Arm64: Implement LoadVector64xAndUnzip and LoadVector128xAndUnzip APIs #94128

TIHan · 2023-10-28T03:10:57Z

Adds LoadVector64xAndUnzip and LoadVector128xAndUnzip APIs

    // LD1 (multiple structures) 2 register variant
    public static unsafe (Vector64<byte>   Value1, Vector64<byte>   Value2) LoadVector64x2AndUnzip(byte*   address);
    public static unsafe (Vector64<sbyte>  Value1, Vector64<sbyte>  Value2) LoadVector64x2AndUnzip(sbyte*  address);
    public static unsafe (Vector64<short>  Value1, Vector64<short>  Value2) LoadVector64x2AndUnzip(short*  address);
    public static unsafe (Vector64<ushort> Value1, Vector64<ushort> Value2) LoadVector64x2AndUnzip(ushort* address);
    public static unsafe (Vector64<int>    Value1, Vector64<int>    Value2) LoadVector64x2AndUnzip(int*    address);
    public static unsafe (Vector64<uint>   Value1, Vector64<uint>   Value2) LoadVector64x2AndUnzip(uint*   address);
    public static unsafe (Vector64<float>  Value1, Vector64<float>  Value2) LoadVector64x2AndUnzip(float*  address);

    // LD1 (multiple structures) 3 register variant
    public static unsafe (Vector64<byte>   Value1, Vector64<byte>   Value2, Vector64<byte>   Value3) LoadVector64x3AndUnzip(byte*   address);
    public static unsafe (Vector64<sbyte>  Value1, Vector64<sbyte>  Value2, Vector64<sbyte>  Value3) LoadVector64x3AndUnzip(sbyte*  address);
    public static unsafe (Vector64<short>  Value1, Vector64<short>  Value2, Vector64<short>  Value3) LoadVector64x3AndUnzip(short*  address);
    public static unsafe (Vector64<ushort> Value1, Vector64<ushort> Value2, Vector64<ushort> Value3) LoadVector64x3AndUnzip(ushort* address);
    public static unsafe (Vector64<int>    Value1, Vector64<int>    Value2, Vector64<int>    Value3) LoadVector64x3AndUnzip(int*    address);
    public static unsafe (Vector64<uint>   Value1, Vector64<uint>   Value2, Vector64<uint>   Value3) LoadVector64x3AndUnzip(uint*   address);
    public static unsafe (Vector64<float>  Value1, Vector64<float>  Value2, Vector64<float>  Value3) LoadVector64x3AndUnzip(float*  address);
    
    // LD1 (multiple structures) 4 register variant            
    public static unsafe (Vector64<byte>   Value1, Vector64<byte>   Value2, Vector64<byte>   Value3, Vector64<byte>   Value4) LoadVector64x4AndUnzip(byte*   address);
    public static unsafe (Vector64<sbyte>  Value1, Vector64<sbyte>  Value2, Vector64<sbyte>  Value3, Vector64<sbyte>  Value4) LoadVector64x4AndUnzip(sbyte*  address);
    public static unsafe (Vector64<short>  Value1, Vector64<short>  Value2, Vector64<short>  Value3, Vector64<short>  Value4) LoadVector64x4AndUnzip(short*  address);
    public static unsafe (Vector64<ushort> Value1, Vector64<ushort> Value2, Vector64<ushort> Value3, Vector64<ushort> Value4) LoadVector64x4AndUnzip(ushort* address);
    public static unsafe (Vector64<int>    Value1, Vector64<int>    Value2, Vector64<int>    Value3, Vector64<int>    Value4) LoadVector64x4AndUnzip(int*    address);
    public static unsafe (Vector64<uint>   Value1, Vector64<uint>   Value2, Vector64<uint>   Value3, Vector64<uint>   Value4) LoadVector64x4AndUnzip(uint*   address);
    public static unsafe (Vector64<float>  Value1, Vector64<float>  Value2, Vector64<float>  Value3, Vector64<float>  Value4) LoadVector64x4AndUnzip(float*  address);

