bfmmla

BFloat16 Matrix Multiply-Accumulate (NEON)

BFMMLA <Vd>.<T>, <Vn>.<T>, <Vm>.<T>

Performs 2x2 matrix multiplication on BFloat16 tiles (NEON).

Details

The BFloat16 Matrix Multiply-Accumulate instruction performs 2x2 matrix multiplication on BFloat16 tiles (NEON).

Pseudocode Operation

// Performs 2x2 matrix multiplication on BFloat16 tiles (NEON)

Example

BFMMLA v0.4s.T, v1.4s.T, v2.4s.T

Encoding

Binary Layout
01001110
10
0
11111
01
Zn
Zd
Zm
 
Format NEON 3-Reg
Opcode 0x4E60FC00
Extension FEAT_BF16 (AI)

Operands

  • Vd
    Destination SIMD/FP vector register
  • Vn
    First source SIMD/FP vector register
  • Vm
    Second source SIMD/FP vector register