Google Git
Sign in
gnu / gcc / 03655cd427b9d8e3b06c950255332eb988b0ade1 / . / gcc / tree-ssa-phiopt.cc
blob: ac805173453dfe1fc552ec50a9f3ca5a3f4dcc35 [file] [log] [blame]
/* Optimization of PHI nodes by converting them into straightline code.
Copyright (C) 2004-2023 Free Software Foundation, Inc.
This file is part of GCC.
GCC is free software; you can redistribute it and/or modify it
under the terms of the GNU General Public License as published by the
Free Software Foundation; either version 3, or (at your option) any
later version.
GCC is distributed in the hope that it will be useful, but WITHOUT
ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
for more details.
You should have received a copy of the GNU General Public License
along with GCC; see the file COPYING3. If not see
<http://www.gnu.org/licenses/>. */
#include "config.h"
#include "system.h"
#include "coretypes.h"
#include "backend.h"
#include "insn-codes.h"
#include "rtl.h"
#include "tree.h"
#include "gimple.h"
#include "cfghooks.h"
#include "tree-pass.h"
#include "ssa.h"
#include "tree-ssa.h"
#include "optabs-tree.h"
#include "insn-config.h"
#include "gimple-pretty-print.h"
#include "fold-const.h"
#include "stor-layout.h"
#include "cfganal.h"
#include "gimplify.h"
#include "gimple-iterator.h"
#include "gimplify-me.h"
#include "tree-cfg.h"
#include "tree-dfa.h"
#include "domwalk.h"
#include "cfgloop.h"
#include "tree-data-ref.h"
#include "tree-scalar-evolution.h"
#include "tree-inline.h"
#include "case-cfn-macros.h"
#include "tree-eh.h"
#include "gimple-fold.h"
#include "internal-fn.h"
#include "gimple-range.h"
#include "gimple-match.h"
#include "dbgcnt.h"
#include "tree-ssa-propagate.h"
#include "tree-ssa-dce.h"
/* Return the singleton PHI in the SEQ of PHIs for edges E0 and E1. */
static gphi *
single_non_singleton_phi_for_edges (gimple_seq seq, edge e0, edge e1)
{
gimple_stmt_iterator i;
gphi *phi = NULL;
if (gimple_seq_singleton_p (seq))
{
phi = as_a <gphi *> (gsi_stmt (gsi_start (seq)));
/* Never return virtual phis. */
if (virtual_operand_p (gimple_phi_result (phi)))
return NULL;
return phi;
}
for (i = gsi_start (seq); !gsi_end_p (i); gsi_next (&i))
{
gphi *p = as_a <gphi *> (gsi_stmt (i));
/* If the PHI arguments are equal then we can skip this PHI. */
if (operand_equal_for_phi_arg_p (gimple_phi_arg_def (p, e0->dest_idx),
gimple_phi_arg_def (p, e1->dest_idx)))
continue;
/* Punt on virtual phis with different arguments from the edges. */
if (virtual_operand_p (gimple_phi_result (p)))
return NULL;
/* If we already have a PHI that has the two edge arguments are
different, then return it is not a singleton for these PHIs. */
if (phi)
return NULL;
phi = p;
}
return phi;
}
/* Replace PHI node element whose edge is E in block BB with variable NEW.
Remove the edge from COND_BLOCK which does not lead to BB (COND_BLOCK
is known to have two edges, one of which must reach BB). */
static void
replace_phi_edge_with_variable (basic_block cond_block,
edge e, gphi *phi, tree new_tree,
bitmap dce_ssa_names = nullptr)
{
basic_block bb = gimple_bb (phi);
gimple_stmt_iterator gsi;
tree phi_result = PHI_RESULT (phi);
bool deleteboth = false;
/* Duplicate range info if they are the only things setting the target PHI.
This is needed as later on, the new_tree will be replacing
The assignement of the PHI.
For an example:
bb1:
_4 = min<a_1, 255>
goto bb2
# RANGE [-INF, 255]
a_3 = PHI<_4(1)>
bb3:
use(a_3)
And _4 gets propagated into the use of a_3 and losing the range info.
This can't be done for more than 2 incoming edges as the propagation
won't happen.
The new_tree needs to be defined in the same basic block as the conditional. */
if (TREE_CODE (new_tree) == SSA_NAME
&& EDGE_COUNT (gimple_bb (phi)->preds) == 2
&& INTEGRAL_TYPE_P (TREE_TYPE (phi_result))
&& !SSA_NAME_RANGE_INFO (new_tree)
&& SSA_NAME_RANGE_INFO (phi_result)
&& gimple_bb (SSA_NAME_DEF_STMT (new_tree)) == cond_block
&& dbg_cnt (phiopt_edge_range))
duplicate_ssa_name_range_info (new_tree, phi_result);
/* Change the PHI argument to new. */
SET_USE (PHI_ARG_DEF_PTR (phi, e->dest_idx), new_tree);
/* Remove the empty basic block. */
edge edge_to_remove = NULL, keep_edge = NULL;
if (EDGE_SUCC (cond_block, 0)->dest == bb)
{
edge_to_remove = EDGE_SUCC (cond_block, 1);
keep_edge = EDGE_SUCC (cond_block, 0);
}
else if (EDGE_SUCC (cond_block, 1)->dest == bb)
{
edge_to_remove = EDGE_SUCC (cond_block, 0);
keep_edge = EDGE_SUCC (cond_block, 1);
}
else if ((keep_edge = find_edge (cond_block, e->src)))
{
basic_block bb1 = EDGE_SUCC (cond_block, 0)->dest;
basic_block bb2 = EDGE_SUCC (cond_block, 1)->dest;
if (single_pred_p (bb1) && single_pred_p (bb2)
&& single_succ_p (bb1) && single_succ_p (bb2)
&& empty_block_p (bb1) && empty_block_p (bb2))
deleteboth = true;
}
else
gcc_unreachable ();
if (edge_to_remove && EDGE_COUNT (edge_to_remove->dest->preds) == 1)
{
e->flags |= EDGE_FALLTHRU;
e->flags &= ~(EDGE_TRUE_VALUE | EDGE_FALSE_VALUE);
e->probability = profile_probability::always ();
delete_basic_block (edge_to_remove->dest);
/* Eliminate the COND_EXPR at the end of COND_BLOCK. */
gsi = gsi_last_bb (cond_block);
gsi_remove (&gsi, true);
}
else if (deleteboth)
{
basic_block bb1 = EDGE_SUCC (cond_block, 0)->dest;
basic_block bb2 = EDGE_SUCC (cond_block, 1)->dest;
edge newedge = redirect_edge_and_branch (keep_edge, bb);
/* The new edge should be the same. */
gcc_assert (newedge == keep_edge);
keep_edge->flags |= EDGE_FALLTHRU;
keep_edge->flags &= ~(EDGE_TRUE_VALUE | EDGE_FALSE_VALUE);
keep_edge->probability = profile_probability::always ();
/* Copy the edge's phi entry from the old one. */
copy_phi_arg_into_existing_phi (e, keep_edge);
/* Delete the old 2 empty basic blocks */
delete_basic_block (bb1);
delete_basic_block (bb2);
/* Eliminate the COND_EXPR at the end of COND_BLOCK. */
gsi = gsi_last_bb (cond_block);
gsi_remove (&gsi, true);
}
else
{
/* If there are other edges into the middle block make
CFG cleanup deal with the edge removal to avoid
updating dominators here in a non-trivial way. */
gcond *cond = as_a <gcond *> (*gsi_last_bb (cond_block));
if (keep_edge->flags & EDGE_FALSE_VALUE)
gimple_cond_make_false (cond);
else if (keep_edge->flags & EDGE_TRUE_VALUE)
gimple_cond_make_true (cond);
}
if (dce_ssa_names)
simple_dce_from_worklist (dce_ssa_names);
statistics_counter_event (cfun, "Replace PHI with variable", 1);
if (dump_file && (dump_flags & TDF_DETAILS))
fprintf (dump_file,
"COND_EXPR in block %d and PHI in block %d converted to straightline code.\n",
cond_block->index,
bb->index);
}
/* PR66726: Factor operations out of COND_EXPR. If the arguments of the PHI
stmt are CONVERT_STMT, factor out the conversion and perform the conversion
to the result of PHI stmt. COND_STMT is the controlling predicate.
Return the newly-created PHI, if any. */
static gphi *
factor_out_conditional_operation (edge e0, edge e1, gphi *phi,
tree arg0, tree arg1, gimple *cond_stmt)
{
gimple *arg0_def_stmt = NULL, *arg1_def_stmt = NULL, *new_stmt;
tree new_arg0 = NULL_TREE, new_arg1 = NULL_TREE;
tree temp, result;
gphi *newphi;
gimple_stmt_iterator gsi, gsi_for_def;
location_t locus = gimple_location (phi);
enum tree_code op_code;
/* Handle only PHI statements with two arguments. TODO: If all
other arguments to PHI are INTEGER_CST or if their defining
statement have the same unary operation, we can handle more
than two arguments too. */
if (gimple_phi_num_args (phi) != 2)
return NULL;
/* First canonicalize to simplify tests. */
if (TREE_CODE (arg0) != SSA_NAME)
{
std::swap (arg0, arg1);
std::swap (e0, e1);
}
if (TREE_CODE (arg0) != SSA_NAME
|| (TREE_CODE (arg1) != SSA_NAME
&& TREE_CODE (arg1) != INTEGER_CST))
return NULL;
/* Check if arg0 is an SSA_NAME and the stmt which defines arg0 is
an unary operation. */
arg0_def_stmt = SSA_NAME_DEF_STMT (arg0);
if (!is_gimple_assign (arg0_def_stmt)
|| (gimple_assign_rhs_class (arg0_def_stmt) != GIMPLE_UNARY_RHS
&& gimple_assign_rhs_code (arg0_def_stmt) != VIEW_CONVERT_EXPR))
return NULL;
/* Use the RHS as new_arg0. */
op_code = gimple_assign_rhs_code (arg0_def_stmt);
new_arg0 = gimple_assign_rhs1 (arg0_def_stmt);
if (op_code == VIEW_CONVERT_EXPR)
{
new_arg0 = TREE_OPERAND (new_arg0, 0);
if (!is_gimple_reg_type (TREE_TYPE (new_arg0)))
return NULL;
}
if (TREE_CODE (new_arg0) == SSA_NAME
&& SSA_NAME_OCCURS_IN_ABNORMAL_PHI (new_arg0))
return NULL;
if (TREE_CODE (arg1) == SSA_NAME)
{
/* Check if arg1 is an SSA_NAME and the stmt which defines arg1
is an unary operation. */
arg1_def_stmt = SSA_NAME_DEF_STMT (arg1);
if (!is_gimple_assign (arg1_def_stmt)
|| gimple_assign_rhs_code (arg1_def_stmt) != op_code)
return NULL;
/* Either arg1_def_stmt or arg0_def_stmt should be conditional. */
if (dominated_by_p (CDI_DOMINATORS, gimple_bb (phi), gimple_bb (arg0_def_stmt))
&& dominated_by_p (CDI_DOMINATORS,
gimple_bb (phi), gimple_bb (arg1_def_stmt)))
return NULL;
/* Use the RHS as new_arg1. */
new_arg1 = gimple_assign_rhs1 (arg1_def_stmt);
if (op_code == VIEW_CONVERT_EXPR)
new_arg1 = TREE_OPERAND (new_arg1, 0);
if (TREE_CODE (new_arg1) == SSA_NAME
&& SSA_NAME_OCCURS_IN_ABNORMAL_PHI (new_arg1))
return NULL;
}
else
{
/* TODO: handle more than just casts here. */
if (!gimple_assign_cast_p (arg0_def_stmt))
return NULL;
/* arg0_def_stmt should be conditional. */
if (dominated_by_p (CDI_DOMINATORS, gimple_bb (phi), gimple_bb (arg0_def_stmt)))
return NULL;
/* If arg1 is an INTEGER_CST, fold it to new type. */
if (INTEGRAL_TYPE_P (TREE_TYPE (new_arg0))
&& (int_fits_type_p (arg1, TREE_TYPE (new_arg0))
|| (TYPE_PRECISION (TREE_TYPE (new_arg0))
== TYPE_PRECISION (TREE_TYPE (arg1)))))
{
if (gimple_assign_cast_p (arg0_def_stmt))
{
/* For the INTEGER_CST case, we are just moving the
conversion from one place to another, which can often
hurt as the conversion moves further away from the
statement that computes the value. So, perform this
only if new_arg0 is an operand of COND_STMT, or
if arg0_def_stmt is the only non-debug stmt in
its basic block, because then it is possible this
could enable further optimizations (minmax replacement
etc.). See PR71016.
