.NET 6 數(shù)組拷貝性能對(duì)比

????????static?Program()
????????{
????????????TestData?=?new?int[1000];
????????????for?(int?i?=?0;?i?1000;?i++)
????????????{
????????????????TestData[i]?=?i;
????????????}
????????}

????????private?static?readonly?int[]?TestData;

使用 for 循環(huán)拷貝的方法如下

????????public?object?CopyByFor(int?start,?int?length)
????????{
????????????var?rawPacketData?=?TestData;

????????????var?data?=?new?int[length];
????????????for?(int?localIndex?=?0,?rawArrayIndex?=?start;?localIndex?????????????{
????????????????data[localIndex]?=?rawPacketData[rawArrayIndex];
????????????}
????????????return?data;
????????}

以上代碼返回 data 作為 object 僅僅只是為了做性能測(cè)試，避免被 dotnet 優(yōu)化掉

另一個(gè)拷貝數(shù)組是采用 Array.Copy 拷貝，邏輯如下

????????public?object?CopyByArray(int?start,?int?length)
????????{
????????????var?rawPacketData?=?TestData;
????????????var?data?=?new?int[length];
????????????Array.Copy(rawPacketData,start,data,0,?length);
????????????return?data;
????????}

采用新的 dotnet 提供的 Span 進(jìn)行拷貝，代碼如下

????????public?object?CopyBySpan(int?start,?int?length)
????????{
????????????var?rawPacketData?=?TestData;
????????????var?rawArrayStartIndex?=?start;
????????????var?data?=?rawPacketData.AsSpan(rawArrayStartIndex,?length).ToArray();
????????????return?data;
????????}

接著加上一些性能調(diào)試輔助邏輯

????????[Benchmark]
????????[ArgumentsSource(nameof(ProvideArguments))]
????????public?object?CopyByFor(int?start,?int?length)
????????{
????????????var?rawPacketData?=?TestData;

????????????var?data?=?new?int[length];
????????????for?(int?localIndex?=?0,?rawArrayIndex?=?start;?localIndex?????????????{
????????????????data[localIndex]?=?rawPacketData[rawArrayIndex];
????????????}
????????????return?data;
????????}

????????[Benchmark]
????????[ArgumentsSource(nameof(ProvideArguments))]
????????public?object?CopyByArray(int?start,?int?length)
????????{
????????????var?rawPacketData?=?TestData;
????????????var?data?=?new?int[length];
????????????Array.Copy(rawPacketData,start,data,0,?length);
????????????return?data;
????????}

????????public?IEnumerable<object[]>?ProvideArguments()
????????{
????????????foreach?(var?start?in?new[]?{?0,?10,?100?})
????????????{
????????????????foreach?(var?length?in?new[]?{?10,?20,?100?})
????????????????{
????????????????????yield?return?new?object[]?{?start,?length?};
????????????????}
????????????}
????????}

在我的設(shè)備上的測(cè)試效果如下

BenchmarkDotNet=v0.13.1,?OS=Windows?10.0.19042.1200?(20H2/October2020Update)
Intel?Core?i7-9700K?CPU?3.60GHz?(Coffee?Lake),?1?CPU,?8?logical?and?8?physical?cores
.NET?SDK=6.0.100-preview.7.21379.14
??[Host]?????:?.NET?6.0.0?(6.0.21.37719),?X64?RyuJIT
??DefaultJob?:?.NET?6.0.0?(6.0.21.37719),?X64?RyuJIT

可以看到，在對(duì)比使用 for 循環(huán)拷貝和使用 Array.Copy 拷貝中，使用 Array.Copy 拷貝的性能更好，在拷貝的數(shù)組長(zhǎng)度越長(zhǎng)的時(shí)候，使用 Array.Copy 拷貝性能優(yōu)勢(shì)就更好

接下來(lái)再加上 Span 的性能比較，如下面代碼

????????[Benchmark]
????????[ArgumentsSource(nameof(ProvideArguments))]
????????public?object?CopyBySpan(int?start,?int?length)
????????{
????????????var?rawPacketData?=?TestData;
????????????var?rawArrayStartIndex?=?start;
????????????var?data?=?rawPacketData.AsSpan(rawArrayStartIndex,?length).ToArray();
????????????return?data;
????????}

性能對(duì)比測(cè)試如下

可以看到 Span 的性能比 Array.Copy 拷貝性能更強(qiáng)

