| Message ID | CAAgBjMmzvQG5GLsWsX86cP2c=ZcRJXU+iRzho0RcNy_ej+WVvw@mail.gmail.com |
|---|---|
| State | New |
| Headers | show |
> On 8 June 2016 at 20:38, Jan Hubicka <hubicka@ucw.cz> wrote: > >> I think it would be nice to work towards transitioning > >> flag_section_anchors to a flag on varpool nodes, thereby removing > >> the Optimization flag from common.opt:fsection-anchors > >> > >> That would simplify the walk over varpool candidates. > > > > Makes sense to me, too. There are more candidates for sutff that should be > > variable specific in common.opt (such as variable alignment, -fdata-sctions, > > -fmerge-constants) and targets. We may try to do it in an easy to extend way > > so incrementally we can get rid of those global flags, too. > In this version I removed Optimization from fsection-anchors entry in > common.opt, > and gated the increase_alignment pass on flag_section_anchors != 0. > Cross tested on arm*-*-*, aarch64*-*-*. > Does it look OK ? If you go this way you will need to do something sane for LTO. Here one can compile some object files with -fsection-anchors and other without and link with random setting (because in traditional compilation linktime flags does not matter). For global flags we have magic in merge_and_complain that determines flags to pass to the LTO compiler. It is not very robust though. > > > > One thing that needs to be done for LTO is sane merging, I guess in this case > > it is clear that the variable should be anchored when its previaling definition > > is. > Um could we determine during WPA if symbol is a section anchor for merging ? > Seems to me SYMBOL_REF_ANCHOR_P is defined only on DECL_RTL and not at > tree level. > Do we have DECL_RTL info available during WPA ? We don't have anchros computed, but we can decide whether we want to potentially anchor the variable if we can. I would say all you need is to have section_anchor flag in varpool node itself which controls RTL production. At varpool_finalize_decl you will set it according to flag_varpool and stream it to LTO objects. At WPA when doing linking, the section_anchor flag of the previaling decl wins.. Honza > > Thanks, > Prathamesh > > > > Honza > >> > >> Richard. > >> > >> > Thanks, > >> > Prathamesh > >> > > > >> > > Honza > >> > >> > >> > >> Richard. > >> > > >> > > >> > >> -- > >> Richard Biener <rguenther@suse.de> > >> SUSE LINUX GmbH, GF: Felix Imendoerffer, Jane Smithard, Graham Norton, HRB 21284 (AG Nuernberg) > diff --git a/gcc/common.opt b/gcc/common.opt > index f0d7196..f93f26c 100644 > --- a/gcc/common.opt > +++ b/gcc/common.opt > @@ -2133,7 +2133,7 @@ Common Report Var(flag_sched_dep_count_heuristic) Init(1) Optimization > Enable the dependent count heuristic in the scheduler. > > fsection-anchors > -Common Report Var(flag_section_anchors) Optimization > +Common Report Var(flag_section_anchors) > Access data in the same section from shared anchor points. > > fsee > diff --git a/gcc/passes.def b/gcc/passes.def > index 3647e90..3a8063c 100644 > --- a/gcc/passes.def > +++ b/gcc/passes.def > @@ -138,12 +138,12 @@ along with GCC; see the file COPYING3. If not see > PUSH_INSERT_PASSES_WITHIN (pass_ipa_tree_profile) > NEXT_PASS (pass_feedback_split_functions); > POP_INSERT_PASSES () > - NEXT_PASS (pass_ipa_increase_alignment); > NEXT_PASS (pass_ipa_tm); > NEXT_PASS (pass_ipa_lower_emutls); > TERMINATE_PASS_LIST (all_small_ipa_passes) > > INSERT_PASSES_AFTER (all_regular_ipa_passes) > + NEXT_PASS (pass_ipa_increase_alignment); > NEXT_PASS (pass_ipa_whole_program_visibility); > NEXT_PASS (pass_ipa_profile); > NEXT_PASS (pass_ipa_icf); > diff --git a/gcc/testsuite/gcc.dg/vect/aligned-section-anchors-vect-73.c b/gcc/testsuite/gcc.dg/vect/aligned-section-anchors-vect-73.c > new file mode 100644 > index 0000000..74eaed8 > --- /dev/null > +++ b/gcc/testsuite/gcc.dg/vect/aligned-section-anchors-vect-73.c > @@ -0,0 +1,25 @@ > +/* { dg-do compile } */ > +/* { dg-require-effective-target section_anchors } */ > +/* { dg-require-effective-target vect_int } */ > + > +#define N 32 > + > +/* Clone of section-anchors-vect-70.c with foo() having -fno-tree-loop-vectorize. */ > + > +static struct A { > + int p1, p2; > + int e[N]; > +} a, b, c; > + > +__attribute__((optimize("-fno-tree-loop-vectorize"))) > +int foo(void) > +{ > + for (int i = 0; i < N; i++) > + a.e[i] = b.e[i] + c.e[i]; > + > + return a.e[0]; > +} > + > +/* { dg-final { scan-ipa-dump-times "Increasing alignment of decl" 0 "increase_alignment" { target aarch64*-*-* } } } */ > +/* { dg-final { scan-ipa-dump-times "Increasing alignment of decl" 0 "increase_alignment" { target powerpc64*-*-* } } } */ > +/* { dg-final { scan-ipa-dump-times "Increasing alignment of decl" 0 "increase_alignment" { target arm*-*-* } } } */ > diff --git a/gcc/tree-pass.h b/gcc/tree-pass.h > index 36299a6..d36aa1d 100644 > --- a/gcc/tree-pass.h > +++ b/gcc/tree-pass.h > @@ -483,7 +483,7 @@ extern simple_ipa_opt_pass *make_pass_local_optimization_passes (gcc::context *c > > extern ipa_opt_pass_d *make_pass_ipa_whole_program_visibility (gcc::context > *ctxt); > -extern simple_ipa_opt_pass *make_pass_ipa_increase_alignment (gcc::context > +extern ipa_opt_pass_d *make_pass_ipa_increase_alignment (gcc::context > *ctxt); > extern ipa_opt_pass_d *make_pass_ipa_inline (gcc::context *ctxt); > extern simple_ipa_opt_pass *make_pass_ipa_free_lang_data (gcc::context *ctxt); > diff --git a/gcc/tree-vectorizer.c b/gcc/tree-vectorizer.c > index 2669813..d34e560 100644 > --- a/gcc/tree-vectorizer.c > +++ b/gcc/tree-vectorizer.c > @@ -899,6 +899,34 @@ get_vec_alignment_for_type (tree type) > return (alignment > TYPE_ALIGN (type)) ? alignment : 0; > } > > +/* Return true if alignment should be increased for this vnode. > + This is done if every function that references/referring to vnode > + has flag_tree_loop_vectorize and flag_section_anchors set. */ > + > +static bool > +increase_alignment_p (varpool_node *vnode) > +{ > + ipa_ref *ref; > + > + for (int i = 0; vnode->iterate_reference (i, ref); i++) > + if (cgraph_node *cnode = dyn_cast<cgraph_node *> (ref->referred)) > + { > + struct cl_optimization *opts = opts_for_fn (cnode->decl); > + if (!opts->x_flag_tree_loop_vectorize) > + return false; > + } > + > + for (int i = 0; vnode->iterate_referring (i, ref); i++) > + if (cgraph_node *cnode = dyn_cast<cgraph_node *> (ref->referring)) > + { > + struct cl_optimization *opts = opts_for_fn (cnode->decl); > + if (!opts->x_flag_tree_loop_vectorize) > + return false; > + } > + > + return true; > +} > + > /* Entry point to increase_alignment pass. */ > static unsigned int > increase_alignment (void) > @@ -916,7 +944,8 @@ increase_alignment (void) > > if ((decl_in_symtab_p (decl) > && !symtab_node::get (decl)->can_increase_alignment_p ()) > - || DECL_USER_ALIGN (decl) || DECL_ARTIFICIAL (decl)) > + || DECL_USER_ALIGN (decl) || DECL_ARTIFICIAL (decl) > + || !increase_alignment_p (vnode)) > continue; > > alignment = get_vec_alignment_for_type (TREE_TYPE (decl)); > @@ -938,7 +967,7 @@ namespace { > > const pass_data pass_data_ipa_increase_alignment = > { > - SIMPLE_IPA_PASS, /* type */ > + IPA_PASS, /* type */ > "increase_alignment", /* name */ > OPTGROUP_LOOP | OPTGROUP_VEC, /* optinfo_flags */ > TV_IPA_OPT, /* tv_id */ > @@ -949,17 +978,26 @@ const pass_data pass_data_ipa_increase_alignment = > 0, /* todo_flags_finish */ > }; > > -class pass_ipa_increase_alignment : public simple_ipa_opt_pass > +class pass_ipa_increase_alignment : public ipa_opt_pass_d > { > public: > pass_ipa_increase_alignment (gcc::context *ctxt) > - : simple_ipa_opt_pass (pass_data_ipa_increase_alignment, ctxt) > + : ipa_opt_pass_d (pass_data_ipa_increase_alignment, ctxt, > + NULL, /* generate_summary */ > + NULL, /* write summary */ > + NULL, /* read summary */ > + NULL, /* write optimization summary */ > + NULL, /* read optimization summary */ > + NULL, /* stmt fixup */ > + 0, /* function_transform_todo_flags_start */ > + NULL, /* transform function */ > + NULL )/* variable transform */ > {} > > /* opt_pass methods: */ > virtual bool gate (function *) > { > - return flag_section_anchors && flag_tree_loop_vectorize; > + return flag_section_anchors != 0; > } > > virtual unsigned int execute (function *) { return increase_alignment (); } > @@ -968,7 +1006,7 @@ public: > > } // anon namespace > > -simple_ipa_opt_pass * > +ipa_opt_pass_d * > make_pass_ipa_increase_alignment (gcc::context *ctxt) > { > return new pass_ipa_increase_alignment (ctxt);
On 10 June 2016 at 01:53, Jan Hubicka <hubicka@ucw.cz> wrote: >> On 8 June 2016 at 20:38, Jan Hubicka <hubicka@ucw.cz> wrote: >> >> I think it would be nice to work towards transitioning >> >> flag_section_anchors to a flag on varpool nodes, thereby removing >> >> the Optimization flag from common.opt:fsection-anchors >> >> >> >> That would simplify the walk over varpool candidates. >> > >> > Makes sense to me, too. There are more candidates for sutff that should be >> > variable specific in common.opt (such as variable alignment, -fdata-sctions, >> > -fmerge-constants) and targets. We may try to do it in an easy to extend way >> > so incrementally we can get rid of those global flags, too. >> In this version I removed Optimization from fsection-anchors entry in >> common.opt, >> and gated the increase_alignment pass on flag_section_anchors != 0. >> Cross tested on arm*-*-*, aarch64*-*-*. >> Does it look OK ? > > If you go this way you will need to do something sane for LTO. Here one can compile > some object files with -fsection-anchors and other without and link with random setting > (because in traditional compilation linktime flags does not matter). > > For global flags we have magic in merge_and_complain that determines flags to pass > to the LTO compiler. > It is not very robust though. >> > >> > One thing that needs to be done for LTO is sane merging, I guess in this case >> > it is clear that the variable should be anchored when its previaling definition >> > is. >> Um could we determine during WPA if symbol is a section anchor for merging ? >> Seems to me SYMBOL_REF_ANCHOR_P is defined only on DECL_RTL and not at >> tree level. >> Do we have DECL_RTL info available during WPA ? > > We don't have anchros computed, but we can decide whether we want to potentially > anchor the variable if we can. > > I would say all you need is to have section_anchor flag in varpool node itself > which controls RTL production. At varpool_finalize_decl you will set it > according to flag_varpool and stream it to LTO objects. At WPA when doing > linking, the section_anchor flag of the previaling decl wins.. Thanks for the suggestions. IIUC, we want to add new section_anchor flag to varpool_node class and set it in varpool_node::finalize_decl and stream it to LTO byte-code, and then during WPA set section_anchor_flag during symbol merging if it is set for prevailing decl. In the increase_alignment_pass if a vnode has section_anchor flag set, we will walk all functions that reference it to check if they have -ftree-loop-vectorize set. Is that correct ? Could you please elaborate a bit more on "at varpool_finalize_decl you will set section_anchor flag according to flag_varpool" ? flag_varpool doesn't appear to be defined. Thanks, Prathamesh > > Honza >> >> Thanks, >> Prathamesh >> > >> > Honza >> >> >> >> Richard. >> >> >> >> > Thanks, >> >> > Prathamesh >> >> > > >> >> > > Honza >> >> > >> >> >> > >> Richard. >> >> > >> >> > >> >> >> >> -- >> >> Richard Biener <rguenther@suse.de> >> >> SUSE LINUX GmbH, GF: Felix Imendoerffer, Jane Smithard, Graham Norton, HRB 21284 (AG Nuernberg) > >> diff --git a/gcc/common.opt b/gcc/common.opt >> index f0d7196..f93f26c 100644 >> --- a/gcc/common.opt >> +++ b/gcc/common.opt >> @@ -2133,7 +2133,7 @@ Common Report Var(flag_sched_dep_count_heuristic) Init(1) Optimization >> Enable the dependent count heuristic in the scheduler. >> >> fsection-anchors >> -Common Report Var(flag_section_anchors) Optimization >> +Common Report Var(flag_section_anchors) >> Access data in the same section from shared anchor points. >> >> fsee >> diff --git a/gcc/passes.def b/gcc/passes.def >> index 3647e90..3a8063c 100644 >> --- a/gcc/passes.def >> +++ b/gcc/passes.def >> @@ -138,12 +138,12 @@ along with GCC; see the file COPYING3. If not see >> PUSH_INSERT_PASSES_WITHIN (pass_ipa_tree_profile) >> NEXT_PASS (pass_feedback_split_functions); >> POP_INSERT_PASSES () >> - NEXT_PASS (pass_ipa_increase_alignment); >> NEXT_PASS (pass_ipa_tm); >> NEXT_PASS (pass_ipa_lower_emutls); >> TERMINATE_PASS_LIST (all_small_ipa_passes) >> >> INSERT_PASSES_AFTER (all_regular_ipa_passes) >> + NEXT_PASS (pass_ipa_increase_alignment); >> NEXT_PASS (pass_ipa_whole_program_visibility); >> NEXT_PASS (pass_ipa_profile); >> NEXT_PASS (pass_ipa_icf); >> diff --git a/gcc/testsuite/gcc.dg/vect/aligned-section-anchors-vect-73.c b/gcc/testsuite/gcc.dg/vect/aligned-section-anchors-vect-73.c >> new file mode 100644 >> index 0000000..74eaed8 >> --- /dev/null >> +++ b/gcc/testsuite/gcc.dg/vect/aligned-section-anchors-vect-73.c >> @@ -0,0 +1,25 @@ >> +/* { dg-do compile } */ >> +/* { dg-require-effective-target section_anchors } */ >> +/* { dg-require-effective-target vect_int } */ >> + >> +#define N 32 >> + >> +/* Clone of section-anchors-vect-70.c with foo() having -fno-tree-loop-vectorize. */ >> + >> +static struct A { >> + int p1, p2; >> + int e[N]; >> +} a, b, c; >> + >> +__attribute__((optimize("-fno-tree-loop-vectorize"))) >> +int foo(void) >> +{ >> + for (int i = 0; i < N; i++) >> + a.e[i] = b.e[i] + c.e[i]; >> + >> + return a.e[0]; >> +} >> + >> +/* { dg-final { scan-ipa-dump-times "Increasing alignment of decl" 0 "increase_alignment" { target aarch64*-*-* } } } */ >> +/* { dg-final { scan-ipa-dump-times "Increasing alignment of decl" 0 "increase_alignment" { target powerpc64*-*-* } } } */ >> +/* { dg-final { scan-ipa-dump-times "Increasing alignment of decl" 0 "increase_alignment" { target arm*-*-* } } } */ >> diff --git a/gcc/tree-pass.h b/gcc/tree-pass.h >> index 36299a6..d36aa1d 100644 >> --- a/gcc/tree-pass.h >> +++ b/gcc/tree-pass.h >> @@ -483,7 +483,7 @@ extern simple_ipa_opt_pass *make_pass_local_optimization_passes (gcc::context *c >> >> extern ipa_opt_pass_d *make_pass_ipa_whole_program_visibility (gcc::context >> *ctxt); >> -extern simple_ipa_opt_pass *make_pass_ipa_increase_alignment (gcc::context >> +extern ipa_opt_pass_d *make_pass_ipa_increase_alignment (gcc::context >> *ctxt); >> extern ipa_opt_pass_d *make_pass_ipa_inline (gcc::context *ctxt); >> extern simple_ipa_opt_pass *make_pass_ipa_free_lang_data (gcc::context *ctxt); >> diff --git a/gcc/tree-vectorizer.c b/gcc/tree-vectorizer.c >> index 2669813..d34e560 100644 >> --- a/gcc/tree-vectorizer.c >> +++ b/gcc/tree-vectorizer.c >> @@ -899,6 +899,34 @@ get_vec_alignment_for_type (tree type) >> return (alignment > TYPE_ALIGN (type)) ? alignment : 0; >> } >> >> +/* Return true if alignment should be increased for this vnode. >> + This is done if every function that references/referring to vnode >> + has flag_tree_loop_vectorize and flag_section_anchors set. */ >> + >> +static bool >> +increase_alignment_p (varpool_node *vnode) >> +{ >> + ipa_ref *ref; >> + >> + for (int i = 0; vnode->iterate_reference (i, ref); i++) >> + if (cgraph_node *cnode = dyn_cast<cgraph_node *> (ref->referred)) >> + { >> + struct cl_optimization *opts = opts_for_fn (cnode->decl); >> + if (!opts->x_flag_tree_loop_vectorize) >> + return false; >> + } >> + >> + for (int i = 0; vnode->iterate_referring (i, ref); i++) >> + if (cgraph_node *cnode = dyn_cast<cgraph_node *> (ref->referring)) >> + { >> + struct cl_optimization *opts = opts_for_fn (cnode->decl); >> + if (!opts->x_flag_tree_loop_vectorize) >> + return false; >> + } >> + >> + return true; >> +} >> + >> /* Entry point to increase_alignment pass. */ >> static unsigned int >> increase_alignment (void) >> @@ -916,7 +944,8 @@ increase_alignment (void) >> >> if ((decl_in_symtab_p (decl) >> && !symtab_node::get (decl)->can_increase_alignment_p ()) >> - || DECL_USER_ALIGN (decl) || DECL_ARTIFICIAL (decl)) >> + || DECL_USER_ALIGN (decl) || DECL_ARTIFICIAL (decl) >> + || !increase_alignment_p (vnode)) >> continue; >> >> alignment = get_vec_alignment_for_type (TREE_TYPE (decl)); >> @@ -938,7 +967,7 @@ namespace { >> >> const pass_data pass_data_ipa_increase_alignment = >> { >> - SIMPLE_IPA_PASS, /* type */ >> + IPA_PASS, /* type */ >> "increase_alignment", /* name */ >> OPTGROUP_LOOP | OPTGROUP_VEC, /* optinfo_flags */ >> TV_IPA_OPT, /* tv_id */ >> @@ -949,17 +978,26 @@ const pass_data pass_data_ipa_increase_alignment = >> 0, /* todo_flags_finish */ >> }; >> >> -class pass_ipa_increase_alignment : public simple_ipa_opt_pass >> +class pass_ipa_increase_alignment : public ipa_opt_pass_d >> { >> public: >> pass_ipa_increase_alignment (gcc::context *ctxt) >> - : simple_ipa_opt_pass (pass_data_ipa_increase_alignment, ctxt) >> + : ipa_opt_pass_d (pass_data_ipa_increase_alignment, ctxt, >> + NULL, /* generate_summary */ >> + NULL, /* write summary */ >> + NULL, /* read summary */ >> + NULL, /* write optimization summary */ >> + NULL, /* read optimization summary */ >> + NULL, /* stmt fixup */ >> + 0, /* function_transform_todo_flags_start */ >> + NULL, /* transform function */ >> + NULL )/* variable transform */ >> {} >> >> /* opt_pass methods: */ >> virtual bool gate (function *) >> { >> - return flag_section_anchors && flag_tree_loop_vectorize; >> + return flag_section_anchors != 0; >> } >> >> virtual unsigned int execute (function *) { return increase_alignment (); } >> @@ -968,7 +1006,7 @@ public: >> >> } // anon namespace >> >> -simple_ipa_opt_pass * >> +ipa_opt_pass_d * >> make_pass_ipa_increase_alignment (gcc::context *ctxt) >> { >> return new pass_ipa_increase_alignment (ctxt); >
On Fri, 10 Jun 2016, Prathamesh Kulkarni wrote: > On 10 June 2016 at 01:53, Jan Hubicka <hubicka@ucw.cz> wrote: > >> On 8 June 2016 at 20:38, Jan Hubicka <hubicka@ucw.cz> wrote: > >> >> I think it would be nice to work towards transitioning > >> >> flag_section_anchors to a flag on varpool nodes, thereby removing > >> >> the Optimization flag from common.opt:fsection-anchors > >> >> > >> >> That would simplify the walk over varpool candidates. > >> > > >> > Makes sense to me, too. There are more candidates for sutff that should be > >> > variable specific in common.opt (such as variable alignment, -fdata-sctions, > >> > -fmerge-constants) and targets. We may try to do it in an easy to extend way > >> > so incrementally we can get rid of those global flags, too. > >> In this version I removed Optimization from fsection-anchors entry in > >> common.opt, > >> and gated the increase_alignment pass on flag_section_anchors != 0. > >> Cross tested on arm*-*-*, aarch64*-*-*. > >> Does it look OK ? > > > > If you go this way you will need to do something sane for LTO. Here one can compile > > some object files with -fsection-anchors and other without and link with random setting > > (because in traditional compilation linktime flags does not matter). > > > > For global flags we have magic in merge_and_complain that determines flags to pass > > to the LTO compiler. > > It is not very robust though. > >> > > >> > One thing that needs to be done for LTO is sane merging, I guess in this case > >> > it is clear that the variable should be anchored when its previaling definition > >> > is. > >> Um could we determine during WPA if symbol is a section anchor for merging ? > >> Seems to me SYMBOL_REF_ANCHOR_P is defined only on DECL_RTL and not at > >> tree level. > >> Do we have DECL_RTL info available during WPA ? > > > > We don't have anchros computed, but we can decide whether we want to potentially > > anchor the variable if we can. > > > > I would say all you need is to have section_anchor flag in varpool node itself > > which controls RTL production. At varpool_finalize_decl you will set it > > according to flag_varpool and stream it to LTO objects. At WPA when doing > > linking, the section_anchor flag of the previaling decl wins.. > Thanks for the suggestions. > IIUC, we want to add new section_anchor flag to varpool_node class > and set it in varpool_node::finalize_decl and stream it to LTO byte-code, > and then during WPA set section_anchor_flag during symbol merging if it is set > for prevailing decl. Yes. > In the increase_alignment_pass if a vnode has section_anchor flag set, > we will walk all functions that reference it to check if they have > -ftree-loop-vectorize set. > Is that correct ? Yes. > Could you please elaborate a bit more on "at varpool_finalize_decl you will > set section_anchor flag according to flag_varpool" ? > flag_varpool doesn't appear to be defined. flag_section_anchors. Richard. > Thanks, > Prathamesh > > > > Honza > >> > >> Thanks, > >> Prathamesh > >> > > >> > Honza > >> >> > >> >> Richard. > >> >> > >> >> > Thanks, > >> >> > Prathamesh > >> >> > > > >> >> > > Honza > >> >> > >> > >> >> > >> Richard. > >> >> > > >> >> > > >> >> > >> >> -- > >> >> Richard Biener <rguenther@suse.de> > >> >> SUSE LINUX GmbH, GF: Felix Imendoerffer, Jane Smithard, Graham Norton, HRB 21284 (AG Nuernberg) > > > >> diff --git a/gcc/common.opt b/gcc/common.opt > >> index f0d7196..f93f26c 100644 > >> --- a/gcc/common.opt > >> +++ b/gcc/common.opt > >> @@ -2133,7 +2133,7 @@ Common Report Var(flag_sched_dep_count_heuristic) Init(1) Optimization > >> Enable the dependent count heuristic in the scheduler. > >> > >> fsection-anchors > >> -Common Report Var(flag_section_anchors) Optimization > >> +Common Report Var(flag_section_anchors) > >> Access data in the same section from shared anchor points. > >> > >> fsee > >> diff --git a/gcc/passes.def b/gcc/passes.def > >> index 3647e90..3a8063c 100644 > >> --- a/gcc/passes.def > >> +++ b/gcc/passes.def > >> @@ -138,12 +138,12 @@ along with GCC; see the file COPYING3. If not see > >> PUSH_INSERT_PASSES_WITHIN (pass_ipa_tree_profile) > >> NEXT_PASS (pass_feedback_split_functions); > >> POP_INSERT_PASSES () > >> - NEXT_PASS (pass_ipa_increase_alignment); > >> NEXT_PASS (pass_ipa_tm); > >> NEXT_PASS (pass_ipa_lower_emutls); > >> TERMINATE_PASS_LIST (all_small_ipa_passes) > >> > >> INSERT_PASSES_AFTER (all_regular_ipa_passes) > >> + NEXT_PASS (pass_ipa_increase_alignment); > >> NEXT_PASS (pass_ipa_whole_program_visibility); > >> NEXT_PASS (pass_ipa_profile); > >> NEXT_PASS (pass_ipa_icf); > >> diff --git a/gcc/testsuite/gcc.dg/vect/aligned-section-anchors-vect-73.c b/gcc/testsuite/gcc.dg/vect/aligned-section-anchors-vect-73.c > >> new file mode 100644 > >> index 0000000..74eaed8 > >> --- /dev/null > >> +++ b/gcc/testsuite/gcc.dg/vect/aligned-section-anchors-vect-73.c > >> @@ -0,0 +1,25 @@ > >> +/* { dg-do compile } */ > >> +/* { dg-require-effective-target section_anchors } */ > >> +/* { dg-require-effective-target vect_int } */ > >> + > >> +#define N 32 > >> + > >> +/* Clone of section-anchors-vect-70.c with foo() having -fno-tree-loop-vectorize. */ > >> + > >> +static struct A { > >> + int p1, p2; > >> + int e[N]; > >> +} a, b, c; > >> + > >> +__attribute__((optimize("-fno-tree-loop-vectorize"))) > >> +int foo(void) > >> +{ > >> + for (int i = 0; i < N; i++) > >> + a.e[i] = b.e[i] + c.e[i]; > >> + > >> + return a.e[0]; > >> +} > >> + > >> +/* { dg-final { scan-ipa-dump-times "Increasing alignment of decl" 0 "increase_alignment" { target aarch64*-*-* } } } */ > >> +/* { dg-final { scan-ipa-dump-times "Increasing alignment of decl" 0 "increase_alignment" { target powerpc64*-*-* } } } */ > >> +/* { dg-final { scan-ipa-dump-times "Increasing alignment of decl" 0 "increase_alignment" { target arm*-*-* } } } */ > >> diff --git a/gcc/tree-pass.h b/gcc/tree-pass.h > >> index 36299a6..d36aa1d 100644 > >> --- a/gcc/tree-pass.h > >> +++ b/gcc/tree-pass.h > >> @@ -483,7 +483,7 @@ extern simple_ipa_opt_pass *make_pass_local_optimization_passes (gcc::context *c > >> > >> extern ipa_opt_pass_d *make_pass_ipa_whole_program_visibility (gcc::context > >> *ctxt); > >> -extern simple_ipa_opt_pass *make_pass_ipa_increase_alignment (gcc::context > >> +extern ipa_opt_pass_d *make_pass_ipa_increase_alignment (gcc::context > >> *ctxt); > >> extern ipa_opt_pass_d *make_pass_ipa_inline (gcc::context *ctxt); > >> extern simple_ipa_opt_pass *make_pass_ipa_free_lang_data (gcc::context *ctxt); > >> diff --git a/gcc/tree-vectorizer.c b/gcc/tree-vectorizer.c > >> index 2669813..d34e560 100644 > >> --- a/gcc/tree-vectorizer.c > >> +++ b/gcc/tree-vectorizer.c > >> @@ -899,6 +899,34 @@ get_vec_alignment_for_type (tree type) > >> return (alignment > TYPE_ALIGN (type)) ? alignment : 0; > >> } > >> > >> +/* Return true if alignment should be increased for this vnode. > >> + This is done if every function that references/referring to vnode > >> + has flag_tree_loop_vectorize and flag_section_anchors set. */ > >> + > >> +static bool > >> +increase_alignment_p (varpool_node *vnode) > >> +{ > >> + ipa_ref *ref; > >> + > >> + for (int i = 0; vnode->iterate_reference (i, ref); i++) > >> + if (cgraph_node *cnode = dyn_cast<cgraph_node *> (ref->referred)) > >> + { > >> + struct cl_optimization *opts = opts_for_fn (cnode->decl); > >> + if (!opts->x_flag_tree_loop_vectorize) > >> + return false; > >> + } > >> + > >> + for (int i = 0; vnode->iterate_referring (i, ref); i++) > >> + if (cgraph_node *cnode = dyn_cast<cgraph_node *> (ref->referring)) > >> + { > >> + struct cl_optimization *opts = opts_for_fn (cnode->decl); > >> + if (!opts->x_flag_tree_loop_vectorize) > >> + return false; > >> + } > >> + > >> + return true; > >> +} > >> + > >> /* Entry point to increase_alignment pass. */ > >> static unsigned int > >> increase_alignment (void) > >> @@ -916,7 +944,8 @@ increase_alignment (void) > >> > >> if ((decl_in_symtab_p (decl) > >> && !symtab_node::get (decl)->can_increase_alignment_p ()) > >> - || DECL_USER_ALIGN (decl) || DECL_ARTIFICIAL (decl)) > >> + || DECL_USER_ALIGN (decl) || DECL_ARTIFICIAL (decl) > >> + || !increase_alignment_p (vnode)) > >> continue; > >> > >> alignment = get_vec_alignment_for_type (TREE_TYPE (decl)); > >> @@ -938,7 +967,7 @@ namespace { > >> > >> const pass_data pass_data_ipa_increase_alignment = > >> { > >> - SIMPLE_IPA_PASS, /* type */ > >> + IPA_PASS, /* type */ > >> "increase_alignment", /* name */ > >> OPTGROUP_LOOP | OPTGROUP_VEC, /* optinfo_flags */ > >> TV_IPA_OPT, /* tv_id */ > >> @@ -949,17 +978,26 @@ const pass_data pass_data_ipa_increase_alignment = > >> 0, /* todo_flags_finish */ > >> }; > >> > >> -class pass_ipa_increase_alignment : public simple_ipa_opt_pass > >> +class pass_ipa_increase_alignment : public ipa_opt_pass_d > >> { > >> public: > >> pass_ipa_increase_alignment (gcc::context *ctxt) > >> - : simple_ipa_opt_pass (pass_data_ipa_increase_alignment, ctxt) > >> + : ipa_opt_pass_d (pass_data_ipa_increase_alignment, ctxt, > >> + NULL, /* generate_summary */ > >> + NULL, /* write summary */ > >> + NULL, /* read summary */ > >> + NULL, /* write optimization summary */ > >> + NULL, /* read optimization summary */ > >> + NULL, /* stmt fixup */ > >> + 0, /* function_transform_todo_flags_start */ > >> + NULL, /* transform function */ > >> + NULL )/* variable transform */ > >> {} > >> > >> /* opt_pass methods: */ > >> virtual bool gate (function *) > >> { > >> - return flag_section_anchors && flag_tree_loop_vectorize; > >> + return flag_section_anchors != 0; > >> } > >> > >> virtual unsigned int execute (function *) { return increase_alignment (); } > >> @@ -968,7 +1006,7 @@ public: > >> > >> } // anon namespace > >> > >> -simple_ipa_opt_pass * > >> +ipa_opt_pass_d * > >> make_pass_ipa_increase_alignment (gcc::context *ctxt) > >> { > >> return new pass_ipa_increase_alignment (ctxt); > > > >
diff --git a/gcc/common.opt b/gcc/common.opt index f0d7196..f93f26c 100644 --- a/gcc/common.opt +++ b/gcc/common.opt @@ -2133,7 +2133,7 @@ Common Report Var(flag_sched_dep_count_heuristic) Init(1) Optimization Enable the dependent count heuristic in the scheduler. fsection-anchors -Common Report Var(flag_section_anchors) Optimization +Common Report Var(flag_section_anchors) Access data in the same section from shared anchor points. fsee diff --git a/gcc/passes.def b/gcc/passes.def index 3647e90..3a8063c 100644 --- a/gcc/passes.def +++ b/gcc/passes.def @@ -138,12 +138,12 @@ along with GCC; see the file COPYING3. If not see PUSH_INSERT_PASSES_WITHIN (pass_ipa_tree_profile) NEXT_PASS (pass_feedback_split_functions); POP_INSERT_PASSES () - NEXT_PASS (pass_ipa_increase_alignment); NEXT_PASS (pass_ipa_tm); NEXT_PASS (pass_ipa_lower_emutls); TERMINATE_PASS_LIST (all_small_ipa_passes) INSERT_PASSES_AFTER (all_regular_ipa_passes) + NEXT_PASS (pass_ipa_increase_alignment); NEXT_PASS (pass_ipa_whole_program_visibility); NEXT_PASS (pass_ipa_profile); NEXT_PASS (pass_ipa_icf); diff --git a/gcc/testsuite/gcc.dg/vect/aligned-section-anchors-vect-73.c b/gcc/testsuite/gcc.dg/vect/aligned-section-anchors-vect-73.c new file mode 100644 index 0000000..74eaed8 --- /dev/null +++ b/gcc/testsuite/gcc.dg/vect/aligned-section-anchors-vect-73.c @@ -0,0 +1,25 @@ +/* { dg-do compile } */ +/* { dg-require-effective-target section_anchors } */ +/* { dg-require-effective-target vect_int } */ + +#define