http://gcc.gnu.org/bugzilla/show_bug.cgi?id=58721
--- Comment #6 from Dominique d'Humieres <dominiq at lps dot ens.fr> --- > It turned out that proposed fix does not help trunk compilers > since now another huge routine is inlined firstly (read_input) > and for perdida we got the following message: This has been seen before and supposed to be fixed: see pr48636, comment #37. > Note that passing --param large-function-growth=130 will restore performance. As does --param max-inline-insns-auto=94. > I assume that additional heuristics must be designed to inline once > called functions which are called inside inner loop. Well, it was supposed to have been found. What did break it?
