consider the following source and timings, were a natural form of a subroutine
S1, and two hand optimized forms are timed:
> cat test.f90
SUBROUTINE S1(N,A)
REAL :: A(3)
DO I=1,N
CALL S2(-A)
ENDDO
END SUBROUTINE
SUBROUTINE S1_opt1(N,A)
REAL :: A(3)
REAL, ALLOCATABLE :: B(:)
ALLOCATE(B(SIZE(A,1)))
DO I=1,N
B=-A
CALL S2(B)
ENDDO
END SUBROUTINE
SUBROUTINE S1_opt2(N,A)
REAL :: A(3),B(3)
DO I=1,N
B=-A
CALL S2(B)
ENDDO
END SUBROUTINE
> cat main.f90
SUBROUTINE S2(A)
REAL :: A(*),D
COMMON /F/D
D=D+A(1)+A(2)+A(3)
END SUBROUTINE
INTEGER, PARAMETER :: N=100000
REAL :: A(3),T1,T2,T3,T4,D
COMMON /F/D
D=0.0
A=0.0
CALL CPU_TIME(T1)
DO I=1,10000
CALL S1(N,A)
ENDDO
CALL CPU_TIME(T2)
DO I=1,10000
CALL S1_opt1(N,A)
ENDDO
CALL CPU_TIME(T3)
DO I=1,10000
CALL S1_opt2(N,A)
ENDDO
CALL CPU_TIME(T4)
write(6,*) "Default [s]:",T2-T1
write(6,*) "OPT1 [s]:",T3-T2
write(6,*) "OPT2 [s]:",T4-T3
write(6,*) D
END
gfortran-4.4 -O3 test.f90 main.f90
Default [s]: 18.293142
OPT1 [s]: 6.2603912
OPT2 [s]: 6.2563915
ifort -O3 test.f90 main.f90
Default [s]: 6.256391
OPT1 [s]: 6.252390
OPT2 [s]: 6.256390
so, gfortran by default is about 3x slower than ifort, which by default moves
the generation of the temporaries out of the loop.
FYI, allowing for multi file IPO, I hope LTO gets that far...
ifort -O3 -fast test.f90 main.f90 (includes ipo)
Default [s]: 3.752234
OPT1 [s]: 1.276080
OPT2 [s]: 3.752234
--
Summary: moving the allocation of temps out of loops.
Product: gcc
Version: 4.4.0
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: fortran
AssignedTo: unassigned at gcc dot gnu dot org
ReportedBy: jv244 at cam dot ac dot uk
OtherBugsDependingO 36854
nThis:
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=38318
