I am not sure I understand this. I tried doing this. If I add -1 and rhs1
for the NEGATE_EXPR to ops list, when it come to rewrite_expr_tree constant
will be sorted early and would make it hard to generate:
x + (-y * z * z) => x - y * z * z
Do you want to swap the constant in MULT_EXPR chain (if present) like in
swap_ops_for_binary_stmt and then create a NEGATE_EXPR ?
In addition to linearize_expr handling you need to handle a -1 in the MULT_EXPR
chain specially at rewrite_expr_tree time by emitting a NEGATE_EXPR instead
of a MULT_EXPR (which also means you should sort the -1 "last").
Hi Richard,
Thanks. Here is an attempt which does this.
Regression tested and bootstrapped on x86-64-linux-gnu with no new
regressions.
Is this OK for trunk?
Thanks,
Kugan
2016-04-23 Kugan Vivekanandarajah <kug...@linaro.org>
PR middle-end/40921
* gcc.dg/tree-ssa/pr40921.c: New test.
gcc/ChangeLog:
2016-04-23 Kugan Vivekanandarajah <kug...@linaro.org>
PR middle-end/40921
* tree-ssa-reassoc.c (try_special_add_to_ops): New.
(linearize_expr_tree): Call try_special_add_to_ops.
(reassociate_bb): Convert MULT_EXPR by (-1) to NEGATE_EXPR.
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr40921.c
b/gcc/testsuite/gcc.dg/tree-ssa/pr40921.c
index e69de29..f587a8f 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/pr40921.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/pr40921.c
@@ -0,0 +1,20 @@
+
+/* { dg-do compile } */
+/* { dg-options "-O2 -fdump-tree-optimized -ffast-math" } */
+
+unsigned int foo (unsigned int x, unsigned int y, unsigned int z)
+{
+ return x + (-y * z*z);
+}
+
+float bar (float x, float y, float z)
+{
+ return x + (-y * z*z);
+}
+
+float bar (float x, float y, float z)
+{
+ return x + (-y * z*z * 5.0);
+}
+
+/* { dg-final { scan-tree-dump-times "_* = -y_" 0 "optimized" } } */
diff --git a/gcc/tree-ssa-reassoc.c b/gcc/tree-ssa-reassoc.c
index d23dabd..1b38207 100644
--- a/gcc/tree-ssa-reassoc.c
+++ b/gcc/tree-ssa-reassoc.c
@@ -4252,6 +4252,45 @@ acceptable_pow_call (gimple *stmt, tree *base,
HOST_WIDE_INT *exponent)
return true;
}
+/* Try to derive and add operand entry for OP to *OPS. Return false if
+ unsuccessful. */
+
+static bool
+try_special_add_to_ops (vec<operand_entry *> *ops,
+ enum tree_code code,
+ tree op, gimple* def_stmt)
+{
+ tree base = NULL_TREE;
+ HOST_WIDE_INT exponent = 0;
+
+ if (TREE_CODE (op) != SSA_NAME)
+ return false;
+
+ if (code == MULT_EXPR
+ && acceptable_pow_call (def_stmt, &base, &exponent))
+ {
+ add_repeat_to_ops_vec (ops, base, exponent);
+ gimple_set_visited (def_stmt, true);
+ return true;
+ }
+ else if (code == MULT_EXPR
+ && is_gimple_assign (def_stmt)
+ && gimple_assign_rhs_code (def_stmt) == NEGATE_EXPR
+ && !HONOR_SNANS (TREE_TYPE (op))
+ && (!HONOR_SIGNED_ZEROS (TREE_TYPE (op))
+ || !COMPLEX_FLOAT_TYPE_P (TREE_TYPE (op))))
+ {
+ tree rhs1 = gimple_assign_rhs1 (def_stmt);
+ tree cst = build_minus_one_cst (TREE_TYPE (op));
+ add_to_ops_vec (ops, rhs1);
+ add_to_ops_vec (ops, cst);
+ gimple_set_visited (def_stmt, true);
+ return true;
+ }
+
+ return false;
+}
+
/* Recursively linearize a binary expression that is the RHS of STMT.
