Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Optimize XxHash3 on ARM platform #77881

Merged
merged 3 commits into from
Nov 5, 2022
Merged

Optimize XxHash3 on ARM platform #77881

Changes from 2 commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
0f60e44
Optimize XxHash3 on ARM platform
xoofx Nov 4, 2022
6b07c09
Extract code to MultiplyWideningLower
xoofx Nov 4, 2022
1a310cc
Update src/libraries/System.IO.Hashing/src/System/IO/Hashing/XxHash3.cs
xoofx Nov 4, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
23 changes: 19 additions & 4 deletions src/libraries/System.IO.Hashing/src/System/IO/Hashing/XxHash3.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,6 +10,7 @@
using System.Runtime.InteropServices;
#if NET7_0_OR_GREATER
using System.Runtime.Intrinsics;
using System.Runtime.Intrinsics.Arm;
using System.Runtime.Intrinsics.X86;
#endif

Expand Down Expand Up @@ -896,16 +897,30 @@ private static Vector128<ulong> Accumulate128(Vector128<ulong> accVec, byte* sou
Vector128<uint> sourceKey = sourceVec ^ secret;

// TODO: Figure out how to unwind this shuffle and just use Vector128.Multiply
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Is this comment still relevant, or does it now refer to code in MultiplyWideningLower?

Vector128<uint> sourceKeyLow = Vector128.Shuffle(sourceKey, Vector128.Create(1u, 0, 3, 0));
Vector128<uint> sourceSwap = Vector128.Shuffle(sourceVec, Vector128.Create(2u, 3, 0, 1));
Vector128<ulong> sum = accVec + sourceSwap.AsUInt64();
Vector128<ulong> product = Sse2.IsSupported ?
Sse2.Multiply(sourceKey, sourceKeyLow) :
(sourceKey & Vector128.Create(~0u, 0u, ~0u, 0u)).AsUInt64() * (sourceKeyLow & Vector128.Create(~0u, 0u, ~0u, 0u)).AsUInt64();

Vector128<ulong> product = MultiplyWideningLower(sourceKey);
accVec = product + sum;
return accVec;
}

[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static Vector128<ulong> MultiplyWideningLower(Vector128<uint> source)
{
if (AdvSimd.IsSupported)
{
Vector64<uint> sourceLow = Vector128.Shuffle(source, Vector128.Create(0u, 2, 0, 0)).GetLower();
Vector64<uint> sourceHigh = Vector128.Shuffle(source, Vector128.Create(1u, 3, 0, 0)).GetLower();
return AdvSimd.MultiplyWideningLower(sourceLow, sourceHigh);
}
else
{
Vector128<uint> sourceLow = Vector128.Shuffle(source, Vector128.Create(1u, 0, 3, 0));
return Sse2.IsSupported ? Sse2.Multiply(source, sourceLow) :
(source & Vector128.Create(~0u, 0u, ~0u, 0u)).AsUInt64() * (sourceLow & Vector128.Create(~0u, 0u, ~0u, 0u)).AsUInt64();
xoofx marked this conversation as resolved.
Show resolved Hide resolved
}
}
#endif

private static void ScrambleAccumulators(ulong* accumulators, byte* secret)
Expand Down