B	0.0053	-	88 B
Vector256	+aaaa(...)aa+aa [33]	7.835 ns	0.2010 ns	0.4496 ns	7.673 ns	0.87	0.07	268 B	0.0053	-	88 B
Current	+aaaa(...)aaaa+ [36]	9.222 ns	0.1996 ns	0.1770 ns	9.249 ns	1.00	0.00	268 B	0.0057	-	96 B
Vector128	+aaaa(...)aaaa+ [36]	9.787 ns	0.2401 ns	0.6572 ns	9.631 ns	1.05	0.09	268 B	0.0057	-	96 B
Vector256	+aaaa(...)aaaa+ [36]	8.698 ns	0.0746 ns	0.0661 ns	8.711 ns	0.94	0.02	268 B	0.0057	-	96 B
Current	+aaaa(...)a+aaa [39]	10.662 ns	0.1480 ns	0.1384 ns	10.681 ns	1.00	0.00	268 B	0.0062	-	104 B
Vector128	+aaaa(...)a+aaa [39]	10.545 ns	0.1155 ns	0.0965 ns	10.537 ns	0.99	0.01	268 B	0.0062	-	104 B
Vector256	+aaaa(...)a+aaa [39]	10.534 ns	0.2004 ns	0.1777 ns	10.492 ns	0.99	0.03	268 B	0.0062	-	104 B
Current	+aaaa(...)+aaaa [40]	9.285 ns	0.1520 ns	0.1269 ns	9.256 ns	1.00	0.00	268 B	0.0062	-	104 B
Vector128	+aaaa(...)+aaaa [40]	9.311 ns	0.2304 ns	0.2042 ns	9.249 ns	1.00	0.02	268 B	0.0062	-	104 B
Vector256	+aaaa(...)+aaaa [40]	8.262 ns	0.2011 ns	0.1975 ns	8.216 ns	0.89	0.02	268 B	0.0062	-	104 B
Current	+aaaa(...)aaa+a [42]	9.764 ns	0.2419 ns	0.3060 ns	9.703 ns	1.00	0.00	268 B	0.0067	-	112 B
Vector128	+aaaa(...)aaa+a [42]	9.771 ns	0.2403 ns	0.3596 ns	9.816 ns	1.00	0.05	268 B	0.0067	-	112 B
Vector256	+aaaa(...)aaa+a [42]	8.852 ns	0.0740 ns	0.0656 ns	8.866 ns	0.90	0.03	268 B	0.0067	-	112 B
Current	+aaaa(...)+aaaa [45]	10.367 ns	0.2522 ns	0.3452 ns	10.257 ns	1.00	0.00	268 B	0.0067	-	112 B
Vector128	+aaaa(...)+aaaa [45]	10.840 ns	0.2087 ns	0.1952 ns	10.784 ns	1.04	0.04	268 B	0.0067	-	112 B
Vector256	+aaaa(...)+aaaa [45]	9.644 ns	0.1184 ns	0.0988 ns	9.632 ns	0.92	0.03	268 B	0.0067	-	112 B
Current	+aaaa(...)aa+aa [48]	10.099 ns	0.1632 ns	0.1446 ns	10.040 ns	1.00	0.00	268 B	0.0072	-	120 B
Vector128	+aaaa(...)aa+aa [48]	10.176 ns	0.2098 ns	0.1860 ns	10.116 ns	1.01	0.03	268 B	0.0072	-	120 B
Vector256	+aaaa(...)aa+aa [48]	8.670 ns	0.2062 ns	0.1929 ns	8.651 ns	0.86	0.02	268 B	0.0072	-	120 B
Current	+aaaa(...)aaaa+ [51]	10.752 ns	0.2346 ns	0.2195 ns	10.669 ns	1.00	0.00	268 B	0.0076	-	128 B
Vector128	+aaaa(...)aaaa+ [51]	10.453 ns	0.2530 ns	0.4296 ns	10.452 ns	0.99	0.04	268 B	0.0076	-	128 B
Vector256	+aaaa(...)aaaa+ [51]	10.028 ns	0.2425 ns	0.4954 ns	9.946 ns	0.93	0.06	268 B	0.0076	-	128 B
Current	+aaaa(...)a+aaa [54]	11.965 ns	0.2794 ns	0.4744 ns	11.923 ns	1.00	0.00	268 B	0.0081	-	136 B
