https://gcc.gnu.org/bugzilla/show_bug.cgi?id=88713
Thomas Koenig <tkoenig at gcc dot gnu.org> changed:
What |Removed |Added
----------------------------------------------------------------------------
Status|RESOLVED |REOPENED
Last reconfirmed| |2019-01-06
Component|fortran |tree-optimization
Blocks|36854 |53947
Resolution|WONTFIX |---
Summary|_gfortran_internal_pack@PLT |Vectorized code slow vs.
|prevents vectorization |flang
Ever confirmed|0 |1
--- Comment #11 from Thomas Koenig <tkoenig at gcc dot gnu.org> ---
OK, so I think it makes sense to reopen this bug as a missed
optimization for the vectorizer (reopen because it would be a shame
to lose all the info you already provided).
It seems like gcc could be much better, also possibly with some
more help from the gfortran front end. A factor of two is not to
be ignored.
Referenced Bugs:
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=36854
[Bug 36854] [meta-bug] fortran front-end optimization
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=53947
[Bug 53947] [meta-bug] vectorizer missed-optimizations