Note no-op conversions don't have this issue as
it will not generate any zero/sign extend in that case. */
if ((TYPE_PRECISION (TREE_TYPE (new_arg0))
!= TYPE_PRECISION (TREE_TYPE (arg1)))
&& new_arg0 != gimple_cond_lhs (cond_stmt)
&& new_arg0 != gimple_cond_rhs (cond_stmt)
&& gimple_bb (arg0_def_stmt) == e0->src)
{
gsi = gsi_for_stmt (arg0_def_stmt);
gsi_prev_nondebug (&gsi);
if (!gsi_end_p (gsi))
{
if (gassign *assign
= dyn_cast <gassign *> (gsi_stmt (gsi)))
{
tree lhs = gimple_assign_lhs (assign);
enum tree_code ass_code
= gimple_assign_rhs_code (assign);
if (ass_code != MAX_EXPR && ass_code != MIN_EXPR)
return NULL;
if (lhs != gimple_assign_rhs1 (arg0_def_stmt))
return NULL;
gsi_prev_nondebug (&gsi);
if (!gsi_end_p (gsi))
return NULL;
}
else
return NULL;
}
gsi = gsi_for_stmt (arg0_def_stmt);
gsi_next_nondebug (&gsi);
if (!gsi_end_p (gsi))
return NULL;
}
new_arg1 = fold_convert (TREE_TYPE (new_arg0), arg1);
/* Drop the overlow that fold_convert might add. */
if (TREE_OVERFLOW (new_arg1))
new_arg1 = drop_tree_overflow (new_arg1);
}
else
return NULL;
}
else
return NULL;
}
/* If arg0/arg1 have > 1 use, then this transformation actually increases
the number of expressions evaluated at runtime. */
if (!has_single_use (arg0)
|| (arg1_def_stmt && !has_single_use (arg1)))
return NULL;
/* If types of new_arg0 and new_arg1 are different bailout. */
if (!types_compatible_p (TREE_TYPE (new_arg0), TREE_TYPE (new_arg1)))
return NULL;
/* Create a new PHI stmt. */
result = PHI_RESULT (phi);
temp = make_ssa_name (TREE_TYPE (new_arg0), NULL);
newphi = create_phi_node (temp, gimple_bb (phi));
if (dump_file && (dump_flags & TDF_DETAILS))
{
fprintf (dump_file, "PHI ");
print_generic_expr (dump_file, gimple_phi_result (phi));
fprintf (dump_file,
" changed to factor operation out from COND_EXPR.\n");
fprintf (dump_file, "New stmt with OPERATION that defines ");
print_generic_expr (dump_file, result);
fprintf (dump_file, ".\n");
}
/* Remove the old operation(s) that has single use. */
gsi_for_def = gsi_for_stmt (arg0_def_stmt);
gsi_remove (&gsi_for_def, true);
release_defs (arg0_def_stmt);
if (arg1_def_stmt)
{
gsi_for_def = gsi_for_stmt (arg1_def_stmt);
gsi_remove (&gsi_for_def, true);
release_defs (arg1_def_stmt);
}
add_phi_arg (newphi, new_arg0, e0, locus);
add_phi_arg (newphi, new_arg1, e1, locus);
/* Create the operation stmt and insert it. */
if (op_code == VIEW_CONVERT_EXPR)
{
temp = fold_build1 (VIEW_CONVERT_EXPR, TREE_TYPE (result), temp);
new_stmt = gimple_build_assign (result, temp);
}
else
new_stmt = gimple_build_assign (result, op_code, temp);
gsi = gsi_after_labels (gimple_bb (phi));
gsi_insert_before (&gsi, new_stmt, GSI_SAME_STMT);
/* Remove the original PHI stmt. */
gsi = gsi_for_stmt (phi);
gsi_remove (&gsi, true);
statistics_counter_event (cfun, "factored out operation", 1);
return newphi;
}
/* Return TRUE if SEQ/OP pair should be allowed during early phiopt.
Currently this is to allow MIN/MAX and ABS/NEGATE and constants. */
static bool
phiopt_early_allow (gimple_seq &seq, gimple_match_op &op)
{
/* Don't allow functions. */
if (!op.code.is_tree_code ())
return false;
tree_code code = (tree_code)op.code;
/* For non-empty sequence, only allow one statement
except for MIN/MAX, allow max 2 statements,
each with MIN/MAX. */
if (!gimple_seq_empty_p (seq))
{
if (code == MIN_EXPR || code == MAX_EXPR)
{
if (!gimple_seq_singleton_p (seq))
return false;
gimple *stmt = gimple_seq_first_stmt (seq);
/* Only allow assignments. */
if (!is_gimple_assign (stmt))
return false;
code = gimple_assign_rhs_code (stmt);
return code == MIN_EXPR || code == MAX_EXPR;
}
/* Check to make sure op was already a SSA_NAME. */
if (code != SSA_NAME)
return false;
if (!gimple_seq_singleton_p (seq))
return false;
gimple *stmt = gimple_seq_first_stmt (seq);
/* Only allow assignments. */
if (!is_gimple_assign (stmt))
return false;
if (gimple_assign_lhs (stmt) != op.ops[0])
return false;
code = gimple_assign_rhs_code (stmt);
}
switch (code)
{
case MIN_EXPR:
case MAX_EXPR:
case ABS_EXPR:
case ABSU_EXPR:
case NEGATE_EXPR:
case SSA_NAME:
return true;
case INTEGER_CST:
case REAL_CST:
case VECTOR_CST:
case FIXED_CST:
return true;
default:
return false;
}
}
/* gimple_simplify_phiopt is like gimple_simplify but designed for PHIOPT.
Return NULL if nothing can be simplified or the resulting simplified value
with parts pushed if EARLY_P was true. Also rejects non allowed tree code
if EARLY_P is set.
Takes the comparison from COMP_STMT and two args, ARG0 and ARG1 and tries
to simplify CMP ? ARG0 : ARG1.
Also try to simplify (!CMP) ? ARG1 : ARG0 if the non-inverse failed. */
static tree
gimple_simplify_phiopt (bool early_p, tree type, gimple *comp_stmt,
tree arg0, tree arg1,
gimple_seq *seq)
{
gimple_seq seq1 = NULL;
enum tree_code comp_code = gimple_cond_code (comp_stmt);
location_t loc = gimple_location (comp_stmt);
tree cmp0 = gimple_cond_lhs (comp_stmt);
tree cmp1 = gimple_cond_rhs (comp_stmt);
/* To handle special cases like floating point comparison, it is easier and
less error-prone to build a tree and gimplify it on the fly though it is
less efficient.
Don't use fold_build2 here as that might create (bool)a instead of just
"a != 0". */
tree cond = build2_loc (loc, comp_code, boolean_type_node,
cmp0, cmp1);
if (dump_file && (dump_flags & TDF_FOLDING))
{
fprintf (dump_file, "\nphiopt match-simplify trying:\n\t");
print_generic_expr (dump_file, cond);
fprintf (dump_file, " ? ");
print_generic_expr (dump_file, arg0);
fprintf (dump_file, " : ");
print_generic_expr (dump_file, arg1);
fprintf (dump_file, "\n");
}
gimple_match_op op (gimple_match_cond::UNCOND,
COND_EXPR, type, cond, arg0, arg1);
if (op.resimplify (&seq1, follow_all_ssa_edges))
{
bool allowed = !early_p || phiopt_early_allow (seq1, op);
tree result = maybe_push_res_to_seq (&op, &seq1);
if (dump_file && (dump_flags & TDF_FOLDING))
{
fprintf (dump_file, "\nphiopt match-simplify back:\n");
if (seq1)
print_gimple_seq (dump_file, seq1, 0, TDF_VOPS|TDF_MEMSYMS);
fprintf (dump_file, "result: ");
if (result)
print_generic_expr (dump_file, result);
else
fprintf (dump_file, " (none)");
fprintf (dump_file, "\n");
if (!allowed)
fprintf (dump_file, "rejected because early\n");
}
/* Early we want only to allow some generated tree codes. */
if (allowed && result)
{
if (loc != UNKNOWN_LOCATION)
annotate_all_with_location (seq1, loc);
gimple_seq_add_seq_without_update (seq, seq1);
return result;
}
}
gimple_seq_discard (seq1);
seq1 = NULL;
/* Try the inverted comparison, that is !COMP ? ARG1 : ARG0. */
comp_code = invert_tree_comparison (comp_code, HONOR_NANS (cmp0));
if (comp_code == ERROR_MARK)
return NULL;
cond = build2_loc (loc,
comp_code, boolean_type_node,
cmp0, cmp1);
if (dump_file && (dump_flags & TDF_FOLDING))
{
fprintf (dump_file, "\nphiopt match-simplify trying:\n\t");
print_generic_expr (dump_file, cond);
fprintf (dump_file, " ? ");
print_generic_expr (dump_file, arg1);
fprintf (dump_file, " : ");
print_generic_expr (dump_file, arg0);
fprintf (dump_file, "\n");
}
gimple_match_op op1 (gimple_match_cond::UNCOND,
COND_EXPR, type, cond, arg1, arg0);
if (op1.resimplify (&seq1, follow_all_ssa_edges))
{
bool allowed = !early_p || phiopt_early_allow (seq1, op1);
tree result = maybe_push_res_to_seq (&op1, &seq1);
if (dump_file && (dump_flags & TDF_FOLDING))
{
fprintf (dump_file, "\nphiopt match-simplify back:\n");
if (seq1)
print_gimple_seq (dump_file, seq1, 0, TDF_VOPS|TDF_MEMSYMS);
fprintf (dump_file, "result: ");
if (result)
print_generic_expr (dump_file, result);
else
fprintf (dump_file, " (none)");
fprintf (dump_file, "\n");
if (!allowed)
fprintf (dump_file, "rejected because early\n");
}
/* Early we want only to allow some generated tree codes. */
if (allowed && result)
{
if (loc != UNKNOWN_LOCATION)
annotate_all_with_location (seq1, loc);
gimple_seq_add_seq_without_update (seq, seq1);
return result;
}
}
gimple_seq_discard (seq1);
return NULL;
}
/* empty_bb_or_one_feeding_into_p returns true if bb was empty basic block
or it has one cheap preparation statement that feeds into the PHI
statement and it sets STMT to that statement. */
static bool
empty_bb_or_one_feeding_into_p (basic_block bb,
gimple *phi,
gimple *&stmt)
{
stmt = nullptr;
gimple *stmt_to_move = nullptr;
tree lhs;
if (empty_block_p (bb))
return true;
if (!single_pred_p (bb))
return false;
/* The middle bb cannot have phi nodes as we don't
move those assignments yet. */
if (!gimple_seq_empty_p (phi_nodes (bb)))
return false;
gimple_stmt_iterator gsi;
gsi = gsi_start_nondebug_after_labels_bb (bb);
while (!gsi_end_p (gsi))
{
gimple *s = gsi_stmt (gsi);
gsi_next_nondebug (&gsi);
/* Skip over Predict and nop statements. */
if (gimple_code (s) == GIMPLE_PREDICT
|| gimple_code (s) == GIMPLE_NOP)
continue;
/* If there is more one statement return false. */
if (stmt_to_move)
return false;
stmt_to_move = s;
}
/* The only statement here was a Predict or a nop statement
so return true. */
if (!stmt_to_move)
return true;
if (gimple_vuse (stmt_to_move))
return false;
if (gimple_could_trap_p (stmt_to_move)
|| gimple_has_side_effects (stmt_to_move))
return false;
ssa_op_iter it;
tree use;
FOR_EACH_SSA_TREE_OPERAND (use, stmt_to_move, it, SSA_OP_USE)
if (ssa_name_maybe_undef_p (use))
return false;
/* Allow assignments but allow some builtin/internal calls.
As const calls don't match any of the above, yet they could
still have some side-effects - they could contain
gimple_could_trap_p statements, like floating point
exceptions or integer division by zero. See PR70586.
FIXME: perhaps gimple_has_side_effects or gimple_could_trap_p
should handle this.
Allow some known builtin/internal calls that are known not to
trap: logical functions (e.g. bswap and bit counting). */
if (!is_gimple_assign (stmt_to_move))
{
if (!is_gimple_call (stmt_to_move))
return false;
combined_fn cfn = gimple_call_combined_fn (stmt_to_move);
switch (cfn)
{
default:
return false;
case CFN_BUILT_IN_BSWAP16:
case CFN_BUILT_IN_BSWAP32:
case CFN_BUILT_IN_BSWAP64:
case CFN_BUILT_IN_BSWAP128:
CASE_CFN_FFS:
CASE_CFN_PARITY:
CASE_CFN_POPCOUNT:
CASE_CFN_CLZ:
CASE_CFN_CTZ:
case CFN_BUILT_IN_CLRSB:
case CFN_BUILT_IN_CLRSBL:
case CFN_BUILT_IN_CLRSBLL:
lhs = gimple_call_lhs (stmt_to_move);
break;
}
}
else
lhs = gimple_assign_lhs (stmt_to_move);
gimple *use_stmt;
use_operand_p use_p;
/* Allow only a statement which feeds into the other stmt. */
if (!lhs || TREE_CODE (lhs) != SSA_NAME
|| !single_imm_use (lhs, &use_p, &use_stmt)
|| use_stmt != phi)
return false;
stmt = stmt_to_move;
return true;
}
/* Move STMT to before GSI and insert its defining
name into INSERTED_EXPRS bitmap. */
static void
move_stmt (gimple *stmt, gimple_stmt_iterator *gsi, auto_bitmap &inserted_exprs)
{
if (!stmt)
return;
if (dump_file && (dump_flags & TDF_DETAILS))
{
fprintf (dump_file, "statement un-sinked:\n");
print_gimple_stmt (dump_file, stmt, 0,
TDF_VOPS|TDF_MEMSYMS);
}
tree name = gimple_get_lhs (stmt);
// Mark the name to be renamed if there is one.
bitmap_set_bit (inserted_exprs, SSA_NAME_VERSION (name));
gimple_stmt_iterator gsi1 = gsi_for_stmt (stmt);
gsi_move_before (&gsi1, gsi);
reset_flow_sensitive_info (name);
}
/* RAII style class to temporarily remove flow sensitive
from ssa names defined by a gimple statement. */
class auto_flow_sensitive
{
public:
auto_flow_sensitive (gimple *s);
~auto_flow_sensitive ();
private:
auto_vec<std::pair<tree, flow_sensitive_info_storage>, 2> stack;
};
/* Constructor for auto_flow_sensitive. Saves
off the ssa names' flow sensitive information
that was defined by gimple statement S and
resets it to be non-flow based ones. */
auto_flow_sensitive::auto_flow_sensitive (gimple *s)
{
if (!s)
return;
ssa_op_iter it;
tree def;
FOR_EACH_SSA_TREE_OPERAND (def, s, it, SSA_OP_DEF)
{
flow_sensitive_info_storage storage;
storage.save_and_clear (def);
stack.safe_push (std::make_pair (def, storage));
}
}
/* Deconstructor, restores the flow sensitive information
for the SSA names that had been saved off. */
auto_flow_sensitive::~auto_flow_sensitive ()
{
for (auto p : stack)
p.second.restore (p.first);
}
/* The function match_simplify_replacement does the main work of doing the
replacement using match and simplify. Return true if the replacement is done.
