[Bug tree-optimization/64745] Generic vectorization missed opportunities

[rguenth at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=64745

Richard Biener <rguenth at gcc dot gnu.org> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
             Status|UNCONFIRMED                 |ASSIGNED
   Last reconfirmed|                            |2015-01-23
           Assignee|unassigned at gcc dot gnu.org      |rguenth at gcc dot gnu.org
     Ever confirmed|0                           |1

--- Comment #1 from Richard Biener <rguenth at gcc dot gnu.org> ---
Mine.  The alignment issue is easily fixed (I have a patch), the cost model
issue is, well, a cost model issue also easily fixed.

A big required change is to re-structure basic-block vectorization to
perform SLP analysis independent of vector types/sizes and to vectorize
independent SLP instances separately (allowing different vector
sizes in a BB).

Loop vectorization could also do SLP analysis first (basically splitting it) to
reduce the number of applicable vectorization factors.  Other analysis phases
could also contribute to that and it would also help compile-time to not
re-do dataref and dependence analysis for each size.