BFMLALB, BFMLALT (vector)
BFloat16 floating-point widening multiply-add long (vector)
This instruction widens the even-numbered (bottom) or
odd-numbered (top) 16-bit elements in the first and second source vectors from Bfloat16 to single-precision format.
The instruction then multiplies and adds these values without intermediate rounding to the
single-precision elements of the destination vector that overlap with the corresponding BFloat16
elements in the source vectors.
ID_AA64ISAR1_EL1.BF16 indicates whether this instruction is supported.
0
1
0
1
1
1
0
1
1
0
1
1
1
1
1
1
BFMLAL<bt> <Vd>.4S, <Vn>.8H, <Vm>.8H
if !IsFeatureImplemented(FEAT_BF16) then UNDEFINED;
constant integer d = UInt(Rd);
constant integer n = UInt(Rn);
constant integer m = UInt(Rm);
constant integer elements = 128 DIV 32;
constant integer sel = UInt(Q);
<bt>
Is the bottom or top element specifier,
<Vd>
Is the name of the SIMD&FP destination register, encoded in the "Rd" field.
<Vn>
Is the name of the first SIMD&FP source register, encoded in the "Rn" field.
<Vm>
Is the name of the second SIMD&FP source register, encoded in the "Rm" field.
CheckFPAdvSIMDEnabled64();
constant bits(128) operand1 = V[n, 128];
constant bits(128) operand2 = V[m, 128];
constant bits(128) operand3 = V[d, 128];
bits(128) result;
for e = 0 to elements-1
constant bits(16) element1 = Elem[operand1, 2 * e + sel, 16];
constant bits(16) element2 = Elem[operand2, 2 * e + sel, 16];
constant bits(32) addend = Elem[operand3, e, 32];
Elem[result, e, 32] = BFMulAddH(addend, element1, element2, FPCR);
V[d, 128] = result;