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

Jump to bottom

[API Proposal]: Arm64: FEAT_SVE2: gather loads #94019

Open
a74nh opened this issue Oct 26, 2023 · 7 comments
Open

[API Proposal]: Arm64: FEAT_SVE2: gather loads #94019

a74nh opened this issue Oct 26, 2023 · 7 comments
Labels
api-suggestion Early API idea and discussion, it is NOT ready for implementation arch-arm64 area-System.Runtime.Intrinsics
Milestone
Future

Comments

@a74nh
Copy link
Contributor

a74nh commented Oct 26, 2023 •
edited
Loading 

namespace System.Runtime.Intrinsics.Arm;

/// VectorT Summary
public abstract partial class Sve2 : AdvSimd /// Feature: FEAT_SVE2  Category: gatherloads
{

  /// T: [int, uint], [uint, uint], [long, ulong], [ulong, ulong]
  public static unsafe Vector<T> GatherVectorByteZeroExtendNonTemporal(Vector<T> mask, Vector<T2> addresses); // LDNT1B

  /// T: [int, uint], [uint, uint], [long, long], [ulong, long], [long, ulong], [ulong, ulong]
  public static unsafe Vector<T> GatherVectorByteZeroExtendNonTemporal(Vector<T> mask, byte* address, Vector<T2> offsets); // LDNT1B

  /// T: [int, uint], [uint, uint], [long, ulong], [ulong, ulong]
  public static unsafe Vector<T> GatherVectorInt16SignExtendNonTemporal(Vector<T> mask, Vector<T2> addresses); // LDNT1SH

  /// T: [long, long], [ulong, long], [long, ulong], [ulong, ulong]
  public static unsafe Vector<T> GatherVectorInt16SignExtendNonTemporal(Vector<T> mask, short* address, Vector<T2> indices); // LDNT1SH

  /// T: [int, uint], [uint, uint], [long, long], [ulong, long], [long, ulong], [ulong, ulong]
  public static unsafe Vector<T> GatherVectorInt16WithByteOffsetsSignExtendNonTemporal(Vector<T> mask, short* address, Vector<T2> offsets); // LDNT1SH

  /// T: [long, ulong], [int, uint], [ulong, ulong], [uint, uint]
  public static unsafe Vector<T> GatherVectorInt32SignExtendNonTemporal(Vector<T> mask, Vector<T2> addresses); // LDNT1SW

  /// T: [long, long], [int, int], [ulong, long], [uint, int], [long, ulong], [int, uint], [ulong, ulong], [uint, uint]
  public static unsafe Vector<T> GatherVectorInt32SignExtendNonTemporal(Vector<T> mask, int* address, Vector<T2> indices); // LDNT1SW

  /// T: [long, long], [int, int], [ulong, long], [uint, int], [long, ulong], [int, uint], [ulong, ulong], [uint, uint]
  public static unsafe Vector<T> GatherVectorInt32WithByteOffsetsSignExtendNonTemporal(Vector<T> mask, int* address, Vector<T2> offsets); // LDNT1SW

  /// T: [float, uint], [int, uint], [double, ulong], [long, ulong]
  public static unsafe Vector<T> GatherVectorNonTemporal(Vector<T> mask, Vector<T2> addresses); // LDNT1W or LDNT1D

  /// T: uint, ulong
  public static unsafe Vector<T> GatherVectorNonTemporal(Vector<T> mask, Vector<T> addresses); // LDNT1W or LDNT1D

  /// T: [float, uint], [int, uint], [double, long], [ulong, long], [double, ulong], [long, ulong]
  public static unsafe Vector<T> GatherVectorNonTemporal(Vector<T> mask, T* address, Vector<T2> offsets); // LDNT1W or LDNT1D

  /// T: uint, long, ulong
  public static unsafe Vector<T> GatherVectorNonTemporal(Vector<T> mask, T* address, Vector<T> offsets); // LDNT1W or LDNT1D

  /// T: [double, long], [ulong, long], [double, ulong], [long, ulong]
  public static unsafe Vector<T> GatherVectorNonTemporal(Vector<T> mask, T* address, Vector<T2> indices); // LDNT1D

  /// T: long, ulong
  public static unsafe Vector<T> GatherVectorNonTemporal(Vector<T> mask, T* address, Vector<T> indices); // LDNT1D

  /// T: [int, uint], [uint, uint], [long, ulong], [ulong, ulong]
  public static unsafe Vector<T> GatherVectorSByteSignExtendNonTemporal(Vector<T> mask, Vector<T2> addresses); // LDNT1SB

  /// T: [int, uint], [uint, uint], [long, long], [ulong, long], [long, ulong], [ulong, ulong]
  public static unsafe Vector<T> GatherVectorSByteSignExtendNonTemporal(Vector<T> mask, sbyte* address, Vector<T2> offsets); // LDNT1SB

  /// T: [int, uint], [uint, uint], [long, long], [ulong, long], [long, ulong], [ulong, ulong]
  public static unsafe Vector<T> GatherVectorUInt16WithByteOffsetsZeroExtendNonTemporal(Vector<T> mask, ushort* address, Vector<T2> offsets); // LDNT1H

  /// T: [int, uint], [uint, uint], [long, ulong], [ulong, ulong]
  public static unsafe Vector<T> GatherVectorUInt16ZeroExtendNonTemporal(Vector<T> mask, Vector<T2> addresses); // LDNT1H

  /// T: [long, long], [ulong, long], [long, ulong], [ulong, ulong]
  public static unsafe Vector<T> GatherVectorUInt16ZeroExtendNonTemporal(Vector<T> mask, ushort* address, Vector<T2> indices); // LDNT1H

  /// T: [long, long], [int, int], [ulong, long], [uint, int], [long, ulong], [int, uint], [ulong, ulong], [uint, uint]
  public static unsafe Vector<T> GatherVectorUInt32WithByteOffsetsZeroExtendNonTemporal(Vector<T> mask, uint* address, Vector<T2> offsets); // LDNT1W

  /// T: [long, ulong], [int, uint], [ulong, ulong], [uint, uint]
  public static unsafe Vector<T> GatherVectorUInt32ZeroExtendNonTemporal(Vector<T> mask, Vector<T2> addresses); // LDNT1W

  /// T: [long, long], [int, int], [ulong, long], [uint, int], [long, ulong], [int, uint], [ulong, ulong], [uint, uint]
  public static unsafe Vector<T> GatherVectorUInt32ZeroExtendNonTemporal(Vector<T> mask, uint* address, Vector<T2> indices); // LDNT1W

  /// total method signatures: 22

}
@ghost ghost added the untriaged New issue has not been triaged by the area owner label Oct 26, 2023
@ghost
Copy link

ghost commented Oct 26, 2023

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

Issue Details 
namespace System.Runtime.Intrinsics.Arm

/// VectorT Summary
public abstract class Sve : AdvSimd /// Feature: FEAT_SVE2  Category: gatherloads
{
  /// T: [int, uint], [long, ulong]
  public static unsafe Vector<T> GatherLoadVector16SignExtendNonTemporal(Vector<T2> bases); // LDNT1SH

  /// T: uint, ulong
  public static unsafe Vector<T> GatherLoadVector16SignExtendNonTemporal(Vector<T> bases); // LDNT1SH

  /// T: [int, uint], [ulong, long], [long, ulong]
  public static unsafe Vector<T> GatherLoadVector16SignExtendNonTemporal(const short *base, Vector<T2> offsets); // LDNT1SH

  /// T: uint, long, ulong
  public static unsafe Vector<T> GatherLoadVector16SignExtendNonTemporal(const short *base, Vector<T> offsets); // LDNT1SH

  /// T: long, ulong
  public static unsafe Vector<T> GatherLoadVector16SignExtendNonTemporal(const short *base, Vector<T> indices); // LDNT1SH

  /// T: [ulong, long], [long, ulong]
  public static unsafe Vector<T> GatherLoadVector16SignExtendNonTemporal(const short *base, Vector<T2> indices); // LDNT1SH

  /// T: [int, uint], [long, ulong]
  public static unsafe Vector<T> GatherLoadVector16SignExtendNonTemporal(Vector<T2> bases, long offset); // LDNT1SH

  /// T: uint, ulong
  public static unsafe Vector<T> GatherLoadVector16SignExtendNonTemporal(Vector<T> bases, long offset); // LDNT1SH

  /// T: [int, uint], [long, ulong]
  public static unsafe Vector<T> GatherLoadVector16SignExtendNonTemporal(Vector<T2> bases, long index); // LDNT1SH

  /// T: uint, ulong
  public static unsafe Vector<T> GatherLoadVector16SignExtendNonTemporal(Vector<T> bases, long index); // LDNT1SH

  /// T: [int, uint], [long, ulong]
  public static unsafe Vector<T> GatherLoadVector16ZeroExtendNonTemporal(Vector<T2> bases); // LDNT1H

  /// T: uint, ulong
  public static unsafe Vector<T> GatherLoadVector16ZeroExtendNonTemporal(Vector<T> bases); // LDNT1H

  /// T: [int, uint], [ulong, long], [long, ulong]
  public static unsafe Vector<T> GatherLoadVector16ZeroExtendNonTemporal(const ushort *base, Vector<T2> offsets); // LDNT1H

  /// T: uint, long, ulong
  public static unsafe Vector<T> GatherLoadVector16ZeroExtendNonTemporal(const ushort *base, Vector<T> offsets); // LDNT1H

  /// T: long, ulong
  public static unsafe Vector<T> GatherLoadVector16ZeroExtendNonTemporal(const ushort *base, Vector<T> indices); // LDNT1H

  /// T: [ulong, long], [long, ulong]
  public static unsafe Vector<T> GatherLoadVector16ZeroExtendNonTemporal(const ushort *base, Vector<T2> indices); // LDNT1H

  /// T: [int, uint], [long, ulong]
  public static unsafe Vector<T> GatherLoadVector16ZeroExtendNonTemporal(Vector<T2> bases, long offset); // LDNT1H

