http://gcc.gnu.org/bugzilla/show_bug.cgi?id=38318
Dominique d'Humieres <dominiq at lps dot ens.fr> changed:
What |Removed |Added
----------------------------------------------------------------------------
CC| |jh at suse dot cz,
| |rguenther at suse dot de
--- Comment #5 from Dominique d'Humieres <dominiq at lps dot ens.fr> 2010-10-07
15:04:34 UTC ---
Another case of interest is "automatic arrays". An interesting example is the
polyhedron test nf.f90.
On Core2 Duo and Darwin the following patch
--- nf.f90 2005-10-11 22:53:32.000000000 +0200
+++ nf_v2.f90 2010-10-07 16:49:38.000000000 +0200
@@ -153,7 +153,7 @@ integer :: nx , nxy , nxyz , maxiter
real(dpkind),dimension(nxyz):: ad,au1,au2,au3,x,b
real(dpkind)::targrms
-real(dpkind),allocatable,dimension(:) :: r,q,p,z,g,gi
+real(dpkind),allocatable,dimension(:) :: r,q,p,z,g,gi,t,u
real(dpkind):: alpha,beta,qr,qrp,rmserr
integer :: iter , tbase , tgi , tcg , tickspersec , maxticks
@@ -163,7 +163,7 @@ call GetGI3D(1,nxyz) ! c
call system_clock(tgi,tickspersec,maxticks)
deallocate(g)
-allocate (r(nxyz),q(nxyz),p(nxyz),z(nxyz))
+allocate (r(nxyz),q(nxyz),p(nxyz),z(nxyz),t(nxyz),u(nxyz))
CALL SPMMULT(x,r) ; r = b - r ! compute initial residual vector
write(*,'(A)') ' Iter Alpha Beta RMS Residual Sum of
Residuals'
@@ -171,12 +171,12 @@ write(*,'(I4,24X,2G18.7)') 0,sqrt(DOT_PR
! Do a single iteration with alpha =1
! to reduce sum of residuals to 0
-p = r ; CALL NF3DPrecon(p,1,nxyz) ; CALL SPMMULT(p,z)
+p = r ; CALL NF3DPrecon(p,t,u,1,nxyz) ; CALL SPMMULT(p,z)
x = x + p ; r = r - z
write(*,'(I4,F12.5,12X,2G18.7)') 0,1.0,sqrt(DOT_PRODUCT(r,r)/nxyz),sum(r)
do iter = 1 , maxiter
- q = r ; CALL NF3DPrecon(q,1,nxyz)
+ q = r ; CALL NF3DPrecon(q,t,u,1,nxyz)
qr = DOT_PRODUCT(q,r)
if ( iter==1 ) then
beta = 0.0
@@ -197,7 +197,7 @@ call system_clock(tcg,tickspersec,maxtic
write(*,'(/A,F10.3/A,F10.3/A,F10.3)') ' Time for setup
',REAL(tgi-tbase)/REAL(tickspersec) , &
' Time per iteration
',REAL(tcg-tgi)/REAL(tickspersec*min(iter,maxiter)) , &
' Total Time
',REAL(tcg-tbase)/REAL(tickspersec)
-deallocate(r,q,p,z,gi)
+deallocate(r,q,p,z,gi,t,u)
contains
!=========================================
! Banded matrix multiply b = A.x
=========
@@ -253,7 +253,7 @@ end subroutine GetGI2D !==
!=========================================
! solve for a plane of cells using
======
-subroutine NF2DPrecon(x,i1,i2) ! 2D NF Preconditioning matrix
+subroutine NF2DPrecon(x,t,i1,i2) ! 2D NF Preconditioning matrix
integer :: i1 , i2
real(dpkind),dimension(i2)::x,t
integer :: i
@@ -272,11 +272,12 @@ end subroutine NF2DPrecon !==
subroutine GetGI3D(i1,i2) ! compute gi for a 3D block of cells
=====
integer :: i1 , i2
integer :: i
+real(dpkind),dimension(nxyz)::t
g = ad
do i = i1 , i2 , nxy ! advance one plane at a time
if ( i>i1 ) then ! get contribution from previous plane
g(i-nxy:i-1) = au3(i-nxy:i-1)
- call NF2DPrecon(g,i-nxy,i-1)
+ call NF2DPrecon(g,t,i-nxy,i-1)
g(i:i+nxy-1) = g(i:i+nxy-1) - au3(i-nxy:i-1)*g(i-nxy:i-1)
endif
call GetGI2D(i,i+nxy-1) ! get contribution from this plane
@@ -285,17 +286,17 @@ end subroutine GetGI3D !==
!=========================================
! solve for a 3D block of cells using
-subroutine NF3DPrecon(x,i1,i2) ! 3D Preconditioning matrix
+subroutine NF3DPrecon(x,t,u,i1,i2) ! 3D Preconditioning matrix
integer :: i1 , i2
-real(dpkind),dimension(i2)::x,t
+real(dpkind),dimension(i2)::x,t,u
integer :: i
do i = i1 , i2 , nxy
if ( i>i1 ) x(i:i+nxy-1) = x(i:i+nxy-1) - au3(i-nxy:i-1)*x(i-nxy:i-1)
- call NF2DPrecon(x,i,i+nxy-1)
+ call NF2DPrecon(x,u,i,i+nxy-1)
enddo
do i = i2-2*nxy+1 , i1 , -nxy
t(i:i+nxy-1) = au3(i:i+nxy-1)*x(i+nxy:i+2*nxy-1)
- call NF2DPrecon(t,i,i+nxy-1)
+ call NF2DPrecon(t,u,i,i+nxy-1)
x(i:i+nxy-1) = x(i:i+nxy-1) - t(i:i+nxy-1)
enddo
end subroutine NF3DPrecon
!=========================================
cuts the execution time from ~28s to ~20s (Note that with the options I use all
the procs are inlined).