https://gcc.gnu.org/bugzilla/show_bug.cgi?id=71231
--- Comment #17 from Dominique d'Humieres <dominiq at lps dot ens.fr> ---
> This problem seems fixed. The runtimes are back to normal.
AFAICT the output does not seem right with r240076 and "-fprotect-parens -Ofast
-funroll-loops -ftree-loop-linear -fomit-frame-pointer -fwhole-program -flto":
...
173 , 181 194373 195269 0.459999979
173 , 189 78369 78688 0.409999996
173 , 197 19089 19224 0.699999988
173 , 205 3063 3176 3.55999994
181 , 197 29924 30167 0.810000002
189 , 197 32866 32970 0.319999993
189 , 205 12258 12376 0.949999988
197 , 205 10923 10808 1.04999995
0: 0:21.328 -> Completed program execution
compared to the output of an executable from Aug 16 2013:
...
173 , 181 194373 193363 0.519999981
173 , 189 78369 78008 0.459999979
173 , 197 19089 18777 1.63000000
181 , 189 81645 81532 0.140000001
181 , 197 29924 29571 1.17999995
189 , 197 32866 33059 0.579999983
189 , 205 12258 12352 0.759999990
197 , 205 10923 10786 1.25000000
205 , 213 3278 3208 2.13999987
0: 0:14.916 -> Completed program execution
or of gfortran 6.2.0
...
173 , 181 194373 193363 0.519999981
173 , 189 78369 78008 0.459999979
173 , 197 19089 18777 1.63000000
181 , 189 81645 81532 0.140000001
181 , 197 29924 29571 1.17999995
189 , 197 32866 33059 0.579999983
189 , 205 12258 12352 0.759999990
197 , 205 10923 10786 1.25000000
205 , 213 3278 3208 2.13999987
0: 0:13.175 -> Completed program execution