  /// T: uint, ulong
  public static unsafe Vector<T> GatherLoadVector16ZeroExtendNonTemporal(Vector<T> bases, long offset); // LDNT1H

  /// T: [int, uint], [long, ulong]
  public static unsafe Vector<T> GatherLoadVector16ZeroExtendNonTemporal(Vector<T2> bases, long index); // LDNT1H

  /// T: uint, ulong
  public static unsafe Vector<T> GatherLoadVector16ZeroExtendNonTemporal(Vector<T> bases, long index); // LDNT1H

  public static unsafe Vector<long> GatherLoadVector32SignExtendNonTemporal(Vector<ulong> bases);

  public static unsafe Vector<ulong> GatherLoadVector32SignExtendNonTemporal(Vector<ulong> bases);

  /// T: long, ulong
  public static unsafe Vector<T> GatherLoadVector32SignExtendNonTemporal(const int *base, Vector<T> offsets); // LDNT1SW

  /// T: [ulong, long], [long, ulong]
  public static unsafe Vector<T> GatherLoadVector32SignExtendNonTemporal(const int *base, Vector<T2> offsets); // LDNT1SW

  /// T: long, ulong
  public static unsafe Vector<T> GatherLoadVector32SignExtendNonTemporal(const int *base, Vector<T> indices); // LDNT1SW

  /// T: [ulong, long], [long, ulong]
  public static unsafe Vector<T> GatherLoadVector32SignExtendNonTemporal(const int *base, Vector<T2> indices); // LDNT1SW

  public static unsafe Vector<long> GatherLoadVector32SignExtendNonTemporal(Vector<ulong> bases, long offset);

  public static unsafe Vector<ulong> GatherLoadVector32SignExtendNonTemporal(Vector<ulong> bases, long offset);

  public static unsafe Vector<long> GatherLoadVector32SignExtendNonTemporal(Vector<ulong> bases, long index);

  public static unsafe Vector<ulong> GatherLoadVector32SignExtendNonTemporal(Vector<ulong> bases, long index);

  public static unsafe Vector<long> GatherLoadVector32ZeroExtendNonTemporal(Vector<ulong> bases);

  public static unsafe Vector<ulong> GatherLoadVector32ZeroExtendNonTemporal(Vector<ulong> bases);

  /// T: long, ulong
  public static unsafe Vector<T> GatherLoadVector32ZeroExtendNonTemporal(const uint *base, Vector<T> offsets); // LDNT1W

  /// T: [ulong, long], [long, ulong]
  public static unsafe Vector<T> GatherLoadVector32ZeroExtendNonTemporal(const uint *base, Vector<T2> offsets); // LDNT1W

  /// T: long, ulong
  public static unsafe Vector<T> GatherLoadVector32ZeroExtendNonTemporal(const uint *base, Vector<T> indices); // LDNT1W

  /// T: [ulong, long], [long, ulong]
  public static unsafe Vector<T> GatherLoadVector32ZeroExtendNonTemporal(const uint *base, Vector<T2> indices); // LDNT1W

  public static unsafe Vector<long> GatherLoadVector32ZeroExtendNonTemporal(Vector<ulong> bases, long offset);

  public static unsafe Vector<ulong> GatherLoadVector32ZeroExtendNonTemporal(Vector<ulong> bases, long offset);

  public static unsafe Vector<long> GatherLoadVector32ZeroExtendNonTemporal(Vector<ulong> bases, long index);

  public static unsafe Vector<ulong> GatherLoadVector32ZeroExtendNonTemporal(Vector<ulong> bases, long index);

  /// T: [int, uint], [long, ulong]
  public static unsafe Vector<T> GatherLoadVector8SignExtendNonTemporal(Vector<T2> bases); // LDNT1SB

  /// T: uint, ulong
  public static unsafe Vector<T> GatherLoadVector8SignExtendNonTemporal(Vector<T> bases); // LDNT1SB

  /// T: [int, uint], [ulong, long], [long, ulong]
  public static unsafe Vector<T> GatherLoadVector8SignExtendNonTemporal(const sbyte *base, Vector<T2> offsets); // LDNT1SB

  /// T: uint, long, ulong
  public static unsafe Vector<T> GatherLoadVector8SignExtendNonTemporal(const sbyte *base, Vector<T> offsets); // LDNT1SB

  /// T: [int, uint], [long, ulong]
  public static unsafe Vector<T> GatherLoadVector8SignExtendNonTemporal(Vector<T2> bases, long offset); // LDNT1SB

  /// T: uint, ulong
  public static unsafe Vector<T> GatherLoadVector8SignExtendNonTemporal(Vector<T> bases, long offset); // LDNT1SB

  /// T: [int, uint], [long, ulong]
  public static unsafe Vector<T> GatherLoadVector8ZeroExtendNonTemporal(Vector<T2> bases); // LDNT1B

  /// T: uint, ulong
  public static unsafe Vector<T> GatherLoadVector8ZeroExtendNonTemporal(Vector<T> bases); // LDNT1B

  /// T: [int, uint], [ulong, long], [long, ulong]
  public static unsafe Vector<T> GatherLoadVector8ZeroExtendNonTemporal(const byte *base, Vector<T2> offsets); // LDNT1B

  /// T: uint, long, ulong
  public static unsafe Vector<T> GatherLoadVector8ZeroExtendNonTemporal(const byte *base, Vector<T> offsets); // LDNT1B

  /// T: [int, uint], [long, ulong]
  public static unsafe Vector<T> GatherLoadVector8ZeroExtendNonTemporal(Vector<T2> bases, long offset); // LDNT1B

  /// T: uint, ulong
  public static unsafe Vector<T> GatherLoadVector8ZeroExtendNonTemporal(Vector<T> bases, long offset); // LDNT1B

  /// T: [float, uint], [int, uint], [double, ulong], [long, ulong]
  public static unsafe Vector<T> GatherLoadVectorNonTemporal(Vector<T2> bases); // LDNT1W or LDNT1D

  /// T: uint, ulong
  public static unsafe Vector<T> GatherLoadVectorNonTemporal(Vector<T> bases); // LDNT1W or LDNT1D

  /// T: [float, uint], [int, uint], [double, long], [ulong, long], [double, ulong], [long, ulong]
  public static unsafe Vector<T> GatherLoadVectorNonTemporal(const T *base, Vector<T2> offsets); // LDNT1W or LDNT1D

  /// T: uint, long, ulong
  public static unsafe Vector<T> GatherLoadVectorNonTemporal(const T *base, Vector<T> offsets); // LDNT1W or LDNT1D

  /// T: [double, long], [ulong, long], [double, ulong], [long, ulong]
  public static unsafe Vector<T> GatherLoadVectorNonTemporal(const T *base, Vector<T2> indices); // LDNT1D

  /// T: long, ulong
  public static unsafe Vector<T> GatherLoadVectorNonTemporal(const T *base, Vector<T> indices); // LDNT1D

  /// T: [float, uint], [int, uint], [double, ulong], [long, ulong]
  public static unsafe Vector<T> GatherLoadVectorNonTemporal(Vector<T2> bases, long offset); // LDNT1W or LDNT1D

  /// T: uint, ulong
  public static unsafe Vector<T> GatherLoadVectorNonTemporal(Vector<T> bases, long offset); // LDNT1W or LDNT1D

  /// T: [float, uint], [int, uint], [double, ulong], [long, ulong]
  public static unsafe Vector<T> GatherLoadVectorNonTemporal(Vector<T2> bases, long index); // LDNT1W or LDNT1D

  /// T: uint, ulong
  public static unsafe Vector<T> GatherLoadVectorNonTemporal(Vector<T> bases, long index); // LDNT1W or LDNT1D

  /// total method signatures: 62
}
Author: a74nh
Assignees: -
Labels:

area-System.Numerics
Milestone: -

@a74nh
Copy link
Contributor Author

a74nh commented Oct 26, 2023 •
edited
Loading 

/// Full API
public abstract partial class Sve2 : AdvSimd /// Feature: FEAT_SVE2  Category: gatherloads
{
    /// GatherVectorByteZeroExtendNonTemporal : Load 8-bit data and zero-extend, non-temporal

    /// svint32_t svldnt1ub_gather[_u32base]_s32(svbool_t pg, svuint32_t bases) : "LDNT1B Zresult.S, Pg/Z, [Zbases.S, XZR]"
  public static unsafe Vector<int> GatherVectorByteZeroExtendNonTemporal(Vector<int> mask, Vector<uint> addresses);

    /// svuint32_t svldnt1ub_gather[_u32base]_u32(svbool_t pg, svuint32_t bases) : "LDNT1B Zresult.S, Pg/Z, [Zbases.S, XZR]"
  public static unsafe Vector<uint> GatherVectorByteZeroExtendNonTemporal(Vector<uint> mask, Vector<uint> addresses);

    /// svint64_t svldnt1ub_gather[_u64base]_s64(svbool_t pg, svuint64_t bases) : "LDNT1B Zresult.D, Pg/Z, [Zbases.D, XZR]"
  public static unsafe Vector<long> GatherVectorByteZeroExtendNonTemporal(Vector<long> mask, Vector<ulong> addresses);

    /// svuint64_t svldnt1ub_gather[_u64base]_u64(svbool_t pg, svuint64_t bases) : "LDNT1B Zresult.D, Pg/Z, [Zbases.D, XZR]"
  public static unsafe Vector<ulong> GatherVectorByteZeroExtendNonTemporal(Vector<ulong> mask, Vector<ulong> addresses);

    /// svint32_t svldnt1ub_gather_[u32]offset_s32(svbool_t pg, const uint8_t *base, svuint32_t offsets) : "LDNT1B Zresult.S, Pg/Z, [Zoffsets.S, Xbase]"
  public static unsafe Vector<int> GatherVectorByteZeroExtendNonTemporal(Vector<int> mask, byte* address, Vector<uint> offsets);

