UVDOT (2-way)

Multi-vector unsigned integer vertical dot-product by indexed element

This instruction computes the vertical dot product of the corresponding two unsigned 16-bit integer values held in the two first source vectors and two unsigned 16-bit integer values in the corresponding indexed 32-bit element of the second source vector. The widened dot product results are destructively added to the corresponding 32-bit element of the ZA single-vector groups.

The groups within the second source vector are specified using an immediate element index which selects the same group position within each 128-bit vector segment. The index range is from 0 to 3.

The single-vector group within each half of the ZA array is selected by the sum of the vector select register and offset, modulo half the number of ZA array vectors.

The vector group symbol VGx2 indicates that the ZA operand consists of two ZA single-vector groups. The vector group symbol is preferred for disassembly, but optional in assembler source code.

This instruction is unpredicated.

Encoding: SME2

Variants: FEAT_SME2 (ARMv9.3)

313029282726252423222120191817161514131211109876543210
11000001010100110
ZmRvopi2ZnUoff3

UVDOT ZA.S[<Wv>, <offs>{, VGx2}], { <Zn1>.H-<Zn2>.H }, <Zm>.H[<index>]

Decoding algorithm

if !IsFeatureImplemented(FEAT_SME2) then EndOfDecode(Decode_UNDEF);
constant integer v = UInt('010':Rv);
constant integer esize = 32;
constant integer n = UInt(Zn:'0');
constant integer m = UInt('0':Zm);
constant integer offset = UInt(off3);
constant integer index = UInt(i2);

Operation

CheckStreamingSVEAndZAEnabled();
constant integer VL = CurrentVL;
constant integer elements = VL DIV esize;
constant integer vectors = VL DIV 8;
constant integer vstride = vectors DIV 2;
constant integer eltspersegment = 128 DIV esize;
constant bits(32) vbase = X[v, 32];
integer vec = (UInt(vbase) + offset) MOD vstride;
constant bits(VL) operand2 = Z[m, VL];
bits(VL) result;

for r = 0 to 1
    constant bits(VL) operand3 = ZAvector[vec, VL];
    for e = 0 to elements-1
        constant integer segmentbase = e - (e MOD eltspersegment);
        constant integer s = segmentbase + index;
        bits(esize) sum = Elem[operand3, e, esize];
        for i = 0 to 1
            constant bits(VL) operand1 = Z[n+i, VL];
            constant integer element1 = UInt(Elem[operand1, 2 * e + r, esize DIV 2]);
            constant integer element2 = UInt(Elem[operand2, 2 * s + i, esize DIV 2]);
            sum = sum + element1 * element2;
        Elem[result, e, esize] = sum;
    ZAvector[vec, VL] = result;
    vec = vec + vstride;

Explanations

<Wv>: Is the 32-bit name of the vector select register W8-W11, encoded in the "Rv" field.
<offs>: Is the vector select offset, in the range 0 to 7, encoded in the "off3" field.
<Zn1>: Is the name of the first scalable vector register of the first source multi-vector group, encoded as "Zn" times 2.
<Zn2>: Is the name of the second scalable vector register of the first source multi-vector group, encoded as "Zn" times 2 plus 1.
<Zm>: Is the name of the second source scalable vector register Z0-Z15, encoded in the "Zm" field.
<index>: Is the immediate index of a group of two 16-bit elements within each 128-bit vector segment, in the range 0 to 3, encoded in the "i2" field.

Operational Notes

If PSTATE.DIT is 1: