The following doesn't run as fast as the 'hand-optimised' routine provided as
well (using current 4.2 on an opteron) using -ffast-math -O2 (makes a factor of
2 difference here). I've tried a number of further switches, but didn't manage
to find a case where the simply loop was as fast as the other.
! simple loop
! assume N is even
SUBROUTINE S31(a,b,c,N)
IMPLICIT NONE
integer :: N
real*8 :: a(N),b(N),c
integer :: i
c=0.0D0
DO i=1,N
c=c+a(i)*b(i)
ENDDO
END SUBROUTINE
! 'improved' loop
SUBROUTINE S32(a,b,c,N)
IMPLICIT NONE
integer :: N
real*8 :: a(N),b(N),c,tmp
integer :: i
c=0.0D0
tmp=0.0D0
DO i=1,N,2
c=c+a(i)*b(i)
tmp=tmp+a(i+1)*b(i+1)
ENDDO
c=c+tmp
END SUBROUTINE
--
Summary: Missed optimisation
Product: gcc
Version: 4.2.0
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: tree-optimization
AssignedTo: unassigned at gcc dot gnu dot org
ReportedBy: jv244 at cam dot ac dot uk
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=25621