    /// svuint32_t svldnt1ub_gather_[u32]offset_u32(svbool_t pg, const uint8_t *base, svuint32_t offsets) : "LDNT1B Zresult.S, Pg/Z, [Zoffsets.S, Xbase]"
  public static unsafe Vector<uint> GatherVectorByteZeroExtendNonTemporal(Vector<uint> mask, byte* address, Vector<uint> offsets);

    /// svint64_t svldnt1ub_gather_[s64]offset_s64(svbool_t pg, const uint8_t *base, svint64_t offsets) : "LDNT1B Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<long> GatherVectorByteZeroExtendNonTemporal(Vector<long> mask, byte* address, Vector<long> offsets);

    /// svuint64_t svldnt1ub_gather_[s64]offset_u64(svbool_t pg, const uint8_t *base, svint64_t offsets) : "LDNT1B Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<ulong> GatherVectorByteZeroExtendNonTemporal(Vector<ulong> mask, byte* address, Vector<long> offsets);

    /// svint64_t svldnt1ub_gather_[u64]offset_s64(svbool_t pg, const uint8_t *base, svuint64_t offsets) : "LDNT1B Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<long> GatherVectorByteZeroExtendNonTemporal(Vector<long> mask, byte* address, Vector<ulong> offsets);

    /// svuint64_t svldnt1ub_gather_[u64]offset_u64(svbool_t pg, const uint8_t *base, svuint64_t offsets) : "LDNT1B Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<ulong> GatherVectorByteZeroExtendNonTemporal(Vector<ulong> mask, byte* address, Vector<ulong> offsets);


    /// GatherVectorInt16SignExtendNonTemporal : Load 16-bit data and sign-extend, non-temporal

    /// svint32_t svldnt1sh_gather[_u32base]_s32(svbool_t pg, svuint32_t bases) : "LDNT1SH Zresult.S, Pg/Z, [Zbases.S, XZR]"
  public static unsafe Vector<int> GatherVectorInt16SignExtendNonTemporal(Vector<int> mask, Vector<uint> addresses);

    /// svuint32_t svldnt1sh_gather[_u32base]_u32(svbool_t pg, svuint32_t bases) : "LDNT1SH Zresult.S, Pg/Z, [Zbases.S, XZR]"
  public static unsafe Vector<uint> GatherVectorInt16SignExtendNonTemporal(Vector<uint> mask, Vector<uint> addresses);

    /// svint64_t svldnt1sh_gather[_u64base]_s64(svbool_t pg, svuint64_t bases) : "LDNT1SH Zresult.D, Pg/Z, [Zbases.D, XZR]"
  public static unsafe Vector<long> GatherVectorInt16SignExtendNonTemporal(Vector<long> mask, Vector<ulong> addresses);

    /// svuint64_t svldnt1sh_gather[_u64base]_u64(svbool_t pg, svuint64_t bases) : "LDNT1SH Zresult.D, Pg/Z, [Zbases.D, XZR]"
  public static unsafe Vector<ulong> GatherVectorInt16SignExtendNonTemporal(Vector<ulong> mask, Vector<ulong> addresses);

    /// svint64_t svldnt1sh_gather_[s64]index_s64(svbool_t pg, const int16_t *base, svint64_t indices) : "LDNT1SH Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<long> GatherVectorInt16SignExtendNonTemporal(Vector<long> mask, short* address, Vector<long> indices);

    /// svuint64_t svldnt1sh_gather_[s64]index_u64(svbool_t pg, const int16_t *base, svint64_t indices) : "LDNT1SH Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<ulong> GatherVectorInt16SignExtendNonTemporal(Vector<ulong> mask, short* address, Vector<long> indices);

    /// svint64_t svldnt1sh_gather_[u64]index_s64(svbool_t pg, const int16_t *base, svuint64_t indices) : "LDNT1SH Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<long> GatherVectorInt16SignExtendNonTemporal(Vector<long> mask, short* address, Vector<ulong> indices);

    /// svuint64_t svldnt1sh_gather_[u64]index_u64(svbool_t pg, const int16_t *base, svuint64_t indices) : "LDNT1SH Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<ulong> GatherVectorInt16SignExtendNonTemporal(Vector<ulong> mask, short* address, Vector<ulong> indices);


    /// GatherVectorInt16WithByteOffsetsSignExtendNonTemporal : Load 16-bit data and sign-extend, non-temporal

    /// svint32_t svldnt1sh_gather_[u32]offset_s32(svbool_t pg, const int16_t *base, svuint32_t offsets) : "LDNT1SH Zresult.S, Pg/Z, [Zoffsets.S, Xbase]"
  public static unsafe Vector<int> GatherVectorInt16WithByteOffsetsSignExtendNonTemporal(Vector<int> mask, short* address, Vector<uint> offsets);

    /// svuint32_t svldnt1sh_gather_[u32]offset_u32(svbool_t pg, const int16_t *base, svuint32_t offsets) : "LDNT1SH Zresult.S, Pg/Z, [Zoffsets.S, Xbase]"
  public static unsafe Vector<uint> GatherVectorInt16WithByteOffsetsSignExtendNonTemporal(Vector<uint> mask, short* address, Vector<uint> offsets);

    /// svint64_t svldnt1sh_gather_[s64]offset_s64(svbool_t pg, const int16_t *base, svint64_t offsets) : "LDNT1SH Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<long> GatherVectorInt16WithByteOffsetsSignExtendNonTemporal(Vector<long> mask, short* address, Vector<long> offsets);

    /// svuint64_t svldnt1sh_gather_[s64]offset_u64(svbool_t pg, const int16_t *base, svint64_t offsets) : "LDNT1SH Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<ulong> GatherVectorInt16WithByteOffsetsSignExtendNonTemporal(Vector<ulong> mask, short* address, Vector<long> offsets);

    /// svint64_t svldnt1sh_gather_[u64]offset_s64(svbool_t pg, const int16_t *base, svuint64_t offsets) : "LDNT1SH Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<long> GatherVectorInt16WithByteOffsetsSignExtendNonTemporal(Vector<long> mask, short* address, Vector<ulong> offsets);

    /// svuint64_t svldnt1sh_gather_[u64]offset_u64(svbool_t pg, const int16_t *base, svuint64_t offsets) : "LDNT1SH Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<ulong> GatherVectorInt16WithByteOffsetsSignExtendNonTemporal(Vector<ulong> mask, short* address, Vector<ulong> offsets);


    /// GatherVectorInt32SignExtendNonTemporal : Load 32-bit data and sign-extend, non-temporal

    /// svint64_t svldnt1sw_gather[_u64base]_s64(svbool_t pg, svuint64_t bases) : "LDNT1SW Zresult.D, Pg/Z, [Zbases.D, XZR]"
  public static unsafe Vector<long> GatherVectorInt32SignExtendNonTemporal(Vector<long> mask, Vector<ulong> addresses);

    /// svint64_t svldnt1sw_gather[_u64base]_s64(svbool_t pg, svuint64_t bases) : "LDNT1SW Zresult.D, Pg/Z, [Zbases.D, XZR]"
  public static unsafe Vector<int> GatherVectorInt32SignExtendNonTemporal(Vector<int> mask, Vector<uint> addresses);

    /// svuint64_t svldnt1sw_gather[_u64base]_u64(svbool_t pg, svuint64_t bases) : "LDNT1SW Zresult.D, Pg/Z, [Zbases.D, XZR]"
  public static unsafe Vector<ulong> GatherVectorInt32SignExtendNonTemporal(Vector<ulong> mask, Vector<ulong> addresses);

    /// svuint64_t svldnt1sw_gather[_u64base]_u64(svbool_t pg, svuint64_t bases) : "LDNT1SW Zresult.D, Pg/Z, [Zbases.D, XZR]"
  public static unsafe Vector<uint> GatherVectorInt32SignExtendNonTemporal(Vector<uint> mask, Vector<uint> addresses);

    /// svint64_t svldnt1sw_gather_[s64]index_s64(svbool_t pg, const int32_t *base, svint64_t indices) : "LDNT1SW Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<long> GatherVectorInt32SignExtendNonTemporal(Vector<long> mask, int* address, Vector<long> indices);

    /// svint64_t svldnt1sw_gather_[s64]index_s64(svbool_t pg, const int32_t *base, svint64_t indices) : "LDNT1SW Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<int> GatherVectorInt32SignExtendNonTemporal(Vector<int> mask, int* address, Vector<int> indices);

    /// svuint64_t svldnt1sw_gather_[s64]index_u64(svbool_t pg, const int32_t *base, svint64_t indices) : "LDNT1SW Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<ulong> GatherVectorInt32SignExtendNonTemporal(Vector<ulong> mask, int* address, Vector<long> indices);

    /// svuint64_t svldnt1sw_gather_[s64]index_u64(svbool_t pg, const int32_t *base, svint64_t indices) : "LDNT1SW Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<uint> GatherVectorInt32SignExtendNonTemporal(Vector<uint> mask, int* address, Vector<int> indices);

    /// svint64_t svldnt1sw_gather_[u64]index_s64(svbool_t pg, const int32_t *base, svuint64_t indices) : "LDNT1SW Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<long> GatherVectorInt32SignExtendNonTemporal(Vector<long> mask, int* address, Vector<ulong> indices);

    /// svint64_t svldnt1sw_gather_[u64]index_s64(svbool_t pg, const int32_t *base, svuint64_t indices) : "LDNT1SW Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<int> GatherVectorInt32SignExtendNonTemporal(Vector<int> mask, int* address, Vector<uint> indices);

    /// svuint64_t svldnt1sw_gather_[u64]index_u64(svbool_t pg, const int32_t *base, svuint64_t indices) : "LDNT1SW Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<ulong> GatherVectorInt32SignExtendNonTemporal(Vector<ulong> mask, int* address, Vector<ulong> indices);

    /// svuint64_t svldnt1sw_gather_[u64]index_u64(svbool_t pg, const int32_t *base, svuint64_t indices) : "LDNT1SW Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<uint> GatherVectorInt32SignExtendNonTemporal(Vector<uint> mask, int* address, Vector<uint> indices);


    /// GatherVectorInt32WithByteOffsetsSignExtendNonTemporal : Load 32-bit data and sign-extend, non-temporal