Place the operands of the expression tree in the vector named OPS. */
@@ -4266,8 +4305,6 @@ linearize_expr_tree (vec<operand_entry *> *ops, gimple
*stmt,
bool binrhsisreassoc = false;
enum tree_code rhscode = gimple_assign_rhs_code (stmt);
struct loop *loop = loop_containing_stmt (stmt);
- tree base = NULL_TREE;
- HOST_WIDE_INT exponent = 0;
if (set_visited)
gimple_set_visited (stmt, true);
@@ -4303,26 +4340,11 @@ linearize_expr_tree (vec<operand_entry *> *ops, gimple
*stmt,
if (!binrhsisreassoc)
{
- if (rhscode == MULT_EXPR
- && TREE_CODE (binrhs) == SSA_NAME
- && acceptable_pow_call (binrhsdef, &base, &exponent))
- {
- add_repeat_to_ops_vec (ops, base, exponent);
- gimple_set_visited (binrhsdef, true);
- }
- else
+ if (!try_special_add_to_ops (ops, rhscode, binrhs, binrhsdef))
add_to_ops_vec (ops, binrhs);
- if (rhscode == MULT_EXPR
- && TREE_CODE (binlhs) == SSA_NAME
- && acceptable_pow_call (binlhsdef, &base, &exponent))
- {
- add_repeat_to_ops_vec (ops, base, exponent);
- gimple_set_visited (binlhsdef, true);
- }
- else
+ if (!try_special_add_to_ops (ops, rhscode, binlhs, binlhsdef))
add_to_ops_vec (ops, binlhs);
-
return;
}
@@ -4360,14 +4382,7 @@ linearize_expr_tree (vec<operand_entry *> *ops, gimple
*stmt,
linearize_expr_tree (ops, SSA_NAME_DEF_STMT (binlhs),
is_associative, set_visited);
- if (rhscode == MULT_EXPR
- && TREE_CODE (binrhs) == SSA_NAME
- && acceptable_pow_call (SSA_NAME_DEF_STMT (binrhs), &base, &exponent))
- {
- add_repeat_to_ops_vec (ops, base, exponent);
- gimple_set_visited (SSA_NAME_DEF_STMT (binrhs), true);
- }
- else
+ if (!try_special_add_to_ops (ops, rhscode, binrhs, binrhsdef))
add_to_ops_vec (ops, binrhs);
}
@@ -5127,6 +5142,19 @@ reassociate_bb (basic_block bb)
powi_result = attempt_builtin_powi (stmt, &ops);
}
+ int last = ops.length () - 1;
+ bool negate_result = false;
+ if (rhs_code == MULT_EXPR
+ && ops.length () > 1
+ && ((TREE_CODE (ops[last]->op) == INTEGER_CST
+ && integer_minus_onep (ops[last]->op))
+ || ((TREE_CODE (ops[last]->op) == REAL_CST)
+ && real_equal (&TREE_REAL_CST (ops[last]->op),
&dconstm1))))
+ {
+ ops.unordered_remove (last);
+ negate_result = true;
+ }
+
/* If the operand vector is now empty, all operands were
consumed by the __builtin_powi optimization. */
if (ops.length () == 0)
@@ -5169,6 +5197,17 @@ reassociate_bb (basic_block bb)
powi_result != NULL);
}
+ if (negate_result)
+ {
+ tree tmp = make_ssa_name (TREE_TYPE (lhs));
+ gimple_set_lhs (stmt, tmp);
+ gassign *neg_stmt = gimple_build_assign (lhs, NEGATE_EXPR,
+ tmp);
+ gimple_stmt_iterator gsi = gsi_for_stmt (stmt);
+ gsi_insert_after (&gsi, neg_stmt, GSI_NEW_STMT);
+ update_stmt (stmt);
+ }
+
/* If we combined some repeated factors into a
__builtin_powi call, multiply that result by the
reassociated operands. */
