@@ -6963,6 +6963,12 @@ This is firstly introduced on ARM/AArch64 targets, please refer to
the hook implementation for how different fusion types are supported.
@end deftypefn
+@deftypefn {Target Hook} void TARGET_EXPAND_DIVMOD_LIBFUNC (bool @var{unsignedp}, machine_mode @var{mode}, @var{rtx}, @var{rtx}, rtx *@var{quot}, rtx *@var{rem})
+Define this hook if the port does not have hardware div and divmod insn for
+the given mode but has divmod libfunc, which is incompatible
+with libgcc2.c:__udivmoddi4
+@end deftypefn
+
@node Sections
@section Dividing the Output into Sections (Texts, Data, @dots{})
@c the above section title is WAY too long. maybe cut the part between
@@ -4848,6 +4848,8 @@ them: try the first ones in this list first.
@hook TARGET_SCHED_FUSION_PRIORITY
+@hook TARGET_EXPAND_DIVMOD_LIBFUNC
+
@node Sections
@section Dividing the Output into Sections (Texts, Data, @dots{})
@c the above section title is WAY too long. maybe cut the part between
@@ -2276,6 +2276,48 @@ multi_vector_optab_supported_p (convert_optab optab, tree_pair types,
#define direct_mask_store_optab_supported_p direct_optab_supported_p
#define direct_store_lanes_optab_supported_p multi_vector_optab_supported_p
+/* Expand DIVMOD() using:
+ a) optab handler for udivmod/sdivmod if it is available.
+ b) If optab_handler doesn't exist, Generate call to
+ optab_libfunc for udivmod/sdivmod. */
+
+static void
+expand_DIVMOD (internal_fn, gcall *stmt)
+{
+ tree lhs = gimple_call_lhs (stmt);
+ tree arg0 = gimple_call_arg (stmt, 0);
+ tree arg1 = gimple_call_arg (stmt, 1);
+
+ gcc_assert (TREE_CODE (TREE_TYPE (lhs)) == COMPLEX_TYPE);
+ tree type = TREE_TYPE (TREE_TYPE (lhs));
+ machine_mode mode = TYPE_MODE (type);
+ bool unsignedp = TYPE_UNSIGNED (type);
+ optab tab = (unsignedp) ? udivmod_optab : sdivmod_optab;
+
+ rtx op0 = expand_normal (arg0);
+ rtx op1 = expand_normal (arg1);
+ rtx target = expand_expr (lhs, NULL_RTX, VOIDmode, EXPAND_WRITE);
+
+ rtx quotient, remainder;
+
+ /* Check if optab handler exists for [u]divmod. */
+ if (optab_handler (tab, mode) != CODE_FOR_nothing)
+ {
+ quotient = gen_reg_rtx (mode);
+ remainder = gen_reg_rtx (mode);
+ expand_twoval_binop (tab, op0, op1, quotient, remainder, unsignedp);
+ }
+ else
+ targetm.expand_divmod_libfunc (unsignedp, mode, op0, op1,
+ "ient, &remainder);
+
+ /* Wrap the return value (quotient, remainder) within COMPLEX_EXPR. */
+ expand_expr (build2 (COMPLEX_EXPR, TREE_TYPE (lhs),
+ make_tree (TREE_TYPE (arg0), quotient),
+ make_tree (TREE_TYPE (arg1), remainder)),
+ target, VOIDmode, EXPAND_NORMAL);
+}
+
/* Return true if FN is supported for the types in TYPES when the
optimization type is OPT_TYPE. The types are those associated with
the "type0" and "type1" fields of FN's direct_internal_fn_info
@@ -194,6 +194,9 @@ DEF_INTERNAL_FN (ATOMIC_BIT_TEST_AND_SET, ECF_LEAF | ECF_NOTHROW, NULL)
DEF_INTERNAL_FN (ATOMIC_BIT_TEST_AND_COMPLEMENT, ECF_LEAF | ECF_NOTHROW, NULL)
DEF_INTERNAL_FN (ATOMIC_BIT_TEST_AND_RESET, ECF_LEAF | ECF_NOTHROW, NULL)
+/* Divmod function. */
+DEF_INTERNAL_FN (DIVMOD, ECF_CONST | ECF_LEAF, NULL)
+
#undef DEF_INTERNAL_INT_FN
#undef DEF_INTERNAL_FLT_FN
#undef DEF_INTERNAL_OPTAB_FN
@@ -4948,6 +4948,16 @@ Normally, this is not needed.",
bool, (const_tree field, machine_mode mode),