    /// svint64_t svldnt1sw_gather_[s64]offset_s64(svbool_t pg, const int32_t *base, svint64_t offsets) : "LDNT1SW Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<long> GatherVectorInt32WithByteOffsetsSignExtendNonTemporal(Vector<long> mask, int* address, Vector<long> offsets);

    /// svint64_t svldnt1sw_gather_[s64]offset_s64(svbool_t pg, const int32_t *base, svint64_t offsets) : "LDNT1SW Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<int> GatherVectorInt32WithByteOffsetsSignExtendNonTemporal(Vector<int> mask, int* address, Vector<int> offsets);

    /// svuint64_t svldnt1sw_gather_[s64]offset_u64(svbool_t pg, const int32_t *base, svint64_t offsets) : "LDNT1SW Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<ulong> GatherVectorInt32WithByteOffsetsSignExtendNonTemporal(Vector<ulong> mask, int* address, Vector<long> offsets);

    /// svuint64_t svldnt1sw_gather_[s64]offset_u64(svbool_t pg, const int32_t *base, svint64_t offsets) : "LDNT1SW Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<uint> GatherVectorInt32WithByteOffsetsSignExtendNonTemporal(Vector<uint> mask, int* address, Vector<int> offsets);

    /// svint64_t svldnt1sw_gather_[u64]offset_s64(svbool_t pg, const int32_t *base, svuint64_t offsets) : "LDNT1SW Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<long> GatherVectorInt32WithByteOffsetsSignExtendNonTemporal(Vector<long> mask, int* address, Vector<ulong> offsets);

    /// svint64_t svldnt1sw_gather_[u64]offset_s64(svbool_t pg, const int32_t *base, svuint64_t offsets) : "LDNT1SW Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<int> GatherVectorInt32WithByteOffsetsSignExtendNonTemporal(Vector<int> mask, int* address, Vector<uint> offsets);

    /// svuint64_t svldnt1sw_gather_[u64]offset_u64(svbool_t pg, const int32_t *base, svuint64_t offsets) : "LDNT1SW Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<ulong> GatherVectorInt32WithByteOffsetsSignExtendNonTemporal(Vector<ulong> mask, int* address, Vector<ulong> offsets);

    /// svuint64_t svldnt1sw_gather_[u64]offset_u64(svbool_t pg, const int32_t *base, svuint64_t offsets) : "LDNT1SW Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<uint> GatherVectorInt32WithByteOffsetsSignExtendNonTemporal(Vector<uint> mask, int* address, Vector<uint> offsets);


    /// GatherVectorNonTemporal : Unextended load, non-temporal

    /// svfloat32_t svldnt1_gather[_u32base]_f32(svbool_t pg, svuint32_t bases) : "LDNT1W Zresult.S, Pg/Z, [Zbases.S, XZR]"
  public static unsafe Vector<float> GatherVectorNonTemporal(Vector<float> mask, Vector<uint> addresses);

    /// svint32_t svldnt1_gather[_u32base]_s32(svbool_t pg, svuint32_t bases) : "LDNT1W Zresult.S, Pg/Z, [Zbases.S, XZR]"
  public static unsafe Vector<int> GatherVectorNonTemporal(Vector<int> mask, Vector<uint> addresses);

    /// svuint32_t svldnt1_gather[_u32base]_u32(svbool_t pg, svuint32_t bases) : "LDNT1W Zresult.S, Pg/Z, [Zbases.S, XZR]"
  public static unsafe Vector<uint> GatherVectorNonTemporal(Vector<uint> mask, Vector<uint> addresses);

    /// svfloat64_t svldnt1_gather[_u64base]_f64(svbool_t pg, svuint64_t bases) : "LDNT1D Zresult.D, Pg/Z, [Zbases.D, XZR]"
  public static unsafe Vector<double> GatherVectorNonTemporal(Vector<double> mask, Vector<ulong> addresses);

    /// svint64_t svldnt1_gather[_u64base]_s64(svbool_t pg, svuint64_t bases) : "LDNT1D Zresult.D, Pg/Z, [Zbases.D, XZR]"
  public static unsafe Vector<long> GatherVectorNonTemporal(Vector<long> mask, Vector<ulong> addresses);

    /// svuint64_t svldnt1_gather[_u64base]_u64(svbool_t pg, svuint64_t bases) : "LDNT1D Zresult.D, Pg/Z, [Zbases.D, XZR]"
  public static unsafe Vector<ulong> GatherVectorNonTemporal(Vector<ulong> mask, Vector<ulong> addresses);

    /// svfloat32_t svldnt1_gather_[u32]offset[_f32](svbool_t pg, const float32_t *base, svuint32_t offsets) : "LDNT1W Zresult.S, Pg/Z, [Zoffsets.S, Xbase]"
  public static unsafe Vector<float> GatherVectorNonTemporal(Vector<float> mask, float* address, Vector<uint> offsets);

    /// svint32_t svldnt1_gather_[u32]offset[_s32](svbool_t pg, const int32_t *base, svuint32_t offsets) : "LDNT1W Zresult.S, Pg/Z, [Zoffsets.S, Xbase]"
  public static unsafe Vector<int> GatherVectorNonTemporal(Vector<int> mask, int* address, Vector<uint> offsets);

    /// svuint32_t svldnt1_gather_[u32]offset[_u32](svbool_t pg, const uint32_t *base, svuint32_t offsets) : "LDNT1W Zresult.S, Pg/Z, [Zoffsets.S, Xbase]"
  public static unsafe Vector<uint> GatherVectorNonTemporal(Vector<uint> mask, uint* address, Vector<uint> offsets);

    /// svfloat64_t svldnt1_gather_[s64]offset[_f64](svbool_t pg, const float64_t *base, svint64_t offsets) : "LDNT1D Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<double> GatherVectorNonTemporal(Vector<double> mask, double* address, Vector<long> offsets);

    /// svint64_t svldnt1_gather_[s64]offset[_s64](svbool_t pg, const int64_t *base, svint64_t offsets) : "LDNT1D Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<long> GatherVectorNonTemporal(Vector<long> mask, long* address, Vector<long> offsets);

    /// svuint64_t svldnt1_gather_[s64]offset[_u64](svbool_t pg, const uint64_t *base, svint64_t offsets) : "LDNT1D Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<ulong> GatherVectorNonTemporal(Vector<ulong> mask, ulong* address, Vector<long> offsets);

    /// svfloat64_t svldnt1_gather_[u64]offset[_f64](svbool_t pg, const float64_t *base, svuint64_t offsets) : "LDNT1D Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<double> GatherVectorNonTemporal(Vector<double> mask, double* address, Vector<ulong> offsets);

    /// svint64_t svldnt1_gather_[u64]offset[_s64](svbool_t pg, const int64_t *base, svuint64_t offsets) : "LDNT1D Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<long> GatherVectorNonTemporal(Vector<long> mask, long* address, Vector<ulong> offsets);

    /// svuint64_t svldnt1_gather_[u64]offset[_u64](svbool_t pg, const uint64_t *base, svuint64_t offsets) : "LDNT1D Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<ulong> GatherVectorNonTemporal(Vector<ulong> mask, ulong* address, Vector<ulong> offsets);

    /// svfloat64_t svldnt1_gather_[s64]index[_f64](svbool_t pg, const float64_t *base, svint64_t indices) : "LDNT1D Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<double> GatherVectorNonTemporal(Vector<double> mask, double* address, Vector<long> indices);

    /// svint64_t svldnt1_gather_[s64]index[_s64](svbool_t pg, const int64_t *base, svint64_t indices) : "LDNT1D Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<long> GatherVectorNonTemporal(Vector<long> mask, long* address, Vector<long> indices);

    /// svuint64_t svldnt1_gather_[s64]index[_u64](svbool_t pg, const uint64_t *base, svint64_t indices) : "LDNT1D Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<ulong> GatherVectorNonTemporal(Vector<ulong> mask, ulong* address, Vector<long> indices);

    /// svfloat64_t svldnt1_gather_[u64]index[_f64](svbool_t pg, const float64_t *base, svuint64_t indices) : "LDNT1D Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<double> GatherVectorNonTemporal(Vector<double> mask, double* address, Vector<ulong> indices);

    /// svint64_t svldnt1_gather_[u64]index[_s64](svbool_t pg, const int64_t *base, svuint64_t indices) : "LDNT1D Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<long> GatherVectorNonTemporal(Vector<long> mask, long* address, Vector<ulong> indices);

    /// svuint64_t svldnt1_gather_[u64]index[_u64](svbool_t pg, const uint64_t *base, svuint64_t indices) : "LDNT1D Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<ulong> GatherVectorNonTemporal(Vector<ulong> mask, ulong* address, Vector<ulong> indices);


    /// GatherVectorSByteSignExtendNonTemporal : Load 8-bit data and sign-extend, non-temporal

    /// svint32_t svldnt1sb_gather[_u32base]_s32(svbool_t pg, svuint32_t bases) : "LDNT1SB Zresult.S, Pg/Z, [Zbases.S, XZR]"
  public static unsafe Vector<int> GatherVectorSByteSignExtendNonTemporal(Vector<int> mask, Vector<uint> addresses);

    /// svuint32_t svldnt1sb_gather[_u32base]_u32(svbool_t pg, svuint32_t bases) : "LDNT1SB Zresult.S, Pg/Z, [Zbases.S, XZR]"
  public static unsafe Vector<uint> GatherVectorSByteSignExtendNonTemporal(Vector<uint> mask, Vector<uint> addresses);

    /// svint64_t svldnt1sb_gather[_u64base]_s64(svbool_t pg, svuint64_t bases) : "LDNT1SB Zresult.D, Pg/Z, [Zbases.D, XZR]"
  public static unsafe Vector<long> GatherVectorSByteSignExtendNonTemporal(Vector<long> mask, Vector<ulong> addresses);

