| Message ID | 20171211211051.GR2353@tucnak |
|---|---|
| State | New |
| Headers | show |
| Series | Handle LOOP_DIST_ALIAS ifns in move_sese_region_to_fn (PR tree-optimization/83359) | expand |
On Mon, 11 Dec 2017, Jakub Jelinek wrote: > Hi! > > Unlike LOOP_VECTORIZED ifns, LOOP_DIST_ALIAS is added by the ldist pass > and needs to be maintained until the vectorizer, and parloops in between > that. Earlier I've added code to update or drop orig_loop_num during > move_sese_region_to_fn, but that is not sufficient. If we move > the whole pair of loops with the associated LOOP_DIST_ALIAS call into > the outlined loopfn, we need to update the first argument, as orig_loop_num > is likely changing. If the whole triplet (two loops with orig_loop_num > and LOOP_DIST_ALIAS with the same first argument) stays in parent function, > we don't need to adjust it. In all other cases, this patch folds the > LOOP_DIST_ALIAS ifn to the second argument, like the vectorizer does if > it fails to vectorize it. > > Bootstrapped/regtested on x86_64-linux, i686-linux, powerpc64le-linux, > bootstrapped on powerpc64-linux, regtest there pending. Ok for trunk? Ok. Thanks, Richard. > 2017-12-11 Jakub Jelinek <jakub@redhat.com> > > PR tree-optimization/83359 > * tree-cfg.h (fold_loop_internal_call): Declare. > * tree-vectorizer.c (fold_loop_internal_call): Moved to ... > * tree-cfg.c (fold_loop_internal_call): ... here. No longer static. > (find_loop_dist_alias): New function. > (move_sese_region_to_fn): If any dloop->orig_loop_num value is > updated, also adjust any corresponding LOOP_DIST_ALIAS internal > calls. > > * gcc.dg/graphite/pr83359.c: New test. > > --- gcc/tree-cfg.h.jj 2017-09-05 23:28:14.000000000 +0200 > +++ gcc/tree-cfg.h 2017-12-11 12:35:24.284777550 +0100 > @@ -77,6 +77,7 @@ extern void gather_blocks_in_sese_region > vec<basic_block> *bbs_p); > extern void verify_sese (basic_block, basic_block, vec<basic_block> *); > extern bool gather_ssa_name_hash_map_from (tree const &, tree const &, void *); > +extern void fold_loop_internal_call (gimple *, tree); > extern basic_block move_sese_region_to_fn (struct function *, basic_block, > basic_block, tree); > extern void dump_function_to_file (tree, FILE *, dump_flags_t); > --- gcc/tree-vectorizer.c.jj 2017-09-01 09:26:37.000000000 +0200 > +++ gcc/tree-vectorizer.c 2017-12-11 12:33:41.436055580 +0100 > @@ -464,27 +464,6 @@ vect_loop_vectorized_call (struct loop * > return NULL; > } > > -/* Fold loop internal call G like IFN_LOOP_VECTORIZED/IFN_LOOP_DIST_ALIAS > - to VALUE and update any immediate uses of it's LHS. */ > - > -static void > -fold_loop_internal_call (gimple *g, tree value) > -{ > - tree lhs = gimple_call_lhs (g); > - use_operand_p use_p; > - imm_use_iterator iter; > - gimple *use_stmt; > - gimple_stmt_iterator gsi = gsi_for_stmt (g); > - > - update_call_from_tree (&gsi, value); > - FOR_EACH_IMM_USE_STMT (use_stmt, iter, lhs) > - { > - FOR_EACH_IMM_USE_ON_STMT (use_p, iter) > - SET_USE (use_p, value); > - update_stmt (use_stmt); > - } > -} > - > /* If LOOP has been versioned during loop distribution, return the gurading > internal call. */ > > --- gcc/tree-cfg.c.jj 2017-12-07 18:05:30.000000000 +0100 > +++ gcc/tree-cfg.c 2017-12-11 12:34:55.054140750 +0100 > @@ -7337,6 +7337,47 @@ gather_ssa_name_hash_map_from (tree cons > return true; > } > > +/* Return LOOP_DIST_ALIAS call if present in BB. */ > + > +static gimple * > +find_loop_dist_alias (basic_block bb) > +{ > + gimple *g = last_stmt (bb); > + if (g == NULL || gimple_code (g) != GIMPLE_COND) > + return NULL; > + > + gimple_stmt_iterator gsi = gsi_for_stmt (g); > + gsi_prev (&gsi); > + if (gsi_end_p (gsi)) > + return