[Bug target/36840] Fortran complex array multiply missed optimization

2008-08-04 Thread victork at gcc dot gnu dot org
--- Comment #5 from victork at gcc dot gnu dot org 2008-08-04 11:15 --- Closing as duplicate of PR30211 (and PR35252). *** This bug has been marked as a duplicate of 30211 *** -- victork at gcc dot gnu dot org changed: What|Removed |Added

[Bug target/36840] Fortran complex array multiply missed optimization

2008-07-24 Thread victork at gcc dot gnu dot org
--- Comment #4 from victork at gcc dot gnu dot org 2008-07-24 12:30 --- I'm going to submit a patch which will enable SLP vectorization on complex data types. But SLP will handle only add, substruct, compare and other operations which doesn't require permutation. Adding ability to handl

[Bug target/36840] Fortran complex array multiply missed optimization

2008-07-23 Thread rguenth at gcc dot gnu dot org
--- Comment #3 from rguenth at gcc dot gnu dot org 2008-07-23 09:37 --- The problem is that SLP and the reduction operation do not mix and that the vectorizer doesn't understand the complex component accessors. : # S.4_40 = PHI D.1045_26 = S.4_40 + -1; CR.27_44 = REALPART_EXPR <(

[Bug target/36840] Fortran complex array multiply missed optimization

2008-07-15 Thread pinskia at gcc dot gnu dot org
--- Comment #2 from pinskia at gcc dot gnu dot org 2008-07-15 19:09 --- PowerPC version looks good: .L3: lfd 12,8(3) lfd 10,0(4) lfd 13,8(4) fmul 11,12,10 lfd 0,0(3) addi 4,4,16 fmul 12,12,13 fmadd 13,0,13,11 fmsub 0