    /// svuint64_t svldnt1sb_gather[_u64base]_u64(svbool_t pg, svuint64_t bases) : "LDNT1SB Zresult.D, Pg/Z, [Zbases.D, XZR]"
  public static unsafe Vector<ulong> GatherVectorSByteSignExtendNonTemporal(Vector<ulong> mask, Vector<ulong> addresses);

    /// svint32_t svldnt1sb_gather_[u32]offset_s32(svbool_t pg, const int8_t *base, svuint32_t offsets) : "LDNT1SB Zresult.S, Pg/Z, [Zoffsets.S, Xbase]"
  public static unsafe Vector<int> GatherVectorSByteSignExtendNonTemporal(Vector<int> mask, sbyte* address, Vector<uint> offsets);

    /// svuint32_t svldnt1sb_gather_[u32]offset_u32(svbool_t pg, const int8_t *base, svuint32_t offsets) : "LDNT1SB Zresult.S, Pg/Z, [Zoffsets.S, Xbase]"
  public static unsafe Vector<uint> GatherVectorSByteSignExtendNonTemporal(Vector<uint> mask, sbyte* address, Vector<uint> offsets);

    /// svint64_t svldnt1sb_gather_[s64]offset_s64(svbool_t pg, const int8_t *base, svint64_t offsets) : "LDNT1SB Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<long> GatherVectorSByteSignExtendNonTemporal(Vector<long> mask, sbyte* address, Vector<long> offsets);

    /// svuint64_t svldnt1sb_gather_[s64]offset_u64(svbool_t pg, const int8_t *base, svint64_t offsets) : "LDNT1SB Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<ulong> GatherVectorSByteSignExtendNonTemporal(Vector<ulong> mask, sbyte* address, Vector<long> offsets);

    /// svint64_t svldnt1sb_gather_[u64]offset_s64(svbool_t pg, const int8_t *base, svuint64_t offsets) : "LDNT1SB Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<long> GatherVectorSByteSignExtendNonTemporal(Vector<long> mask, sbyte* address, Vector<ulong> offsets);

    /// svuint64_t svldnt1sb_gather_[u64]offset_u64(svbool_t pg, const int8_t *base, svuint64_t offsets) : "LDNT1SB Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<ulong> GatherVectorSByteSignExtendNonTemporal(Vector<ulong> mask, sbyte* address, Vector<ulong> offsets);


    /// GatherVectorUInt16WithByteOffsetsZeroExtendNonTemporal : Load 16-bit data and zero-extend, non-temporal

    /// svint32_t svldnt1uh_gather_[u32]offset_s32(svbool_t pg, const uint16_t *base, svuint32_t offsets) : "LDNT1H Zresult.S, Pg/Z, [Zoffsets.S, Xbase]"
  public static unsafe Vector<int> GatherVectorUInt16WithByteOffsetsZeroExtendNonTemporal(Vector<int> mask, ushort* address, Vector<uint> offsets);

    /// svuint32_t svldnt1uh_gather_[u32]offset_u32(svbool_t pg, const uint16_t *base, svuint32_t offsets) : "LDNT1H Zresult.S, Pg/Z, [Zoffsets.S, Xbase]"
  public static unsafe Vector<uint> GatherVectorUInt16WithByteOffsetsZeroExtendNonTemporal(Vector<uint> mask, ushort* address, Vector<uint> offsets);

    /// svint64_t svldnt1uh_gather_[s64]offset_s64(svbool_t pg, const uint16_t *base, svint64_t offsets) : "LDNT1H Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<long> GatherVectorUInt16WithByteOffsetsZeroExtendNonTemporal(Vector<long> mask, ushort* address, Vector<long> offsets);

    /// svuint64_t svldnt1uh_gather_[s64]offset_u64(svbool_t pg, const uint16_t *base, svint64_t offsets) : "LDNT1H Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<ulong> GatherVectorUInt16WithByteOffsetsZeroExtendNonTemporal(Vector<ulong> mask, ushort* address, Vector<long> offsets);

    /// svint64_t svldnt1uh_gather_[u64]offset_s64(svbool_t pg, const uint16_t *base, svuint64_t offsets) : "LDNT1H Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<long> GatherVectorUInt16WithByteOffsetsZeroExtendNonTemporal(Vector<long> mask, ushort* address, Vector<ulong> offsets);

    /// svuint64_t svldnt1uh_gather_[u64]offset_u64(svbool_t pg, const uint16_t *base, svuint64_t offsets) : "LDNT1H Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<ulong> GatherVectorUInt16WithByteOffsetsZeroExtendNonTemporal(Vector<ulong> mask, ushort* address, Vector<ulong> offsets);


    /// GatherVectorUInt16ZeroExtendNonTemporal : Load 16-bit data and zero-extend, non-temporal

    /// svint32_t svldnt1uh_gather[_u32base]_s32(svbool_t pg, svuint32_t bases) : "LDNT1H Zresult.S, Pg/Z, [Zbases.S, XZR]"
  public static unsafe Vector<int> GatherVectorUInt16ZeroExtendNonTemporal(Vector<int> mask, Vector<uint> addresses);

    /// svuint32_t svldnt1uh_gather[_u32base]_u32(svbool_t pg, svuint32_t bases) : "LDNT1H Zresult.S, Pg/Z, [Zbases.S, XZR]"
  public static unsafe Vector<uint> GatherVectorUInt16ZeroExtendNonTemporal(Vector<uint> mask, Vector<uint> addresses);

    /// svint64_t svldnt1uh_gather[_u64base]_s64(svbool_t pg, svuint64_t bases) : "LDNT1H Zresult.D, Pg/Z, [Zbases.D, XZR]"
  public static unsafe Vector<long> GatherVectorUInt16ZeroExtendNonTemporal(Vector<long> mask, Vector<ulong> addresses);

    /// svuint64_t svldnt1uh_gather[_u64base]_u64(svbool_t pg, svuint64_t bases) : "LDNT1H Zresult.D, Pg/Z, [Zbases.D, XZR]"
  public static unsafe Vector<ulong> GatherVectorUInt16ZeroExtendNonTemporal(Vector<ulong> mask, Vector<ulong> addresses);

    /// svint64_t svldnt1uh_gather_[s64]index_s64(svbool_t pg, const uint16_t *base, svint64_t indices) : "LDNT1H Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<long> GatherVectorUInt16ZeroExtendNonTemporal(Vector<long> mask, ushort* address, Vector<long> indices);

    /// svuint64_t svldnt1uh_gather_[s64]index_u64(svbool_t pg, const uint16_t *base, svint64_t indices) : "LDNT1H Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<ulong> GatherVectorUInt16ZeroExtendNonTemporal(Vector<ulong> mask, ushort* address, Vector<long> indices);

    /// svint64_t svldnt1uh_gather_[u64]index_s64(svbool_t pg, const uint16_t *base, svuint64_t indices) : "LDNT1H Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<long> GatherVectorUInt16ZeroExtendNonTemporal(Vector<long> mask, ushort* address, Vector<ulong> indices);

    /// svuint64_t svldnt1uh_gather_[u64]index_u64(svbool_t pg, const uint16_t *base, svuint64_t indices) : "LDNT1H Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<ulong> GatherVectorUInt16ZeroExtendNonTemporal(Vector<ulong> mask, ushort* address, Vector<ulong> indices);


    /// GatherVectorUInt32WithByteOffsetsZeroExtendNonTemporal : Load 32-bit data and zero-extend, non-temporal

    /// svint64_t svldnt1uw_gather_[s64]offset_s64(svbool_t pg, const uint32_t *base, svint64_t offsets) : "LDNT1W Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<long> GatherVectorUInt32WithByteOffsetsZeroExtendNonTemporal(Vector<long> mask, uint* address, Vector<long> offsets);

    /// svint64_t svldnt1uw_gather_[s64]offset_s64(svbool_t pg, const uint32_t *base, svint64_t offsets) : "LDNT1W Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<int> GatherVectorUInt32WithByteOffsetsZeroExtendNonTemporal(Vector<int> mask, uint* address, Vector<int> offsets);

    /// svuint64_t svldnt1uw_gather_[s64]offset_u64(svbool_t pg, const uint32_t *base, svint64_t offsets) : "LDNT1W Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<ulong> GatherVectorUInt32WithByteOffsetsZeroExtendNonTemporal(Vector<ulong> mask, uint* address, Vector<long> offsets);

    /// svuint64_t svldnt1uw_gather_[s64]offset_u64(svbool_t pg, const uint32_t *base, svint64_t offsets) : "LDNT1W Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<uint> GatherVectorUInt32WithByteOffsetsZeroExtendNonTemporal(Vector<uint> mask, uint* address, Vector<int> offsets);

    /// svint64_t svldnt1uw_gather_[u64]offset_s64(svbool_t pg, const uint32_t *base, svuint64_t offsets) : "LDNT1W Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<long> GatherVectorUInt32WithByteOffsetsZeroExtendNonTemporal(Vector<long> mask, uint* address, Vector<ulong> offsets);

    /// svint64_t svldnt1uw_gather_[u64]offset_s64(svbool_t pg, const uint32_t *base, svuint64_t offsets) : "LDNT1W Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<int> GatherVectorUInt32WithByteOffsetsZeroExtendNonTemporal(Vector<int> mask, uint* address, Vector<uint> offsets);

    /// svuint64_t svldnt1uw_gather_[u64]offset_u64(svbool_t pg, const uint32_t *base, svuint64_t offsets) : "LDNT1W Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<ulong> GatherVectorUInt32WithByteOffsetsZeroExtendNonTemporal(Vector<ulong> mask, uint* address, Vector<ulong> offsets);

    /// svuint64_t svldnt1uw_gather_[u64]offset_u64(svbool_t pg, const uint32_t *base, svuint64_t offsets) : "LDNT1W Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<uint> GatherVectorUInt32WithByteOffsetsZeroExtendNonTemporal(Vector<uint> mask, uint* address, Vector<uint> offsets);


    /// GatherVectorUInt32ZeroExtendNonTemporal : Load 32-bit data and zero-extend, non-temporal

