On 06/06/2016 18:56, "Jeff Law" <l...@redhat.com> wrote: >On 06/06/2016 06:46 AM, Alan Hayward wrote: >> Lots of code calls dump_gimple_stmt then print a newline, however >> dump_gimple_stmt will print a newline itself. This makes the vectorizer >> debug >> file messy. I think the confusion is because dump_generic_expr does NOT >> print a >> newline. This patch removes all prints of a newline direcly after a >> dump_gimple_stmt. >> >> Tested by examining a selection of vect dump files. >> >> gcc/ >> \* tree-vect-data-refs.c (vect_analyze_data_refs): Remove debug >>newline. >> \* tree-vect-loop-manip.c (slpeel_make_loop_iterate_ntimes): likewise. >> (vect_can_advance_ivs_p): likewise. >> (vect_update_ivs_after_vectorizer): likewise. >> \* tree-vect-loop.c (vect_determine_vectorization_factor): likewise. >> (vect_analyze_scalar_cycles_1): likewise. >> (vect_analyze_loop_operations): likewise. >> (report_vect_op): likewise. >> (vect_is_slp_reduction): likewise. >> (vect_is_simple_reduction): likewise. >> (get_initial_def_for_induction): likewise. >> (vect_transform_loop): likewise. >> \* tree-vect-patterns.c (vect_recog_dot_prod_pattern): likewise. >> (vect_recog_sad_pattern): likewise. >> (vect_recog_widen_sum_pattern): likewise. >> (vect_recog_widening_pattern): likewise. >> (vect_recog_divmod_pattern): likewise. >> \* tree-vect-slp.c (vect-build-slp_tree_1): likewise. >> (vect_analyze_slp_instance): likewise. >> (vect_transform_slp_perm_load): likewise. >> (vect_schedule_slp_instance): likewise. >Wouldn't you also need to verify that the testsuite passes since it >could potentially have tests which assume the extra newlines in the >test's regexps? > >So I'm fine with this patch once the testsuite has been verified to run >without regressions on a target which exercises the vectorizer. >
Sorry, I should have said that I have done a check run on x86 and aarch64, and there were no regressions. Alan.