FMAD
Floating-point fused multiply-add vectors (predicated), writing multiplicand [Zdn = Za + Zdn * Zm]
Multiply the corresponding active floating-point elements of the first and second source vectors and add to elements of the third (addend) vector without intermediate rounding. Destructively place the results in the destination and first source (multiplicand) vector. Inactive elements in the destination vector register remain unmodified.
Green
True
True
True
0
1
1
0
0
1
0
1
1
1
0
0
FMAD <Zdn>.<T>, <Pg>/M, <Zm>.<T>, <Za>.<T>
if !IsFeatureImplemented(FEAT_SVE) && !IsFeatureImplemented(FEAT_SME) then UNDEFINED;
if size == '00' then UNDEFINED;
constant integer esize = 8 << UInt(size);
constant integer g = UInt(Pg);
constant integer dn = UInt(Zdn);
constant integer m = UInt(Zm);
constant integer a = UInt(Za);
constant boolean op1_neg = FALSE;
constant boolean op3_neg = FALSE;
<Zdn>
Is the name of the first source and destination scalable vector register, encoded in the "Zdn" field.
<T>
Is the size specifier,
size
<T>
00
RESERVED
01
H
10
S
11
D
<Pg>
Is the name of the governing scalable predicate register P0-P7, encoded in the "Pg" field.
<Zm>
Is the name of the second source scalable vector register, encoded in the "Zm" field.
<Za>
Is the name of the third source scalable vector register, encoded in the "Za" field.
CheckSVEEnabled();
constant integer VL = CurrentVL;
constant integer PL = VL DIV 8;
constant integer elements = VL DIV esize;
constant bits(PL) mask = P[g, PL];
constant bits(VL) op1 = Z[dn, VL];
constant bits(VL) op2 = if AnyActiveElement(mask, esize) then Z[m, VL] else Zeros(VL);
constant bits(VL) op3 = if AnyActiveElement(mask, esize) then Z[a, VL] else Zeros(VL);
bits(VL) result;
for e = 0 to elements-1
if ActivePredicateElement(mask, e, esize) then
constant bits(esize) elem1 = (if op1_neg then FPNeg(Elem[op1, e, esize], FPCR)
else Elem[op1, e, esize]);
constant bits(esize) elem2 = Elem[op2, e, esize];
constant bits(esize) elem3 = (if op3_neg then FPNeg(Elem[op3, e, esize], FPCR)
else Elem[op3, e, esize]);
Elem[result, e, esize] = FPMulAdd(elem3, elem1, elem2, FPCR);
else
Elem[result, e, esize] = Elem[op1, e, esize];
Z[dn, VL] = result;