This is the mail archive of the fortran@gcc.gnu.org mailing list for the GNU Fortran project.


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]
Other format: [Raw text]

Re: Polyhedron Benchmark


Uros Bizjak wrote:
> Could you perhaps add -fvect-cost-model to
> gcc-4.3 compile flags? There are some surprises there ;)

Well, a 2% overall improvement, some slower, some faster. Only for
induct an improvement by a 1/3.

Should I use -fvect-cost-model in general for my nightly runs or should
I add another column with one -fvect-cost-model run?


For Core2 the results with -fvect-cost-model are:

              gfortran
   benchmark  Vec   VecCost   ifort
------------  ----- -------   -----
          ac  12.95    12.84  17.36
      aermod  36.32    36.17  25.30
         air   9.41     9.16   9.16
    capacita  51.85    52.55   0.09 (ifort crashed)
     channel   2.87     2.97   3.56
       doduc  47.41    48.00  47.69
     fatigue  12.86    12.62  10.96
     gas_dyn   8.57     8.59   3.97
      induct  92.82    64.38  63.08 <<<<<
       linpk  22.67    22.48  22.47
        mdbx  19.03    18.98  17.66
          nf  26.10    25.97   0.23 (ifort crashed)
     protein  60.30    60.42  55.11
      rnflow  35.11    35.06  42.29
    test_fpu  12.68    12.64  10.78
        tfft   2.97     3.04  2.88
------------  -----    -----
Geometr.mean  18.99    18.58

Tobias


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]