This fixes PR65494 - I don't remember why I re-allocated matches
before recursing into operands. But that at least breaks backtracking.
Bootstrapped and tested on x86_64-unknown-linux-gnu, applied.
Richard.
2015-03-23 Richard Biener <rguent...@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.
Index: gcc/tree-vect-slp.c
===================================================================
--- gcc/tree-vect-slp.c (revision 221532)
+++ gcc/tree-vect-slp.c (working copy)
@@ -926,14 +926,9 @@ vect_build_slp_tree (loop_vec_info loop_
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_
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
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. */
Index: gcc/testsuite/gcc.dg/vect/pr65494.c
===================================================================
--- gcc/testsuite/gcc.dg/vect/pr65494.c (revision 0)
+++ gcc/testsuite/gcc.dg/vect/pr65494.c (working copy)
@@ -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" } } */
