This makes sure to use splats early when facing uniform internal
operands in BB SLP discovery rather than relying on the late
heuristincs re-building nodes from scratch.
Bootstrapped and tested on x86_64-unknown-linux-gnu, pushed.
2020-10-27 Richard Biener <rguent...@suse.de>
* tree-vect-slp.c (vect_build_slp_tree_2): When vectorizing
BBs splat uniform operands and stop SLP discovery.
* gcc.target/i386/pr95866-1.c: Adjust.
---
gcc/testsuite/gcc.target/i386/pr95866-1.c | 2 +-
gcc/tree-vect-slp.c | 22 ++++++++++++++++++++++
2 files changed, 23 insertions(+), 1 deletion(-)
diff --git a/gcc/testsuite/gcc.target/i386/pr95866-1.c
b/gcc/testsuite/gcc.target/i386/pr95866-1.c
index 991370cf669..553d415eed8 100644
--- a/gcc/testsuite/gcc.target/i386/pr95866-1.c
+++ b/gcc/testsuite/gcc.target/i386/pr95866-1.c
@@ -13,6 +13,6 @@ void foo(int i)
/* We should not use vector operations for i + 1 and (i + 1) & 31 but
instead use { j, j, j, j }. */
-/* { dg-final { scan-tree-dump-times "Building parent vector operands from
scalars" 2 "slp2" } } */
+/* { dg-final { scan-tree-dump-times "Using a splat of the uniform operand" 2
"slp2" } } */
/* { dg-final { scan-tree-dump-not " = \{i_" "slp2" } } */
/* { dg-final { scan-tree-dump-times " = \{j_" 1 "slp2" } } */
diff --git a/gcc/tree-vect-slp.c b/gcc/tree-vect-slp.c
index 894f045c0fe..85865dae1ab 100644
--- a/gcc/tree-vect-slp.c
+++ b/gcc/tree-vect-slp.c
@@ -1486,6 +1486,28 @@ vect_build_slp_tree_2 (vec_info *vinfo,
continue;
}
+ if (is_a <bb_vec_info> (vinfo)
+ && oprnd_info->first_dt == vect_internal_def)
+ {
+ /* For BB vectorization, if all defs are the same do not
+ bother to continue the build along the single-lane
+ graph but use a splat of the scalar value. */
+ stmt_vec_info first_def = oprnd_info->def_stmts[0];
+ for (j = 1; j < group_size; ++j)
+ if (oprnd_info->def_stmts[j] != first_def)
+ break;
+ if (j == group_size
+ /* But avoid doing this for loads where we may be
+ able to CSE things. */
+ && !gimple_vuse (first_def->stmt))
+ {
+ if (dump_enabled_p ())
+ dump_printf_loc (MSG_NOTE, vect_location,
+ "Using a splat of the uniform operand\n");
+ oprnd_info->first_dt = vect_external_def;
+ }
+ }
+
if (oprnd_info->first_dt != vect_internal_def
&& oprnd_info->first_dt != vect_reduction_def
&& oprnd_info->first_dt != vect_induction_def)
--
2.26.2
