re PR tree-optimization/71347 (Performance drop after r235513 on x86-64 in 32-bit mode.)

PR tree-optimization/71347
	* tree-ssa-loop-ivopts.c (determine_group_iv_cost_address): Compute
	cost for all uses in group.

	PR tree-optimization/71347
	* gcc.dg/tree-ssa/pr71347.c: New test.

From-SVN: r237552
This commit is contained in:
Bin Cheng 2016-06-17 09:26:05 +00:00 committed by Bin Cheng
parent bd8fb1146e
commit d3ee260a28
4 changed files with 34 additions and 25 deletions

View File

@ -1,3 +1,9 @@
2016-06-17 Bin Cheng <bin.cheng@arm.com>
PR tree-optimization/71347
* tree-ssa-loop-ivopts.c (determine_group_iv_cost_address): Compute
cost for all uses in group.
2016-06-17 Bin Cheng <bin.cheng@arm.com>
* tree-vect-loop.c (vect_create_epilog_for_reduction): Only

View File

@ -1,3 +1,8 @@
2016-06-17 Bin Cheng <bin.cheng@arm.com>
PR tree-optimization/71347
* gcc.dg/tree-ssa/pr71347.c: New test.
2016-06-17 Bin Cheng <bin.cheng@arm.com>
PR tree-optimization/71354

View File

@ -0,0 +1,17 @@
/* { dg-do compile } */
/* { dg-options "-O2 -fdump-tree-optimized" } */
double in;
extern void Write (double);
void foo (void)
{
static double X[9];
int i;
X[1] = in * in;
for (i = 2; i <= 8; i++)
X[i] = X[i - 1] * X[1];
Write (X[5]);
}
/* Load of X[i - i] can be omitted by reusing X[i] in previous iteration. */
/* { dg-final { scan-tree-dump-not ".* = MEM.*;" "optimized"} } */

View File

@ -5115,7 +5115,7 @@ determine_group_iv_cost_address (struct ivopts_data *data,
{
unsigned i;
bitmap depends_on;
bool can_autoinc, first = true;
bool can_autoinc;
iv_inv_expr_ent *inv_expr = NULL;
struct iv_use *use = group->vuses[0];
comp_cost sum_cost = no_cost, cost;
@ -5142,30 +5142,11 @@ determine_group_iv_cost_address (struct ivopts_data *data,
{
struct iv_use *next = group->vuses[i];
/* Compute cost for the first use with different offset to the main
use and add it afterwards. Costs for these uses could be quite
different. Given below uses in a group:
use 0 : {base + A + offset_0, step}
use 0.1: {base + A + offset_0, step}
use 0.2: {base + A + offset_1, step}
use 0.3: {base + A + offset_2, step}
when we need to compute costs with candidate:
cand 1 : {base + B + offset_0, step}
The first use with different offset is use 0.2, its cost is larger
than cost of use 0/0.1 because we need to compute:
A - B + offset_1 - offset_0
rather than:
A - B. */
if (first && next->addr_offset != use->addr_offset)
{
first = false;
cost = get_computation_cost (data, next, cand, true,
NULL, &can_autoinc, NULL);
/* Remove setup cost. */
if (!cost.infinite_cost_p ())
cost -= cost.scratch;
}
/* TODO: We could skip computing cost for sub iv_use when it has the
same cost as the first iv_use, but the cost really depends on the
offset and where the iv_use is. */
cost = get_computation_cost (data, next, cand, true,
NULL, &can_autoinc, NULL);
sum_cost += cost;
}
set_group_iv_cost (data, group, cand, sum_cost, depends_on,