[Bug tree-optimization/107090] [aarch64] sequence logic should be combined with mul and umulh

[liuhongt at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=107090

--- Comment #16 from Hongtao Liu <liuhongt at gcc dot gnu.org> ---
Created attachment 63963
  --> https://gcc.gnu.org/bugzilla/attachment.cgi?id=63963&action=edit
A patch.

Add gimple pattern to match and simplify pure c implementation of 64-bit to
128-bit widen_mult.

A pattern match in the match.pd can optimized the instruction sequence to
widen_mult before inline, and help inline to get a more accurate number of
instructions size of the function.