The following avoids creating a niter peeling epilog more consistently,
matching what peeling later uses for the skip_vector condition, in
particular when versioning is required which then also ensures the
vector loop is entered unless the epilog is vectorized. This should
ideally match LOOP_VINFO_VERSIONING_THRESHOLD which is only computed
later, some refactoring could make that better matching.
The patch also makes sure to adjust the upper bound of the epilogues
when we do not have a skip edge around the vector loop.
Bootstrapped and tested on x86_64-unknown-linux-gnu.
Tamar, I assume this will clash with early break vectorization
a bit so I'll defer until after that's in.
Thanks,
Richard.
PR tree-optimization/113026
* tree-vect-loop.cc (vect_need_peeling_or_partial_vectors_p):
Avoid an epilog in more cases.
* tree-vect-loop-manip.cc (vect_do_peeling): Adjust the
epilogues niter upper bounds and estimates.
* gcc.dg/torture/pr113026-1.c: New testcase.
* gcc.dg/torture/pr113026-2.c: Likewise.
---
gcc/testsuite/gcc.dg/torture/pr113026-1.c | 11 +++++++++++
gcc/testsuite/gcc.dg/torture/pr113026-2.c | 18 ++++++++++++++++++
gcc/tree-vect-loop-manip.cc | 13 +++++++++++++
gcc/tree-vect-loop.cc | 6 +++++-
4 files changed, 47 insertions(+), 1 deletion(-)
create mode 100644 gcc/testsuite/gcc.dg/torture/pr113026-1.c
create mode 100644 gcc/testsuite/gcc.dg/torture/pr113026-2.c
diff --git a/gcc/testsuite/gcc.dg/torture/pr113026-1.c
b/gcc/testsuite/gcc.dg/torture/pr113026-1.c
new file mode 100644
index 00000000000..56dfef3b36c
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/torture/pr113026-1.c
@@ -0,0 +1,11 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-Wall" } */
+
+char dst[16];
+
+void
+foo (char *src, long n)
+{
+ for (long i = 0; i < n; i++)
+ dst[i] = src[i]; /* { dg-bogus "" } */
+}
diff --git a/gcc/testsuite/gcc.dg/torture/pr113026-2.c
b/gcc/testsuite/gcc.dg/torture/pr113026-2.c
new file mode 100644
index 00000000000..b9d5857a403
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/torture/pr113026-2.c
@@ -0,0 +1,18 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-Wall" } */
+
+char dst1[17];
+void
+foo1 (char *src, long n)
+{
+ for (long i = 0; i < n; i++)
+ dst1[i] = src[i]; /* { dg-bogus "" } */
+}
+
+char dst2[18];
+void
+foo2 (char *src, long n)
+{
+ for (long i = 0; i < n; i++)
+ dst2[i] = src[i]; /* { dg-bogus "" } */
+}
diff --git a/gcc/tree-vect-loop-manip.cc b/gcc/tree-vect-loop-manip.cc
index bcd90a331f5..07a30b7ee98 100644
--- a/gcc/tree-vect-loop-manip.cc
+++ b/gcc/tree-vect-loop-manip.cc
@@ -3193,6 +3193,19 @@ vect_do_peeling (loop_vec_info loop_vinfo, tree niters,
tree nitersm1,
bb_before_epilog->count = single_pred_edge
(bb_before_epilog)->count ();
bb_before_epilog = loop_preheader_edge (epilog)->src;
}
+ else
+ {
+ /* When we do not have a loop-around edge to the epilog we know
+ the vector loop covered at least VF scalar iterations. Update
+ any known upper bound with this knowledge. */
+ if (loop->any_upper_bound)
+ epilog->nb_iterations_upper_bound -= constant_lower_bound (vf);
+ if (loop->any_likely_upper_bound)
+ epilog->nb_iterations_likely_upper_bound -= constant_lower_bound
(vf);
+ if (loop->any_estimate)
+ epilog->nb_iterations_estimate -= constant_lower_bound (vf);
+ }
+
/* If loop is peeled for non-zero constant times, now niters refers to
orig_niters - prolog_peeling, it won't overflow even the orig_niters
overflows. */
diff --git a/gcc/tree-vect-loop.cc b/gcc/tree-vect-loop.cc
index 7a3db5f098b..a4dd2caa400 100644
--- a/gcc/tree-vect-loop.cc
+++ b/gcc/tree-vect-loop.cc
@@ -1260,7 +1260,11 @@ vect_need_peeling_or_partial_vectors_p (loop_vec_info
loop_vinfo)
the epilogue is unnecessary. */
&& (!LOOP_REQUIRES_VERSIONING (loop_vinfo)
|| ((unsigned HOST_WIDE_INT) max_niter
- > (th / const_vf) * const_vf))))
+ /* We'd like to use LOOP_VINFO_VERSIONING_THRESHOLD
+ but that's only computed later based on our result.
+ The following is the most conservative approximation. */
+ > (std::max ((unsigned HOST_WIDE_INT) th,
+ const_vf) / const_vf) * const_vf))))
return true;
return false;
--
2.35.3