NULL; > + > + g = gsi_stmt (gsi); > + if (gimple_call_internal_p (g, IFN_LOOP_DIST_ALIAS)) > + return g; > + return NULL; > +} > + > +/* Fold loop internal call G like IFN_LOOP_VECTORIZED/IFN_LOOP_DIST_ALIAS > + to VALUE and update any immediate uses of it's LHS. */ > + > +void > +fold_loop_internal_call (gimple *g, tree value) > +{ > + tree lhs = gimple_call_lhs (g); > + use_operand_p use_p; > + imm_use_iterator iter; > + gimple *use_stmt; > + gimple_stmt_iterator gsi = gsi_for_stmt (g); > + > + update_call_from_tree (&gsi, value); > + FOR_EACH_IMM_USE_STMT (use_stmt, iter, lhs) > + { > + FOR_EACH_IMM_USE_ON_STMT (use_p, iter) > + SET_USE (use_p, value); > + update_stmt (use_stmt); > + } > +} > + > /* Move a single-entry, single-exit region delimited by ENTRY_BB and > EXIT_BB to function DEST_CFUN. The whole region is replaced by a > single basic block in the original CFG and the new basic block is > @@ -7510,7 +7551,6 @@ move_sese_region_to_fn (struct function > } > } > > - > /* Adjust the number of blocks in the tree root of the outlined part. */ > get_loop (dest_cfun, 0)->num_nodes = bbs.length () + 2; > > @@ -7521,19 +7561,77 @@ move_sese_region_to_fn (struct function > /* Fix up orig_loop_num. If the block referenced in it has been moved > to dest_cfun, update orig_loop_num field, otherwise clear it. */ > struct loop *dloop; > + signed char *moved_orig_loop_num = NULL; > FOR_EACH_LOOP_FN (dest_cfun, dloop, 0) > if (dloop->orig_loop_num) > { > + if (moved_orig_loop_num == NULL) > + moved_orig_loop_num > + = XCNEWVEC (signed char, vec_safe_length (larray)); > if ((*larray)[dloop->orig_loop_num] != NULL > && get_loop (saved_cfun, dloop->orig_loop_num) == NULL) > - dloop->orig_loop_num = (*larray)[dloop->orig_loop_num]->num; > + { > + if (moved_orig_loop_num[dloop->orig_loop_num] >= 0 > + && moved_orig_loop_num[dloop->orig_loop_num] < 2) > + moved_orig_loop_num[dloop->orig_loop_num]++; > + dloop->orig_loop_num = (*larray)[dloop->orig_loop_num]->num; > + } > else > - dloop->orig_loop_num = 0; > + { > + moved_orig_loop_num[dloop->orig_loop_num] = -1; > + dloop->orig_loop_num = 0; > + } > } > - ggc_free (larray); > - > pop_cfun (); > > + if (moved_orig_loop_num) > + { > + FOR_EACH_VEC_ELT (bbs, i, bb) > + { > + gimple *g = find_loop_dist_alias (bb); > + if (g == NULL) > + continue; > + > + int orig_loop_num = tree_to_shwi (gimple_call_arg (g, 0)); > + gcc_assert (orig_loop_num > + && (unsigned) orig_loop_num < vec_safe_length (larray)); > + if (moved_orig_loop_num[orig_loop_num] == 2) > + { > + /* If we have moved both loops with this orig_loop_num into > + dest_cfun and the LOOP_DIST_ALIAS call is being moved there > + too, update the first argument. */ > + gcc_assert ((*larray)[dloop->orig_loop_num] != NULL > + && (get_loop (saved_cfun, dloop->orig_loop_num) > + == NULL)); > + tree t = build_int_cst (integer_type_node, > + (*larray)[dloop->orig_loop_num]->num); > + gimple_call_set_arg (g, 0, t); > + update_stmt (g); > + /* Make sure the following loop will not update it. */ > + moved_orig_loop_num[orig_loop_num] = 0; > + } > + else > + /* Otherwise at least one of the loops stayed in saved_cfun. > + Remove the LOOP_DIST_ALIAS call. */ > + fold_loop_internal_call (g, gimple_call_arg (g, 1)); > + } > + FOR_EACH_BB_FN (bb, saved_cfun) > + { > + gimple *g = find_loop_dist_alias (bb); > + if (g == NULL) > + continue; > + int orig_loop_num = tree_to_shwi (gimple_call_arg (g, 0)); > + gcc_assert (orig_loop_num > + && (unsigned) orig_loop_num < vec_safe_length (larray)); > + if (moved_orig_loop_num[orig_loop_num]) > + /* LOOP_DIST_ALIAS call remained in saved_cfun, if at least one > + of the corresponding loops was moved, remove