[Bug fortran/83064] DO CONCURRENT and auto-parallelization
tkoenig at gcc dot gnu.org
gcc-bugzilla@gcc.gnu.org
Tue Oct 30 19:16:00 GMT 2018
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=83064
Thomas Koenig <tkoenig at gcc dot gnu.org> changed:
What |Removed |Added
----------------------------------------------------------------------------
Status|NEW |RESOLVED
Resolution|--- |FIXED
--- Comment #31 from Thomas Koenig <tkoenig at gcc dot gnu.org> ---
Hm, on my system (current trunk), with the unrolled loop, parallelization
only happens with -Ofast:
$ gfortran -ftree-parallelize-loops=2 -O1 conc.f90 && time ./a.out
PI 3.1415926553497115
PI 3.14159274
real 0m0.313s
user 0m0.345s
sys 0m0.001s
$ gfortran -ftree-parallelize-loops=2 -O2 conc.f90 && time ./a.out
PI 3.1415926553497115
PI 3.14159274
real 0m0.273s
user 0m0.272s
sys 0m0.001s
$ gfortran -ftree-parallelize-loops=2 -O3 conc.f90 && time ./a.out
PI 3.1415926553497115
PI 3.14159274
real 0m0.278s
user 0m0.278s
sys 0m0.001s
$ gfortran -ftree-parallelize-loops=2 -Ofast conc.f90 && time ./a.out
PI 3.1415926553497115
PI 3.14159274
real 0m0.152s
user 0m0.296s
sys 0m0.001s
However, the wrong-code bug is indeed fixed. I'll look at paralellization
separately.
More information about the Gcc-bugs
mailing list