Vector128	+aaaa(...)a+aaa [54]	12.079 ns	0.2844 ns	0.5546 ns	11.907 ns	1.02	0.06	268 B	0.0081	-	136 B
Vector256	+aaaa(...)a+aaa [54]	11.446 ns	0.2696 ns	0.6861 ns	11.245 ns	0.97	0.07	268 B	0.0081	-	136 B
Current	+aaaa(...)aaaa+ [56]	10.735 ns	0.2532 ns	0.2601 ns	10.648 ns	1.00	0.00	268 B	0.0081	-	136 B
Vector128	+aaaa(...)aaaa+ [56]	11.315 ns	0.2751 ns	0.7936 ns	11.012 ns	1.18	0.04	268 B	0.0081	-	136 B
Vector256	+aaaa(...)aaaa+ [56]	9.749 ns	0.2228 ns	0.3783 ns	9.640 ns	0.92	0.03	268 B	0.0081	-	136 B
Current	+aaaa(...)aaa+a [57]	10.860 ns	0.1088 ns	0.0965 ns	10.840 ns	1.00	0.00	268 B	0.0081	-	136 B
Vector128	+aaaa(...)aaa+a [57]	11.114 ns	0.2534 ns	0.2919 ns	11.131 ns	1.02	0.03	268 B	0.0081	-	136 B
Vector256	+aaaa(...)aaa+a [57]	9.772 ns	0.0717 ns	0.0636 ns	9.784 ns	0.90	0.01	268 B	0.0081	-	136 B
Current	+aaaa(...)+aaaa [60]	11.475 ns	0.2683 ns	0.2509 ns	11.409 ns	1.00	0.00	268 B	0.0086	-	144 B
Vector128	+aaaa(...)+aaaa [60]	11.387 ns	0.2435 ns	0.2277 ns	11.316 ns	0.99	0.03	268 B	0.0086	-	144 B
Vector256	+aaaa(...)+aaaa [60]	11.662 ns	0.2776 ns	0.4934 ns	11.603 ns	1.02	0.05	268 B	0.0086	-	144 B
Current	+aaaa(...)aa+aa [63]	13.621 ns	0.3160 ns	0.4919 ns	13.662 ns	1.00	0.00	268 B	0.0091	-	152 B
Vector128	+aaaa(...)aa+aa [63]	13.656 ns	0.3106 ns	0.4836 ns	13.620 ns	1.00	0.04	268 B	0.0091	-	152 B
Vector256	+aaaa(...)aa+aa [63]	12.873 ns	0.2998 ns	0.4394 ns	12.912 ns	0.94	0.04	268 B	0.0091	-	152 B
Current	+aaaa(...)a+aaa [64]	12.709 ns	0.2938 ns	0.4988 ns	12.636 ns	1.00	0.00	268 B	0.0091	-	152 B
Vector128	+aaaa(...)a+aaa [64]	12.535 ns	0.2941 ns	0.5666 ns	12.575 ns	0.99	0.06	268 B	0.0091	-	152 B
Vector256	+aaaa(...)a+aaa [64]	11.161 ns	0.2590 ns	0.3714 ns	11.147 ns	0.88	0.04	268 B	0.0091	-	152 B
Current	+aaaa(...)aaaa+ [66]	13.500 ns	0.3160 ns	0.8597 ns	13.387 ns	1.00	0.00	268 B	0.0095	-	160 B
Vector128	+aaaa(...)aaaa+ [66]	12.992 ns	0.2799 ns	0.5589 ns	12.933 ns	0.95	0.07	268 B	0.0095	-	160 B
Vector256	+aaaa(...)aaaa+ [66]	11.205 ns	0.2691 ns	0.4345 ns	11.205 ns	0.81	0.06	268 B	0.0096	-	160 B
Current	+aaaa(...)a+aaa [69]	13.630 ns	0.3179 ns	0.5398 ns	13.564 ns	1.00	0.00	268 B	0.0095	-	160 B
Vector128	+aaaa(...)a+aaa [69]	13.717 ns	0.3157 ns	0.5188 ns	13.736 ns	1.01	0.06	268 B	0.0095	-	160 B
Vector256	+aaaa(...)a+aaa [69]	12.319 ns	0.2923 ns	0.6833 ns	12.146 ns	0.92	0.06	268 B	0.0096	-	160 B
Current	+aaaa(...)aaa+a [72]	12.244 ns	0.2777 ns	0.3611 ns	12.113 ns	1.00	0.00	268 B	0.0100	-	168 B