Otherwise return false.
BB is the basic block where the replacement is going to be done on. ARG0
is argument 0 from PHI. Likewise for ARG1. */
static bool
match_simplify_replacement (basic_block cond_bb, basic_block middle_bb,
basic_block middle_bb_alt,
edge e0, edge e1, gphi *phi,
tree arg0, tree arg1, bool early_p,
bool threeway_p)
{
gimple *stmt;
gimple_stmt_iterator gsi;
edge true_edge, false_edge;
gimple_seq seq = NULL;
tree result;
gimple *stmt_to_move = NULL;
gimple *stmt_to_move_alt = NULL;
tree arg_true, arg_false;
/* Special case A ? B : B as this will always simplify to B. */
if (operand_equal_for_phi_arg_p (arg0, arg1))
return false;
/* If the basic block only has a cheap preparation statement,
allow it and move it once the transformation is done. */
if (!empty_bb_or_one_feeding_into_p (middle_bb, phi, stmt_to_move))
return false;
if (threeway_p
&& middle_bb != middle_bb_alt
&& !empty_bb_or_one_feeding_into_p (middle_bb_alt, phi,
stmt_to_move_alt))
return false;
/* At this point we know we have a GIMPLE_COND with two successors.
One successor is BB, the other successor is an empty block which
falls through into BB.
There is a single PHI node at the join point (BB).
So, given the condition COND, and the two PHI arguments, match and simplify
can happen on (COND) ? arg0 : arg1. */
stmt = last_nondebug_stmt (cond_bb);
/* We need to know which is the true edge and which is the false
edge so that we know when to invert the condition below. */
extract_true_false_edges_from_block (cond_bb, &true_edge, &false_edge);
/* Forward the edges over the middle basic block. */
if (true_edge->dest == middle_bb)
true_edge = EDGE_SUCC (true_edge->dest, 0);
if (false_edge->dest == middle_bb)
false_edge = EDGE_SUCC (false_edge->dest, 0);
/* When THREEWAY_P then e1 will point to the edge of the final transition
from middle-bb to end. */
if (true_edge == e0)
{
if (!threeway_p)
gcc_assert (false_edge == e1);
arg_true = arg0;
arg_false = arg1;
}
else
{
gcc_assert (false_edge == e0);
if (!threeway_p)
gcc_assert (true_edge == e1);
arg_true = arg1;
arg_false = arg0;
}
/* Do not make conditional undefs unconditional. */
if ((TREE_CODE (arg_true) == SSA_NAME
&& ssa_name_maybe_undef_p (arg_true))
|| (TREE_CODE (arg_false) == SSA_NAME
&& ssa_name_maybe_undef_p (arg_false)))
return false;
tree type = TREE_TYPE (gimple_phi_result (phi));
{
auto_flow_sensitive s1(stmt_to_move);
auto_flow_sensitive s_alt(stmt_to_move_alt);
result = gimple_simplify_phiopt (early_p, type, stmt,
arg_true, arg_false,
&seq);
}
if (!result)
return false;
if (dump_file && (dump_flags & TDF_FOLDING))
fprintf (dump_file, "accepted the phiopt match-simplify.\n");
auto_bitmap exprs_maybe_dce;
/* Mark the cond statements' lhs/rhs as maybe dce. */
if (TREE_CODE (gimple_cond_lhs (stmt)) == SSA_NAME
&& !SSA_NAME_IS_DEFAULT_DEF (gimple_cond_lhs (stmt)))
bitmap_set_bit (exprs_maybe_dce,
SSA_NAME_VERSION (gimple_cond_lhs (stmt)));
if (TREE_CODE (gimple_cond_rhs (stmt)) == SSA_NAME
&& !SSA_NAME_IS_DEFAULT_DEF (gimple_cond_rhs (stmt)))
bitmap_set_bit (exprs_maybe_dce,
SSA_NAME_VERSION (gimple_cond_rhs (stmt)));
gsi = gsi_last_bb (cond_bb);
/* Insert the sequence generated from gimple_simplify_phiopt. */
if (seq)
{
// Mark the lhs of the new statements maybe for dce
gimple_stmt_iterator gsi1 = gsi_start (seq);
for (; !gsi_end_p (gsi1); gsi_next (&gsi1))
{
gimple *stmt = gsi_stmt (gsi1);
tree name = gimple_get_lhs (stmt);
if (name && TREE_CODE (name) == SSA_NAME)
bitmap_set_bit (exprs_maybe_dce, SSA_NAME_VERSION (name));
}
gsi_insert_seq_before (&gsi, seq, GSI_CONTINUE_LINKING);
}
/* If there was a statement to move, move it to right before
the original conditional. */
move_stmt (stmt_to_move, &gsi, exprs_maybe_dce);
move_stmt (stmt_to_move_alt, &gsi, exprs_maybe_dce);
replace_phi_edge_with_variable (cond_bb, e1, phi, result, exprs_maybe_dce);
/* Add Statistic here even though replace_phi_edge_with_variable already
does it as we want to be able to count when match-simplify happens vs
the others. */
statistics_counter_event (cfun, "match-simplify PHI replacement", 1);
/* Note that we optimized this PHI. */
return true;
}
/* Update *ARG which is defined in STMT so that it contains the
computed value if that seems profitable. Return true if the
statement is made dead by that rewriting. */
static bool
jump_function_from_stmt (tree *arg, gimple *stmt)
{
enum tree_code code = gimple_assign_rhs_code (stmt);
if (code == ADDR_EXPR)
{
/* For arg = &p->i transform it to p, if possible. */
tree rhs1 = gimple_assign_rhs1 (stmt);
poly_int64 offset;
tree tem = get_addr_base_and_unit_offset (TREE_OPERAND (rhs1, 0),
&offset);
if (tem
&& TREE_CODE (tem) == MEM_REF
&& known_eq (mem_ref_offset (tem) + offset, 0))
{
*arg = TREE_OPERAND (tem, 0);
return true;
}
}
/* TODO: Much like IPA-CP jump-functions we want to handle constant
additions symbolically here, and we'd need to update the comparison
code that compares the arg + cst tuples in our caller. For now the
code above exactly handles the VEC_BASE pattern from vec.h. */
return false;
}
/* RHS is a source argument in a BIT_AND_EXPR which feeds a conditional
of the form SSA_NAME NE 0.
If RHS is fed by a simple EQ_EXPR comparison of two values, see if
the two input values of the EQ_EXPR match arg0 and arg1.
If so update *code and return TRUE. Otherwise return FALSE. */
static bool
rhs_is_fed_for_value_replacement (const_tree arg0, const_tree arg1,
enum tree_code *code, const_tree rhs)
{
/* Obviously if RHS is not an SSA_NAME, we can't look at the defining
statement. */
if (TREE_CODE (rhs) == SSA_NAME)
{
gimple *def1 = SSA_NAME_DEF_STMT (rhs);
/* Verify the defining statement has an EQ_EXPR on the RHS. */
if (is_gimple_assign (def1) && gimple_assign_rhs_code (def1) == EQ_EXPR)
{
/* Finally verify the source operands of the EQ_EXPR are equal
to arg0 and arg1. */
tree op0 = gimple_assign_rhs1 (def1);
tree op1 = gimple_assign_rhs2 (def1);
if ((operand_equal_for_phi_arg_p (arg0, op0)
&& operand_equal_for_phi_arg_p (arg1, op1))
|| (operand_equal_for_phi_arg_p (arg0, op1)
&& operand_equal_for_phi_arg_p (arg1, op0)))
{
/* We will perform the optimization. */
*code = gimple_assign_rhs_code (def1);
return true;
}
}
}
return false;
}
/* Return TRUE if arg0/arg1 are equal to the rhs/lhs or lhs/rhs of COND.
Also return TRUE if arg0/arg1 are equal to the source arguments of a
an EQ comparison feeding a BIT_AND_EXPR which feeds COND.
Return FALSE otherwise. */
static bool
operand_equal_for_value_replacement (const_tree arg0, const_tree arg1,
enum tree_code *code, gimple *cond)
{
gimple *def;
tree lhs = gimple_cond_lhs (cond);
tree rhs = gimple_cond_rhs (cond);
if ((operand_equal_for_phi_arg_p (arg0, lhs)
&& operand_equal_for_phi_arg_p (arg1, rhs))
|| (operand_equal_for_phi_arg_p (arg1, lhs)
&& operand_equal_for_phi_arg_p (arg0, rhs)))
return true;
/* Now handle more complex case where we have an EQ comparison
which feeds a BIT_AND_EXPR which feeds COND.
First verify that COND is of the form SSA_NAME NE 0. */
if (*code != NE_EXPR || !integer_zerop (rhs)
|| TREE_CODE (lhs) != SSA_NAME)
return false;
/* Now ensure that SSA_NAME is set by a BIT_AND_EXPR. */
def = SSA_NAME_DEF_STMT (lhs);
if (!is_gimple_assign (def) || gimple_assign_rhs_code (def) != BIT_AND_EXPR)
return false;
/* Now verify arg0/arg1 correspond to the source arguments of an
EQ comparison feeding the BIT_AND_EXPR. */
tree tmp = gimple_assign_rhs1 (def);
if (rhs_is_fed_for_value_replacement (arg0, arg1, code, tmp))
return true;
tmp = gimple_assign_rhs2 (def);
if (rhs_is_fed_for_value_replacement (arg0, arg1, code, tmp))
return true;
return false;
}
/* Returns true if ARG is a neutral element for operation CODE
on the RIGHT side. */
static bool
neutral_element_p (tree_code code, tree arg, bool right)
{
switch (code)
{
case PLUS_EXPR:
case BIT_IOR_EXPR:
case BIT_XOR_EXPR:
return integer_zerop (arg);
case LROTATE_EXPR:
case RROTATE_EXPR:
case LSHIFT_EXPR:
case RSHIFT_EXPR:
case MINUS_EXPR:
case POINTER_PLUS_EXPR:
return right && integer_zerop (arg);
case MULT_EXPR:
return integer_onep (arg);
case TRUNC_DIV_EXPR:
case CEIL_DIV_EXPR:
case FLOOR_DIV_EXPR:
case ROUND_DIV_EXPR:
case EXACT_DIV_EXPR:
return right && integer_onep (arg);
case BIT_AND_EXPR:
return integer_all_onesp (arg);
default:
return false;
}
}
/* Returns true if ARG is an absorbing element for operation CODE. */
static bool
absorbing_element_p (tree_code code, tree arg, bool right, tree rval)
{
switch (code)
{
case BIT_IOR_EXPR:
return integer_all_onesp (arg);
case MULT_EXPR:
case BIT_AND_EXPR:
return integer_zerop (arg);
case LSHIFT_EXPR:
case RSHIFT_EXPR:
case LROTATE_EXPR:
case RROTATE_EXPR:
return !right && integer_zerop (arg);
case TRUNC_DIV_EXPR:
case CEIL_DIV_EXPR:
case FLOOR_DIV_EXPR:
case ROUND_DIV_EXPR:
case EXACT_DIV_EXPR:
case TRUNC_MOD_EXPR:
case CEIL_MOD_EXPR:
case FLOOR_MOD_EXPR:
case ROUND_MOD_EXPR:
return (!right
&& integer_zerop (arg)
&& tree_single_nonzero_warnv_p (rval, NULL));
default:
return false;
}
}
/* The function value_replacement does the main work of doing the value
replacement. Return non-zero if the replacement is done. Otherwise return
0. If we remove the middle basic block, return 2.
BB is the basic block where the replacement is going to be done on. ARG0
is argument 0 from the PHI. Likewise for ARG1. */
static int
value_replacement (basic_block cond_bb, basic_block middle_bb,
edge e0, edge e1, gphi *phi, tree arg0, tree arg1)
{
gimple_stmt_iterator gsi;
edge true_edge, false_edge;
enum tree_code code;
bool empty_or_with_defined_p = true;
/* If the type says honor signed zeros we cannot do this
optimization. */
if (HONOR_SIGNED_ZEROS (arg1))
return 0;
/* If there is a statement in MIDDLE_BB that defines one of the PHI
arguments, then adjust arg0 or arg1. */
gsi = gsi_start_nondebug_after_labels_bb (middle_bb);
while (!gsi_end_p (gsi))
{
gimple *stmt = gsi_stmt (gsi);
tree lhs;
gsi_next_nondebug (&gsi);
if (!is_gimple_assign (stmt))
{
if (gimple_code (stmt) != GIMPLE_PREDICT
&& gimple_code (stmt) != GIMPLE_NOP)
empty_or_with_defined_p = false;
continue;
}
/* Now try to adjust arg0 or arg1 according to the computation
in the statement. */
lhs = gimple_assign_lhs (stmt);
if (!(lhs == arg0
&& jump_function_from_stmt (&arg0, stmt))
|| (lhs == arg1
&& jump_function_from_stmt (&arg1, stmt)))
empty_or_with_defined_p = false;
}
gcond *cond = as_a <gcond *> (*gsi_last_bb (cond_bb));
code = gimple_cond_code (cond);
/* This transformation is only valid for equality comparisons. */
if (code != NE_EXPR && code != EQ_EXPR)
return 0;
/* We need to know which is the true edge and which is the false
edge so that we know if have abs or negative abs. */
extract_true_false_edges_from_block (cond_bb, &true_edge, &false_edge);
/* At this point we know we have a COND_EXPR with two successors.