    // LD1 (multiple structures) 2 register variant
    public static unsafe (Vector128<byte>   Value1, Vector128<byte>   Value2) LoadVector128x2AndUnzip(byte*   address);
    public static unsafe (Vector128<sbyte>  Value1, Vector128<sbyte>  Value2) LoadVector128x2AndUnzip(sbyte*  address);
    public static unsafe (Vector128<short>  Value1, Vector128<short>  Value2) LoadVector128x2AndUnzip(short*  address);
    public static unsafe (Vector128<ushort> Value1, Vector128<ushort> Value2) LoadVector128x2AndUnzip(ushort* address);
    public static unsafe (Vector128<int>    Value1, Vector128<int>    Value2) LoadVector128x2AndUnzip(int*    address);
    public static unsafe (Vector128<uint>   Value1, Vector128<uint>   Value2) LoadVector128x2AndUnzip(uint*   address);
    public static unsafe (Vector128<long>   Value1, Vector128<long>   Value2) LoadVector128x2AndUnzip(long*   address);
    public static unsafe (Vector128<ulong>  Value1, Vector128<ulong>  Value2) LoadVector128x2AndUnzip(ulong*  address);
    public static unsafe (Vector128<float>  Value1, Vector128<float>  Value2) LoadVector128x2AndUnzip(float*  address);
    public static unsafe (Vector128<double> Value1, Vector128<double> Value2) LoadVector128x2AndUnzip(double* address);

    // LD1 (multiple structures) 3 register variant
    public static unsafe (Vector128<byte>   Value1, Vector128<byte>   Value2, Vector128<byte>   Value3) LoadVector128x3AndUnzip(byte*   address);
    public static unsafe (Vector128<sbyte>  Value1, Vector128<sbyte>  Value2, Vector128<sbyte>  Value3) LoadVector128x3AndUnzip(sbyte*  address);
    public static unsafe (Vector128<short>  Value1, Vector128<short>  Value2, Vector128<short>  Value3) LoadVector128x3AndUnzip(short*  address);
    public static unsafe (Vector128<ushort> Value1, Vector128<ushort> Value2, Vector128<ushort> Value3) LoadVector128x3AndUnzip(ushort* address);
    public static unsafe (Vector128<int>    Value1, Vector128<int>    Value2, Vector128<int>    Value3) LoadVector128x3AndUnzip(int*    address);
    public static unsafe (Vector128<uint>   Value1, Vector128<uint>   Value2, Vector128<uint>   Value3) LoadVector128x3AndUnzip(uint*   address);
    public static unsafe (Vector128<long>   Value1, Vector128<long>   Value2, Vector128<long>   Value3) LoadVector128x3AndUnzip(long*   address);
    public static unsafe (Vector128<ulong>  Value1, Vector128<ulong>  Value2, Vector128<ulong>  Value3) LoadVector128x3AndUnzip(ulong*  address);
    public static unsafe (Vector128<float>  Value1, Vector128<float>  Value2, Vector128<float>  Value3) LoadVector128x3AndUnzip(float*  address);
    public static unsafe (Vector128<double> Value1, Vector128<double> Value2, Vector128<double> Value3) LoadVector128x3AndUnzip(double* address);
    
