xvf16ger2pn
VSX Vector 16-bit Floating-Point GER (rank-2 update) Positive multiply, Negative accumulate
Performs a rank-2 update of an accumulator register using 16-bit floating-point outer product, with positive multiply and negative accumulate.
Details
The xvf16ger2pn instruction computes a rank-2 General Exterior-product Register (GER) update using 16-bit floating-point operands. It multiplies pairs of 16-bit floating-point elements from two VSX vector registers with a positive sign, then subtracts (negative accumulate) the resulting outer product from the destination accumulator register. This instruction is part of the MMA (Matrix Multiply Assist) extension introduced in PowerISA v3.1.
Programming Note
When Rc=1 (dot form), CR0 is updated with the signed comparison of the result against zero (LT, GT, EQ) and the current SO bit from XER.