[Arm64] "Move" Intrinsics

[tannergooding]

namespace System.Runtime.Intrinsics.Arm
{
    public abstract class AdvSimd
    {
        /// <summary>
        /// Duplicate general-purpose register to vector
        /// For each element result[elem] = value
        /// Corresponds to vector forms of DUP and VDUP
        /// </summary>
        Vector64<byte>    DuplicateToVector64(byte value);
        Vector64<short>   DuplicateToVector64(short value);
        Vector64<int>     DuplicateToVector64(int value);
        Vector64<sbyte>   DuplicateToVector64(sbyte value);
        Vector64<ushort>  DuplicateToVector64(ushort value);
        Vector64<uint>    DuplicateToVector64(uint value);

        Vector128<byte>   DuplicateToVector128(byte value);
        Vector128<short>  DuplicateToVector128(short value);
        Vector128<int>    DuplicateToVector128(int value);
        Vector128<sbyte>  DuplicateToVector128(sbyte value);
        Vector128<ushort> DuplicateToVector128(ushort value);
        Vector128<uint>   DuplicateToVector128(uint value);

        /// <summary>
        /// Duplicate vector element to vector
        /// For each element result[elem] = value[index]
        /// Corresponds to vector forms of DUP and VDUP
        /// </summary>
        Vector64<byte>    DuplicateSelectedScalarToVector64(Vector64<byte> value,     byte index);
        Vector64<short>   DuplicateSelectedScalarToVector64(Vector64<short> value,    byte index);
        Vector64<int>     DuplicateSelectedScalarToVector64(Vector64<int> value,      byte index);
        Vector64<float>   DuplicateSelectedScalarToVector64(Vector64<float> value,    byte index);
        Vector64<sbyte>   DuplicateSelectedScalarToVector64(Vector64<sbyte> value,    byte index);
        Vector64<ushort>  DuplicateSelectedScalarToVector64(Vector64<ushort> value,   byte index);
        Vector64<uint>    DuplicateSelectedScalarToVector64(Vector64<uint> value,     byte index);

        Vector64<byte>    DuplicateSelectedScalarToVector64(Vector128<byte> value,     byte index);
        Vector64<short>   DuplicateSelectedScalarToVector64(Vector128<short> value,    byte index);
        Vector64<int>     DuplicateSelectedScalarToVector64(Vector128<int> value,      byte index);
        Vector64<float>   DuplicateSelectedScalarToVector64(Vector128<float> value,    byte index);
        Vector64<sbyte>   DuplicateSelectedScalarToVector64(Vector128<sbyte> value,    byte index);
        Vector64<ushort>  DuplicateSelectedScalarToVector64(Vector128<ushort> value,   byte index);
        Vector64<uint>    DuplicateSelectedScalarToVector64(Vector128<uint> value,     byte index);

        Vector128<byte>   DuplicateSelectedScalarToVector128(Vector64<byte> value,    byte index);
        Vector128<short>  DuplicateSelectedScalarToVector128(Vector64<short> value,   byte index);
        Vector128<int>    DuplicateSelectedScalarToVector128(Vector64<int> value,     byte index);
        Vector128<float>  DuplicateSelectedScalarToVector128(Vector64<float> value,   byte index);
        Vector128<sbyte>  DuplicateSelectedScalarToVector128(Vector64<sbyte> value,   byte index);
        Vector128<ushort> DuplicateSelectedScalarToVector128(Vector64<ushort> value,  byte index);
        Vector128<uint>   DuplicateSelectedScalarToVector128(Vector64<uint> value,    byte index);

        Vector128<byte>   DuplicateSelectedScalarToVector128(Vector128<byte> value,   byte index);
        Vector128<double> DuplicateSelectedScalarToVector128(Vector128<double> value, byte index);
        Vector128<short>  DuplicateSelectedScalarToVector128(Vector128<short> value,  byte index);
        Vector128<int>    DuplicateSelectedScalarToVector128(Vector128<int> value,    byte index);
        Vector128<long>   DuplicateSelectedScalarToVector128(Vector128<long> value,   byte index);
        Vector128<float>  DuplicateSelectedScalarToVector128(Vector128<float> value,  byte index);
        Vector128<sbyte>  DuplicateSelectedScalarToVector128(Vector128<sbyte> value,  byte index);
        Vector128<ushort> DuplicateSelectedScalarToVector128(Vector128<ushort> value, byte index);
        Vector128<uint>   DuplicateSelectedScalarToVector128(Vector128<uint> value,   byte index);
        Vector128<ulong>  DuplicateSelectedScalarToVector128(Vector128<ulong> value,  byte index);

        public abstract class Arm64
        {
            /// <summary>
            /// Duplicate general-purpose register to vector
            /// For each element result[elem] = value
            /// Corresponds to vector forms of DUP
            /// </summary>
            Vector128<long>   DuplicateToVector64(long value);
            Vector128<ulong>  DuplicateToVector64(ulong value);