    // LD1 (multiple structures) 4 register variant            
    public static unsafe (Vector128<byte>   Value1, Vector128<byte>   Value2, Vector128<byte>   Value3, Vector128<byte>   Value4) LoadVector128x4AndUnzip(byte*   address);
    public static unsafe (Vector128<sbyte>  Value1, Vector128<sbyte>  Value2, Vector128<sbyte>  Value3, Vector128<sbyte>  Value4) LoadVector128x4AndUnzip(sbyte*  address);
    public static unsafe (Vector128<short>  Value1, Vector128<short>  Value2, Vector128<short>  Value3, Vector128<short>  Value4) LoadVector128x4AndUnzip(short*  address);
    public static unsafe (Vector128<ushort> Value1, Vector128<ushort> Value2, Vector128<ushort> Value3, Vector128<ushort> Value4) LoadVector128x4AndUnzip(ushort* address);
    public static unsafe (Vector128<int>    Value1, Vector128<int>    Value2, Vector128<int>    Value3, Vector128<int>    Value4) LoadVector128x4AndUnzip(int*    address);
    public static unsafe (Vector128<uint>   Value1, Vector128<uint>   Value2, Vector128<uint>   Value3, Vector128<uint>   Value4) LoadVector128x4AndUnzip(uint*   address);
    public static unsafe (Vector128<long>   Value1, Vector128<long>   Value2, Vector128<long>   Value3, Vector128<long>   Value4) LoadVector128x4AndUnzip(long*   address);
    public static unsafe (Vector128<ulong>  Value1, Vector128<ulong>  Value2, Vector128<ulong>  Value3, Vector128<ulong>  Value4) LoadVector128x4AndUnzip(ulong*  address);
    public static unsafe (Vector128<float>  Value1, Vector128<float>  Value2, Vector128<float>  Value3, Vector128<float>  Value4) LoadVector128x4AndUnzip(float*  address);
    public static unsafe (Vector128<double> Value1, Vector128<double> Value2, Vector128<double> Value3, Vector128<double> Value4) LoadVector128x4AndUnzip(double* address);

Contributes to #84510

dotnet-issue-labeler · 2023-10-28T03:11:04Z

Note regarding the new-api-needs-documentation label:

This serves as a reminder for when your PR is modifying a ref *.cs file and adding/modifying public APIs, please make sure the API implementation in the src *.cs file is documented with triple slash comments, so the PR reviewers can sign off that change.

ghost · 2023-10-28T03:11:09Z

Tagging subscribers to this area: @dotnet/area-system-runtime-intrinsics
See info in area-owners.md if you want to be subscribed.

Issue Details

Adds LoadVector64xAndUnzip and LoadVector128xAndUnzip APIs

    // LD1 (multiple structures) 2 register variant
    public static unsafe (Vector64<byte>   Value1, Vector64<byte>   Value2) LoadVector64x2AndUnzip(byte*   address);
    public static unsafe (Vector64<sbyte>  Value1, Vector64<sbyte>  Value2) LoadVector64x2AndUnzip(sbyte*  address);
    public static unsafe (Vector64<short>  Value1, Vector64<short>  Value2) LoadVector64x2AndUnzip(short*  address);
    public static unsafe (Vector64<ushort> Value1, Vector64<ushort> Value2) LoadVector64x2AndUnzip(ushort* address);
    public static unsafe (Vector64<int>    Value1, Vector64<int>    Value2) LoadVector64x2AndUnzip(int*    address);
    public static unsafe (Vector64<uint>   Value1, Vector64<uint>   Value2) LoadVector64x2AndUnzip(uint*   address);
    public static unsafe (Vector64<float>  Value1, Vector64<float>  Value2) LoadVector64x2AndUnzip(float*  address);

    // LD1 (multiple structures) 3 register variant
    public static unsafe (Vector64<byte>   Value1, Vector64<byte>   Value2, Vector64<byte>   Value3) LoadVector64x3AndUnzip(byte*   address);
    public static unsafe (Vector64<sbyte>  Value1, Vector64<sbyte>  Value2, Vector64<sbyte>  Value3) LoadVector64x3AndUnzip(sbyte*  address);
    public static unsafe (Vector64<short>  Value1, Vector64<short>  Value2, Vector64<short>  Value3) LoadVector64x3AndUnzip(short*  address);
    public static unsafe (Vector64<ushort> Value1, Vector64<ushort> Value2, Vector64<ushort> Value3) LoadVector64x3AndUnzip(ushort* address);
    public static unsafe (Vector64<int>    Value1, Vector64<int>    Value2, Vector64<int>    Value3) LoadVector64x3AndUnzip(int*    address);
    public static unsafe (Vector64<uint>   Value1, Vector64<uint>   Value2, Vector64<uint>   Value3) LoadVector64x3AndUnzip(uint*   address);
    public static unsafe (Vector64<float>  Value1, Vector64<float>  Value2, Vector64<float>  Value3) LoadVector64x3AndUnzip(float*  address);
    
