OpenE2K/gcc
2
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

re PR tree-optimization/64909 (Missed vectorization with bdver1)

Browse Source 
2015-02-10  Richard Biener  <rguenther@suse.de>

	PR tree-optimization/64909
	* tree-vect-loop.c (vect_estimate_min_profitable_iters): Properly
	pass a scalar-stmt count estimate to the cost model.
	* tree-vect-data-refs.c (vect_peeling_hash_get_lowest_cost): Likewise.

	* gcc.dg/vect/costmodel/x86_64/costmodel-pr64909.c: New testcase.

From-SVN: r220580
This commit is contained in:
Richard Biener 2015-02-10 11:48:47 +00:00 committed by Richard Biener
parent 644a47612e
commit 696814edb8
5 changed files with 42 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
gcc/ChangeLog
View File

@ -1,3 +1,10 @@
2015-02-10 Richard Biener <rguenther@suse.de>
PR tree-optimization/64909
* tree-vect-loop.c (vect_estimate_min_profitable_iters): Properly
pass a scalar-stmt count estimate to the cost model.
* tree-vect-data-refs.c (vect_peeling_hash_get_lowest_cost): Likewise.
2015-02-10 Alexander Monakov <amonakov@ispras.ru>
* doc/invoke.texi (-fvar-tracking-assignments): Clarify that VTA is

5
gcc/testsuite/ChangeLog
View File

@ -1,3 +1,8 @@
2015-02-10 Richard Biener <rguenther@suse.de>
PR tree-optimization/64909
* gcc.dg/vect/costmodel/x86_64/costmodel-pr64909.c: New testcase.
2015-02-10 Rainer Orth <ro@CeBiTec.Uni-Bielefeld.DE>
* gcc.dg/signbit-sa.c: New test.

15
gcc/testsuite/gcc.dg/vect/costmodel/x86_64/costmodel-pr64909.c Normal file
View File

@ -0,0 +1,15 @@
/* { dg-do compile } */
/* { dg-require-effective-target vect_int } */
/* { dg-additional-options "-mtune=bdver1" } */
unsigned short a[32];
unsigned int b[32];
void t()
{
int i;
for (i=0;i<12;i++)
b[i]=a[i];
}
/* { dg-final { scan-tree-dump "vectorized 1 loops in function" "vect" } } */
/* { dg-final { cleanup-tree-dump "vect" } } */

11
gcc/tree-vect-data-refs.c
View File

@ -1184,10 +1184,13 @@ vect_peeling_hash_get_lowest_cost (_vect_peel_info **slot,
}
single_iter_cost = vect_get_single_scalar_iteration_cost (loop_vinfo);
outside_cost += vect_get_known_peeling_cost (loop_vinfo, elem->npeel,
&dummy, single_iter_cost,
&prologue_cost_vec,
&epilogue_cost_vec);
outside_cost += vect_get_known_peeling_cost
(loop_vinfo, elem->npeel, &dummy,
/* ??? We use this cost as number of stmts with scalar_stmt cost,
thus divide by that. This introduces rounding errors, thus better
introduce a new cost kind (raw_cost? scalar_iter_cost?). */
single_iter_cost / vect_get_stmt_cost (scalar_stmt),
&prologue_cost_vec, &epilogue_cost_vec);
/* Prologue and epilogue costs are added to the target model later.
These costs depend only on the scalar iteration cost, the

11
gcc/tree-vect-loop.c
View File

@ -2834,6 +2834,11 @@ vect_estimate_min_profitable_iters (loop_vec_info loop_vinfo,
statements. */
scalar_single_iter_cost = vect_get_single_scalar_iteration_cost (loop_vinfo);
/* ??? Below we use this cost as number of stmts with scalar_stmt cost,
thus divide by that. This introduces rounding errors, thus better
introduce a new cost kind (raw_cost? scalar_iter_cost?). */
int scalar_single_iter_stmts
= scalar_single_iter_cost / vect_get_stmt_cost (scalar_stmt);
/* Add additional cost for the peeled instructions in prologue and epilogue
loop.
@ -2868,10 +2873,10 @@ vect_estimate_min_profitable_iters (loop_vec_info loop_vinfo,
/* FORNOW: Don't attempt to pass individual scalar instructions to
the model; just assume linear cost for scalar iterations. */
(void) add_stmt_cost (target_cost_data,
peel_iters_prologue * scalar_single_iter_cost,
peel_iters_prologue * scalar_single_iter_stmts,
scalar_stmt, NULL, 0, vect_prologue);
(void) add_stmt_cost (target_cost_data,
peel_iters_epilogue * scalar_single_iter_cost,
peel_iters_epilogue * scalar_single_iter_stmts,
scalar_stmt, NULL, 0, vect_epilogue);
}
else
@ -2887,7 +2892,7 @@ vect_estimate_min_profitable_iters (loop_vec_info loop_vinfo,
(void) vect_get_known_peeling_cost (loop_vinfo, peel_iters_prologue,
&peel_iters_epilogue,
scalar_single_iter_cost,
scalar_single_iter_stmts,
&prologue_cost_vec,
&epilogue_cost_vec);