[Bug target/124271] x86/AVX2: missed simplification — low32×low32→u64 vectorized multiply expands to generic u64-mul sequence instead of single vpmuludq

[adamant.pwn at gmail dot com via Gcc-bugs]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=124271

--- Comment #11 from Oleksandr Kulkov <adamant.pwn at gmail dot com> ---
Hongtao, is there an updated version of the widening-multiply patch from
comment 7? The last feedback in comment 10 concerned using `vec_widen_mult_odd`
on big-endian targets. Is anything else needed to move it forward?