One successor is BB, the other successor is an empty block which
falls through into BB.
The condition for the COND_EXPR is known to be NE_EXPR or EQ_EXPR.
There is a single PHI node at the join point (BB) with two arguments.
We now need to verify that the two arguments in the PHI node match
the two arguments to the equality comparison. */
bool equal_p = operand_equal_for_value_replacement (arg0, arg1, &code, cond);
bool maybe_equal_p = false;
if (!equal_p
&& empty_or_with_defined_p
&& TREE_CODE (gimple_cond_rhs (cond)) == INTEGER_CST
&& (operand_equal_for_phi_arg_p (gimple_cond_lhs (cond), arg0)
? TREE_CODE (arg1) == INTEGER_CST
: (operand_equal_for_phi_arg_p (gimple_cond_lhs (cond), arg1)
&& TREE_CODE (arg0) == INTEGER_CST)))
maybe_equal_p = true;
if (equal_p || maybe_equal_p)
{
edge e;
tree arg;
/* For NE_EXPR, we want to build an assignment result = arg where
arg is the PHI argument associated with the true edge. For
EQ_EXPR we want the PHI argument associated with the false edge. */
e = (code == NE_EXPR ? true_edge : false_edge);
/* Unfortunately, E may not reach BB (it may instead have gone to
OTHER_BLOCK). If that is the case, then we want the single outgoing
edge from OTHER_BLOCK which reaches BB and represents the desired
path from COND_BLOCK. */
if (e->dest == middle_bb)
e = single_succ_edge (e->dest);
/* Now we know the incoming edge to BB that has the argument for the
RHS of our new assignment statement. */
if (e0 == e)
arg = arg0;
else
arg = arg1;
/* If the middle basic block was empty or is defining the
PHI arguments and this is a single phi where the args are different
for the edges e0 and e1 then we can remove the middle basic block. */
if (empty_or_with_defined_p
&& single_non_singleton_phi_for_edges (phi_nodes (gimple_bb (phi)),
e0, e1) == phi)
{
use_operand_p use_p;
gimple *use_stmt;
/* Even if arg0/arg1 isn't equal to second operand of cond, we
can optimize away the bb if we can prove it doesn't care whether
phi result is arg0/arg1 or second operand of cond. Consider:
<bb 2> [local count: 118111600]:
if (i_2(D) == 4)
goto <bb 4>; [97.00%]
else
goto <bb 3>; [3.00%]
<bb 3> [local count: 3540129]:
<bb 4> [local count: 118111600]:
# i_6 = PHI <i_2(D)(3), 6(2)>
_3 = i_6 != 0;
Here, carg is 4, oarg is 6, crhs is 0, and because
(4 != 0) == (6 != 0), we don't care if i_6 is 4 or 6, both
have the same outcome. So, can can optimize this to:
_3 = i_2(D) != 0;
If the single imm use of phi result >, >=, < or <=, similarly
we can check if both carg and oarg compare the same against
crhs using ccode. */
if (maybe_equal_p
&& TREE_CODE (arg) != INTEGER_CST
&& single_imm_use (gimple_phi_result (phi), &use_p, &use_stmt))
{
enum tree_code ccode = ERROR_MARK;
tree clhs = NULL_TREE, crhs = NULL_TREE;
tree carg = gimple_cond_rhs (cond);
tree oarg = e0 == e ? arg1 : arg0;
if (is_gimple_assign (use_stmt)
&& (TREE_CODE_CLASS (gimple_assign_rhs_code (use_stmt))
== tcc_comparison))
{
ccode = gimple_assign_rhs_code (use_stmt);
clhs = gimple_assign_rhs1 (use_stmt);
crhs = gimple_assign_rhs2 (use_stmt);
}
else if (gimple_code (use_stmt) == GIMPLE_COND)
{
ccode = gimple_cond_code (use_stmt);
clhs = gimple_cond_lhs (use_stmt);
crhs = gimple_cond_rhs (use_stmt);
}
if (ccode != ERROR_MARK
&& clhs == gimple_phi_result (phi)
&& TREE_CODE (crhs) == INTEGER_CST)
switch (ccode)
{
case EQ_EXPR:
case NE_EXPR:
if (!tree_int_cst_equal (crhs, carg)
&& !tree_int_cst_equal (crhs, oarg))
equal_p = true;
break;
case GT_EXPR:
if (tree_int_cst_lt (crhs, carg)
== tree_int_cst_lt (crhs, oarg))
equal_p = true;
break;
case GE_EXPR:
if (tree_int_cst_le (crhs, carg)
== tree_int_cst_le (crhs, oarg))
equal_p = true;
break;
case LT_EXPR:
if (tree_int_cst_lt (carg, crhs)
== tree_int_cst_lt (oarg, crhs))
equal_p = true;
break;
case LE_EXPR:
if (tree_int_cst_le (carg, crhs)
== tree_int_cst_le (oarg, crhs))
equal_p = true;
break;
default:
break;
}
if (equal_p)
{
tree phires = gimple_phi_result (phi);
if (SSA_NAME_RANGE_INFO (phires))
{
/* After the optimization PHI result can have value
which it couldn't have previously. */
int_range_max r;
if (get_global_range_query ()->range_of_expr (r, phires,
phi))
{
wide_int warg = wi::to_wide (carg);
int_range<2> tmp (TREE_TYPE (carg), warg, warg);
r.union_ (tmp);
reset_flow_sensitive_info (phires);
set_range_info (phires, r);
}
else
reset_flow_sensitive_info (phires);
}
}
if (equal_p && MAY_HAVE_DEBUG_BIND_STMTS)
{
imm_use_iterator imm_iter;
tree phires = gimple_phi_result (phi);
tree temp = NULL_TREE;
bool reset_p = false;
/* Add # DEBUG D#1 => arg != carg ? arg : oarg. */
FOR_EACH_IMM_USE_STMT (use_stmt, imm_iter, phires)
{
if (!is_gimple_debug (use_stmt))
continue;
if (temp == NULL_TREE)
{
if (!single_pred_p (middle_bb)
|| EDGE_COUNT (gimple_bb (phi)->preds) != 2)
{
/* But only if middle_bb has a single
predecessor and phi bb has two, otherwise
we could use a SSA_NAME not usable in that
place or wrong-debug. */
reset_p = true;
break;
}
gimple_stmt_iterator gsi
= gsi_after_labels (gimple_bb (phi));
tree type = TREE_TYPE (phires);
temp = build_debug_expr_decl (type);
tree t = build2 (NE_EXPR, boolean_type_node,
arg, carg);
t = build3 (COND_EXPR, type, t, arg, oarg);
gimple *g = gimple_build_debug_bind (temp, t, phi);
gsi_insert_before (&gsi, g, GSI_SAME_STMT);
}
FOR_EACH_IMM_USE_ON_STMT (use_p, imm_iter)
replace_exp (use_p, temp);
update_stmt (use_stmt);
}
if (reset_p)
reset_debug_uses (phi);
}
}
if (equal_p)
{
replace_phi_edge_with_variable (cond_bb, e1, phi, arg);
/* Note that we optimized this PHI. */
return 2;
}
}
else if (equal_p)
{
if (!single_pred_p (middle_bb))
return 0;
statistics_counter_event (cfun, "Replace PHI with "
"variable/value_replacement", 1);
/* Replace the PHI arguments with arg. */
SET_PHI_ARG_DEF (phi, e0->dest_idx, arg);
SET_PHI_ARG_DEF (phi, e1->dest_idx, arg);
if (dump_file && (dump_flags & TDF_DETAILS))
{
fprintf (dump_file, "PHI ");
print_generic_expr (dump_file, gimple_phi_result (phi));
fprintf (dump_file, " reduced for COND_EXPR in block %d to ",
cond_bb->index);
print_generic_expr (dump_file, arg);
fprintf (dump_file, ".\n");
}
return 1;
}
}
if (!single_pred_p (middle_bb))
return 0;
/* Now optimize (x != 0) ? x + y : y to just x + y. */
gsi = gsi_last_nondebug_bb (middle_bb);
if (gsi_end_p (gsi))
return 0;
gimple *assign = gsi_stmt (gsi);
if (!is_gimple_assign (assign)
|| (!INTEGRAL_TYPE_P (TREE_TYPE (arg0))
&& !POINTER_TYPE_P (TREE_TYPE (arg0))))
return 0;
if (gimple_assign_rhs_class (assign) != GIMPLE_BINARY_RHS)
{
/* If last stmt of the middle_bb is a conversion, handle it like
a preparation statement through constant evaluation with
checking for UB. */
enum tree_code sc = gimple_assign_rhs_code (assign);
if (CONVERT_EXPR_CODE_P (sc))
assign = NULL;
else
return 0;
}
/* Punt if there are (degenerate) PHIs in middle_bb, there should not be. */
if (!gimple_seq_empty_p (phi_nodes (middle_bb)))
return 0;
/* Allow up to 2 cheap preparation statements that prepare argument
for assign, e.g.:
if (y_4 != 0)
goto <bb 3>;
else
goto <bb 4>;
<bb 3>:
_1 = (int) y_4;
iftmp.0_6 = x_5(D) r<< _1;
<bb 4>:
# iftmp.0_2 = PHI <iftmp.0_6(3), x_5(D)(2)>
or:
if (y_3(D) == 0)
goto <bb 4>;
else
goto <bb 3>;
<bb 3>:
y_4 = y_3(D) & 31;
_1 = (int) y_4;
_6 = x_5(D) r<< _1;
<bb 4>:
# _2 = PHI <x_5(D)(2), _6(3)> */
gimple *prep_stmt[2] = { NULL, NULL };
int prep_cnt;
for (prep_cnt = 0; ; prep_cnt++)
{
if (prep_cnt || assign)
gsi_prev_nondebug (&gsi);
if (gsi_end_p (gsi))
break;
gimple *g = gsi_stmt (gsi);
if (gimple_code (g) == GIMPLE_LABEL)
break;
if (prep_cnt == 2 || !is_gimple_assign (g))
return 0;
tree lhs = gimple_assign_lhs (g);
tree rhs1 = gimple_assign_rhs1 (g);
use_operand_p use_p;
gimple *use_stmt;
if (TREE_CODE (lhs) != SSA_NAME
|| TREE_CODE (rhs1) != SSA_NAME
|| !INTEGRAL_TYPE_P (TREE_TYPE (lhs))
|| !INTEGRAL_TYPE_P (TREE_TYPE (rhs1))
|| !single_imm_use (lhs, &use_p, &use_stmt)
|| ((prep_cnt || assign)
&& use_stmt != (prep_cnt ? prep_stmt[prep_cnt - 1] : assign)))
return 0;
switch (gimple_assign_rhs_code (g))
{
CASE_CONVERT:
break;
case PLUS_EXPR:
case BIT_AND_EXPR:
case BIT_IOR_EXPR:
case BIT_XOR_EXPR:
if (TREE_CODE (gimple_assign_rhs2 (g)) != INTEGER_CST)
return 0;
break;
default:
return 0;
}
prep_stmt[prep_cnt] = g;
}
/* Only transform if it removes the condition. */
if (!single_non_singleton_phi_for_edges (phi_nodes (gimple_bb (phi)), e0, e1))
return 0;
/* Size-wise, this is always profitable. */
if (optimize_bb_for_speed_p (cond_bb)
/* The special case is useless if it has a low probability. */
&& profile_status_for_fn (cfun) != PROFILE_ABSENT
&& EDGE_PRED (middle_bb, 0)->probability < profile_probability::even ()
/* If assign is cheap, there is no point avoiding it. */
&& estimate_num_insns_seq (bb_seq (middle_bb), &eni_time_weights)
>= 3 * estimate_num_insns (cond, &eni_time_weights))
return 0;
tree cond_lhs = gimple_cond_lhs (cond);
tree cond_rhs = gimple_cond_rhs (cond);
/* Propagate the cond_rhs constant through preparation stmts,
make sure UB isn't invoked while doing that. */
for (int i = prep_cnt - 1; i >= 0; --i)
{
gimple *g = prep_stmt[i];
tree grhs1 = gimple_assign_rhs1 (g);
if (!operand_equal_for_phi_arg_p (cond_lhs, grhs1))
return 0;
cond_lhs = gimple_assign_lhs (g);
cond_rhs = fold_convert (TREE_TYPE (grhs1), cond_rhs);
if (TREE_CODE (cond_rhs) != INTEGER_CST
|| TREE_OVERFLOW (cond_rhs))
return 0;
if (gimple_assign_rhs_class (g) == GIMPLE_BINARY_RHS)
{
cond_rhs = int_const_binop (gimple_assign_rhs_code (g), cond_rhs,
gimple_assign_rhs2 (g));
if (TREE_OVERFLOW (cond_rhs))
return 0;
}
cond_rhs = fold_convert (TREE_TYPE (cond_lhs), cond_rhs);
if (TREE_CODE (cond_rhs) != INTEGER_CST
|| TREE_OVERFLOW (cond_rhs))
return 0;
}
tree lhs, rhs1, rhs2;
enum tree_code code_def;
if (assign)
{
lhs = gimple_assign_lhs (assign);
rhs1 = gimple_assign_rhs1 (assign);
rhs2 = gimple_assign_rhs2 (assign);
code_def = gimple_assign_rhs_code (assign);
}
else
{
gcc_assert (prep_cnt > 0);
lhs = cond_lhs;
rhs1 = NULL_TREE;
rhs2 = NULL_TREE;
code_def = ERROR_MARK;
}
if (((code == NE_EXPR && e1 == false_edge)
|| (code == EQ_EXPR && e1 == true_edge))
&& arg0 == lhs
&& ((assign == NULL
&& operand_equal_for_phi_arg_p (arg1, cond_rhs))
|| (assign
&& arg1 == rhs1
&& operand_equal_for_phi_arg_p (rhs2, cond_lhs)
&& neutral_element_p (code_def, cond_rhs, true))
|| (assign
&& arg1 == rhs2
&& operand_equal_for_phi_arg_p (rhs1, cond_lhs)
&& neutral_element_p (code_def, cond_rhs, false))
|| (assign
&& operand_equal_for_phi_arg_p (arg1, cond_rhs)
&& ((operand_equal_for_phi_arg_p (rhs2, cond_lhs)
&& absorbing_element_p (code_def, cond_rhs, true, rhs2))
|| (operand_equal_for_phi_arg_p (rhs1, cond_lhs)
&& absorbing_element_p (code_def,
cond_rhs, false, rhs2))))))
{
gsi = gsi_for_stmt (cond);
/* Moving ASSIGN might change VR of lhs, e.g. when moving u_6
def-stmt in:
if (n_5 != 0)
goto <bb 3>;
else
goto <bb 4>;
<bb 3>:
# RANGE [0, 4294967294]
u_6 = n_5 + 4294967295;
<bb 4>:
# u_3 = PHI <u_6(3), 4294967295(2)> */
reset_flow_sensitive_info (lhs);
gimple_stmt_iterator gsi_from;
for (int i = prep_cnt - 1; i >= 0; --i)
{
tree plhs = gimple_assign_lhs (prep_stmt[i]);
reset_flow_sensitive_info (plhs);
gsi_from = gsi_for_stmt (prep_stmt[i]);
gsi_move_before (&gsi_from, &gsi);
}
if (assign)
{
gsi_from = gsi_for_stmt (assign);
gsi_move_before (&gsi_from, &gsi);
}
replace_phi_edge_with_variable (cond_bb, e1, phi, lhs);
return 2;
}
return 0;
}
/* If VAR is an SSA_NAME that points to a BIT_NOT_EXPR then return the TREE for
the value being inverted. */
static tree
strip_bit_not (tree var)
{
if (TREE_CODE (var) != SSA_NAME)
return NULL_TREE;
gimple *assign = SSA_NAME_DEF_STMT (var);
if (gimple_code (assign) != GIMPLE_ASSIGN)
return NULL_TREE;
if (gimple_assign_rhs_code (assign) != BIT_NOT_EXPR)
return NULL_TREE;
return gimple_assign_rhs1 (assign);
}
/* Invert a MIN to a MAX or a MAX to a MIN expression CODE. */
enum tree_code
invert_minmax_code (enum tree_code code)
{
switch (code) {
case MIN_EXPR:
return MAX_EXPR;
case MAX_EXPR:
return MIN_EXPR;
default:
gcc_unreachable ();
}
}
/* The function minmax_replacement does the main work of doing the minmax
replacement. Return true if the replacement is done. Otherwise return
false.