it. */ > + fold_loop_internal_call (g, gimple_call_arg (g, 1)); > + } > + XDELETEVEC (moved_orig_loop_num); > + } > + ggc_free (larray); > + > /* Move blocks from BBS into DEST_CFUN. */ > gcc_assert (bbs.length () >= 2); > after = dest_cfun->cfg->x_entry_block_ptr; > --- gcc/testsuite/gcc.dg/graphite/pr83359.c.jj 2017-12-11 11:43:10.433737382 +0100 > +++ gcc/testsuite/gcc.dg/graphite/pr83359.c 2017-12-11 11:43:01.000000000 +0100 > @@ -0,0 +1,40 @@ > +/* PR tree-optimization/83359 */ > +/* { dg-do compile { target pthread } } */ > +/* { dg-options "-O3 -floop-parallelize-all -ftree-parallelize-loops=2" } */ > + > +int a, b, c; > + > +void > +foo (int x, int y) > +{ > + int *d = &a; > + int *e = &x; > + > + for (a = 0; a < 1; ++a) > + d = &x; > + > + while (b < 10) > + { > + for (b = 0; b < 1; ++b) > + if (x == 0) > + while (x < 1) > + ++x; > + else > + while (x < 1) > + { > + d = &y; > + ++x; > + } > + ++b; > + } > + > + for (;;) > + for (c = 0; c < 2; ++c) > + { > + if (*d != 0) > + a = *e; > + > + e = &b; > + y = 0; > + } > +} > > Jakub > >
--- gcc/tree-cfg.h.jj 2017-09-05 23:28:14.000000000 +0200 +++ gcc/tree-cfg.h 2017-12-11 12:35:24.284777550 +0100 @@ -77,6 +77,7 @@ extern void gather_blocks_in_sese_region vec<basic_block> *bbs_p); extern void verify_sese (basic_block, basic_block, vec<basic_block> *); extern bool gather_ssa_name_hash_map_from (tree const &, tree const &, void *); +extern void fold_loop_internal_call (gimple *, tree); extern basic_block move_sese_region_to_fn (struct function *, basic_block, basic_block, tree); extern void dump_function_to_file (tree, FILE *, dump_flags_t); --- gcc/tree-vectorizer.c.jj 2017-09-01 09:26:37.000000000 +0200 +++ gcc/tree-vectorizer.c 2017-12-11 12:33:41.436055580 +0100 @@ -464,27 +464,6 @@ vect_loop_vectorized_call (struct loop * return NULL; } -/* Fold loop internal call G like IFN_LOOP_VECTORIZED/IFN_LOOP_DIST_ALIAS - to VALUE and update any immediate uses of it's LHS. */ - -static void -fold_loop_internal_call (gimple *g, tree value) -{ - tree lhs = gimple_call_lhs (g); - use_operand_p use_p; - imm_use_iterator iter; - gimple *use_stmt; - gimple_stmt_iterator gsi = gsi_for_stmt (g); - - update_call_from_tree (&gsi, value); - FOR_EACH_IMM_USE_STMT (use_stmt, iter, lhs) - { - FOR_EACH_IMM_USE_ON_STMT (use_p, iter) - SET_USE (use_p, value); - update_stmt (use_stmt); - } -} - /* If LOOP has been versioned during loop distribution, return the gurading internal call. */ --- gcc/tree-cfg.c.jj 2017-12-07 18:05:30.000000000 +0100 +++ gcc/tree-cfg.c 2017-12-11 12:34:55.054140750 +0100 @@ -7337,6 +7337,47 @@ gather_ssa_name_hash_map_from (tree cons return true; } +/* Return LOOP_DIST_ALIAS call if present in BB. */ + +static gimple * +find_loop_dist_alias (basic_block bb) +{ + gimple *g = last_stmt (bb); + if (g == NULL || gimple_code (g) != GIMPLE_COND) + return NULL; + + gimple_stmt_iterator gsi = gsi_for_stmt (g); + gsi_prev (&gsi); + if (gsi_end_p (gsi)) + return NULL; + + g = gsi_stmt (gsi); + if (gimple_call_internal_p (g, IFN_LOOP_DIST_ALIAS)) + return g; + return NULL; +} + +/* Fold loop internal call G like IFN_LOOP_VECTORIZED/IFN_LOOP_DIST_ALIAS + to VALUE and update any immediate uses of it's LHS. */ + +void +fold_loop_internal_call (gimple *g, tree value) +{ + tree lhs = gimple_call_lhs (g); + use_operand_p use_p; + imm_use_iterator iter; + gimple *use_stmt; + gimple_stmt_iterator gsi = gsi_for_stmt (g); + + update_call_from_tree (&gsi, value); + FOR_EACH_IMM_USE_STMT (use_stmt, iter, lhs) + { + FOR_EACH_IMM_USE_ON_STMT (use_p, iter) + SET_USE (use_p, value); + update_stmt (use_stmt); + } +} + /* Move a single-entry, single-exit region delimited by ENTRY_BB and