Vector128	+aaaa(...)aaa+a [72]	12.490 ns	0.2614 ns	0.2567 ns	12.484 ns	1.01	0.04	268 B	0.0100	-	168 B
Vector256	+aaaa(...)aaa+a [72]	11.086 ns	0.2530 ns	0.2366 ns	11.091 ns	0.90	0.04	268 B	0.0100	-	168 B
Current	+aaaa(...)+aaaa [75]	13.882 ns	0.3074 ns	0.7597 ns	13.716 ns	1.00	0.00	268 B	0.0105	-	176 B
Vector128	+aaaa(...)+aaaa [75]	12.934 ns	0.3003 ns	0.4209 ns	12.752 ns	0.93	0.06	268 B	0.0105	-	176 B
Vector256	+aaaa(...)+aaaa [75]	11.234 ns	0.1232 ns	0.1092 ns	11.252 ns	0.81	0.05	268 B	0.0105	-	176 B
Current	+aaaa(...)aa+aa [78]	13.607 ns	0.1608 ns	0.1342 ns	13.574 ns	1.00	0.00	268 B	0.0110	-	184 B
Vector128	+aaaa(...)aa+aa [78]	13.795 ns	0.2030 ns	0.1799 ns	13.738 ns	1.01	0.01	268 B	0.0110	-	184 B
Vector256	+aaaa(...)aa+aa [78]	12.569 ns	0.1045 ns	0.0816 ns	12.573 ns	0.93	0.01	268 B	0.0110	-	184 B
Current	+aaaa(...)+aaaa [80]	13.036 ns	0.1234 ns	0.1094 ns	12.996 ns	1.00	0.00	268 B	0.0110	-	184 B
Vector128	+aaaa(...)+aaaa [80]	13.307 ns	0.3094 ns	0.6458 ns	13.083 ns	1.00	0.05	268 B	0.0110	-	184 B
Vector256	+aaaa(...)+aaaa [80]	11.540 ns	0.2750 ns	0.3167 ns	11.409 ns	0.89	0.03	268 B	0.0110	-	184 B
Current	+aaaa(...)aaaa+ [81]	12.631 ns	0.1100 ns	0.0975 ns	12.615 ns	1.00	0.00	268 B	0.0110	-	184 B
Vector128	+aaaa(...)aaaa+ [81]	12.653 ns	0.1733 ns	0.1353 ns	12.678 ns	1.00	0.01	268 B	0.0110	-	184 B
Vector256	+aaaa(...)aaaa+ [81]	11.787 ns	0.2366 ns	0.2098 ns	11.788 ns	0.93	0.01	268 B	0.0110	-	184 B
Current	+aaaa(...)a+aaa [84]	14.024 ns	0.3248 ns	0.5426 ns	13.801 ns	1.00	0.00	268 B	0.0115	-	192 B
Vector128	+aaaa(...)a+aaa [84]	13.521 ns	0.1766 ns	0.1566 ns	13.523 ns	0.96	0.04	268 B	0.0115	-	192 B
Vector256	+aaaa(...)a+aaa [84]	12.507 ns	0.2648 ns	0.3050 ns	12.453 ns	0.90	0.03	268 B	0.0115	-	192 B
Current	+aaaa(...)aaa+a [87]	15.462 ns	0.3287 ns	0.6714 ns	15.217 ns	1.00	0.00	268 B	0.0120	-	200 B
Vector128	+aaaa(...)aaa+a [87]	14.881 ns	0.3351 ns	0.5218 ns	14.716 ns	0.97	0.06	268 B	0.0120	-	200 B
Vector256	+aaaa(...)aaa+a [87]	13.941 ns	0.3229 ns	0.5483 ns	13.715 ns	0.90	0.05	268 B	0.0120	-	200 B
Current	+aaaa(...)aa+aa [88]	13.809 ns	0.2364 ns	0.2095 ns	13.787 ns	1.00	0.00	268 B	0.0120	-	200 B
Vector128	+aaaa(...)aa+aa [88]	14.332 ns	0.3311 ns	0.3813 ns	14.330 ns	1.04	0.04	268 B	0.0120	-	200 B
Vector256	+aaaa(...)aa+aa [88]	11.981 ns	0.2404 ns	0.2132 ns	11.937 ns	0.87	0.02	268 B	0.0120	-	200 B
