[Bug fortran/52473] New: CSHIFT slow - inline it?

[Bug fortran/52473] New: CSHIFT slow - inline it?

[burnus at gcc dot gnu.org]

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=52473

             Bug #: 52473
           Summary: CSHIFT slow - inline it?
    Classification: Unclassified
           Product: gcc
           Version: 4.7.0
            Status: UNCONFIRMED
          Keywords: missed-optimization
          Severity: normal
          Priority: P3
         Component: fortran
        AssignedTo: unassigned@gcc.gnu.org
        ReportedBy: burnus@gcc.gnu.org


For the program http://www.cita.utoronto.ca/~pen/MHD/mhd.f90 GCC produces
relatively slow code:

$ gfortran -Ofast mhd.f90; time ./a.out > /dev/null
real    0m0.534s

$ pathf95 -O3 mhd.f90; time ./a.out > /dev/null
real    0m0.169s

Which is 3.2 times faster. A closer analyis shows that it is sufficient to
compile the functions advectbyzx, tvd1 and tvdb with pathf95 to gain the same
speed. If one only compiles advectbyzx and tvd1 (and the rest with gfortran)
the speed is 0m0.301s.

The performance difference seems to be due to the calls to _gfortran_cshift0_4.

Expected: CSHIFT should be inlined (at least for a scalar SHIFT) - as pathf95
and ifort do.

 * * *

13.7.43 CSHIFT (ARRAY, SHIFT [, DIM])
Description. Circular shift of an array.Description. Circular shift of an
array.

[Bug fortran/52473] CSHIFT slow - inline it?

[burnus at gcc dot gnu.org]

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=52473

Tobias Burnus <burnus at gcc dot gnu.org> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
                 CC|                            |burnus at gcc dot gnu.org

--- Comment #1 from Tobias Burnus <burnus at gcc dot gnu.org> 2012-04-10 15:22:30 UTC ---
Cf. also http://gcc.gnu.org/ml/fortran/2012-04/msg00041.html

[Bug fortran/52473] CSHIFT slow - inline it?

[burnus at gcc dot gnu.org]

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=52473

Tobias Burnus <burnus at gcc dot gnu.org> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
                 CC|                            |matz at gcc dot gnu.org

--- Comment #2 from Tobias Burnus <burnus at gcc dot gnu.org> 2012-04-11 12:51:34 UTC ---
*** Bug 52934 has been marked as a duplicate of this bug. ***

[Bug fortran/52473] CSHIFT slow - inline it?

[dominiq at lps dot ens.fr]

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=52473

Dominique d'Humieres <dominiq at lps dot ens.fr> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
             Status|UNCONFIRMED                 |NEW
   Last reconfirmed|                            |2013-06-16
     Ever confirmed|0                           |1

--- Comment #3 from Dominique d'Humieres <dominiq at lps dot ens.fr> ---
I don't have access to pathf95, but the following test (modified for some IDRIS
benchmarks)

  subroutine test_cshift()
    !-----------------------------------------------------------------
    ! Test de la fonction intrinsèque "cshift"
    !-----------------------------------------------------------------
    implicit none
    integer, parameter             :: n=ordre
    integer                        :: i,j
    integer, dimension(n)          :: vect=(/ (-i, i=1,n) /)
    real(kind=prec),dimension(n,n) :: t,td,t2,t1
    real(kind=prec)                :: cste

    call impression_entete("test_cshift")
    print *, "Order of matrix:", n

    !---- Initialisations --------------------------
    cste=exp(1._prec)
    t(:,:)  = reshape( &
              source=(/ (i*cste,i=1,n*n) /) , shape = (/ n,n /) )

    td(:,:) = 0._prec
    call cpu_time( val_temps(1) )
    td(:,:) = cshift(array=t(:,:), shift=vect(:), dim=1)
    call cpu_time( val_temps(2) )
    t1(:,:)  = td(:,:)

    call temps_consomme("test_cshift> 1) CSHIFT")

