The following fixes an oversight when handling permuted non-grouped
.MASK_LOAD SLP discovery.
Bootstrapped and tested on x86_64-unknown-linux-gnu. This requires
1/2.
PR tree-optimization/117050
* tree-vect-slp.cc (vect_build_slp_tree_2): Properly handle
non-grouped masked loads when handling permutations.
* gcc.dg/vect/pr117050.c: New testcase.
---
gcc/testsuite/gcc.dg/vect/pr117050.c | 18 ++++++++++++++++++
gcc/tree-vect-slp.cc | 15 ++++++++-------
2 files changed, 26 insertions(+), 7 deletions(-)
create mode 100644 gcc/testsuite/gcc.dg/vect/pr117050.c
diff --git a/gcc/testsuite/gcc.dg/vect/pr117050.c
b/gcc/testsuite/gcc.dg/vect/pr117050.c
new file mode 100644
index 00000000000..7b12cbc9ef4
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/pr117050.c
@@ -0,0 +1,18 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-mavx2" { target { x86_64-*-* i?86-*-* } } } */
+
+typedef struct {
+ char *data;
+} song_sample_t;
+typedef struct {
+ int right_ramp;
+ int left_ramp;
+} song_voice_t;
+song_sample_t *csf_stop_sample_smp, *csf_stop_sample_v_3;
+song_voice_t *csf_stop_sample_v;
+void csf_stop_sample()
+{
+ for (int i; i; i++, csf_stop_sample_v++)
+ if (csf_stop_sample_v_3 || csf_stop_sample_smp->data)
+ csf_stop_sample_v->left_ramp = csf_stop_sample_v->right_ramp = 0;
+}
diff --git a/gcc/tree-vect-slp.cc b/gcc/tree-vect-slp.cc
index 796fc4ba577..dd8f1befa25 100644
--- a/gcc/tree-vect-slp.cc
+++ b/gcc/tree-vect-slp.cc
@@ -1986,7 +1986,8 @@ vect_build_slp_tree_2 (vec_info *vinfo, slp_tree node,
stmt_vec_info load_info;
load_permutation.create (group_size);
stmt_vec_info first_stmt_info
- = DR_GROUP_FIRST_ELEMENT (SLP_TREE_SCALAR_STMTS (node)[0]);
+ = STMT_VINFO_GROUPED_ACCESS (stmt_info)
+ ? DR_GROUP_FIRST_ELEMENT (stmt_info) : stmt_info;
bool any_permute = false;
bool any_null = false;
FOR_EACH_VEC_ELT (SLP_TREE_SCALAR_STMTS (node), j, load_info)
@@ -2045,17 +2046,17 @@ vect_build_slp_tree_2 (vec_info *vinfo, slp_tree node,
{
/* Discover the whole unpermuted load. */
vec<stmt_vec_info> stmts2;
- stmts2.create (DR_GROUP_SIZE (first_stmt_info));
- stmts2.quick_grow_cleared (DR_GROUP_SIZE (first_stmt_info));
+ unsigned dr_group_size = STMT_VINFO_GROUPED_ACCESS (stmt_info)
+ ? DR_GROUP_SIZE (first_stmt_info) : 1;
+ stmts2.create (dr_group_size);
+ stmts2.quick_grow_cleared (dr_group_size);
unsigned i = 0;
for (stmt_vec_info si = first_stmt_info;
si; si = DR_GROUP_NEXT_ELEMENT (si))
stmts2[i++] = si;
- bool *matches2
- = XALLOCAVEC (bool, DR_GROUP_SIZE (first_stmt_info));
+ bool *matches2 = XALLOCAVEC (bool, dr_group_size);
slp_tree unperm_load
- = vect_build_slp_tree (vinfo, stmts2,
- DR_GROUP_SIZE (first_stmt_info),
+ = vect_build_slp_tree (vinfo, stmts2, dr_group_size,
&this_max_nunits, matches2, limit,
&this_tree_size, bst_map);
/* When we are able to do the full masked load emit that
--
2.43.0