default_member_type_forces_blk)
+/* See tree-ssa-math-opts.c:divmod_candidate_p for conditions that gate
+ the divmod transform. */
+DEFHOOK
+(expand_divmod_libfunc,
+ "Define this hook if the port does not have hardware div and divmod insn for\n\
+the given mode but has divmod libfunc, which is incompatible\n\
+with libgcc2.c:__udivmoddi4",
+ void, (bool unsignedp, machine_mode mode, rtx, rtx, rtx *quot, rtx *rem),
+ default_expand_divmod_libfunc)
+
/* Return the class for a secondary reload, and fill in extra information. */
DEFHOOK
(secondary_reload,
@@ -1965,4 +1965,31 @@ default_optab_supported_p (int, machine_mode, machine_mode, optimization_type)
return true;
}
+/* Generate call to
+ DImode __udivmoddi4 (DImode op0, DImode op1, DImode *rem). */
+
+void
+default_expand_divmod_libfunc (bool unsignedp, machine_mode mode,
+ rtx op0, rtx op1,
+ rtx *quot_p, rtx *rem_p)
+{
+ gcc_assert (mode == DImode);
+ gcc_assert (unsignedp);
+
+ rtx libfunc = optab_libfunc (udivmod_optab, DImode);
+ gcc_assert (libfunc);
+
+ rtx remainder = assign_stack_temp (DImode, GET_MODE_SIZE (DImode));
+ rtx address = XEXP (remainder, 0);
+
+ rtx quotient = emit_library_call_value (libfunc, NULL_RTX, LCT_CONST,
+ DImode, 3,
+ op0, GET_MODE (op0),
+ op1, GET_MODE (op1),
+ address, GET_MODE (address));
+
+ *quot_p = quotient;
+ *rem_p = remainder;
+}
+
#include "gt-targhooks.h"
@@ -254,4 +254,7 @@ extern void default_setup_incoming_vararg_bounds (cumulative_args_t ca ATTRIBUTE
extern bool default_optab_supported_p (int, machine_mode, machine_mode,
optimization_type);
+extern void default_expand_divmod_libfunc (bool, machine_mode,
+ rtx, rtx, rtx *, rtx *);
+
#endif /* GCC_TARGHOOKS_H */
@@ -112,6 +112,9 @@ along with GCC; see the file COPYING3. If not see
#include "params.h"
#include "internal-fn.h"
#include "case-cfn-macros.h"
+#include "optabs-libfuncs.h"
+#include "tree-eh.h"
+#include "targhooks.h"
/* This structure represents one basic block that either computes a
division, or is a common dominator for basic block that compute a
@@ -184,6 +187,9 @@ static struct
/* Number of fp fused multiply-add ops inserted. */
int fmas_inserted;
+
+ /* Number of divmod calls inserted. */
+ int divmod_calls_inserted;
} widen_mul_stats;
/* The instance of "struct occurrence" representing the highest
@@ -3784,6 +3790,228 @@ match_uaddsub_overflow (gimple_stmt_iterator *gsi, gimple *stmt,
return true;
}
+/* Return true if target has support for divmod. */
+
+static bool
+target_supports_divmod_p (optab divmod_optab, optab div_optab, machine_mode mode)
+{
+ /* If target supports hardware divmod insn, use it for divmod. */
+ if (optab_handler (divmod_optab, mode) != CODE_FOR_nothing)
+ return true;
+
+ /* Check if libfunc for divmod is available. */
+ rtx libfunc = optab_libfunc (divmod_optab, mode);
+ if (libfunc != NULL_RTX)
+ {
+ /* If optab_handler exists for div_optab, perhaps in a wider mode,
+ we don't want to use the libfunc even if it exists for given mode. */
+ for (machine_mode div_mode = mode;
+ div_mode != VOIDmode;
+ div_mode = GET_MODE_WIDER_MODE (div_mode))
+ if (optab_handler (div_optab, div_mode) != CODE_FOR_nothing)
+ return false;
+
+ /* FIXME: This is a hack to workaround an issue with optab_libfunc().