    // LD1 (multiple structures) 4 register variant            
    public static unsafe (Vector64<byte>   Value1, Vector64<byte>   Value2, Vector64<byte>   Value3, Vector64<byte>   Value4) LoadVector64x4AndUnzip(byte*   address);
    public static unsafe (Vector64<sbyte>  Value1, Vector64<sbyte>  Value2, Vector64<sbyte>  Value3, Vector64<sbyte>  Value4) LoadVector64x4AndUnzip(sbyte*  address);
    public static unsafe (Vector64<short>  Value1, Vector64<short>  Value2, Vector64<short>  Value3, Vector64<short>  Value4) LoadVector64x4AndUnzip(short*  address);
    public static unsafe (Vector64<ushort> Value1, Vector64<ushort> Value2, Vector64<ushort> Value3, Vector64<ushort> Value4) LoadVector64x4AndUnzip(ushort* address);
    public static unsafe (Vector64<int>    Value1, Vector64<int>    Value2, Vector64<int>    Value3, Vector64<int>    Value4) LoadVector64x4AndUnzip(int*    address);
    public static unsafe (Vector64<uint>   Value1, Vector64<uint>   Value2, Vector64<uint>   Value3, Vector64<uint>   Value4) LoadVector64x4AndUnzip(uint*   address);
    public static unsafe (Vector64<float>  Value1, Vector64<float>  Value2, Vector64<float>  Value3, Vector64<float>  Value4) LoadVector64x4AndUnzip(float*  address);

        // LD1 (multiple structures) 2 register variant
        public static unsafe (Vector128<byte>   Value1, Vector128<byte>   Value2) LoadVector128x2AndUnzip(byte*   address);
        public static unsafe (Vector128<sbyte>  Value1, Vector128<sbyte>  Value2) LoadVector128x2AndUnzip(sbyte*  address);
        public static unsafe (Vector128<short>  Value1, Vector128<short>  Value2) LoadVector128x2AndUnzip(short*  address);
        public static unsafe (Vector128<ushort> Value1, Vector128<ushort> Value2) LoadVector128x2AndUnzip(ushort* address);
        public static unsafe (Vector128<int>    Value1, Vector128<int>    Value2) LoadVector128x2AndUnzip(int*    address);
        public static unsafe (Vector128<uint>   Value1, Vector128<uint>   Value2) LoadVector128x2AndUnzip(uint*   address);
        public static unsafe (Vector128<long>   Value1, Vector128<long>   Value2) LoadVector128x2AndUnzip(long*   address);
        public static unsafe (Vector128<ulong>  Value1, Vector128<ulong>  Value2) LoadVector128x2AndUnzip(ulong*  address);
        public static unsafe (Vector128<float>  Value1, Vector128<float>  Value2) LoadVector128x2AndUnzip(float*  address);
        public static unsafe (Vector128<double> Value1, Vector128<double> Value2) LoadVector128x2AndUnzip(double* address);

        // LD1 (multiple structures) 3 register variant
        public static unsafe (Vector128<byte>   Value1, Vector128<byte>   Value2, Vector128<byte>   Value3) LoadVector128x3AndUnzip(byte*   address);
        public static unsafe (Vector128<sbyte>  Value1, Vector128<sbyte>  Value2, Vector128<sbyte>  Value3) LoadVector128x3AndUnzip(sbyte*  address);
        public static unsafe (Vector128<short>  Value1, Vector128<short>  Value2, Vector128<short>  Value3) LoadVector128x3AndUnzip(short*  address);
        public static unsafe (Vector128<ushort> Value1, Vector128<ushort> Value2, Vector128<ushort> Value3) LoadVector128x3AndUnzip(ushort* address);
        public static unsafe (Vector128<int>    Value1, Vector128<int>    Value2, Vector128<int>    Value3) LoadVector128x3AndUnzip(int*    address);
        public static unsafe (Vector128<uint>   Value1, Vector128<uint>   Value2, Vector128<uint>   Value3) LoadVector128x3AndUnzip(uint*   address);
        public static unsafe (Vector128<long>   Value1, Vector128<long>   Value2, Vector128<long>   Value3) LoadVector128x3AndUnzip(long*   address);
        public static unsafe (Vector128<ulong>  Value1, Vector128<ulong>  Value2, Vector128<ulong>  Value3) LoadVector128x3AndUnzip(ulong*  address);
        public static unsafe (Vector128<float>  Value1, Vector128<float>  Value2, Vector128<float>  Value3) LoadVector128x3AndUnzip(float*  address);
        public static unsafe (Vector128<double> Value1, Vector128<double> Value2, Vector128<double> Value3) LoadVector128x3AndUnzip(double* address);
        