            /// <summary>
            /// Insert vector element from another vector element
            /// result[resultIndex] = value[valueIndex]
            /// Corresponds to vector forms of INS
            /// </summary>
            Vector128<byte>   InsertSelectedScalar(Vector128<byte> result,   byte resultIndex, Vector64<byte> value,    byte valueIndex);
            Vector128<short>  InsertSelectedScalar(Vector128<short> result,  byte resultIndex, Vector64<short> value,   byte valueIndex);
            Vector128<int>    InsertSelectedScalar(Vector128<int> result,    byte resultIndex, Vector64<int> value,     byte valueIndex);
            Vector128<float>  InsertSelectedScalar(Vector128<float> result,  byte resultIndex, Vector64<float> value,   byte valueIndex);
            Vector128<sbyte>  InsertSelectedScalar(Vector128<sbyte> result,  byte resultIndex, Vector64<sbyte> value,   byte valueIndex);
            Vector128<ushort> InsertSelectedScalar(Vector128<ushort> result, byte resultIndex, Vector64<ushort> value,  byte valueIndex);
            Vector128<uint>   InsertSelectedScalar(Vector128<uint> result,   byte resultIndex, Vector64<uint> value,    byte valueIndex);

            Vector128<byte>   InsertSelectedScalar(Vector128<byte> result,   byte resultIndex, Vector128<byte> value,   byte valueIndex);
            Vector128<double> InsertSelectedScalar(Vector128<double> result, byte resultIndex, Vector128<double> value, byte valueIndex);
            Vector128<short>  InsertSelectedScalar(Vector128<short> result,  byte resultIndex, Vector128<short> value,  byte valueIndex);
            Vector128<int>    InsertSelectedScalar(Vector128<int> result,    byte resultIndex, Vector128<int> value,    byte valueIndex);
            Vector128<long>   InsertSelectedScalar(Vector128<long> result,   byte resultIndex, Vector128<long> value,   byte valueIndex);
            Vector128<float>  InsertSelectedScalar(Vector128<float> result,  byte resultIndex, Vector128<float> value,  byte valueIndex);
            Vector128<sbyte>  InsertSelectedScalar(Vector128<sbyte> result,  byte resultIndex, Vector128<sbyte> value,  byte valueIndex);
            Vector128<ushort> InsertSelectedScalar(Vector128<ushort> result, byte resultIndex, Vector128<ushort> value, byte valueIndex);
            Vector128<uint>   InsertSelectedScalar(Vector128<uint> result,   byte resultIndex, Vector128<uint> value,   byte valueIndex);
            Vector128<ulong>  InsertSelectedScalar(Vector128<ulong> result,  byte resultIndex, Vector128<ulong> value,  byte valueIndex);
        }
    }
}

Tagging subscribers to this area: @tannergooding
Notify danmosemsft if you want to be subscribed.

[tannergooding]

CC. @echesakovMSFT, @CarolEidt, @TamarChristinaArm

[echesakov]

For InsertSelectedScalar I believe we want Cartesian product of [typeof(result) is Vector64<T>; typeof(result) is Vector128<T>] x [typeof(value) is Vector64<T>; typeof(value) is Vector128<T>]?

[echesakov]

Same for DuplicateSelectedScalarToVector128 and DuplicateSelectedScalarToVector64 corresponding to DUP (element)?

[tannergooding]

Added the Vector128 DuplicateSelectedScalarToVector64(Vector128, byte) overloads that were missing.

For INS the decoding isn't clear on whether the full set is supported...

[tannergooding]

Actually, it looks like the result should always be 128-bits:

Operation
    CheckFPAdvSIMDEnabled64();
    bits(idxdsize) operand = V[n];
    bits(128) result;
    result = V[d];
    Elem[result, dst_index, esize] = Elem[operand, src_index, esize];
    V[d] = result;

[TamarChristinaArm]

DuplicateSelectedScalarToVector64 and DuplicateSelectedScalarToVector128 are both definitely implementable on AArch32. InsertSelectedScalar is tricky for 16 and 8 bit ones on AArch32. I'll have to have a think on these..

[tannergooding]

DuplicateSelectedScalarToVector64 and DuplicateSelectedScalarToVector128 are both definitely implementable on AArch32

This would be incrementing the register by 1 if the index is greater than Count / 2, correct?

[TamarChristinaArm]

Yup, that's correct.