BB is the basic block where the replacement is going to be done on. ARG0
is argument 0 from the PHI. Likewise for ARG1.
If THREEWAY_P then expect the BB to be laid out in diamond shape with each
BB containing only a MIN or MAX expression. */
static bool
minmax_replacement (basic_block cond_bb, basic_block middle_bb, basic_block alt_middle_bb,
edge e0, edge e1, gphi *phi, tree arg0, tree arg1, bool threeway_p)
{
tree result;
edge true_edge, false_edge;
enum tree_code minmax, ass_code;
tree smaller, larger, arg_true, arg_false;
gimple_stmt_iterator gsi, gsi_from;
tree type = TREE_TYPE (PHI_RESULT (phi));
gcond *cond = as_a <gcond *> (*gsi_last_bb (cond_bb));
enum tree_code cmp = gimple_cond_code (cond);
tree rhs = gimple_cond_rhs (cond);
/* Turn EQ/NE of extreme values to order comparisons. */
if ((cmp == NE_EXPR || cmp == EQ_EXPR)
&& TREE_CODE (rhs) == INTEGER_CST
&& INTEGRAL_TYPE_P (TREE_TYPE (rhs)))
{
if (wi::eq_p (wi::to_wide (rhs), wi::min_value (TREE_TYPE (rhs))))
{
cmp = (cmp == EQ_EXPR) ? LT_EXPR : GE_EXPR;
rhs = wide_int_to_tree (TREE_TYPE (rhs),
wi::min_value (TREE_TYPE (rhs)) + 1);
}
else if (wi::eq_p (wi::to_wide (rhs), wi::max_value (TREE_TYPE (rhs))))
{
cmp = (cmp == EQ_EXPR) ? GT_EXPR : LE_EXPR;
rhs = wide_int_to_tree (TREE_TYPE (rhs),
wi::max_value (TREE_TYPE (rhs)) - 1);
}
}
/* This transformation is only valid for order comparisons. Record which
operand is smaller/larger if the result of the comparison is true. */
tree alt_smaller = NULL_TREE;
tree alt_larger = NULL_TREE;
if (cmp == LT_EXPR || cmp == LE_EXPR)
{
smaller = gimple_cond_lhs (cond);
larger = rhs;
/* If we have smaller < CST it is equivalent to smaller <= CST-1.
Likewise smaller <= CST is equivalent to smaller < CST+1. */
if (TREE_CODE (larger) == INTEGER_CST
&& INTEGRAL_TYPE_P (TREE_TYPE (larger)))
{
if (cmp == LT_EXPR)
{
wi::overflow_type overflow;
wide_int alt = wi::sub (wi::to_wide (larger), 1,
TYPE_SIGN (TREE_TYPE (larger)),
&overflow);
if (! overflow)
alt_larger = wide_int_to_tree (TREE_TYPE (larger), alt);
}
else
{
wi::overflow_type overflow;
wide_int alt = wi::add (wi::to_wide (larger), 1,
TYPE_SIGN (TREE_TYPE (larger)),
&overflow);
if (! overflow)
alt_larger = wide_int_to_tree (TREE_TYPE (larger), alt);
}
}
}
else if (cmp == GT_EXPR || cmp == GE_EXPR)
{
smaller = rhs;
larger = gimple_cond_lhs (cond);
/* If we have larger > CST it is equivalent to larger >= CST+1.
Likewise larger >= CST is equivalent to larger > CST-1. */
if (TREE_CODE (smaller) == INTEGER_CST
&& INTEGRAL_TYPE_P (TREE_TYPE (smaller)))
{
wi::overflow_type overflow;
if (cmp == GT_EXPR)
{
wide_int alt = wi::add (wi::to_wide (smaller), 1,
TYPE_SIGN (TREE_TYPE (smaller)),
&overflow);
if (! overflow)
alt_smaller = wide_int_to_tree (TREE_TYPE (smaller), alt);
}
else
{
wide_int alt = wi::sub (wi::to_wide (smaller), 1,
TYPE_SIGN (TREE_TYPE (smaller)),
&overflow);
if (! overflow)
alt_smaller = wide_int_to_tree (TREE_TYPE (smaller), alt);
}
}
}
else
return false;
/* Handle the special case of (signed_type)x < 0 being equivalent
to x > MAX_VAL(signed_type) and (signed_type)x >= 0 equivalent
to x <= MAX_VAL(signed_type). */
if ((cmp == GE_EXPR || cmp == LT_EXPR)
&& INTEGRAL_TYPE_P (type)
&& TYPE_UNSIGNED (type)
&& integer_zerop (rhs))
{
tree op = gimple_cond_lhs (cond);
if (TREE_CODE (op) == SSA_NAME
&& INTEGRAL_TYPE_P (TREE_TYPE (op))
&& !TYPE_UNSIGNED (TREE_TYPE (op)))
{
gimple *def_stmt = SSA_NAME_DEF_STMT (op);
if (gimple_assign_cast_p (def_stmt))
{
tree op1 = gimple_assign_rhs1 (def_stmt);
if (INTEGRAL_TYPE_P (TREE_TYPE (op1))
&& TYPE_UNSIGNED (TREE_TYPE (op1))
&& (TYPE_PRECISION (TREE_TYPE (op))
== TYPE_PRECISION (TREE_TYPE (op1)))
&& useless_type_conversion_p (type, TREE_TYPE (op1)))
{
wide_int w1 = wi::max_value (TREE_TYPE (op));
wide_int w2 = wi::add (w1, 1);
if (cmp == LT_EXPR)
{
larger = op1;
smaller = wide_int_to_tree (TREE_TYPE (op1), w1);
alt_smaller = wide_int_to_tree (TREE_TYPE (op1), w2);
alt_larger = NULL_TREE;
}
else
{
smaller = op1;
larger = wide_int_to_tree (TREE_TYPE (op1), w1);
alt_larger = wide_int_to_tree (TREE_TYPE (op1), w2);
alt_smaller = NULL_TREE;
}
}
}
}
}
/* We need to know which is the true edge and which is the false
edge so that we know if have abs or negative abs. */
extract_true_false_edges_from_block (cond_bb, &true_edge, &false_edge);
/* Forward the edges over the middle basic block. */
if (true_edge->dest == middle_bb)
true_edge = EDGE_SUCC (true_edge->dest, 0);
if (false_edge->dest == middle_bb)
false_edge = EDGE_SUCC (false_edge->dest, 0);
/* When THREEWAY_P then e1 will point to the edge of the final transition
from middle-bb to end. */
if (true_edge == e0)
{
if (!threeway_p)
gcc_assert (false_edge == e1);
arg_true = arg0;
arg_false = arg1;
}
else
{
gcc_assert (false_edge == e0);
if (!threeway_p)
gcc_assert (true_edge == e1);
arg_true = arg1;
arg_false = arg0;
}
if (empty_block_p (middle_bb)
&& (!threeway_p
|| empty_block_p (alt_middle_bb)))
{
if ((operand_equal_for_phi_arg_p (arg_true, smaller)
|| (alt_smaller
&& operand_equal_for_phi_arg_p (arg_true, alt_smaller)))
&& (operand_equal_for_phi_arg_p (arg_false, larger)
|| (alt_larger
&& operand_equal_for_phi_arg_p (arg_true, alt_larger))))
{
/* Case
if (smaller < larger)
rslt = smaller;
else
rslt = larger; */
minmax = MIN_EXPR;
}
else if ((operand_equal_for_phi_arg_p (arg_false, smaller)
|| (alt_smaller
&& operand_equal_for_phi_arg_p (arg_false, alt_smaller)))
&& (operand_equal_for_phi_arg_p (arg_true, larger)
|| (alt_larger
&& operand_equal_for_phi_arg_p (arg_true, alt_larger))))
minmax = MAX_EXPR;
else
return false;
}
else if (HONOR_NANS (type) || HONOR_SIGNED_ZEROS (type))
/* The optimization may be unsafe due to NaNs. */
return false;
else if (middle_bb != alt_middle_bb && threeway_p)
{
/* Recognize the following case:
if (smaller < larger)
a = MIN (smaller, c);
else
b = MIN (larger, c);
x = PHI <a, b>
This is equivalent to
a = MIN (smaller, c);
x = MIN (larger, a); */
gimple *assign = last_and_only_stmt (middle_bb);
tree lhs, op0, op1, bound;
tree alt_lhs, alt_op0, alt_op1;
bool invert = false;
/* When THREEWAY_P then e1 will point to the edge of the final transition
from middle-bb to end. */
if (true_edge == e0)
gcc_assert (false_edge == EDGE_PRED (e1->src, 0));
else
gcc_assert (true_edge == EDGE_PRED (e1->src, 0));
bool valid_minmax_p = false;
gimple_stmt_iterator it1
= gsi_start_nondebug_after_labels_bb (middle_bb);
gimple_stmt_iterator it2
= gsi_start_nondebug_after_labels_bb (alt_middle_bb);
if (gsi_one_nondebug_before_end_p (it1)
&& gsi_one_nondebug_before_end_p (it2))
{
gimple *stmt1 = gsi_stmt (it1);
gimple *stmt2 = gsi_stmt (it2);
if (is_gimple_assign (stmt1) && is_gimple_assign (stmt2))
{
enum tree_code code1 = gimple_assign_rhs_code (stmt1);
enum tree_code code2 = gimple_assign_rhs_code (stmt2);
valid_minmax_p = (code1 == MIN_EXPR || code1 == MAX_EXPR)
&& (code2 == MIN_EXPR || code2 == MAX_EXPR);
}
}
if (!valid_minmax_p)
return false;
if (!assign
|| gimple_code (assign) != GIMPLE_ASSIGN)
return false;
lhs = gimple_assign_lhs (assign);
ass_code = gimple_assign_rhs_code (assign);
if (ass_code != MAX_EXPR && ass_code != MIN_EXPR)
return false;
op0 = gimple_assign_rhs1 (assign);
op1 = gimple_assign_rhs2 (assign);
assign = last_and_only_stmt (alt_middle_bb);
if (!assign
|| gimple_code (assign) != GIMPLE_ASSIGN)
return false;
alt_lhs = gimple_assign_lhs (assign);
if (ass_code != gimple_assign_rhs_code (assign))
return false;
if (!operand_equal_for_phi_arg_p (lhs, arg_true)
|| !operand_equal_for_phi_arg_p (alt_lhs, arg_false))
return false;
alt_op0 = gimple_assign_rhs1 (assign);
alt_op1 = gimple_assign_rhs2 (assign);
if ((operand_equal_for_phi_arg_p (op0, smaller)
|| (alt_smaller
&& operand_equal_for_phi_arg_p (op0, alt_smaller)))
&& (operand_equal_for_phi_arg_p (alt_op0, larger)
|| (alt_larger
&& operand_equal_for_phi_arg_p (alt_op0, alt_larger))))
{
/* We got here if the condition is true, i.e., SMALLER < LARGER. */
if (!operand_equal_for_phi_arg_p (op1, alt_op1))
return false;
if ((arg0 = strip_bit_not (op0)) != NULL
&& (arg1 = strip_bit_not (alt_op0)) != NULL
&& (bound = strip_bit_not (op1)) != NULL)
{
minmax = MAX_EXPR;
ass_code = invert_minmax_code (ass_code);
invert = true;
}
else
{
bound = op1;
minmax = MIN_EXPR;
arg0 = op0;
arg1 = alt_op0;
}
}
else if ((operand_equal_for_phi_arg_p (op0, larger)
|| (alt_larger
&& operand_equal_for_phi_arg_p (op0, alt_larger)))
&& (operand_equal_for_phi_arg_p (alt_op0, smaller)
|| (alt_smaller
&& operand_equal_for_phi_arg_p (alt_op0, alt_smaller))))
{
/* We got here if the condition is true, i.e., SMALLER > LARGER. */
if (!operand_equal_for_phi_arg_p (op1, alt_op1))
return false;
if ((arg0 = strip_bit_not (op0)) != NULL
&& (arg1 = strip_bit_not (alt_op0)) != NULL
&& (bound = strip_bit_not (op1)) != NULL)
{
minmax = MIN_EXPR;
ass_code = invert_minmax_code (ass_code);
invert = true;
}
else
{
bound = op1;
minmax = MAX_EXPR;
arg0 = op0;
arg1 = alt_op0;
}
}
else
return false;
/* Emit the statement to compute min/max. */