Current	+aaaa(...)+aaaa [90]	14.149 ns	0.3236 ns	0.4537 ns	14.120 ns	1.00	0.00	268 B	0.0124	-	208 B
Vector128	+aaaa(...)+aaaa [90]	14.019 ns	0.2680 ns	0.2238 ns	14.052 ns	1.00	0.03	268 B	0.0124	-	208 B
Vector256	+aaaa(...)+aaaa [90]	12.778 ns	0.2307 ns	0.1926 ns	12.788 ns	0.91	0.04	268 B	0.0124	-	208 B
Current	+aaaa(...)aa+aa [93]	15.313 ns	0.3471 ns	0.3997 ns	15.264 ns	1.00	0.00	268 B	0.0124	-	208 B
Vector128	+aaaa(...)aa+aa [93]	14.595 ns	0.1778 ns	0.1576 ns	14.586 ns	0.95	0.03	268 B	0.0124	-	208 B
Vector256	+aaaa(...)aa+aa [93]	13.446 ns	0.3100 ns	0.2899 ns	13.340 ns	0.88	0.02	268 B	0.0124	-	208 B
Current	+aaaa(...)aaaa+ [96]	14.415 ns	0.2375 ns	0.2221 ns	14.446 ns	1.00	0.00	268 B	0.0129	-	216 B
Vector128	+aaaa(...)aaaa+ [96]	15.563 ns	0.3515 ns	0.8948 ns	15.393 ns	1.07	0.07	268 B	0.0129	-	216 B
Vector256	+aaaa(...)aaaa+ [96]	13.138 ns	0.2274 ns	0.2016 ns	13.221 ns	0.91	0.02	268 B	0.0129	-	216 B
Current	+aaaa(...)a+aaa [99]	15.288 ns	0.3082 ns	0.2883 ns	15.330 ns	1.00	0.00	268 B	0.0134	-	224 B
Vector128	+aaaa(...)a+aaa [99]	15.227 ns	0.1411 ns	0.1251 ns	15.263 ns	0.99	0.02	268 B	0.0134	-	224 B
Vector256	+aaaa(...)a+aaa [99]	14.198 ns	0.3299 ns	0.7515 ns	14.149 ns	0.96	0.04	268 B	0.0134	-	224 B
Current	+aaa(...)+aaa [104]	17.024 ns	0.5917 ns	1.7259 ns	16.576 ns	1.00	0.00	268 B	0.0139	-	232 B
Vector128	+aaa(...)+aaa [104]	17.033 ns	0.3829 ns	0.8643 ns	16.957 ns	1.03	0.13	268 B	0.0139	-	232 B
Vector256	+aaa(...)+aaa [104]	15.328 ns	0.4278 ns	1.2065 ns	15.030 ns	0.91	0.10	268 B	0.0139	-	232 B
Current	+aaa(...)aa+a [112]	18.593 ns	0.4188 ns	0.6997 ns	18.468 ns	1.00	0.00	268 B	0.0148	-	248 B
Vector128	+aaa(...)aa+a [112]	18.209 ns	0.4378 ns	1.2492 ns	17.997 ns	0.95	0.05	268 B	0.0148	-	248 B
Vector256	+aaa(...)aa+a [112]	16.548 ns	0.4382 ns	1.2501 ns	16.147 ns	0.88	0.07	268 B	0.0148	-	248 B
Current	+aaa(...)aaaa [120]	19.267 ns	0.4327 ns	1.1625 ns	19.324 ns	1.00	0.00	268 B	0.0158	-	264 B
Vector128	+aaa(...)aaaa [120]	19.518 ns	0.6646 ns	1.8636 ns	19.104 ns	1.02	0.12	268 B	0.0158	-	264 B
Vector256	+aaa(...)aaaa [120]	16.689 ns	0.3820 ns	1.0328 ns	16.699 ns	0.87	0.06	268 B	0.0158	-	264 B
Current	+aaa(...)a+aa [128]	21.188 ns	0.4655 ns	1.1678 ns	21.279 ns	1.00	0.00	268 B	0.0167	-	280 B
Vector128	+aaa(...)a+aa [128]	20.310 ns	0.4527 ns	1.0126 ns	20.268 ns	0.96	0.07	268 B	0.0167	-	280 B