EXIT_BB to function DEST_CFUN. The whole region is replaced by a single basic block in the original CFG and the new basic block is @@ -7510,7 +7551,6 @@ move_sese_region_to_fn (struct function } } - /* Adjust the number of blocks in the tree root of the outlined part. */ get_loop (dest_cfun, 0)->num_nodes = bbs.length () + 2; @@ -7521,19 +7561,77 @@ move_sese_region_to_fn (struct function /* Fix up orig_loop_num. If the block referenced in it has been moved to dest_cfun, update orig_loop_num field, otherwise clear it. */ struct loop *dloop; + signed char *moved_orig_loop_num = NULL; FOR_EACH_LOOP_FN (dest_cfun, dloop, 0) if (dloop->orig_loop_num) { + if (moved_orig_loop_num == NULL) + moved_orig_loop_num + = XCNEWVEC (signed char, vec_safe_length (larray)); if ((*larray)[dloop->orig_loop_num] != NULL && get_loop (saved_cfun, dloop->orig_loop_num) == NULL) - dloop->orig_loop_num = (*larray)[dloop->orig_loop_num]->num; + { + if (moved_orig_loop_num[dloop->orig_loop_num] >= 0 + && moved_orig_loop_num[dloop->orig_loop_num] < 2) + moved_orig_loop_num[dloop->orig_loop_num]++; + dloop->orig_loop_num = (*larray)[dloop->orig_loop_num]->num; + } else - dloop->orig_loop_num = 0; + { + moved_orig_loop_num[dloop->orig_loop_num] = -1; + dloop->orig_loop_num = 0; + } } - ggc_free (larray); - pop_cfun (); + if (moved_orig_loop_num) + { + FOR_EACH_VEC_ELT (bbs, i, bb) + { + gimple *g = find_loop_dist_alias (bb); + if (g == NULL) + continue; + + int orig_loop_num = tree_to_shwi (gimple_call_arg (g, 0)); + gcc_assert (orig_loop_num + && (unsigned) orig_loop_num < vec_safe_length (larray)); + if (moved_orig_loop_num[orig_loop_num] == 2) + { + /* If we have moved both loops with this orig_loop_num into + dest_cfun and the LOOP_DIST_ALIAS call is being moved there + too, update the first argument. */ + gcc_assert ((*larray)[dloop->orig_loop_num] != NULL + && (get_loop (saved_cfun, dloop->orig_loop_num) + == NULL)); + tree t = build_int_cst (integer_type_node, + (*larray)[dloop->orig_loop_num]->num); + gimple_call_set_arg (g, 0, t); + update_stmt (g); + /* Make sure the following loop will not update it. */ + moved_orig_loop_num[orig_loop_num] = 0; + } + else + /* Otherwise at least one of the loops stayed in saved_cfun. + Remove the LOOP_DIST_ALIAS call. */ + fold_loop_internal_call (g, gimple_call_arg (g, 1)); + } + FOR_EACH_BB_FN (bb, saved_cfun) + { + gimple *g = find_loop_dist_alias (bb); + if (g == NULL) + continue; + int orig_loop_num = tree_to_shwi (gimple_call_arg (g, 0)); + gcc_assert (orig_loop_num + && (unsigned) orig_loop_num < vec_safe_length (larray)); + if (moved_orig_loop_num[orig_loop_num]) + /* LOOP_DIST_ALIAS call remained in saved_cfun, if at least one + of the corresponding loops was moved, remove it. */ + fold_loop_internal_call (g, gimple_call_arg (g, 1)); + } + XDELETEVEC (moved_orig_loop_num); + } + ggc_free (larray); + /* Move blocks from BBS into DEST_CFUN. */ gcc_assert (bbs.length () >= 2); after = dest_cfun->cfg->x_entry_block_ptr; --- gcc/testsuite/gcc.dg/graphite/pr83359.c.jj 2017-12-11 11:43:10.433737382 +0100 +++ gcc/testsuite/gcc.dg/graphite/pr83359.c 2017-12-11 11:43:01.000000000 +0100 @@ -0,0 +1,40 @@ +/* PR tree-optimization/83359 */ +/* { dg-do compile { target pthread } } */ +/* { dg-options "-O3 -floop-parallelize-all -ftree-parallelize-loops=2" } */ + +int a, b, c; + +void +foo (int x, int y) +{ + int *d = &a; + int *e = &x; + + for (a = 0; a < 1; ++a) + d = &x; + + while (b < 10) + { + for (b = 0; b < 1; ++b) + if (x == 0) + while (x < 1) + ++x; + else + while (x < 1) + { + d = &y; + ++x; + } + ++b; + } + + for (;;) + for (c = 0; c < 2; ++c) + { + if (*d != 0) + a = *e; + + e = &b; + y = 0; + } +}