        // LD1 (multiple structures) 4 register variant            
        public static unsafe (Vector128<byte>   Value1, Vector128<byte>   Value2, Vector128<byte>   Value3, Vector128<byte>   Value4) LoadVector128x4AndUnzip(byte*   address);
        public static unsafe (Vector128<sbyte>  Value1, Vector128<sbyte>  Value2, Vector128<sbyte>  Value3, Vector128<sbyte>  Value4) LoadVector128x4AndUnzip(sbyte*  address);
        public static unsafe (Vector128<short>  Value1, Vector128<short>  Value2, Vector128<short>  Value3, Vector128<short>  Value4) LoadVector128x4AndUnzip(short*  address);
        public static unsafe (Vector128<ushort> Value1, Vector128<ushort> Value2, Vector128<ushort> Value3, Vector128<ushort> Value4) LoadVector128x4AndUnzip(ushort* address);
        public static unsafe (Vector128<int>    Value1, Vector128<int>    Value2, Vector128<int>    Value3, Vector128<int>    Value4) LoadVector128x4AndUnzip(int*    address);
        public static unsafe (Vector128<uint>   Value1, Vector128<uint>   Value2, Vector128<uint>   Value3, Vector128<uint>   Value4) LoadVector128x4AndUnzip(uint*   address);
        public static unsafe (Vector128<long>   Value1, Vector128<long>   Value2, Vector128<long>   Value3, Vector128<long>   Value4) LoadVector128x4AndUnzip(long*   address);
        public static unsafe (Vector128<ulong>  Value1, Vector128<ulong>  Value2, Vector128<ulong>  Value3, Vector128<ulong>  Value4) LoadVector128x4AndUnzip(ulong*  address);
        public static unsafe (Vector128<float>  Value1, Vector128<float>  Value2, Vector128<float>  Value3, Vector128<float>  Value4) LoadVector128x4AndUnzip(float*  address);
        public static unsafe (Vector128<double> Value1, Vector128<double> Value2, Vector128<double> Value3, Vector128<double> Value4) LoadVector128x4AndUnzip(double* address);

Contributes to #84510

Author:	TIHan
Assignees:	-
Labels:	`area-System.Runtime.Intrinsics`, `new-api-needs-documentation`
Milestone:	-

src/libraries/System.Private.CoreLib/src/System/Runtime/Intrinsics/Arm/AdvSimd.cs

TIHan · 2023-10-30T14:21:51Z

@dotnet/jit-contrib @kunalspathak this is ready

TIHan · 2023-10-30T18:17:37Z

src/libraries/System.Private.CoreLib/src/System/Runtime/Intrinsics/Arm/AdvSimd.cs

@@ -9034,6 +9184,111 @@ public new abstract class Arm64 : ArmBase.Arm64
        /// </summary>
        public static unsafe Vector128<ulong> LoadVector128(ulong* address) => LoadVector128(address);

+        /// <summary>
+        ///   A64: LD1 { Vn.16B, Vn+1.16B }, [Xn]


@tannergooding I think the noted register in this comment should be:

/// A64: LD1 { Vn.8B, Vn+1.8B }, [Xn]

as well as adjusting the other noted registers in the comments on the other LoadVector64x2/3/4* methods for sbyte,short,ushort,long,ulong,float.

/// A64: LD1 { Vn.4H, Vn+1.4H }, [Xn]

/// A64: LD1 { Vn.2S, Vn+1.2S }, [Xn]

https://developer.arm.com/documentation/102159/0400/Load-and-store---data-structures

yes, this should be half the sizes i.e. 8B, 4H, etc.

