SQRDMLSH (vectors)
Signed saturating rounding doubling multiply-subtract high from accumulator (unpredicated)
Multiply then double the corresponding signed elements of the first and second source vectors, and destructively subtract the rounded high half of each result from the corresponding elements of the addend and destination vector. Each destination element is saturated to the N-bit element's signed integer range -2(N-1) to (2(N-1) )-1. This instruction is unpredicated.
Green
False
True
0
1
0
0
0
1
0
0
0
0
1
1
1
0
1
SQRDMLSH <Zda>.<T>, <Zn>.<T>, <Zm>.<T>
if !IsFeatureImplemented(FEAT_SVE2) && !IsFeatureImplemented(FEAT_SME) then UNDEFINED;
constant integer esize = 8 << UInt(size);
constant integer n = UInt(Zn);
constant integer m = UInt(Zm);
constant integer da = UInt(Zda);
<Zda>
Is the name of the third source and destination scalable vector register, encoded in the "Zda" field.
<T>
Is the size specifier,
size
<T>
00
B
01
H
10
S
11
D
<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 elements = VL DIV esize;
constant bits(VL) operand1 = Z[n, VL];
constant bits(VL) operand2 = Z[m, VL];
constant bits(VL) operand3 = Z[da, VL];
bits(VL) result;
for e = 0 to elements-1
constant integer element1 = SInt(Elem[operand1, e, esize]);
constant integer element2 = SInt(Elem[operand2, e, esize]);
constant integer element3 = SInt(Elem[operand3, e, esize]);
constant integer res = (element3 << esize) - (2 * element1 * element2);
Elem[result, e, esize] = SignedSat((res + (1 << (esize - 1))) >> esize, esize);
Z[da, VL] = result;