+ optab_libfunc (sdivmod_optab, DImode) returns libfunc "__divmoddi4",
+ although __divmoddi4() does not exist in libgcc. For now, enable the
+ transform only if libfunc is guaranteed to be __udivmoddi4. */
+ return (targetm.expand_divmod_libfunc != default_expand_divmod_libfunc
+ || !strcmp (XSTR (libfunc, 0), "__udivmoddi4"));
+ }
+
+ return false;
+}
+
+/* Check if stmt is candidate for divmod transform. */
+
+static bool
+divmod_candidate_p (gassign *stmt)
+{
+ tree type = TREE_TYPE (gimple_assign_lhs (stmt));
+ enum machine_mode mode = TYPE_MODE (type);
+ optab divmod_optab, div_optab;
+
+ if (TYPE_UNSIGNED (type))
+ {
+ divmod_optab = udivmod_optab;
+ div_optab = udiv_optab;
+ }
+ else
+ {
+ divmod_optab = sdivmod_optab;
+ div_optab = sdiv_optab;
+ }
+
+ tree op1 = gimple_assign_rhs1 (stmt);
+ tree op2 = gimple_assign_rhs2 (stmt);
+
+ /* Disable the transform if either is a constant, since division-by-constant
+ may have specialized expansion. */
+ if (CONSTANT_CLASS_P (op1) || CONSTANT_CLASS_P (op2))
+ return false;
+
+ /* Exclude the case where TYPE_OVERFLOW_TRAPS (type) as that should
+ expand using the [su]divv optabs. */
+ if (TYPE_OVERFLOW_TRAPS (type))
+ return false;
+
+ if (!target_supports_divmod_p (divmod_optab, div_optab, mode))
+ return false;
+
+ return true;
+}
+
+/* This function looks for:
+ t1 = a TRUNC_DIV_EXPR b;
+ t2 = a TRUNC_MOD_EXPR b;
+ and transforms it to the following sequence:
+ complex_tmp = DIVMOD (a, b);
+ t1 = REALPART_EXPR(a);
+ t2 = IMAGPART_EXPR(b);
+ For conditions enabling the transform see divmod_candidate_p().
+
+ The pass works in two phases:
+ 1) Walk through all immediate uses of stmt's operand and find a
+ TRUNC_DIV_EXPR with matching operands and if such a stmt is found add
+ it to stmts vector.
+ 2) Insert DIVMOD call before first div/mod stmt in top_bb (basic block that
+ dominates other div/mod stmts with same operands) and update entries in
+ stmts vector to use return value of DIMOVD (REALEXPR_PART for div,
+ IMAGPART_EXPR for mod). */
+
+static bool
+convert_to_divmod (gassign *stmt)
+{
+ if (!divmod_candidate_p (stmt))
+ return false;
+
+ tree op1 = gimple_assign_rhs1 (stmt);
+ tree op2 = gimple_assign_rhs2 (stmt);
+
+ imm_use_iterator use_iter;
+ gimple *use_stmt;
+ auto_vec<gimple *> stmts;
+
+ gimple *top_stmt = stmt;
+ basic_block top_bb = gimple_bb (stmt);
+
+ /* Try to set top_stmt to "topmost" stmt
+ with code TRUNC_DIV_EXPR/TRUNC_MOD_EXPR having same operands as stmt. */
+
+ FOR_EACH_IMM_USE_STMT (use_stmt, use_iter, op1)
+ {
+ if (is_gimple_assign (use_stmt)
+ && (gimple_assign_rhs_code (use_stmt) == TRUNC_DIV_EXPR
+ || gimple_assign_rhs_code (use_stmt) == TRUNC_MOD_EXPR)
+ && operand_equal_p (op1, gimple_assign_rhs1 (use_stmt), 0)
+ && operand_equal_p (op2, gimple_assign_rhs2 (use_stmt), 0))
+ {
+ if (stmt_can_throw_internal (use_stmt))
+ continue;
+
+ basic_block bb = gimple_bb (use_stmt);
+
+ if (bb == top_bb)
+ {
+ if (gimple_uid (use_stmt) < gimple_uid (top_stmt))
+ top_stmt = use_stmt;
+ }
+ else if (dominated_by_p (CDI_DOMINATORS, top_bb, bb))
+ {
+ top_bb = bb;
+ top_stmt = use_stmt;
+ }
+ }
+ }
+
+ if (top_stmt == stmt && stmt_can_throw_internal (top_stmt))
+ return false;
+
+ tree top_op1 = gimple_assign_rhs1 (top_stmt);
