[Hexagon] Move selection of HVX multiply from lowering to patterns
Also, change i32*i32 to V6_vmpyieoh + V6_vmpyiewuh_acc, which works on V60 as well.
Loading
Please sign in to comment
Also, change i32*i32 to V6_vmpyieoh + V6_vmpyiewuh_acc, which works on V60 as well.