    /// svint64_t svldnt1uw_gather[_u64base]_s64(svbool_t pg, svuint64_t bases) : "LDNT1W Zresult.D, Pg/Z, [Zbases.D, XZR]"
  public static unsafe Vector<long> GatherVectorUInt32ZeroExtendNonTemporal(Vector<long> mask, Vector<ulong> addresses);

    /// svint64_t svldnt1uw_gather[_u64base]_s64(svbool_t pg, svuint64_t bases) : "LDNT1W Zresult.D, Pg/Z, [Zbases.D, XZR]"
  public static unsafe Vector<int> GatherVectorUInt32ZeroExtendNonTemporal(Vector<int> mask, Vector<uint> addresses);

    /// svuint64_t svldnt1uw_gather[_u64base]_u64(svbool_t pg, svuint64_t bases) : "LDNT1W Zresult.D, Pg/Z, [Zbases.D, XZR]"
  public static unsafe Vector<ulong> GatherVectorUInt32ZeroExtendNonTemporal(Vector<ulong> mask, Vector<ulong> addresses);

    /// svuint64_t svldnt1uw_gather[_u64base]_u64(svbool_t pg, svuint64_t bases) : "LDNT1W Zresult.D, Pg/Z, [Zbases.D, XZR]"
  public static unsafe Vector<uint> GatherVectorUInt32ZeroExtendNonTemporal(Vector<uint> mask, Vector<uint> addresses);

    /// svint64_t svldnt1uw_gather_[s64]index_s64(svbool_t pg, const uint32_t *base, svint64_t indices) : "LDNT1W Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<long> GatherVectorUInt32ZeroExtendNonTemporal(Vector<long> mask, uint* address, Vector<long> indices);

    /// svint64_t svldnt1uw_gather_[s64]index_s64(svbool_t pg, const uint32_t *base, svint64_t indices) : "LDNT1W Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<int> GatherVectorUInt32ZeroExtendNonTemporal(Vector<int> mask, uint* address, Vector<int> indices);

    /// svuint64_t svldnt1uw_gather_[s64]index_u64(svbool_t pg, const uint32_t *base, svint64_t indices) : "LDNT1W Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<ulong> GatherVectorUInt32ZeroExtendNonTemporal(Vector<ulong> mask, uint* address, Vector<long> indices);

    /// svuint64_t svldnt1uw_gather_[s64]index_u64(svbool_t pg, const uint32_t *base, svint64_t indices) : "LDNT1W Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<uint> GatherVectorUInt32ZeroExtendNonTemporal(Vector<uint> mask, uint* address, Vector<int> indices);

    /// svint64_t svldnt1uw_gather_[u64]index_s64(svbool_t pg, const uint32_t *base, svuint64_t indices) : "LDNT1W Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<long> GatherVectorUInt32ZeroExtendNonTemporal(Vector<long> mask, uint* address, Vector<ulong> indices);

    /// svint64_t svldnt1uw_gather_[u64]index_s64(svbool_t pg, const uint32_t *base, svuint64_t indices) : "LDNT1W Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<int> GatherVectorUInt32ZeroExtendNonTemporal(Vector<int> mask, uint* address, Vector<uint> indices);

    /// svuint64_t svldnt1uw_gather_[u64]index_u64(svbool_t pg, const uint32_t *base, svuint64_t indices) : "LDNT1W Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<ulong> GatherVectorUInt32ZeroExtendNonTemporal(Vector<ulong> mask, uint* address, Vector<ulong> indices);

    /// svuint64_t svldnt1uw_gather_[u64]index_u64(svbool_t pg, const uint32_t *base, svuint64_t indices) : "LDNT1W Zresult.D, Pg/Z, [Zoffsets.D, Xbase]"
  public static unsafe Vector<uint> GatherVectorUInt32ZeroExtendNonTemporal(Vector<uint> mask, uint* address, Vector<uint> indices);


  /// total method signatures: 109
  /// total method names:      11
}

@a74nh
Copy link
Contributor Author

a74nh commented Oct 26, 2023 •
edited
Loading 

  /// Rejected:
  ///   public static unsafe Vector<int> GatherVectorByteZeroExtendNonTemporal(Vector<int> mask, Vector<uint> addresses, long offset); // svldnt1ub_gather[_u32base]_offset_s32
  ///   public static unsafe Vector<uint> GatherVectorByteZeroExtendNonTemporal(Vector<uint> mask, Vector<uint> addresses, long offset); // svldnt1ub_gather[_u32base]_offset_u32
  ///   public static unsafe Vector<long> GatherVectorByteZeroExtendNonTemporal(Vector<long> mask, Vector<ulong> addresses, long offset); // svldnt1ub_gather[_u64base]_offset_s64
  ///   public static unsafe Vector<ulong> GatherVectorByteZeroExtendNonTemporal(Vector<ulong> mask, Vector<ulong> addresses, long offset); // svldnt1ub_gather[_u64base]_offset_u64
  ///   public static unsafe Vector<int> GatherVectorInt16SignExtendNonTemporal(Vector<int> mask, Vector<uint> addresses, long index); // svldnt1sh_gather[_u32base]_index_s32
  ///   public static unsafe Vector<uint> GatherVectorInt16SignExtendNonTemporal(Vector<uint> mask, Vector<uint> addresses, long index); // svldnt1sh_gather[_u32base]_index_u32
  ///   public static unsafe Vector<long> GatherVectorInt16SignExtendNonTemporal(Vector<long> mask, Vector<ulong> addresses, long index); // svldnt1sh_gather[_u64base]_index_s64
  ///   public static unsafe Vector<ulong> GatherVectorInt16SignExtendNonTemporal(Vector<ulong> mask, Vector<ulong> addresses, long index); // svldnt1sh_gather[_u64base]_index_u64
  ///   public static unsafe Vector<int> GatherVectorInt16WithByteOffsetsSignExtendNonTemporal(Vector<int> mask, Vector<uint> addresses, long offset); // svldnt1sh_gather[_u32base]_offset_s32
  ///   public static unsafe Vector<uint> GatherVectorInt16WithByteOffsetsSignExtendNonTemporal(Vector<uint> mask, Vector<uint> addresses, long offset); // svldnt1sh_gather[_u32base]_offset_u32
  ///   public static unsafe Vector<long> GatherVectorInt16WithByteOffsetsSignExtendNonTemporal(Vector<long> mask, Vector<ulong> addresses, long offset); // svldnt1sh_gather[_u64base]_offset_s64
  ///   public static unsafe Vector<ulong> GatherVectorInt16WithByteOffsetsSignExtendNonTemporal(Vector<ulong> mask, Vector<ulong> addresses, long offset); // svldnt1sh_gather[_u64base]_offset_u64
  ///   public static unsafe Vector<long> GatherVectorInt32SignExtendNonTemporal(Vector<long> mask, Vector<ulong> addresses, long index); // svldnt1sw_gather[_u64base]_index_s64
  ///   public static unsafe Vector<int> GatherVectorInt32SignExtendNonTemporal(Vector<int> mask, Vector<uint> addresses, long index); // svldnt1sw_gather[_u64base]_index_s64
  ///   public static unsafe Vector<ulong> GatherVectorInt32SignExtendNonTemporal(Vector<ulong> mask, Vector<ulong> addresses, long index); // svldnt1sw_gather[_u64base]_index_u64
  ///   public static unsafe Vector<uint> GatherVectorInt32SignExtendNonTemporal(Vector<uint> mask, Vector<uint> addresses, long index); // svldnt1sw_gather[_u64base]_index_u64
  ///   public static unsafe Vector<long> GatherVectorInt32WithByteOffsetsSignExtendNonTemporal(Vector<long> mask, Vector<ulong> addresses, long offset); // svldnt1sw_gather[_u64base]_offset_s64
  ///   public static unsafe Vector<int> GatherVectorInt32WithByteOffsetsSignExtendNonTemporal(Vector<int> mask, Vector<uint> addresses, long offset); // svldnt1sw_gather[_u64base]_offset_s64
  ///   public static unsafe Vector<ulong> GatherVectorInt32WithByteOffsetsSignExtendNonTemporal(Vector<ulong> mask, Vector<ulong> addresses, long offset); // svldnt1sw_gather[_u64base]_offset_u64
  ///   public static unsafe Vector<uint> GatherVectorInt32WithByteOffsetsSignExtendNonTemporal(Vector<uint> mask, Vector<uint> addresses, long offset); // svldnt1sw_gather[_u64base]_offset_u64
  ///   public static unsafe Vector<float> GatherVectorNonTemporal(Vector<float> mask, Vector<uint> addresses, long offset); // svldnt1_gather[_u32base]_offset_f32
  ///   public static unsafe Vector<int> GatherVectorNonTemporal(Vector<int> mask, Vector<uint> addresses, long offset); // svldnt1_gather[_u32base]_offset_s32
  ///   public static unsafe Vector<uint> GatherVectorNonTemporal(Vector<uint> mask, Vector<uint> addresses, long offset); // svldnt1_gather[_u32base]_offset_u32
  ///   public static unsafe Vector<double> GatherVectorNonTemporal(Vector<double> mask, Vector<ulong> addresses, long offset); // svldnt1_gather[_u64base]_offset_f64
  ///   public static unsafe Vector<long> GatherVectorNonTemporal(Vector<long> mask, Vector<ulong> addresses, long offset); // svldnt1_gather[_u64base]_offset_s64
  ///   public static unsafe Vector<ulong> GatherVectorNonTemporal(Vector<ulong> mask, Vector<ulong> addresses, long offset); // svldnt1_gather[_u64base]_offset_u64
  ///   public static unsafe Vector<float> GatherVectorNonTemporal(Vector<float> mask, Vector<uint> addresses, long index); // svldnt1_gather[_u32base]_index_f32
  ///   public static unsafe Vector<int> GatherVectorNonTemporal(Vector<int> mask, Vector<uint> addresses, long index); // svldnt1_gather[_u32base]_index_s32
  ///   public static unsafe Vector<uint> GatherVectorNonTemporal(Vector<uint> mask, Vector<uint> addresses, long index); // svldnt1_gather[_u32base]_index_u32
  ///   public static unsafe Vector<double> GatherVectorNonTemporal(Vector<double> mask, Vector<ulong> addresses, long index); // svldnt1_gather[_u64base]_index_f64
  ///   public static unsafe Vector<long> GatherVectorNonTemporal(Vector<long> mask, Vector<ulong> addresses, long index); // svldnt1_gather[_u64base]_index_s64
  ///   public static unsafe Vector<ulong> GatherVectorNonTemporal(Vector<ulong> mask, Vector<ulong> addresses, long index); // svldnt1_gather[_u64base]_index_u64
  ///   public static unsafe Vector<int> GatherVectorSByteSignExtendNonTemporal(Vector<int> mask, Vector<uint> addresses, long offset); // svldnt1sb_gather[_u32base]_offset_s32
  ///   public static unsafe Vector<uint> GatherVectorSByteSignExtendNonTemporal(Vector<uint> mask, Vector<uint> addresses, long offset); // svldnt1sb_gather[_u32base]_offset_u32
  ///   public static unsafe Vector<long> GatherVectorSByteSignExtendNonTemporal(Vector<long> mask, Vector<ulong> addresses, long offset); // svldnt1sb_gather[_u64base]_offset_s64
  ///   public static unsafe Vector<ulong> GatherVectorSByteSignExtendNonTemporal(Vector<ulong> mask, Vector<ulong> addresses, long offset); // svldnt1sb_gather[_u64base]_offset_u64
  ///   public static unsafe Vector<int> GatherVectorUInt16WithByteOffsetsZeroExtendNonTemporal(Vector<int> mask, Vector<uint> addresses, long offset); // svldnt1uh_gather[_u32base]_offset_s32
  ///   public static unsafe Vector<uint> GatherVectorUInt16WithByteOffsetsZeroExtendNonTemporal(Vector<uint> mask, Vector<uint> addresses, long offset); // svldnt1uh_gather[_u32base]_offset_u32
  ///   public static unsafe Vector<long> GatherVectorUInt16WithByteOffsetsZeroExtendNonTemporal(Vector<long> mask, Vector<ulong> addresses, long offset); // svldnt1uh_gather[_u64base]_offset_s64
  ///   public static unsafe Vector<ulong> GatherVectorUInt16WithByteOffsetsZeroExtendNonTemporal(Vector<ulong> mask, Vector<ulong> addresses, long offset); // svldnt1uh_gather[_u64base]_offset_u64
  ///   public static unsafe Vector<int> GatherVectorUInt16ZeroExtendNonTemporal(Vector<int> mask, Vector<uint> addresses, long index); // svldnt1uh_gather[_u32base]_index_s32
  ///   public static unsafe Vector<uint> GatherVectorUInt16ZeroExtendNonTemporal(Vector<uint> mask, Vector<uint> addresses, long index); // svldnt1uh_gather[_u32base]_index_u32
  ///   public static unsafe Vector<long> GatherVectorUInt16ZeroExtendNonTemporal(Vector<long> mask, Vector<ulong> addresses, long index); // svldnt1uh_gather[_u64base]_index_s64
  ///   public static unsafe Vector<ulong> GatherVectorUInt16ZeroExtendNonTemporal(Vector<ulong> mask, Vector<ulong> addresses, long index); // svldnt1uh_gather[_u64base]_index_u64
  ///   public static unsafe Vector<long> GatherVectorUInt32WithByteOffsetsZeroExtendNonTemporal(Vector<long> mask, Vector<ulong> addresses, long offset); // svldnt1uw_gather[_u64base]_offset_s64
  ///   public static unsafe Vector<int> GatherVectorUInt32WithByteOffsetsZeroExtendNonTemporal(Vector<int> mask, Vector<uint> addresses, long offset); // svldnt1uw_gather[_u64base]_offset_s64
  ///   public static unsafe Vector<ulong> GatherVectorUInt32WithByteOffsetsZeroExtendNonTemporal(Vector<ulong> mask, Vector<ulong> addresses, long offset); // svldnt1uw_gather[_u64base]_offset_u64
  ///   public static unsafe Vector<uint> GatherVectorUInt32WithByteOffsetsZeroExtendNonTemporal(Vector<uint> mask, Vector<uint> addresses, long offset); // svldnt1uw_gather[_u64base]_offset_u64
  ///   public static unsafe Vector<long> GatherVectorUInt32ZeroExtendNonTemporal(Vector<long> mask, Vector<ulong> addresses, long index); // svldnt1uw_gather[_u64base]_index_s64
  ///   public static unsafe Vector<int> GatherVectorUInt32ZeroExtendNonTemporal(Vector<int> mask, Vector<uint> addresses, long index); // svldnt1uw_gather[_u64base]_index_s64
  ///   public static unsafe Vector<ulong> GatherVectorUInt32ZeroExtendNonTemporal(Vector<ulong> mask, Vector<ulong> addresses, long index); // svldnt1uw_gather[_u64base]_index_u64
  ///   public static unsafe Vector<uint> GatherVectorUInt32ZeroExtendNonTemporal(Vector<uint> mask, Vector<uint> addresses, long index); // svldnt1uw_gather[_u64base]_index_u64
  ///   Total Rejected: 52

