Skip to content
GitLab

i#2626: AArch64 v8.2 codec: add indexed FMLAL/FMLSL instructions

Merged Assad Hashmi requested to merge i2626-aarch64-v82-indexed-fmlal-fmlsl into master

This patch adds indexed variants of the floating-point fused multiply-add/subtract long to/from accumulator instructions.

FMLAL <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.H[<index>]
FMLAL2 <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.H[<index>]
FMLSL <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.H[<index>]
FMLSL2 <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.H[<index>]

Issue: #2626