FreeChainXenon/gcc
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

re PR tree-optimization/65494 (Loop is not vectorized because of operand canonicalization.)

Browse source 
2015-03-23  Richard Biener  <rguenther@suse.de>

	PR tree-optimization/65494
	* tree-vect-slp.c (vect_build_slp_tree): Do not (re-)allocate
	matches here.
	(vect_analyze_slp_instance): But do that here, always and once.

	* gcc.dg/vect/pr65494.c: New testcase.

From-SVN: r221592
This commit is contained in:
Richard Biener 2015-03-23 12:47:54 +00:00 • committed by Richard Biener
parent c61928d098
commit 89d390e57a
4 changed files with 44 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

7
gcc/ChangeLog
View file

@ -1,3 +1,10 @@
2015-03-23 Richard Biener <rguenther@suse.de>
PR tree-optimization/65494
* tree-vect-slp.c (vect_build_slp_tree): Do not (re-)allocate
matches here.
(vect_analyze_slp_instance): But do that here, always and once.
2015-03-23 Kyrylo Tkachov <kyrylo.tkachov@arm.com>
* expmed.c (synth_mult): Fix comment about multiplying by T-1 and

5
gcc/testsuite/ChangeLog
View file

@ -1,3 +1,8 @@
2015-03-23 Richard Biener <rguenther@suse.de>
PR tree-optimization/65494
* gcc.dg/vect/pr65494.c: New testcase.
2015-03-23 Jakub Jelinek <jakub@redhat.com>
PR preprocessor/65238

28
gcc/testsuite/gcc.dg/vect/pr65494.c Normal file
View file

@ -0,0 +1,28 @@
/* { dg-do compile } */
/* { dg-additional-options "-Ofast -funroll-loops" } */
typedef unsigned char uchar;
typedef struct rgb_ {uchar r; uchar g; uchar b;} rgb;
#define N 512
rgb in[N], out[N];
float c[N];
void foo(int n)
{
int i, j;
for (i = 0; i < n; i++) //in and out are RGB byte arrays
{
float r = 0, g = 0, b = 0;
for (j = 0; j < 5; j++)
{
r += (float)in[i + j].r * c[j];
g += (float)in[i + j].g * c[j];
b += (float)in[i + j].b * c[j];
}
out[i].r = (uchar)r;
out[i].g = (uchar)g;
out[i].b = (uchar)b;
}
}
/* { dg-final { scan-tree-dump "vectorized 1 loops in function" "vect" { target { vect_float && vect_intfloat_cvt } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */

12
gcc/tree-vect-slp.c
View file

@ -926,14 +926,9 @@ vect_build_slp_tree (loop_vec_info loop_vinfo, bb_vec_info bb_vinfo,
bool *matches, unsigned *npermutes, unsigned *tree_size,
unsigned max_tree_size)
{
unsigned nops, i, this_npermutes = 0, this_tree_size = 0;
unsigned nops, i, this_tree_size = 0;
gimple stmt;
if (!matches)
matches = XALLOCAVEC (bool, group_size);
if (!npermutes)
npermutes = &this_npermutes;
matches[0] = false;
stmt = SLP_TREE_SCALAR_STMTS (*node)[0];
@ -1012,7 +1007,6 @@ vect_build_slp_tree (loop_vec_info loop_vinfo, bb_vec_info bb_vinfo,
return false;
}
bool *matches = XALLOCAVEC (bool, group_size);
if (vect_build_slp_tree (loop_vinfo, bb_vinfo, &child,
group_size, max_nunits, loads,
vectorization_factor, matches,
@ -1637,9 +1631,11 @@ vect_analyze_slp_instance (loop_vec_info loop_vinfo, bb_vec_info bb_vinfo,
loads.create (group_size);
/* Build the tree for the SLP instance. */
bool *matches = XALLOCAVEC (bool, group_size);
unsigned npermutes = 0;
if (vect_build_slp_tree (loop_vinfo, bb_vinfo, &node, group_size,
&max_nunits, &loads,
vectorization_factor, NULL, NULL, NULL,
vectorization_factor, matches, &npermutes, NULL,
max_tree_size))
{
/* Calculate the unrolling factor based on the smallest type. */