location_t locus = gimple_location (last_nondebug_stmt (cond_bb));
gimple_seq stmts = NULL;
tree phi_result = PHI_RESULT (phi);
result = gimple_build (&stmts, locus, minmax, TREE_TYPE (phi_result),
arg0, arg1);
result = gimple_build (&stmts, locus, ass_code, TREE_TYPE (phi_result),
result, bound);
if (invert)
result = gimple_build (&stmts, locus, BIT_NOT_EXPR, TREE_TYPE (phi_result),
result);
gsi = gsi_last_bb (cond_bb);
gsi_insert_seq_before (&gsi, stmts, GSI_NEW_STMT);
replace_phi_edge_with_variable (cond_bb, e1, phi, result);
return true;
}
else if (!threeway_p
|| empty_block_p (alt_middle_bb))
{
/* Recognize the following case, assuming d <= u:
if (a <= u)
b = MAX (a, d);
x = PHI <b, u>
This is equivalent to
b = MAX (a, d);
x = MIN (b, u); */
gimple *assign = last_and_only_stmt (middle_bb);
tree lhs, op0, op1, bound;
if (!single_pred_p (middle_bb))
return false;
if (!assign
|| gimple_code (assign) != GIMPLE_ASSIGN)
return false;
lhs = gimple_assign_lhs (assign);
ass_code = gimple_assign_rhs_code (assign);
if (ass_code != MAX_EXPR && ass_code != MIN_EXPR)
return false;
op0 = gimple_assign_rhs1 (assign);
op1 = gimple_assign_rhs2 (assign);
if (true_edge->src == middle_bb)
{
/* We got here if the condition is true, i.e., SMALLER < LARGER. */
if (!operand_equal_for_phi_arg_p (lhs, arg_true))
return false;
if (operand_equal_for_phi_arg_p (arg_false, larger)
|| (alt_larger
&& operand_equal_for_phi_arg_p (arg_false, alt_larger)))
{
/* Case
if (smaller < larger)
{
r' = MAX_EXPR (smaller, bound)
}
r = PHI <r', larger> --> to be turned to MIN_EXPR. */
if (ass_code != MAX_EXPR)
return false;
minmax = MIN_EXPR;
if (operand_equal_for_phi_arg_p (op0, smaller)
|| (alt_smaller
&& operand_equal_for_phi_arg_p (op0, alt_smaller)))
bound = op1;
else if (operand_equal_for_phi_arg_p (op1, smaller)
|| (alt_smaller
&& operand_equal_for_phi_arg_p (op1, alt_smaller)))
bound = op0;
else
return false;
/* We need BOUND <= LARGER. */
if (!integer_nonzerop (fold_build2 (LE_EXPR, boolean_type_node,
bound, arg_false)))
return false;
}
else if (operand_equal_for_phi_arg_p (arg_false, smaller)
|| (alt_smaller
&& operand_equal_for_phi_arg_p (arg_false, alt_smaller)))
{
/* Case
if (smaller < larger)
{
r' = MIN_EXPR (larger, bound)
}
r = PHI <r', smaller> --> to be turned to MAX_EXPR. */
if (ass_code != MIN_EXPR)
return false;
minmax = MAX_EXPR;
if (operand_equal_for_phi_arg_p (op0, larger)
|| (alt_larger
&& operand_equal_for_phi_arg_p (op0, alt_larger)))
bound = op1;
else if (operand_equal_for_phi_arg_p (op1, larger)
|| (alt_larger
&& operand_equal_for_phi_arg_p (op1, alt_larger)))
bound = op0;
else
return false;
/* We need BOUND >= SMALLER. */
if (!integer_nonzerop (fold_build2 (GE_EXPR, boolean_type_node,
bound, arg_false)))
return false;
}
else
return false;
}
else
{
/* We got here if the condition is false, i.e., SMALLER > LARGER. */
if (!operand_equal_for_phi_arg_p (lhs, arg_false))
return false;
if (operand_equal_for_phi_arg_p (arg_true, larger)
|| (alt_larger
&& operand_equal_for_phi_arg_p (arg_true, alt_larger)))
{
/* Case
if (smaller > larger)
{
r' = MIN_EXPR (smaller, bound)
}
r = PHI <r', larger> --> to be turned to MAX_EXPR. */
if (ass_code != MIN_EXPR)
return false;
minmax = MAX_EXPR;
if (operand_equal_for_phi_arg_p (op0, smaller)
|| (alt_smaller
&& operand_equal_for_phi_arg_p (op0, alt_smaller)))
bound = op1;
else if (operand_equal_for_phi_arg_p (op1, smaller)
|| (alt_smaller
&& operand_equal_for_phi_arg_p (op1, alt_smaller)))
bound = op0;
else
return false;
/* We need BOUND >= LARGER. */
if (!integer_nonzerop (fold_build2 (GE_EXPR, boolean_type_node,
bound, arg_true)))
return false;
}
else if (operand_equal_for_phi_arg_p (arg_true, smaller)
|| (alt_smaller
&& operand_equal_for_phi_arg_p (arg_true, alt_smaller)))
{
/* Case
if (smaller > larger)
{
r' = MAX_EXPR (larger, bound)
}
r = PHI <r', smaller> --> to be turned to MIN_EXPR. */
if (ass_code != MAX_EXPR)
return false;
minmax = MIN_EXPR;
if (operand_equal_for_phi_arg_p (op0, larger))
bound = op1;
else if (operand_equal_for_phi_arg_p (op1, larger))
bound = op0;
else
return false;
/* We need BOUND <= SMALLER. */
if (!integer_nonzerop (fold_build2 (LE_EXPR, boolean_type_node,
bound, arg_true)))
return false;
}
else
return false;
}
/* Move the statement from the middle block. */
gsi = gsi_last_bb (cond_bb);
gsi_from = gsi_last_nondebug_bb (middle_bb);
reset_flow_sensitive_info (SINGLE_SSA_TREE_OPERAND (gsi_stmt (gsi_from),
SSA_OP_DEF));
gsi_move_before (&gsi_from, &gsi);
}
else
return false;
/* Emit the statement to compute min/max. */
gimple_seq stmts = NULL;
tree phi_result = PHI_RESULT (phi);
/* When we can't use a MIN/MAX_EXPR still make sure the expression
stays in a form to be recognized by ISA that map to IEEE x > y ? x : y
semantics (that's not IEEE max semantics). */
if (HONOR_NANS (type) || HONOR_SIGNED_ZEROS (type))
{
result = gimple_build (&stmts, cmp, boolean_type_node,
gimple_cond_lhs (cond), rhs);
result = gimple_build (&stmts, COND_EXPR, TREE_TYPE (phi_result),
result, arg_true, arg_false);
}
else
result = gimple_build (&stmts, minmax, TREE_TYPE (phi_result), arg0, arg1);
gsi = gsi_last_bb (cond_bb);
gsi_insert_seq_before (&gsi, stmts, GSI_NEW_STMT);
replace_phi_edge_with_variable (cond_bb, e1, phi, result);
return true;
}
/* Attempt to optimize (x <=> y) cmp 0 and similar comparisons.
For strong ordering <=> try to match something like:
<bb 2> : // cond3_bb (== cond2_bb)
if (x_4(D) != y_5(D))
goto <bb 3>; [INV]
else
goto <bb 6>; [INV]
<bb 3> : // cond_bb
if (x_4(D) < y_5(D))
goto <bb 6>; [INV]
else
goto <bb 4>; [INV]
<bb 4> : // middle_bb
<bb 6> : // phi_bb
# iftmp.0_2 = PHI <1(4), 0(2), -1(3)>
_1 = iftmp.0_2 == 0;
and for partial ordering <=> something like:
<bb 2> : // cond3_bb
if (a_3(D) == b_5(D))
goto <bb 6>; [50.00%]
else
goto <bb 3>; [50.00%]
<bb 3> [local count: 536870913]: // cond2_bb
if (a_3(D) < b_5(D))
goto <bb 6>; [50.00%]
else
goto <bb 4>; [50.00%]
<bb 4> [local count: 268435456]: // cond_bb
if (a_3(D) > b_5(D))
goto <bb 6>; [50.00%]
else
goto <bb 5>; [50.00%]
<bb 5> [local count: 134217728]: // middle_bb
<bb 6> [local count: 1073741824]: // phi_bb
# SR.27_4 = PHI <0(2), -1(3), 1(4), 2(5)>
_2 = SR.27_4 > 0; */
static bool
spaceship_replacement (basic_block cond_bb, basic_block middle_bb,
edge e0, edge e1, gphi *phi,
tree arg0, tree arg1)
{
tree phires = PHI_RESULT (phi);
if (!INTEGRAL_TYPE_P (TREE_TYPE (phires))
|| TYPE_UNSIGNED (TREE_TYPE (phires))
|| !tree_fits_shwi_p (arg0)
|| !tree_fits_shwi_p (arg1)
|| !IN_RANGE (tree_to_shwi (arg0), -1, 2)
|| !IN_RANGE (tree_to_shwi (arg1), -1, 2))
return false;
basic_block phi_bb = gimple_bb (phi);
gcc_assert (phi_bb == e0->dest && phi_bb == e1->dest);
if (!IN_RANGE (EDGE_COUNT (phi_bb->preds), 3, 4))
return false;
use_operand_p use_p;
gimple *use_stmt;
if (SSA_NAME_OCCURS_IN_ABNORMAL_PHI (phires))
return false;
if (!single_imm_use (phires, &use_p, &use_stmt))
return false;
enum tree_code cmp;
tree lhs, rhs;
gimple *orig_use_stmt = use_stmt;
tree orig_use_lhs = NULL_TREE;
int prec = TYPE_PRECISION (TREE_TYPE (phires));
bool is_cast = false;
/* Deal with the case when match.pd has rewritten the (res & ~1) == 0
into res <= 1 and has left a type-cast for signed types. */
if (gimple_assign_cast_p (use_stmt))
{
orig_use_lhs = gimple_assign_lhs (use_stmt);
/* match.pd would have only done this for a signed type,
so the conversion must be to an unsigned one. */
tree ty1 = TREE_TYPE (gimple_assign_rhs1 (use_stmt));
tree ty2 = TREE_TYPE (orig_use_lhs);
if (!TYPE_UNSIGNED (ty2) || !INTEGRAL_TYPE_P (ty2))
return false;
if (TYPE_PRECISION (ty1) > TYPE_PRECISION (ty2))
return false;
if (SSA_NAME_OCCURS_IN_ABNORMAL_PHI (orig_use_lhs))
return false;
if (!single_imm_use (orig_use_lhs, &use_p, &use_stmt))
return false;
is_cast = true;
}
else if (is_gimple_assign (use_stmt)
&& gimple_assign_rhs_code (use_stmt) == BIT_AND_EXPR
&& TREE_CODE (gimple_assign_rhs2 (use_stmt)) == INTEGER_CST
&& (wi::to_wide (gimple_assign_rhs2 (use_stmt))
== wi::shifted_mask (1, prec - 1, false, prec)))
{
/* For partial_ordering result operator>= with unspec as second
argument is (res & 1) == res, folded by match.pd into
(res & ~1) == 0. */
orig_use_lhs = gimple_assign_lhs (use_stmt);
if (SSA_NAME_OCCURS_IN_ABNORMAL_PHI (orig_use_lhs))
return false;
if (!single_imm_use (orig_use_lhs, &use_p, &use_stmt))
return false;
}
if (gimple_code (use_stmt) == GIMPLE_COND)
{
cmp = gimple_cond_code (use_stmt);
lhs = gimple_cond_lhs (use_stmt);
rhs = gimple_cond_rhs (use_stmt);
}
else if (is_gimple_assign (use_stmt))
{
if (gimple_assign_rhs_class (use_stmt) == GIMPLE_BINARY_RHS)
{
cmp = gimple_assign_rhs_code (use_stmt);
lhs = gimple_assign_rhs1 (use_stmt);
rhs = gimple_assign_rhs2 (use_stmt);
}
else if (gimple_assign_rhs_code (use_stmt) == COND_EXPR)
{
tree cond = gimple_assign_rhs1 (use_stmt);
if (!COMPARISON_CLASS_P (cond))
return false;
cmp = TREE_CODE (cond);
lhs = TREE_OPERAND (cond, 0);
rhs = TREE_OPERAND (cond, 1);
}
else