Vector256	+aaa(...)a+aa [128]	17.619 ns	0.4745 ns	1.3382 ns	17.458 ns	0.83	0.07	268 B	0.0167	-	280 B
Current	+aaa(...)aaa+ [136]	21.304 ns	0.4751 ns	1.2007 ns	21.244 ns	1.00	0.00	268 B	0.0176	-	296 B
Vector128	+aaa(...)aaa+ [136]	20.424 ns	0.4542 ns	1.2735 ns	20.043 ns	0.97	0.08	268 B	0.0177	-	296 B
Vector256	+aaa(...)aaa+ [136]	18.526 ns	0.4387 ns	1.2586 ns	18.413 ns	0.88	0.08	268 B	0.0177	-	296 B
Current	+aaa(...)+aaa [144]	21.509 ns	0.4735 ns	1.1965 ns	21.425 ns	1.00	0.00	268 B	0.0186	-	312 B
Vector128	+aaa(...)+aaa [144]	21.998 ns	0.4844 ns	1.4054 ns	21.849 ns	1.03	0.09	268 B	0.0186	-	312 B
Vector256	+aaa(...)+aaa [144]	18.403 ns	0.4131 ns	1.1446 ns	18.348 ns	0.86	0.06	268 B	0.0186	-	312 B
Current	+aaa(...)aa+a [152]	22.317 ns	0.5075 ns	1.4724 ns	22.046 ns	1.00	0.00	268 B	0.0196	-	328 B
Vector128	+aaa(...)aa+a [152]	22.100 ns	0.4911 ns	1.1186 ns	22.059 ns	1.00	0.09	268 B	0.0196	-	328 B
Vector256	+aaa(...)aa+a [152]	18.878 ns	0.4248 ns	1.1484 ns	18.938 ns	0.85	0.07	268 B	0.0196	-	328 B
Current	+aaa(...)aaaa [160]	23.005 ns	0.5084 ns	1.1784 ns	23.027 ns	1.00	0.00	268 B	0.0206	-	344 B
Vector128	+aaa(...)aaaa [160]	23.755 ns	0.5216 ns	1.1667 ns	23.714 ns	1.03	0.08	268 B	0.0206	-	344 B
Vector256	+aaa(...)aaaa [160]	19.209 ns	0.4288 ns	0.8856 ns	19.240 ns	0.84	0.07	268 B	0.0206	-	344 B
Current	+aaa(...)a+aa [168]	24.510 ns	0.5378 ns	1.4354 ns	24.685 ns	1.00	0.00	268 B	0.0215	0.0000	360 B
Vector128	+aaa(...)a+aa [168]	24.648 ns	0.6216 ns	1.7633 ns	24.336 ns	1.01	0.09	268 B	0.0215	0.0000	360 B
Vector256	+aaa(...)a+aa [168]	21.353 ns	0.5572 ns	1.6077 ns	20.850 ns	0.87	0.08	268 B	0.0215	0.0000	360 B
Current	+aaa(...)aaa+ [176]	24.522 ns	0.5384 ns	1.1357 ns	24.484 ns	1.00	0.00	268 B	0.0225	0.0000	376 B
Vector128	+aaa(...)aaa+ [176]	24.146 ns	0.4916 ns	0.9471 ns	24.111 ns	0.99	0.05	268 B	0.0225	0.0000	376 B
Vector256	+aaa(...)aaa+ [176]	20.777 ns	0.4613 ns	1.1315 ns	20.931 ns	0.84	0.06	268 B	0.0225	0.0000	376 B
Current	+aaa(...)+aaa [184]	26.085 ns	0.5695 ns	1.6341 ns	25.920 ns	1.00	0.00	268 B	0.0234	0.0000	392 B
Vector128	+aaa(...)+aaa [184]	26.304 ns	0.5659 ns	1.3002 ns	26.151 ns	1.02	0.07	268 B	0.0234	0.0000	392 B
Vector256	+aaa(...)+aaa [184]	21.886 ns	0.5015 ns	1.3979 ns	21.747 ns	0.84	0.08	268 B	0.0234	0.0000	392 B
Current	+aaa(...)aa+a [192]	28.742 ns	0.9242 ns	2.6958 ns	27.904 ns	1.00	0.00	268 B	0.0244	0.0000	408 B
