https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81362
--- Comment #7 from Andreas Schwab ---
This fixes both no-vfa-vect-57.c and no-vfa-vect-61.c for -m64 and -m32.
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81362
--- Comment #6 from rdapp at linux dot vnet.ibm.com ---
Created attachment 41715
--> https://gcc.gnu.org/bugzilla/attachment.cgi?id=41715=edit
Tentative patch
Removed the npeel function argument, also removed body_cost_vec and the
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81362
--- Comment #5 from rdapp at linux dot vnet.ibm.com ---
Ah, npeel is set by vect_peeling_hash_get_lowest_cost although the
corresponding dr is not used afterwards. It should be save to get rid of the
npeel parameter since we use the returned
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81362
--- Comment #4 from Andreas Schwab ---
There is no VSX on G5.
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81362
--- Comment #3 from Andreas Schwab ---
Created attachment 41709
--> https://gcc.gnu.org/bugzilla/attachment.cgi?id=41709=edit
no-vfa-vect-57.s
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81362
--- Comment #2 from Andreas Schwab ---
Created attachment 41708
--> https://gcc.gnu.org/bugzilla/attachment.cgi?id=41708=edit
no-vfa-vect-57.c.159t.vect
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81362
--- Comment #1 from rdapp at linux dot vnet.ibm.com ---
Could you provide the vectorizer dump (-fdump-tree-vect-details)? The generated
assembly might also be interesting as well as the exact command line for
building (in the test suite logs). I