You copied the Doc URL to your clipboard.


BFloat16 floating-point widening multiply-add long (vector) 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 to the overlapping single-precision elements of the destination vector.

This performs a fused multiply-add without intermediate rounding that honors all of the control bits in the FPCR that apply to single-precision arithmetic, including the rounding mode. It can also generate a floating-point exception that causes cumulative exception bits in the FPSR to be set, or a synchronous exception to be taken, depending on the enable bits in the FPCR. ID_AA64ISAR1_EL1.BF16 indicates whether these instruction is supported.



BFMLAL<bt> <Vd>.4S, <Vn>.8H, <Vm>.8H

if !HaveBF16Ext() then UNDEFINED;
integer d = UInt(Rd);
integer n = UInt(Rn);
integer m = UInt(Rm);

integer elements = 128 DIV 32;
integer sel = UInt(Q);

Assembler Symbols

<bt> Is the bottom or top element specifier, encoded in Q:
Q <bt>
0 B
1 T

Is the name of the SIMD&FP destination register, encoded in the "Rd" field.


Is the name of the first SIMD&FP source register, encoded in the "Rn" field.


Is the name of the second SIMD&FP source register, encoded in the "Rm" field.


bits(128) operand1 = V[n];
bits(128) operand2 = V[m];
bits(128) operand3 = V[d];
bits(128) result;

for e = 0 to elements-1
    bits(32) element1 = Elem[operand1, 2*e+sel, 16]:Zeros(16);
    bits(32) element2 = Elem[operand2, 2*e+sel, 16]:Zeros(16);
    bits(32) addend = Elem[operand3, e, 32];
    Elem[result, e, 32] = BFMulAdd(addend, element1, element2, FPCR[]);

V[d] = result;