Looks like it, yeah. I definitely might've made a mistake in documenting some of the things. Lots of APIs and lots of copy/pasting

kunalspathak

LGTM

TIHan · 2023-10-30T21:32:45Z

@kunalspathak I'll make another PR to fix the comments for the LoadVector64x2/3/4, merging this now.

kunalspathak · 2023-10-30T21:51:06Z

cc: @a74nh @SwapnilGaikwad

TIHan added 3 commits October 27, 2023 19:41

Initial LoadVector64/128AndUnzip APIs

6c0544b

Added hwintrinsics

b53ccc7

Added generating tests

0ff186c

dotnet-issue-labeler bot added area-System.Runtime.Intrinsics new-api-needs-documentation labels Oct 28, 2023

ghost assigned TIHan Oct 28, 2023

TIHan added 7 commits October 27, 2023 20:25

Fix semi

cc607b6

Whitespace

47b7d57

Whitespace

565f321

Whitespace

454eaab

Whitespace

a91e2bd

Whitespace

3a376c1

Whitespace

a63ca96

TIHan commented Oct 28, 2023

View reviewed changes

src/libraries/System.Private.CoreLib/src/System/Runtime/Intrinsics/Arm/AdvSimd.cs Show resolved Hide resolved

Fix test generation

56deb7e

This was referenced Oct 28, 2023

Timeout in System.Net.Quic.Functional.Tests #86019

Closed

CI error: System.Net.Quic.QuicException: The connection timed out from inactivity #91757

Closed

fix missing cases in gentree

988737f

build-analysis bot mentioned this pull request Oct 28, 2023

Test_EventSource_EtwManifestGeneration* tests failing in CI #48798

Closed

TIHan added 4 commits October 29, 2023 15:01

Minor formatting of the test generator

2f59c1b

Fix comments

48806a1

Fixing up tests

7a8bb04

Use the right register variants

2d5f697

TIHan marked this pull request as ready for review October 30, 2023 14:22

TIHan commented Oct 30, 2023

View reviewed changes

kunalspathak approved these changes Oct 30, 2023

View reviewed changes

TIHan merged commit 4b5756d into dotnet:main Oct 30, 2023
193 of 195 checks passed

TIHan deleted the arm64-load-vector-and-unzip branch October 30, 2023 21:32

ghost locked as resolved and limited conversation to collaborators Nov 30, 2023

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Arm64: Implement LoadVector64xAndUnzip and LoadVector128xAndUnzip APIs #94128

Arm64: Implement LoadVector64xAndUnzip and LoadVector128xAndUnzip APIs #94128

TIHan commented Oct 28, 2023 •

edited

Loading

dotnet-issue-labeler bot commented Oct 28, 2023

ghost commented Oct 28, 2023

TIHan commented Oct 30, 2023

TIHan Oct 30, 2023

kunalspathak Oct 30, 2023

tannergooding Oct 30, 2023

kunalspathak left a comment

TIHan commented Oct 30, 2023

kunalspathak commented Oct 30, 2023

Arm64: Implement LoadVector64x*AndUnzip and LoadVector128x*AndUnzip APIs #94128

Arm64: Implement LoadVector64x*AndUnzip and LoadVector128x*AndUnzip APIs #94128

Conversation

TIHan commented Oct 28, 2023 • edited Loading

dotnet-issue-labeler bot commented Oct 28, 2023

ghost commented Oct 28, 2023

TIHan commented Oct 30, 2023

TIHan Oct 30, 2023

Choose a reason for hiding this comment

kunalspathak Oct 30, 2023

Choose a reason for hiding this comment

tannergooding Oct 30, 2023

Choose a reason for hiding this comment

kunalspathak left a comment

Choose a reason for hiding this comment

TIHan commented Oct 30, 2023

kunalspathak commented Oct 30, 2023

Arm64: Implement LoadVector64xAndUnzip and LoadVector128xAndUnzip APIs #94128

Arm64: Implement LoadVector64xAndUnzip and LoadVector128xAndUnzip APIs #94128

TIHan commented Oct 28, 2023 •

edited

Loading