Optimize scalar RHS packing function NxK F32 <- QAI8DXP x QSU4C32 (!230) · Merge requests · Kleidi / KleidiAI · GitLab

Gian Marco Iodice requested to merge rhs_pack_scalar into main Dec 11, 2024

Optimize the generic RHS packing NxK. The performance improvement is around ~1.5x

Signed-off-by: Gian Marco Iodice gianmarco.iodice@arm.com