+ tree top_op2 = gimple_assign_rhs2 (top_stmt);
+
+ stmts.safe_push (top_stmt);
+ bool div_seen = (gimple_assign_rhs_code (top_stmt) == TRUNC_DIV_EXPR);
+
+ /* Ensure that gimple_bb (use_stmt) is dominated by top_bb. */
+
+ FOR_EACH_IMM_USE_STMT (use_stmt, use_iter, top_op1)
+ {
+ if (is_gimple_assign (use_stmt)
+ && (gimple_assign_rhs_code (use_stmt) == TRUNC_DIV_EXPR
+ || gimple_assign_rhs_code (use_stmt) == TRUNC_MOD_EXPR)
+ && operand_equal_p (top_op1, gimple_assign_rhs1 (use_stmt), 0)
+ && operand_equal_p (top_op2, gimple_assign_rhs2 (use_stmt), 0))
+ {
+ if (use_stmt == top_stmt)
+ continue;
+
+ if (stmt_can_throw_internal (use_stmt))
+ continue;
+
+ if (!dominated_by_p (CDI_DOMINATORS, gimple_bb (use_stmt), top_bb))
+ {
+ end_imm_use_stmt_traverse (&use_iter);
+ return false;
+ }
+
+ stmts.safe_push (use_stmt);
+ if (gimple_assign_rhs_code (use_stmt) == TRUNC_DIV_EXPR)
+ div_seen = true;
+ }
+ }
+
+ if (!div_seen)
+ return false;
+
+ /* Create libcall to internal fn DIVMOD:
+ divmod_tmp = DIVMOD (op1, op2). */
+
+ gcall *call_stmt = gimple_build_call_internal (IFN_DIVMOD, 2, op1, op2);
+ tree res = make_temp_ssa_name (
+ build_complex_type (TREE_TYPE (op1)),
+ call_stmt, "divmod_tmp");
+ gimple_call_set_lhs (call_stmt, res);
+
+ /* Insert the call before top_stmt. */
+ gimple_stmt_iterator top_stmt_gsi = gsi_for_stmt (top_stmt);
+ gsi_insert_before (&top_stmt_gsi, call_stmt, GSI_SAME_STMT);
+
+ widen_mul_stats.divmod_calls_inserted++;
+
+ /* Update all statements in stmts.
+ if stmt is lhs = op1 TRUNC_DIV_EXPR op2, change to lhs = REALPART_EXPR<divmod_tmp>
+ if stmt is lhs = op1 TRUNC_MOD_EXPR op2, change to lhs = IMAGPART_EXPR<divmod_tmp>. */
+
+ bool cfg_changed = false;
+ for (unsigned i = 0; stmts.iterate (i, &use_stmt); ++i)
+ {
+ tree new_rhs;
+
+ switch (gimple_assign_rhs_code (use_stmt))
+ {
+ case TRUNC_DIV_EXPR:
+ new_rhs = fold_build1 (REALPART_EXPR, TREE_TYPE (op1), res);
+ break;
+
+ case TRUNC_MOD_EXPR:
+ new_rhs = fold_build1 (IMAGPART_EXPR, TREE_TYPE (op2), res);
+ break;
+
+ default:
+ gcc_unreachable ();
+ }
+
+ gimple_stmt_iterator gsi = gsi_for_stmt (use_stmt);
+ gimple_assign_set_rhs_from_tree (&gsi, new_rhs);
+ update_stmt (use_stmt);
+
+ if (maybe_clean_or_replace_eh_stmt (use_stmt, use_stmt))
+ cfg_changed = true;
+ }
+
+ return cfg_changed;
+}
/* Find integer multiplications where the operands are extended from
smaller types, and replace the MULT_EXPR with a WIDEN_MULT_EXPR
@@ -3828,6 +4056,8 @@ pass_optimize_widening_mul::execute (function *fun)
bool cfg_changed = false;
memset (&widen_mul_stats, 0, sizeof (widen_mul_stats));
+ calculate_dominance_info (CDI_DOMINATORS);
+ renumber_gimple_stmt_uids ();
FOR_EACH_BB_FN (bb, fun)
{
@@ -3861,6 +4091,10 @@ pass_optimize_widening_mul::execute (function *fun)
match_uaddsub_overflow (&gsi, stmt, code);
break;
+ case TRUNC_MOD_EXPR:
+ cfg_changed = convert_to_divmod (as_a<gassign *> (stmt));
+ break;
+
default:;
}
}
@@ -3907,6 +4141,8 @@ pass_optimize_widening_mul::execute (function *fun)
widen_mul_stats.maccs_inserted);
statistics_counter_event (fun, "fused multiply-adds inserted",
widen_mul_stats.fmas_inserted);
+ statistics_counter_event (fun, "divmod calls inserted",
+ widen_mul_stats.divmod_calls_inserted);
return cfg_changed ? TODO_cleanup_cfg : 0;
}