return false;
}
else
return false;
switch (cmp)
{
case EQ_EXPR:
case NE_EXPR:
case LT_EXPR:
case GT_EXPR:
case LE_EXPR:
case GE_EXPR:
break;
default:
return false;
}
if (lhs != (orig_use_lhs ? orig_use_lhs : phires)
|| !tree_fits_shwi_p (rhs)
|| !IN_RANGE (tree_to_shwi (rhs), -1, 1))
return false;
if (is_cast)
{
if (TREE_CODE (rhs) != INTEGER_CST)
return false;
/* As for -ffast-math we assume the 2 return to be
impossible, canonicalize (unsigned) res <= 1U or
(unsigned) res < 2U into res >= 0 and (unsigned) res > 1U
or (unsigned) res >= 2U as res < 0. */
switch (cmp)
{
case LE_EXPR:
if (!integer_onep (rhs))
return false;
cmp = GE_EXPR;
break;
case LT_EXPR:
if (wi::ne_p (wi::to_widest (rhs), 2))
return false;
cmp = GE_EXPR;
break;
case GT_EXPR:
if (!integer_onep (rhs))
return false;
cmp = LT_EXPR;
break;
case GE_EXPR:
if (wi::ne_p (wi::to_widest (rhs), 2))
return false;
cmp = LT_EXPR;
break;
default:
return false;
}
rhs = build_zero_cst (TREE_TYPE (phires));
}
else if (orig_use_lhs)
{
if ((cmp != EQ_EXPR && cmp != NE_EXPR) || !integer_zerop (rhs))
return false;
/* As for -ffast-math we assume the 2 return to be
impossible, canonicalize (res & ~1) == 0 into
res >= 0 and (res & ~1) != 0 as res < 0. */
cmp = cmp == EQ_EXPR ? GE_EXPR : LT_EXPR;
}
if (!empty_block_p (middle_bb))
return false;
gcond *cond1 = as_a <gcond *> (*gsi_last_bb (cond_bb));
enum tree_code cmp1 = gimple_cond_code (cond1);
switch (cmp1)
{
case LT_EXPR:
case LE_EXPR:
case GT_EXPR:
case GE_EXPR:
break;
default:
return false;
}
tree lhs1 = gimple_cond_lhs (cond1);
tree rhs1 = gimple_cond_rhs (cond1);
/* The optimization may be unsafe due to NaNs. */
if (HONOR_NANS (TREE_TYPE (lhs1)))
return false;
if (TREE_CODE (lhs1) == SSA_NAME && SSA_NAME_OCCURS_IN_ABNORMAL_PHI (lhs1))
return false;
if (TREE_CODE (rhs1) == SSA_NAME && SSA_NAME_OCCURS_IN_ABNORMAL_PHI (rhs1))
return false;
if (!single_pred_p (cond_bb) || !cond_only_block_p (cond_bb))
return false;
basic_block cond2_bb = single_pred (cond_bb);
if (EDGE_COUNT (cond2_bb->succs) != 2)
return false;
edge cond2_phi_edge;
if (EDGE_SUCC (cond2_bb, 0)->dest == cond_bb)
{
if (EDGE_SUCC (cond2_bb, 1)->dest != phi_bb)
return false;
cond2_phi_edge = EDGE_SUCC (cond2_bb, 1);
}
else if (EDGE_SUCC (cond2_bb, 0)->dest != phi_bb)
return false;
else
cond2_phi_edge = EDGE_SUCC (cond2_bb, 0);
tree arg2 = gimple_phi_arg_def (phi, cond2_phi_edge->dest_idx);
if (!tree_fits_shwi_p (arg2))
return false;
gcond *cond2 = safe_dyn_cast <gcond *> (*gsi_last_bb (cond2_bb));
if (!cond2)
return false;
enum tree_code cmp2 = gimple_cond_code (cond2);
tree lhs2 = gimple_cond_lhs (cond2);
tree rhs2 = gimple_cond_rhs (cond2);
if (lhs2 == lhs1)
{
if (!operand_equal_p (rhs2, rhs1, 0))
{
if ((cmp2 == EQ_EXPR || cmp2 == NE_EXPR)
&& TREE_CODE (rhs1) == INTEGER_CST
&& TREE_CODE (rhs2) == INTEGER_CST)
{
/* For integers, we can have cond2 x == 5
and cond1 x < 5, x <= 4, x <= 5, x < 6,
x > 5, x >= 6, x >= 5 or x > 4. */
if (tree_int_cst_lt (rhs1, rhs2))
{
if (wi::ne_p (wi::to_wide (rhs1) + 1, wi::to_wide (rhs2)))
return false;
if (cmp1 == LE_EXPR)
cmp1 = LT_EXPR;
else if (cmp1 == GT_EXPR)
cmp1 = GE_EXPR;
else
return false;
}
else
{
gcc_checking_assert (tree_int_cst_lt (rhs2, rhs1));
if (wi::ne_p (wi::to_wide (rhs2) + 1, wi::to_wide (rhs1)))
return false;
if (cmp1 == LT_EXPR)
cmp1 = LE_EXPR;
else if (cmp1 == GE_EXPR)
cmp1 = GT_EXPR;
else
return false;
}
rhs1 = rhs2;
}
else
return false;
}
}
else if (lhs2 == rhs1)
{
if (rhs2 != lhs1)
return false;
}
else
return false;
tree arg3 = arg2;
basic_block cond3_bb = cond2_bb;
edge cond3_phi_edge = cond2_phi_edge;
gcond *cond3 = cond2;
enum tree_code cmp3 = cmp2;
tree lhs3 = lhs2;
tree rhs3 = rhs2;
if (EDGE_COUNT (phi_bb->preds) == 4)
{
if (absu_hwi (tree_to_shwi (arg2)) != 1)
return false;
if (e1->flags & EDGE_TRUE_VALUE)
{
if (tree_to_shwi (arg0) != 2
|| absu_hwi (tree_to_shwi (arg1)) != 1
|| wi::to_widest (arg1) == wi::to_widest (arg2))
return false;
}
else if (tree_to_shwi (arg1) != 2
|| absu_hwi (tree_to_shwi (arg0)) != 1
|| wi::to_widest (arg0) == wi::to_widest (arg1))
return false;
switch (cmp2)
{
case LT_EXPR:
case LE_EXPR:
case GT_EXPR:
case GE_EXPR:
break;
default:
return false;
}
/* if (x < y) goto phi_bb; else fallthru;
if (x > y) goto phi_bb; else fallthru;
bbx:;
phi_bb:;
is ok, but if x and y are swapped in one of the comparisons,
or the comparisons are the same and operands not swapped,
or the true and false edges are swapped, it is not. */
if ((lhs2 == lhs1)
^ (((cond2_phi_edge->flags
& ((cmp2 == LT_EXPR || cmp2 == LE_EXPR)
? EDGE_TRUE_VALUE : EDGE_FALSE_VALUE)) != 0)
!= ((e1->flags
& ((cmp1 == LT_EXPR || cmp1 == LE_EXPR)
? EDGE_TRUE_VALUE : EDGE_FALSE_VALUE)) != 0)))
return false;
if (!single_pred_p (cond2_bb) || !cond_only_block_p (cond2_bb))
return false;
cond3_bb = single_pred (cond2_bb);
if (EDGE_COUNT (cond2_bb->succs) != 2)
return false;
if (EDGE_SUCC (cond3_bb, 0)->dest == cond2_bb)
{
if (EDGE_SUCC (cond3_bb, 1)->dest != phi_bb)
return false;
cond3_phi_edge = EDGE_SUCC (cond3_bb, 1);
}
else if (EDGE_SUCC (cond3_bb, 0)->dest != phi_bb)
return false;
else
cond3_phi_edge = EDGE_SUCC (cond3_bb, 0);
arg3 = gimple_phi_arg_def (phi, cond3_phi_edge->dest_idx);
cond3 = safe_dyn_cast <gcond *> (*gsi_last_bb (cond3_bb));
if (!cond3)
return false;
cmp3 = gimple_cond_code (cond3);
lhs3 = gimple_cond_lhs (cond3);
rhs3 = gimple_cond_rhs (cond3);
if (lhs3 == lhs1)
{
if (!operand_equal_p (rhs3, rhs1, 0))
return false;
}
else if (lhs3 == rhs1)
{
if (rhs3 != lhs1)
return false;
}
else
return false;
}
else if (absu_hwi (tree_to_shwi (arg0)) != 1
|| absu_hwi (tree_to_shwi (arg1)) != 1
|| wi::to_widest (arg0) == wi::to_widest (arg1))
return false;
if (!integer_zerop (arg3) || (cmp3 != EQ_EXPR && cmp3 != NE_EXPR))
return false;
if ((cond3_phi_edge->flags & (cmp3 == EQ_EXPR
? EDGE_TRUE_VALUE : EDGE_FALSE_VALUE)) == 0)
return false;
/* lhs1 one_cmp rhs1 results in phires of 1. */
enum tree_code one_cmp;
if ((cmp1 == LT_EXPR || cmp1 == LE_EXPR)
^ (!integer_onep ((e1->flags & EDGE_TRUE_VALUE) ? arg1 : arg0)))
one_cmp = LT_EXPR;
else
one_cmp = GT_EXPR;
enum tree_code res_cmp;
switch (cmp)
{
case EQ_EXPR:
if (integer_zerop (rhs))
res_cmp = EQ_EXPR;
else if (integer_minus_onep (rhs))
res_cmp = one_cmp == LT_EXPR ? GT_EXPR : LT_EXPR;
else if (integer_onep (rhs))
res_cmp = one_cmp;
else
return false;
break;
case NE_EXPR:
if (integer_zerop (rhs))
res_cmp = NE_EXPR;
else if (integer_minus_onep (rhs))
res_cmp = one_cmp == LT_EXPR ? LE_EXPR : GE_EXPR;
else if (integer_onep (rhs))
res_cmp = one_cmp == LT_EXPR ? GE_EXPR : LE_EXPR;
else
return false;
break;
case LT_EXPR:
if (integer_onep (rhs))
res_cmp = one_cmp == LT_EXPR ? GE_EXPR : LE_EXPR;
else if (integer_zerop (rhs))
res_cmp = one_cmp == LT_EXPR ? GT_EXPR : LT_EXPR;
else
return false;
break;
case LE_EXPR:
if (integer_zerop (rhs))
res_cmp = one_cmp == LT_EXPR ? GE_EXPR : LE_EXPR;
else if (integer_minus_onep (rhs))
res_cmp = one_cmp == LT_EXPR ? GT_EXPR : LT_EXPR;
else
return false;
break;
case GT_EXPR:
if (integer_minus_onep (rhs))
res_cmp = one_cmp == LT_EXPR ? LE_EXPR : GE_EXPR;
else if (integer_zerop (rhs))
res_cmp = one_cmp;
else
return false;
break;
case GE_EXPR:
if (integer_zerop (rhs))
res_cmp = one_cmp == LT_EXPR ? LE_EXPR : GE_EXPR;
else if (integer_onep (rhs))
res_cmp = one_cmp;
else
return false;
break;
default:
gcc_unreachable ();
}
if (gimple_code (use_stmt) == GIMPLE_COND)
{
gcond *use_cond = as_a <gcond *> (use_stmt);
gimple_cond_set_code (use_cond, res_cmp);
gimple_cond_set_lhs (use_cond, lhs1);
gimple_cond_set_rhs (use_cond, rhs1);
}
else if (gimple_assign_rhs_class (use_stmt) == GIMPLE_BINARY_RHS)
{
gimple_assign_set_rhs_code (use_stmt, res_cmp);
gimple_assign_set_rhs1 (use_stmt, lhs1);
gimple_assign_set_rhs2 (use_stmt, rhs1);
}
else
{
tree cond = build2 (res_cmp, TREE_TYPE (gimple_assign_rhs1 (use_stmt)),
lhs1, rhs1);
gimple_assign_set_rhs1 (use_stmt, cond);
}
update_stmt (use_stmt);
if (MAY_HAVE_DEBUG_BIND_STMTS)
{
use_operand_p use_p;
imm_use_iterator iter;
bool has_debug_uses = false;
bool has_cast_debug_uses = false;
FOR_EACH_IMM_USE_FAST (use_p, iter, phires)
{
gimple *use_stmt = USE_STMT (use_p);
if (orig_use_lhs && use_stmt == orig_use_stmt)
continue;
gcc_assert (is_gimple_debug (use_stmt));
has_debug_uses = true;
break;
}
if (orig_use_lhs)
{
if (!has_debug_uses || is_cast)
FOR_EACH_IMM_USE_FAST (use_p, iter, orig_use_lhs)
{
gimple *use_stmt = USE_STMT (use_p);
gcc_assert (is_gimple_debug (use_stmt));
has_debug_uses = true;
if (is_cast)
has_cast_debug_uses = true;
}
gimple_stmt_iterator gsi = gsi_for_stmt (orig_use_stmt);
tree zero = build_zero_cst (TREE_TYPE (orig_use_lhs));
gimple_assign_set_rhs_with_ops (&gsi, INTEGER_CST, zero);
update_stmt (orig_use_stmt);
}
if (has_debug_uses)
{
/* If there are debug uses, emit something like:
# DEBUG D#1 => i_2(D) > j_3(D) ? 1 : -1
# DEBUG D#2 => i_2(D) == j_3(D) ? 0 : D#1
where > stands for the comparison that yielded 1
and replace debug uses of phi result with that D#2.