N 32 + +/* Clone of section-anchors-vect-70.c with foo() having -fno-tree-loop-vectorize. */ + +static struct A { + int p1, p2; + int e[N]; +} a, b, c; + +__attribute__((optimize("-fno-tree-loop-vectorize"))) +int foo(void) +{ + for (int i = 0; i < N; i++) + a.e[i] = b.e[i] + c.e[i]; + + return a.e[0]; +} + +/* { dg-final { scan-ipa-dump-times "Increasing alignment of decl" 0 "increase_alignment" { target aarch64*-*-* } } } */ +/* { dg-final { scan-ipa-dump-times "Increasing alignment of decl" 0 "increase_alignment" { target powerpc64*-*-* } } } */ +/* { dg-final { scan-ipa-dump-times "Increasing alignment of decl" 0 "increase_alignment" { target arm*-*-* } } } */ diff --git a/gcc/tree-pass.h b/gcc/tree-pass.h index 36299a6..d36aa1d 100644 --- a/gcc/tree-pass.h +++ b/gcc/tree-pass.h @@ -483,7 +483,7 @@ extern simple_ipa_opt_pass *make_pass_local_optimization_passes (gcc::context *c extern ipa_opt_pass_d *make_pass_ipa_whole_program_visibility (gcc::context *ctxt); -extern simple_ipa_opt_pass *make_pass_ipa_increase_alignment (gcc::context +extern ipa_opt_pass_d *make_pass_ipa_increase_alignment (gcc::context *ctxt); extern ipa_opt_pass_d *make_pass_ipa_inline (gcc::context *ctxt); extern simple_ipa_opt_pass *make_pass_ipa_free_lang_data (gcc::context *ctxt); diff --git a/gcc/tree-vectorizer.c b/gcc/tree-vectorizer.c index 2669813..d34e560 100644 --- a/gcc/tree-vectorizer.c +++ b/gcc/tree-vectorizer.c @@ -899,6 +899,34 @@ get_vec_alignment_for_type (tree type) return (alignment > TYPE_ALIGN (type)) ? alignment : 0; } +/* Return true if alignment should be increased for this vnode. + This is done if every function that references/referring to vnode + has flag_tree_loop_vectorize and flag_section_anchors set. */ + +static bool +increase_alignment_p (varpool_node *vnode) +{ + ipa_ref *ref; + + for (int i = 0; vnode->iterate_reference (i, ref); i++) + if (cgraph_node *cnode = dyn_cast<cgraph_node *> (ref->referred)) + { + struct cl_optimization *opts = opts_for_fn (cnode->decl); + if (!opts->x_flag_tree_loop_vectorize) + return false; + } + + for (int i = 0; vnode->iterate_referring (i, ref); i++) + if (cgraph_node *cnode = dyn_cast<cgraph_node *> (ref->referring)) + { + struct cl_optimization *opts = opts_for_fn (cnode->decl); + if (!opts->x_flag_tree_loop_vectorize) + return false; + } + + return true; +} + /* Entry point to increase_alignment pass. */ static unsigned int increase_alignment (void) @@ -916,7 +944,8 @@ increase_alignment (void) if ((decl_in_symtab_p (decl) && !symtab_node::get (decl)->can_increase_alignment_p ()) - || DECL_USER_ALIGN (decl) || DECL_ARTIFICIAL (decl)) + || DECL_USER_ALIGN (decl) || DECL_ARTIFICIAL (decl) + || !increase_alignment_p (vnode)) continue; alignment = get_vec_alignment_for_type (TREE_TYPE (decl)); @@ -938,7 +967,7 @@ namespace { const pass_data pass_data_ipa_increase_alignment = { - SIMPLE_IPA_PASS, /* type */ + IPA_PASS, /* type */ "increase_alignment", /* name */ OPTGROUP_LOOP | OPTGROUP_VEC, /* optinfo_flags */ TV_IPA_OPT, /* tv_id */ @@ -949,17 +978,26 @@ const pass_data pass_data_ipa_increase_alignment = 0, /* todo_flags_finish */ }; -class pass_ipa_increase_alignment : public simple_ipa_opt_pass +class pass_ipa_increase_alignment : public ipa_opt_pass_d { public: pass_ipa_increase_alignment (gcc::context *ctxt) - : simple_ipa_opt_pass (pass_data_ipa_increase_alignment, ctxt) + : ipa_opt_pass_d (pass_data_ipa_increase_alignment, ctxt, + NULL, /* generate_summary */ + NULL, /* write summary */ + NULL, /* read summary */ + NULL, /* write optimization summary */ + NULL, /* read optimization summary */ + NULL, /* stmt fixup */ + 0, /* function_transform_todo_flags_start */ + NULL, /* transform function */ + NULL )/* variable transform */ {} /* opt_pass methods: */ virtual bool gate (function *) { - return flag_section_anchors && flag_tree_loop_vectorize; + return flag_section_anchors != 0; } virtual unsigned int execute (function *) { return increase_alignment (); } @@ -968,7 +1006,7 @@ public: } // anon namespace -simple_ipa_opt_pass * +ipa_opt_pass_d * make_pass_ipa_increase_alignment (gcc::context *ctxt) { return new pass_ipa_increase_alignment (ctxt);