  /// Total ACLE covered across API:      161

@a74nh
Copy link
Contributor Author

a74nh commented Oct 26, 2023

This contributes to #93095

It covers instructions in FEAT_SVE2 related to gather loads. They are similar to the SVE gather load methods.

This list was auto generated from the C ACLE for SVE, and is in three parts:

The methods list reduced down to Vector versions. All possible varaints of T are given above the method.
The complete list of all methods. The corresponding ACLE methods and SVE instructions are given above the method.
All rejected ACLE methods. These are methods we have agreed that do not need including in C#.
Where possible, existing C# naming conventions have been matched.

Many of the C functions include predicate argument(s), of type svbool_t as the first argument. These are missing from the C# method. It is expected that the Jit will create predicates where required, or combine with uses of conditionalSelect(). For more discussion see #88140 comment.

@a74nh a74nh mentioned this issue Oct 26, 2023
Closed
31 tasks
@a74nh
Copy link
Contributor Author

a74nh commented Nov 6, 2023

Updated to reflect review comments from other API proposals.

@a74nh a74nh mentioned this issue Nov 13, 2023
Closed
@kunalspathak kunalspathak added the api-ready-for-review API is ready for review, it is NOT ready for implementation label Feb 7, 2024
@ghost
Copy link

ghost commented Feb 8, 2024

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

Issue Details 
namespace System.Runtime.Intrinsics.Arm

/// VectorT Summary
public abstract class Sve : AdvSimd /// Feature: FEAT_SVE2  Category: gatherloads
{

  /// T: [int, uint], [long, ulong]
  public static unsafe Vector<T> GatherVectorByteSignExtendNonTemporal(Vector<T> mask, Vector<T2> bases); // LDNT1SB

  /// T: uint, ulong
  public static unsafe Vector<T> GatherVectorByteSignExtendNonTemporal(Vector<T> mask, Vector<T> bases); // LDNT1SB

  /// T: [int, uint], [ulong, long], [long, ulong]
  public static unsafe Vector<T> GatherVectorByteSignExtendNonTemporal(Vector<T> mask, const sbyte *base, Vector<T2> offsets); // LDNT1SB

  /// T: uint, long, ulong
  public static unsafe Vector<T> GatherVectorByteSignExtendNonTemporal(Vector<T> mask, const sbyte *base, Vector<T> offsets); // LDNT1SB

  /// T: [int, uint], [long, ulong]
  public static unsafe Vector<T> GatherVectorByteSignExtendNonTemporal(Vector<T> mask, Vector<T2> bases, long offset); // LDNT1SB

  /// T: uint, ulong
  public static unsafe Vector<T> GatherVectorByteSignExtendNonTemporal(Vector<T> mask, Vector<T> bases, long offset); // LDNT1SB

  /// T: [int, uint], [long, ulong]
  public static unsafe Vector<T> GatherVectorByteZeroExtendNonTemporal(Vector<T> mask, Vector<T2> bases); // LDNT1B

  /// T: uint, ulong
  public static unsafe Vector<T> GatherVectorByteZeroExtendNonTemporal(Vector<T> mask, Vector<T> bases); // LDNT1B

  /// T: [int, uint], [ulong, long], [long, ulong]
  public static unsafe Vector<T> GatherVectorByteZeroExtendNonTemporal(Vector<T> mask, const byte *base, Vector<T2> offsets); // LDNT1B

  /// T: uint, long, ulong
  public static unsafe Vector<T> GatherVectorByteZeroExtendNonTemporal(Vector<T> mask, const byte *base, Vector<T> offsets); // LDNT1B

  /// T: [int, uint], [long, ulong]
  public static unsafe Vector<T> GatherVectorByteZeroExtendNonTemporal(Vector<T> mask, Vector<T2> bases, long offset); // LDNT1B

  /// T: uint, ulong
  public static unsafe Vector<T> GatherVectorByteZeroExtendNonTemporal(Vector<T> mask, Vector<T> bases, long offset); // LDNT1B

  /// T: [int, uint], [long, ulong]
  public static unsafe Vector<T> GatherVectorInt16SignExtendNonTemporal(Vector<T> mask, Vector<T2> bases); // LDNT1SH

  /// T: uint, ulong
  public static unsafe Vector<T> GatherVectorInt16SignExtendNonTemporal(Vector<T> mask, Vector<T> bases); // LDNT1SH

  /// T: [int, uint], [ulong, long], [long, ulong]
  public static unsafe Vector<T> GatherVectorInt16SignExtendNonTemporal(Vector<T> mask, const short *base, Vector<T2> offsets); // LDNT1SH

  /// T: uint, long, ulong
  public static unsafe Vector<T> GatherVectorInt16SignExtendNonTemporal(Vector<T> mask, const short *base, Vector<T> offsets); // LDNT1SH

  /// T: long, ulong
  public static unsafe Vector<T> GatherVectorInt16SignExtendNonTemporal(Vector<T> mask, const short *base, Vector<T> indices); // LDNT1SH