在 Span 里面，轉(zhuǎn)換為數(shù)組的邏輯如下

????????[MethodImpl(MethodImplOptions.AggressiveInlining)]
????????public?T[]?ToArray()
????????{
????????????if?(_length?==?0)
????????????????return?Array.Empty();

????????????var?destination?=?new?T[_length];
????????????Buffer.Memmove(ref?MemoryMarshal.GetArrayDataReference(destination),?ref?_pointer.Value,?(nuint)_length);
????????????return?destination;
????????}

這里使用到的 Buffer 的有黑科技的 Memmove 方法，此方法的實(shí)現(xiàn)如下

????????[MethodImpl(MethodImplOptions.AggressiveInlining)]
????????internal?static?void?Memmove(ref?T?destination,?ref?T?source,?nuint?elementCount)
????????{
????????????if?(!RuntimeHelpers.IsReferenceOrContainsReferences())
????????????{
????????????????//?Blittable?memmove

????????????????Memmove(
????????????????????ref?Unsafe.Asbyte="">(ref?destination),
????????????????????ref?Unsafe.Asbyte="">(ref?source),
????????????????????elementCount?*?(nuint)Unsafe.SizeOf());
????????????}
????????????else
????????????{
????????????????//?Non-blittable?memmove
????????????????BulkMoveWithWriteBarrier(
????????????????????ref?Unsafe.Asbyte="">(ref?destination),
????????????????????ref?Unsafe.Asbyte="">(ref?source),
????????????????????elementCount?*?(nuint)Unsafe.SizeOf());
????????????}
????????}

以上性能測(cè)試使用的是 int 數(shù)組，剛好能進(jìn)入 Memmove 的分支，而不是 BulkMoveWithWriteBarrier 這個(gè)分支。在里層的 Memmove 方法里面用到了很多黑科技，本文只是用來(lái)對(duì)比多個(gè)方法拷貝數(shù)組的性能，黑科技部分就需要大家自己去閱讀 dotnet 的源代碼啦

另外，如果需要做完全的數(shù)組的拷貝，數(shù)組里面存放的是值類型對(duì)象，如 int 類型，那么拷貝整個(gè)數(shù)組還有另一個(gè)可選項(xiàng)是通過(guò) Clone 方法進(jìn)行拷貝，代碼如下

????????public?object?CopyByClone()
????????{
????????????var?data?=?(int[])?TestData.Clone();
????????????return?data;
????????}

使用 Clone 的方法的行為是返回?cái)?shù)組的淺表拷貝，也就是說(shuō)數(shù)組里面的元素沒(méi)有做深拷貝，只是拷貝數(shù)組本身而已。對(duì)于值類型來(lái)說(shuō)，就沒(méi)有啥問(wèn)題了

稍微更改一下性能測(cè)試，更改的代碼如下

????[MemoryDiagnoser]
????public?class?Program
????{
????????static?void?Main(string[]?args)
????????{
????????????BenchmarkRunner.Run();
????????}

????????static?Program()
????????{
????????????TestData?=?new?int[1000];
????????????for?(int?i?=?0;?i?1000;?i++)
????????????{
????????????????TestData[i]?=?i;
????????????}
????????}

????????[Benchmark]
????????public?object?CopyByFor()
????????{
????????????var?rawPacketData?=?TestData;
????????????var?length?=?TestData.Length;

????????????var?data?=?new?int[length];
????????????for?(int?localIndex?=?0,?rawArrayIndex?=?0;?localIndex?????????????{
????????????????data[localIndex]?=?rawPacketData[rawArrayIndex];
????????????}
????????????return?data;
????????}

????????[Benchmark]
????????public?object?CopyByArray()
????????{
????????????var?length?=?TestData.Length;
????????????var?start?=?0;

????????????var?rawPacketData?=?TestData;
????????????var?data?=?new?int[length];
????????????Array.Copy(rawPacketData,start,data,0,?length);
????????????return?data;
????????}

????????[Benchmark]
????????public?object?CopyByClone()
????????{
????????????var?data?=?(int[])?TestData.Clone();
????????????return?data;
????????}

????????private?static?readonly?int[]?TestData;
????}

通過(guò)下圖可以了解到采用 Clone 方法和采用 Array.Copy 方法的性能差不多，但 Clone 稍微快一點(diǎn)

以上是給 WPF 框架做性能優(yōu)化時(shí)測(cè)試。