    !---- Décalage selon les lignes via des boucles --------------------
    td(:,:) = 0._prec
    call cpu_time( val_temps(1) )
    do j=1,n
       do i=n+vect(j),1,-1
          td(i-vect(j),j) = t(i,j)
       end do
       do i=1,-vect(j)
          td(i,j)=t(n+vect(j)+i,j)
       end do
    end do
    call cpu_time( val_temps(2) )
    t2(:,:) = td(:,:)

    call temps_consomme("test__cshift> 2) DO loop")

    if (sum(abs(t2-t1)) /= 0._prec) then
       print *,'Mauvais résultats !!!!',sum(abs(t2-t1))
    else
        print *,'Results OK'
    end if    

  end subroutine test_cshift

gives

====================
 Call to test_cshift
====================

 Order of matrix:        1000
 test_cshift> 1) CSHIFT
                                       Used CPU time ==>         7.624 ms
 test__cshift> 2) DO loop
                                       Used CPU time ==>         4.482 ms
 Results OK

So CSHIFT is 50% slower than the DO loop.

Note that I get similar results for EOSHIFT and RESHAPE:

=====================
 Call to test_eoshift
=====================

 Order of matrix:        1000
 test_eoshift> 1) EOSHIFT
                                       Used CPU time ==>         7.443 ms
 test__eoshift> 2) DO loop
                                       Used CPU time ==>         3.775 ms
 Results OK

=====================
 Call to test_reshape
=====================

 Order of matrix:        1000
 test__reshape> 1) RESHAPE
                                       Used CPU time ==>        10.624 ms
 test__reshape> 2) DO loop
                                       Used CPU time ==>         4.442 ms
 Results OK

PR45689 should probably fixed at the same time.
>From gcc-bugs-return-424460-listarch-gcc-bugs=gcc.gnu.org@gcc.gnu.org Sun Jun 16 12:06:58 2013
Return-Path: <gcc-bugs-return-424460-listarch-gcc-bugs=gcc.gnu.org@gcc.gnu.org>
Delivered-To: listarch-gcc-bugs@gcc.gnu.org
Received: (qmail 11959 invoked by alias); 16 Jun 2013 12:06:58 -0000
Mailing-List: contact gcc-bugs-help@gcc.gnu.org; run by ezmlm
Precedence: bulk
List-Id: <gcc-bugs.gcc.gnu.org>
List-Archive: <http://gcc.gnu.org/ml/gcc-bugs/>
List-Post: <mailto:gcc-bugs@gcc.gnu.org>
List-Help: <mailto:gcc-bugs-help@gcc.gnu.org>
Sender: gcc-bugs-owner@gcc.gnu.org
Delivered-To: mailing list gcc-bugs@gcc.gnu.org
Received: (qmail 11915 invoked by uid 48); 16 Jun 2013 12:06:55 -0000
From: "dominiq at lps dot ens.fr" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug fortran/45689] [F2003] Missing transformational intrinsic in the trans_func_f2003 list
Date: Sun, 16 Jun 2013 12:06:00 -0000
X-Bugzilla-Reason: CC
X-Bugzilla-Type: changed
X-Bugzilla-Watch-Reason: None
X-Bugzilla-Product: gcc
X-Bugzilla-Component: fortran
X-Bugzilla-Version: 4.6.0
X-Bugzilla-Keywords:
X-Bugzilla-Severity: normal
X-Bugzilla-Who: dominiq at lps dot ens.fr
X-Bugzilla-Status: NEW
X-Bugzilla-Priority: P3
X-Bugzilla-Assigned-To: unassigned at gcc dot gnu.org
X-Bugzilla-Target-Milestone: ---
X-Bugzilla-Flags:
X-Bugzilla-Changed-Fields: bug_status cf_reconfirmed_on everconfirmed
Message-ID: <bug-45689-4-VxjXv5IZ5e@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-45689-4@http.gcc.gnu.org/bugzilla/>
References: <bug-45689-4@http.gcc.gnu.org/bugzilla/>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: 7bit
X-Bugzilla-URL: http://gcc.gnu.org/bugzilla/
Auto-Submitted: auto-generated
MIME-Version: 1.0
X-SW-Source: 2013-06/txt/msg00839.txt.bz2
Content-length: 514

http://gcc.gnu.org/bugzilla/show_bug.cgi?idE689

Dominique d'Humieres <dominiq at lps dot ens.fr> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
             Status|UNCONFIRMED                 |NEW
   Last reconfirmed|                            |2013-06-16
     Ever confirmed|0                           |1

--- Comment #5 from Dominique d'Humieres <dominiq at lps dot ens.fr> ---
Related or duplicate of PR52473.