Ignore the value of 2, because if NaNs aren't expected,
all floating point numbers should be comparable. */
gimple_stmt_iterator gsi = gsi_after_labels (gimple_bb (phi));
tree type = TREE_TYPE (phires);
tree temp1 = build_debug_expr_decl (type);
tree t = build2 (one_cmp, boolean_type_node, lhs1, rhs2);
t = build3 (COND_EXPR, type, t, build_one_cst (type),
build_int_cst (type, -1));
gimple *g = gimple_build_debug_bind (temp1, t, phi);
gsi_insert_before (&gsi, g, GSI_SAME_STMT);
tree temp2 = build_debug_expr_decl (type);
t = build2 (EQ_EXPR, boolean_type_node, lhs1, rhs2);
t = build3 (COND_EXPR, type, t, build_zero_cst (type), temp1);
g = gimple_build_debug_bind (temp2, t, phi);
gsi_insert_before (&gsi, g, GSI_SAME_STMT);
replace_uses_by (phires, temp2);
if (orig_use_lhs)
{
if (has_cast_debug_uses)
{
tree temp3 = make_node (DEBUG_EXPR_DECL);
DECL_ARTIFICIAL (temp3) = 1;
TREE_TYPE (temp3) = TREE_TYPE (orig_use_lhs);
SET_DECL_MODE (temp3, TYPE_MODE (type));
t = fold_convert (TREE_TYPE (temp3), temp2);
g = gimple_build_debug_bind (temp3, t, phi);
gsi_insert_before (&gsi, g, GSI_SAME_STMT);
replace_uses_by (orig_use_lhs, temp3);
}
else
replace_uses_by (orig_use_lhs, temp2);
}
}
}
if (orig_use_lhs)
{
gimple_stmt_iterator gsi = gsi_for_stmt (orig_use_stmt);
gsi_remove (&gsi, true);
}
gimple_stmt_iterator psi = gsi_for_stmt (phi);
remove_phi_node (&psi, true);
statistics_counter_event (cfun, "spaceship replacement", 1);
return true;
}
/* Optimize x ? __builtin_fun (x) : C, where C is __builtin_fun (0).
Convert
<bb 2>
if (b_4(D) != 0)
goto <bb 3>
else
goto <bb 4>
<bb 3>
_2 = (unsigned long) b_4(D);
_9 = __builtin_popcountl (_2);
OR
_9 = __builtin_popcountl (b_4(D));
<bb 4>
c_12 = PHI <0(2), _9(3)>
Into
<bb 2>
_2 = (unsigned long) b_4(D);
_9 = __builtin_popcountl (_2);
OR
_9 = __builtin_popcountl (b_4(D));
<bb 4>
c_12 = PHI <_9(2)>
Similarly for __builtin_clz or __builtin_ctz if
C?Z_DEFINED_VALUE_AT_ZERO is 2, optab is present and
instead of 0 above it uses the value from that macro. */
static bool
cond_removal_in_builtin_zero_pattern (basic_block cond_bb,
basic_block middle_bb,
edge e1, edge e2, gphi *phi,
tree arg0, tree arg1)
{
gimple_stmt_iterator gsi, gsi_from;
gimple *call;
gimple *cast = NULL;
tree lhs, arg;
/* Check that
_2 = (unsigned long) b_4(D);
_9 = __builtin_popcountl (_2);
OR
_9 = __builtin_popcountl (b_4(D));
are the only stmts in the middle_bb. */
gsi = gsi_start_nondebug_after_labels_bb (middle_bb);
if (gsi_end_p (gsi))
return false;
cast = gsi_stmt (gsi);
gsi_next_nondebug (&gsi);
if (!gsi_end_p (gsi))
{
call = gsi_stmt (gsi);
gsi_next_nondebug (&gsi);
if (!gsi_end_p (gsi))
return false;
}
else
{
call = cast;
cast = NULL;
}
/* Check that we have a popcount/clz/ctz builtin. */
if (!is_gimple_call (call))
return false;
lhs = gimple_get_lhs (call);
if (lhs == NULL_TREE)
return false;
combined_fn cfn = gimple_call_combined_fn (call);
if (gimple_call_num_args (call) != 1
&& (gimple_call_num_args (call) != 2
|| cfn == CFN_CLZ
|| cfn == CFN_CTZ))
return false;
arg = gimple_call_arg (call, 0);
internal_fn ifn = IFN_LAST;
int val = 0;
bool any_val = false;
switch (cfn)
{
case CFN_BUILT_IN_BSWAP16:
case CFN_BUILT_IN_BSWAP32:
case CFN_BUILT_IN_BSWAP64:
case CFN_BUILT_IN_BSWAP128:
CASE_CFN_FFS:
CASE_CFN_PARITY:
CASE_CFN_POPCOUNT:
break;
CASE_CFN_CLZ:
if (INTEGRAL_TYPE_P (TREE_TYPE (arg)))
{
tree type = TREE_TYPE (arg);
if (TREE_CODE (type) == BITINT_TYPE)
{
if (gimple_call_num_args (call) == 1)
{
any_val = true;
ifn = IFN_CLZ;
break;
}
if (!tree_fits_shwi_p (gimple_call_arg (call, 1)))
return false;
HOST_WIDE_INT at_zero = tree_to_shwi (gimple_call_arg (call, 1));
if ((int) at_zero != at_zero)
return false;
ifn = IFN_CLZ;
val = at_zero;
break;
}
if (direct_internal_fn_supported_p (IFN_CLZ, type, OPTIMIZE_FOR_BOTH)
&& CLZ_DEFINED_VALUE_AT_ZERO (SCALAR_INT_TYPE_MODE (type),
val) == 2)
{
ifn = IFN_CLZ;
break;
}
}
return false;
CASE_CFN_CTZ:
if (INTEGRAL_TYPE_P (TREE_TYPE (arg)))
{
tree type = TREE_TYPE (arg);
if (TREE_CODE (type) == BITINT_TYPE)
{
if (gimple_call_num_args (call) == 1)
{
any_val = true;
ifn = IFN_CTZ;
break;
}
if (!tree_fits_shwi_p (gimple_call_arg (call, 1)))
return false;
HOST_WIDE_INT at_zero = tree_to_shwi (gimple_call_arg (call, 1));
if ((int) at_zero != at_zero)
return false;
ifn = IFN_CTZ;
val = at_zero;
break;
}
if (direct_internal_fn_supported_p (IFN_CTZ, type, OPTIMIZE_FOR_BOTH)
&& CTZ_DEFINED_VALUE_AT_ZERO (SCALAR_INT_TYPE_MODE (type),
val) == 2)
{
ifn = IFN_CTZ;
break;
}
}
return false;
case CFN_BUILT_IN_CLRSB:
val = TYPE_PRECISION (integer_type_node) - 1;
break;
case CFN_BUILT_IN_CLRSBL:
val = TYPE_PRECISION (long_integer_type_node) - 1;
break;
case CFN_BUILT_IN_CLRSBLL:
val = TYPE_PRECISION (long_long_integer_type_node) - 1;
break;
default:
return false;
}
if (cast)
{
/* We have a cast stmt feeding popcount/clz/ctz builtin. */
/* Check that we have a cast prior to that. */
if (gimple_code (cast) != GIMPLE_ASSIGN
|| !CONVERT_EXPR_CODE_P (gimple_assign_rhs_code (cast)))
return false;
/* Result of the cast stmt is the argument to the builtin. */
if (arg != gimple_assign_lhs (cast))
return false;
arg = gimple_assign_rhs1 (cast);
}
gcond *cond = dyn_cast <gcond *> (*gsi_last_bb (cond_bb));
/* Cond_bb has a check for b_4 [!=|==] 0 before calling the popcount/clz/ctz
builtin. */
if (!cond
|| (gimple_cond_code (cond) != NE_EXPR
&& gimple_cond_code (cond) != EQ_EXPR)
|| !integer_zerop (gimple_cond_rhs (cond))
|| arg != gimple_cond_lhs (cond))
return false;
/* Canonicalize. */
if ((e2->flags & EDGE_TRUE_VALUE
&& gimple_cond_code (cond) == NE_EXPR)
|| (e1->flags & EDGE_TRUE_VALUE
&& gimple_cond_code (cond) == EQ_EXPR))
{
std::swap (arg0, arg1);
std::swap (e1, e2);
}
/* Check PHI arguments. */
if (lhs != arg0
|| TREE_CODE (arg1) != INTEGER_CST)
return false;
if (any_val)
{
if (!tree_fits_shwi_p (arg1))
return false;
HOST_WIDE_INT at_zero = tree_to_shwi (arg1);
if ((int) at_zero != at_zero)
return false;
val = at_zero;
}
else if (wi::to_wide (arg1) != val)
return false;
/* And insert the popcount/clz/ctz builtin and cast stmt before the
cond_bb. */
gsi = gsi_last_bb (cond_bb);
if (cast)
{
gsi_from = gsi_for_stmt (cast);
gsi_move_before (&gsi_from, &gsi);
reset_flow_sensitive_info (gimple_get_lhs (cast));
}
gsi_from = gsi_for_stmt (call);
if (ifn == IFN_LAST
|| (gimple_call_internal_p (call) && gimple_call_num_args (call) == 2))
gsi_move_before (&gsi_from, &gsi);
else
{
/* For __builtin_c[lt]z* force .C[LT]Z ifn, because only
the latter is well defined at zero. */
call = gimple_build_call_internal (ifn, 2, gimple_call_arg (call, 0),
build_int_cst (integer_type_node, val));
gimple_call_set_lhs (call, lhs);
gsi_insert_before (&gsi, call, GSI_SAME_STMT);
gsi_remove (&gsi_from, true);
}
reset_flow_sensitive_info (lhs);
/* Now update the PHI and remove unneeded bbs. */
replace_phi_edge_with_variable (cond_bb, e2, phi, lhs);
return true;
}
/* Auxiliary functions to determine the set of memory accesses which
can't trap because they are preceded by accesses to the same memory
portion. We do that for MEM_REFs, so we only need to track
the SSA_NAME of the pointer indirectly referenced. The algorithm
simply is a walk over all instructions in dominator order. When
we see an MEM_REF we determine if we've already seen a same
ref anywhere up to the root of the dominator tree. If we do the
current access can't trap. If we don't see any dominating access
the current access might trap, but might also make later accesses
non-trapping, so we remember it. We need to be careful with loads
or stores, for instance a load might not trap, while a store would,
so if we see a dominating read access this doesn't mean that a later
write access would not trap. Hence we also need to differentiate the
type of access(es) seen.
??? We currently are very conservative and assume that a load might
trap even if a store doesn't (write-only memory). This probably is
overly conservative.
We currently support a special case that for !TREE_ADDRESSABLE automatic
variables, it could ignore whether something is a load or store because the
local stack should be always writable. */
/* A hash-table of references (MEM_REF/ARRAY_REF/COMPONENT_REF), and in which
basic block an *_REF through it was seen, which would constitute a
no-trap region for same accesses.
Size is needed to support 2 MEM_REFs of different types, like
MEM<double>(s_1) and MEM<long>(s_1), which would compare equal with
OEP_ADDRESS_OF. */
struct ref_to_bb
{
tree exp;
HOST_WIDE_INT size;
unsigned int phase;
basic_block bb;
};
/* Hashtable helpers. */
struct refs_hasher : free_ptr_hash<ref_to_bb>
{
static inline hashval_t hash (const ref_to_bb *);
static inline bool equal (const ref_to_bb *, const ref_to_bb *);
};
/* Used for quick clearing of the hash-table when we see calls.
Hash entries with phase < nt_call_phase are invalid. */
static unsigned int nt_call_phase;
/* The hash function. */
inline hashval_t
refs_hasher::hash (const ref_to_bb *n)
{
inchash::hash hstate;
inchash::add_expr (n->exp, hstate, OEP_ADDRESS_OF);
hstate.add_hwi (n->size);
return hstate.end ();
}
/* The equality function of *P1 and *P2. */
inline bool
refs_hasher::equal (const ref_to_bb *n1, const ref_to_bb *n2)
{
return operand_equal_p (n1->exp, n2->exp, OEP_ADDRESS_OF)
&& n1->size == n2->size;
}
class nontrapping_dom_walker : public dom_walker
{
public:
nontrapping_dom_walker (cdi_direction direction, hash_set<tree> *ps)
: dom_walker (direction), m_nontrapping (ps), m_seen_refs (128)
{}
edge before_dom_children (basic_block) final override;
void after_dom_children (basic_block) final override;
private:
/* We see the expression EXP in basic block BB. If it's an interesting
expression (an MEM_REF through an SSA_NAME) possibly insert the
expression into the set NONTRAP or the hash table of seen expressions.
STORE is true if this expression is on the LHS, otherwise it's on
the RHS. */
void add_or_mark_expr <