  /// T: [ulong, long], [long, ulong]
  public static unsafe Vector<T> GatherVectorInt16SignExtendNonTemporal(Vector<T> mask, const short *base, Vector<T2> indices); // LDNT1SH

  /// T: [int, uint], [long, ulong]
  public static unsafe Vector<T> GatherVectorInt16SignExtendNonTemporal(Vector<T> mask, Vector<T2> bases, long offset); // LDNT1SH

  /// T: uint, ulong
  public static unsafe Vector<T> GatherVectorInt16SignExtendNonTemporal(Vector<T> mask, Vector<T> bases, long offset); // LDNT1SH

  /// T: [int, uint], [long, ulong]
  public static unsafe Vector<T> GatherVectorInt16SignExtendNonTemporal(Vector<T> mask, Vector<T2> bases, long index); // LDNT1SH

  /// T: uint, ulong
  public static unsafe Vector<T> GatherVectorInt16SignExtendNonTemporal(Vector<T> mask, Vector<T> bases, long index); // LDNT1SH

  /// T: [int, uint], [long, ulong]
  public static unsafe Vector<T> GatherVectorInt16ZeroExtendNonTemporal(Vector<T> mask, Vector<T2> bases); // LDNT1H

  /// T: uint, ulong
  public static unsafe Vector<T> GatherVectorInt16ZeroExtendNonTemporal(Vector<T> mask, Vector<T> bases); // LDNT1H

  /// T: [int, uint], [ulong, long], [long, ulong]
  public static unsafe Vector<T> GatherVectorInt16ZeroExtendNonTemporal(Vector<T> mask, const ushort *base, Vector<T2> offsets); // LDNT1H

  /// T: uint, long, ulong
  public static unsafe Vector<T> GatherVectorInt16ZeroExtendNonTemporal(Vector<T> mask, const ushort *base, Vector<T> offsets); // LDNT1H

  /// T: long, ulong
  public static unsafe Vector<T> GatherVectorInt16ZeroExtendNonTemporal(Vector<T> mask, const ushort *base, Vector<T> indices); // LDNT1H

  /// T: [ulong, long], [long, ulong]
  public static unsafe Vector<T> GatherVectorInt16ZeroExtendNonTemporal(Vector<T> mask, const ushort *base, Vector<T2> indices); // LDNT1H

  /// T: [int, uint], [long, ulong]
  public static unsafe Vector<T> GatherVectorInt16ZeroExtendNonTemporal(Vector<T> mask, Vector<T2> bases, long offset); // LDNT1H

  /// T: uint, ulong
  public static unsafe Vector<T> GatherVectorInt16ZeroExtendNonTemporal(Vector<T> mask, Vector<T> bases, long offset); // LDNT1H

  /// T: [int, uint], [long, ulong]
  public static unsafe Vector<T> GatherVectorInt16ZeroExtendNonTemporal(Vector<T> mask, Vector<T2> bases, long index); // LDNT1H

  /// T: uint, ulong
  public static unsafe Vector<T> GatherVectorInt16ZeroExtendNonTemporal(Vector<T> mask, Vector<T> bases, long index); // LDNT1H

  public static unsafe Vector<long> GatherVectorInt32SignExtendNonTemporal(Vector<long> mask, Vector<ulong> bases); // LDNT1SW

  public static unsafe Vector<ulong> GatherVectorInt32SignExtendNonTemporal(Vector<ulong> mask, Vector<ulong> bases); // LDNT1SW

  /// T: long, ulong
  public static unsafe Vector<T> GatherVectorInt32SignExtendNonTemporal(Vector<T> mask, const int *base, Vector<T> offsets); // LDNT1SW

  /// T: [ulong, long], [long, ulong]
  public static unsafe Vector<T> GatherVectorInt32SignExtendNonTemporal(Vector<T> mask, const int *base, Vector<T2> offsets); // LDNT1SW

  /// T: long, ulong
  public static unsafe Vector<T> GatherVectorInt32SignExtendNonTemporal(Vector<T> mask, const int *base, Vector<T> indices); // LDNT1SW

  /// T: [ulong, long], [long, ulong]
  public static unsafe Vector<T> GatherVectorInt32SignExtendNonTemporal(Vector<T> mask, const int *base, Vector<T2> indices); // LDNT1SW

  public static unsafe Vector<long> GatherVectorInt32SignExtendNonTemporal(Vector<long> mask, Vector<ulong> bases, long offset); // LDNT1SW

  public static unsafe Vector<ulong> GatherVectorInt32SignExtendNonTemporal(Vector<ulong> mask, Vector<ulong> bases, long offset); // LDNT1SW

  public static unsafe Vector<long> GatherVectorInt32SignExtendNonTemporal(Vector<long> mask, Vector<ulong> bases, long index); // LDNT1SW

  public static unsafe Vector<ulong> GatherVectorInt32SignExtendNonTemporal(Vector<ulong> mask, Vector<ulong> bases, long index); // LDNT1SW

  public static unsafe Vector<long> GatherVectorInt32ZeroExtendNonTemporal(Vector<long> mask, Vector<ulong> bases); // LDNT1W

  public static unsafe Vector<ulong> GatherVectorInt32ZeroExtendNonTemporal(Vector<ulong> mask, Vector<ulong> bases); // LDNT1W

  /// T: long, ulong
  public static unsafe Vector<T> GatherVectorInt32ZeroExtendNonTemporal(Vector<T> mask, const uint *base, Vector<T> offsets); // LDNT1W

  /// T: [ulong, long], [long, ulong]
  public static unsafe Vector<T> GatherVectorInt32ZeroExtendNonTemporal(Vector<T> mask, const uint *base, Vector<T2> offsets); // LDNT1W

  /// T: long, ulong
  public static unsafe Vector<T> GatherVectorInt32ZeroExtendNonTemporal(Vector<T> mask, const uint *base, Vector<T> indices); // LDNT1W

  /// T: [ulong, long], [long, ulong]
  public static unsafe Vector<T> GatherVectorInt32ZeroExtendNonTemporal(Vector<T> mask, const uint *base, Vector<T2> indices); // LDNT1W

  public static unsafe Vector<long> GatherVectorInt32ZeroExtendNonTemporal(Vector<long> mask, Vector<ulong> bases, long offset); // LDNT1W

  public static unsafe Vector<ulong> GatherVectorInt32ZeroExtendNonTemporal(Vector<ulong> mask, Vector<ulong> bases, long offset); // LDNT1W

  public static unsafe Vector<long> GatherVectorInt32ZeroExtendNonTemporal(Vector<long> mask, Vector<ulong> bases, long index); // LDNT1W

  public static unsafe Vector<ulong> GatherVectorInt32ZeroExtendNonTemporal(Vector<ulong> mask, Vector<ulong> bases, long index); // LDNT1W

  /// T: [float, uint], [int, uint], [double, ulong], [long, ulong]
  public static unsafe Vector<T> GatherVectorNonTemporal(Vector<T> mask, Vector<T2> bases); // LDNT1W or LDNT1D

  /// T: uint, ulong
  public static unsafe Vector<T> GatherVectorNonTemporal(Vector<T> mask, Vector<T> bases); // LDNT1W or LDNT1D

  /// T: [float, uint], [int, uint], [double, long], [ulong, long], [double, ulong], [long, ulong]
  public static unsafe Vector<T> GatherVectorNonTemporal(Vector<T> mask, const T *base, Vector<T2> offsets); // LDNT1W or LDNT1D

  /// T: uint, long, ulong
  public static unsafe Vector<T> GatherVectorNonTemporal(Vector<T> mask, const T *base, Vector<T> offsets); // LDNT1W or LDNT1D

  /// T: [double, long], [ulong, long], [double, ulong], [long, ulong]
  public static unsafe Vector<T> GatherVectorNonTemporal(Vector<T> mask, const T *base, Vector<T2> indices); // LDNT1D

  /// T: long, ulong
  public static unsafe Vector<T> GatherVectorNonTemporal(Vector<T> mask, const T *base, Vector<T> indices); // LDNT1D

  /// T: [float, uint], [int, uint], [double, ulong], [long, ulong]
  public static unsafe Vector<T> GatherVectorNonTemporal(Vector<T> mask, Vector<T2> bases, long offset); // LDNT1W or LDNT1D

  /// T: uint, ulong
  public static unsafe Vector<T> GatherVectorNonTemporal(Vector<T> mask, Vector<T> bases, long offset); // LDNT1W or LDNT1D

  /// T: [float, uint], [int, uint], [double, ulong], [long, ulong]
  public static unsafe Vector<T> GatherVectorNonTemporal(Vector<T> mask, Vector<T2> bases, long index); // LDNT1W or LDNT1D

  /// T: uint, ulong
  public static unsafe Vector<T> GatherVectorNonTemporal(Vector<T> mask, Vector<T> bases, long index); // LDNT1W or LDNT1D

  /// total method signatures: 62

}
Author: a74nh
Assignees: -
Labels:

area-System.Runtime.Intrinsics, untriaged, api-ready-for-review
Milestone: -

@kunalspathak kunalspathak mentioned this issue Mar 19, 2024
Closed
@kunalspathak kunalspathak added this to the Future milestone May 1, 2024
@jeffschwMSFT jeffschwMSFT removed the untriaged New issue has not been triaged by the area owner label May 3, 2024
@tannergooding tannergooding added api-suggestion Early API idea and discussion, it is NOT ready for implementation arch-arm64 and removed api-ready-for-review API is ready for review, it is NOT ready for implementation labels Aug 20, 2024
@a74nh
Copy link
Contributor Author

a74nh commented Aug 21, 2024

Updated to match implemented SVE1 methods.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
api-suggestion Early API idea and discussion, it is NOT ready for implementation arch-arm64 area-System.Runtime.Intrinsics
Projects
None yet
Milestone
Future
Development

No branches or pull requests
4 participants
@a74nh @jeffschwMSFT @tannergooding @kunalspathak