FMLALB (vectors, FP16 to FP32)
Half-precision floating-point multiply-add long to single-precision (bottom)
This half-precision floating-point multiply-add long instruction widens the even-numbered half-precision elements in the first source vector and the corresponding elements in the second source vector to single-precision format and then destructively multiplies and adds these values without intermediate rounding to the single-precision elements of the destination vector that overlap with the corresponding half-precision elements in the source vectors. This instruction is unpredicated.
Green
False
True
0
1
1
0
0
1
0
0
1
0
1
1
0
0
0
0
0
FMLALB <Zda>.S, <Zn>.H, <Zm>.H
if !IsFeatureImplemented(FEAT_SVE2) && !IsFeatureImplemented(FEAT_SME) then UNDEFINED;
constant integer esize = 32;
constant integer n = UInt(Zn);
constant integer m = UInt(Zm);
constant integer da = UInt(Zda);
constant boolean op1_neg = FALSE;
<Zda>
Is the name of the third source and destination scalable vector register, encoded in the "Zda" field.
<Zn>
Is the name of the first source scalable vector register, encoded in the "Zn" field.
<Zm>
Is the name of the second source scalable vector register, encoded in the "Zm" field.
CheckSVEEnabled();
constant integer VL = CurrentVL;
constant integer PL = VL DIV 8;
constant integer elements = VL DIV esize;
constant bits(VL) op1 = Z[n, VL];
constant bits(VL) op2 = Z[m, VL];
constant bits(VL) op3 = Z[da, VL];
bits(VL) result;
for e = 0 to elements-1
constant bits(esize DIV 2) elem1 = (if op1_neg then FPNeg(Elem[op1, 2*e + 0, esize DIV 2], FPCR)
else Elem[op1, 2*e + 0, esize DIV 2]);
constant bits(esize DIV 2) elem2 = Elem[op2, 2*e + 0, esize DIV 2];
constant bits(esize) elem3 = Elem[op3, e, esize];
Elem[result, e, esize] = FPMulAddH(elem3, elem1, elem2, FPCR);
Z[da, VL] = result;