Vector128	+aaa(...)aa+a [192]	27.654 ns	0.6941 ns	1.9916 ns	27.324 ns	0.97	0.10	268 B	0.0244	0.0000	408 B
Vector256	+aaa(...)aa+a [192]	22.258 ns	0.4957 ns	1.3653 ns	22.107 ns	0.78	0.08	268 B	0.0244	0.0000	408 B
Current	+aaa(...)aaaa [200]	29.885 ns	1.0554 ns	3.0786 ns	29.443 ns	1.00	0.00	268 B	0.0253	-	424 B
Vector128	+aaa(...)aaaa [200]	28.064 ns	0.6095 ns	1.7585 ns	27.722 ns	0.95	0.12	268 B	0.0253	0.0000	424 B
Vector256	+aaa(...)aaaa [200]	22.789 ns	0.4998 ns	1.2902 ns	22.664 ns	0.78	0.07	268 B	0.0253	0.0000	424 B
Current	+aaa(...)a+aa [208]	29.526 ns	0.6345 ns	1.2224 ns	29.609 ns	1.00	0.00	268 B	0.0263	-	440 B
Vector128	+aaa(...)a+aa [208]	28.778 ns	0.6219 ns	1.4901 ns	28.653 ns	0.97	0.06	268 B	0.0263	-	440 B
Vector256	+aaa(...)a+aa [208]	23.159 ns	0.5035 ns	0.8273 ns	23.458 ns	0.79	0.04	268 B	0.0263	0.0000	440 B
Current	+aaa(...)aaa+ [216]	31.064 ns	0.7214 ns	2.0583 ns	30.759 ns	1.00	0.00	268 B	0.0272	-	456 B
Vector128	+aaa(...)aaa+ [216]	33.746 ns	0.9434 ns	2.7670 ns	33.670 ns	1.09	0.11	268 B	0.0272	-	456 B
Vector256	+aaa(...)aaa+ [216]	24.240 ns	0.5350 ns	1.5177 ns	24.163 ns	0.78	0.08	268 B	0.0272	0.0000	456 B
Current	+aaa(...)+aaa [224]	29.885 ns	0.6492 ns	1.7661 ns	29.748 ns	1.00	0.00	268 B	0.0282	-	472 B
Vector128	+aaa(...)+aaa [224]	32.060 ns	0.6837 ns	1.6772 ns	32.302 ns	1.08	0.09	268 B	0.0282	-	472 B
Vector256	+aaa(...)+aaa [224]	26.376 ns	0.9178 ns	2.6626 ns	26.089 ns	0.90	0.11	268 B	0.0281	-	472 B
Current	+aaa(...)aa+a [232]	30.928 ns	0.6637 ns	1.8279 ns	30.508 ns	1.00	0.00	268 B	0.0291	-	488 B
Vector128	+aaa(...)aa+a [232]	32.001 ns	0.6846 ns	2.0078 ns	31.669 ns	1.04	0.09	268 B	0.0291	-	488 B
Vector256	+aaa(...)aa+a [232]	26.456 ns	0.5799 ns	1.1715 ns	26.268 ns	0.85	0.07	268 B	0.0291	-	488 B
Current	+aaa(...)aaaa [240]	32.413 ns	0.6928 ns	1.8128 ns	32.347 ns	1.00	0.00	268 B	0.0301	-	504 B
Vector128	+aaa(...)aaaa [240]	34.191 ns	0.7350 ns	1.6287 ns	33.978 ns	1.06	0.08	268 B	0.0301	-	504 B
Vector256	+aaa(...)aaaa [240]	25.143 ns	0.7002 ns	2.0534 ns	24.541 ns	0.79	0.08	268 B	0.0301	0.0000	504 B
Current	+aaa(...)a+aa [248]	30.748 ns	0.5971 ns	0.5586 ns	30.750 ns	1.00	0.00	268 B	0.0311	0.0001	520 B
Vector128	+aaa(...)a+aa [248]	30.368 ns	0.6346 ns	0.8686 ns	30.275 ns	0.99	0.03	268 B	0.0311	0.0001	520 B
Vector256	+aaa(...)a+aa [248]	24.939 ns	0.5433 ns	0.8458 ns	25.057 ns	0.81	0.03	268 B	0.0311	0.0001	520 B