The following fixes missed optimizations due to the strange way we
split stores in BB vectorization. The solution is to split at
the failure boundary and not re-align that to the initial piece
chosen vector size. Also re-analyze any larger matching rest.
Bootstrapped / tested on x86_64-unknown-linux-gnu, pushed.
2020-10-28 Richard Biener <rguent...@suse.de>
* tree-vect-slp.c (vect_build_slp_instance): Split the store
group at the failure boundary and also re-analyze a large enough
matching rest.
* gcc.dg/vect/bb-slp-68.c: New testcase.
---
gcc/testsuite/gcc.dg/vect/bb-slp-68.c | 22 ++++++++++++++++++++++
gcc/tree-vect-slp.c | 20 +++++++++++++-------
2 files changed, 35 insertions(+), 7 deletions(-)
create mode 100644 gcc/testsuite/gcc.dg/vect/bb-slp-68.c
diff --git a/gcc/testsuite/gcc.dg/vect/bb-slp-68.c
b/gcc/testsuite/gcc.dg/vect/bb-slp-68.c
new file mode 100644
index 00000000000..8718031cc71
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/bb-slp-68.c
@@ -0,0 +1,22 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target vect_double } */
+/* { dg-additional-options "-mavx" { target avx } } */
+
+double x[10], y[6], z[4];
+
+void foo ()
+{
+ x[0] = y[0];
+ x[1] = y[1];
+ x[2] = y[2];
+ x[3] = y[3];
+ x[4] = y[4];
+ x[5] = y[5];
+ x[6] = z[0] + 1.;
+ x[7] = z[1] + 1.;
+ x[8] = z[2] + 1.;
+ x[9] = z[3] + 1.;
+}
+
+/* We want to have the store group split into 4, 2, 4 when using 32byte
vectors. */
+/* { dg-final { scan-tree-dump-not "from scalars" "slp2" } } */
diff --git a/gcc/tree-vect-slp.c b/gcc/tree-vect-slp.c
index 470b67d76b5..50a2d37eb25 100644
--- a/gcc/tree-vect-slp.c
+++ b/gcc/tree-vect-slp.c
@@ -2412,15 +2412,21 @@ vect_build_slp_instance (vec_info *vinfo,
group1_size);
bool res = vect_analyze_slp_instance (vinfo, bst_map, stmt_info,
max_tree_size);
- /* If the first non-match was in the middle of a vector,
- skip the rest of that vector. Do not bother to re-analyze
- single stmt groups. */
- if (group1_size < i)
+ /* Split the rest at the failure point and possibly
+ re-analyze the remaining matching part if it has
+ at least two lanes. */
+ if (group1_size < i
+ && (i + 1 < group_size
+ || i - group1_size > 1))
{
- i = group1_size + const_nunits;
- if (i + 1 < group_size)
- rest = vect_split_slp_store_group (rest, const_nunits);
+ stmt_vec_info rest2 = rest;
+ rest = vect_split_slp_store_group (rest, i - group1_size);
+ if (i - group1_size > 1)
+ res |= vect_analyze_slp_instance (vinfo, bst_map,
+ rest2, max_tree_size);
}
+ /* Re-analyze the non-matching tail if it has at least
+ two lanes. */
if (i + 1 < group_size)
res |= vect_analyze_slp_instance (vinfo, bst_map,
rest, max_tree_size);
--
2.26.2
