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

Accelerate Vector128<long>::op_Multiply on x64 #103555

Merged
merged 21 commits into from
Jun 28, 2024
Merged

Accelerate Vector128<long>::op_Multiply on x64 #103555

Changes from 1 commit
Commits
Show all changes
21 commits
Select commit Hold shift + click to select a range
ae17211
Accelerate Vector128 mul for long/ulong
EgorBo Jun 17, 2024
afda312
better ulong version
EgorBo Jun 17, 2024
ab01574
fix build
EgorBo Jun 17, 2024
21b42de
Update Vector128_1.cs
EgorBo Jun 17, 2024
581f1e2
Sse41 version
EgorBo Jun 17, 2024
49a359f
Update src/libraries/System.Private.CoreLib/src/System/Runtime/Intrin…
EgorBo Jun 17, 2024
57898f0
Update Vector128_1.cs
EgorBo Jun 17, 2024
f1be705
Update Vector128_1.cs
EgorBo Jun 19, 2024
95d0eb8
Update Vector128_1.cs
EgorBo Jun 19, 2024
dcfd93d
Update Vector128_1.cs
EgorBo Jun 19, 2024
7fec9e3
Update Vector128_1.cs
EgorBo Jun 19, 2024
e172296
Update Vector128_1.cs
EgorBo Jun 19, 2024
0456d12
Update Vector128_1.cs
EgorBo Jun 20, 2024
8af6104
Merge branch 'main' of https://github.com/dotnet/runtime into arm-mul…
EgorBo Jun 20, 2024
69572a2
Update Vector128_1.cs
EgorBo Jun 20, 2024
d607549
clean up
EgorBo Jun 20, 2024
573a37b
move to jit
EgorBo Jun 20, 2024
3790d1b
clean up
EgorBo Jun 20, 2024
60441f3
revert unrelated changes
EgorBo Jun 21, 2024
5b78ddd
Merge branch 'main' of https://github.com/dotnet/runtime into arm-mul…
EgorBo Jun 28, 2024
cc257dd
Address feedback
EgorBo Jun 28, 2024
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
Prev Previous commit
Next Next commit
Update Vector128_1.cs
  • Loading branch information
@EgorBo
EgorBo authored Jun 20, 2024
commit 0456d1260af6b61a3827b3157c648b9e0b6713e3
16 changes: 8 additions & 8 deletions src/libraries/System.Private.CoreLib/src/System/Runtime/Intrinsics/Vector128_1.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -276,15 +276,15 @@ public static Vector128<T> Zero
Sse41.MultiplyLow(a.AsUInt32(),
Sse2.Shuffle(b.AsUInt32(), 0xB1)).AsInt32(), Vector128<int>.Zero), 0x73).AsUInt64()));
}
if (AdvSimd.Arm64.IsSupported && typeof(T) == typeof(ulong))
if (AdvSimd.Arm64.IsSupported && (typeof(T) == typeof(long) || typeof(T) == typeof(ulong)))
{
Vector128<ulong> a = left.AsUInt64();
Vector128<ulong> b = right.AsUInt64();
return AdvSimd.Arm64.UnzipEven(
AdvSimd.MultiplyWideningLower(
a.GetLower().AsUInt32(), b.GetLower().AsUInt32()).AsUInt16(),
AdvSimd.MultiplyWideningUpper(
a.AsUInt32(), b.AsUInt32()).AsUInt16()).AsUInt64().As<ulong, T>();
Vector64<uint> aHi = AdvSimd.ShiftRightLogicalNarrowingLower(a.AsUInt64(), 32);
Vector64<uint> aLo = AdvSimd.ExtractNarrowingLower(a.AsUInt64());
Vector64<uint> bHi = AdvSimd.ShiftRightLogicalNarrowingLower(b.AsUInt64(), 32);
Vector64<uint> bLo = AdvSimd.ExtractNarrowingLower(b.AsUInt64());
Vector128<ulong> ret64 = AdvSimd.MultiplyWideningLower(aHi, bLo);
ret64 = AdvSimd.MultiplyWideningLowerAndAdd(ret64, aLo, bHi);
return AdvSimd.MultiplyWideningLowerAndAdd(ret64 << 32, aLo, bLo).As<ulong, T>();
}

return Vector128.Create(
Expand Down
Loading