[RFC][PATCH][PR40921] Convert x + (-y * z * z) into x - y * z * z
Kugan Vivekanandarajah
kugan.vivekanandarajah@linaro.org
Wed May 18 08:38:00 GMT 2016
>>> Please move the whole thing under the else { } case of the ops.length
>>> == 0, ops.length == 1 test chain
>>> as you did for the actual emit of the negate.
>>>
>>
>> I see your point. However, when we remove the (-1) from the ops list, that
>> intern can result in ops.length becoming 1. Therefore, I moved the the
>> following if (negate_result), outside the condition.
>
> Ah, indeed. But now you have to care for ops.length () == 0 and thus
> the unconditonally ops.last () may now trap. So I suggest to
> do
Done.
> Yes - the patch is ok with the above suggested change.
While testing on an arm variant, vector types are not handled.
Therefore, I had to change:
+ || ((TREE_CODE (last->op) == REAL_CST)
+ && real_equal (&TREE_REAL_CST (last->op), &dconstm1))
to
+ || real_minus_onep (last->op))
Is this Still OK. Bootstrap and regression testing on ARM, AARCH64 and
x86-64 didn’t have any new regressions.
Thanks,
Kugan
-------------- next part --------------
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr40921.c b/gcc/testsuite/gcc.dg/tree-ssa/pr40921.c
index e69de29..3a5a23a 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/pr40921.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/pr40921.c
@@ -0,0 +1,26 @@
+
+/* { 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 bar2 (float x, float y, float z)
+{
+ return x + (-y * z * z * 5.0f);
+}
+
+float bar3 (float x, float y, float z)
+{
+ return x + (-y * x * -z);
+}
+
+
+/* { dg-final { scan-tree-dump-times "_* = -y_" 0 "optimized" } } */
diff --git a/gcc/tree-ssa-reassoc.c b/gcc/tree-ssa-reassoc.c
index 7408977..b54e3eb 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);
@@ -4303,24 +4340,10 @@ 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 +4383,7 @@ 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 +5143,24 @@ reassociate_bb (basic_block bb)
powi_result = attempt_builtin_powi (stmt, &ops);
}
+ operand_entry *last;
+ bool negate_result = false;
+ if (ops.length () > 1
+ && rhs_code == MULT_EXPR)
+ {
+ last = ops.last ();
+ if (((TREE_CODE (last->op) == INTEGER_CST
+ && integer_minus_onep (last->op))
+ || real_minus_onep (last->op))
+ && !HONOR_SNANS (TREE_TYPE (lhs))
+ && (!HONOR_SIGNED_ZEROS (TREE_TYPE (lhs))
+ || !COMPLEX_FLOAT_TYPE_P (TREE_TYPE (lhs))))
+ {
+ ops.pop ();
+ negate_result = true;
+ }
+ }
+
/* If the operand vector is now empty, all operands were
consumed by the __builtin_powi optimization. */
if (ops.length () == 0)
@@ -5189,6 +5223,18 @@ reassociate_bb (basic_block bb)
gsi_insert_after (&gsi, mul_stmt, GSI_NEW_STMT);
}
}
+
+ if (negate_result)
+ {
+ stmt = SSA_NAME_DEF_STMT (lhs);
+ 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);
+ }
}
}
}
More information about the Gcc-patches
mailing list