public inbox for gcc-cvs@sourceware.org
help / color / mirror / Atom feed
From: Richard Biener <rguenth@gcc.gnu.org>
To: gcc-cvs@gcc.gnu.org
Subject: [gcc r13-3273] tree-optimization/107160 - avoid reusing multiple accumulators
Date: Thu, 13 Oct 2022 13:17:41 +0000 (GMT)	[thread overview]
Message-ID: <20221013131741.25FA03858C55@sourceware.org> (raw)

https://gcc.gnu.org/g:5cbaf84c191b9a3e3cb26545c808d208bdbf2ab5

commit r13-3273-g5cbaf84c191b9a3e3cb26545c808d208bdbf2ab5
Author: Richard Biener <rguenther@suse.de>
Date:   Thu Oct 13 14:24:05 2022 +0200

    tree-optimization/107160 - avoid reusing multiple accumulators
    
    Epilogue vectorization is not set up to re-use a vectorized
    accumulator consisting of more than one vector.  For non-SLP
    we always reduce to a single but for SLP that isn't happening.
    In such case we currenlty miscompile the epilog so avoid this.
    
            PR tree-optimization/107160
            * tree-vect-loop.cc (vect_create_epilog_for_reduction):
            Do not register accumulator if we failed to reduce it
            to a single vector.
    
            * gcc.dg/vect/pr107160.c: New testcase.

Diff:
---
 gcc/testsuite/gcc.dg/vect/pr107160.c | 41 ++++++++++++++++++++++++++++++++++++
 gcc/tree-vect-loop.cc                |  3 ++-
 2 files changed, 43 insertions(+), 1 deletion(-)

diff --git a/gcc/testsuite/gcc.dg/vect/pr107160.c b/gcc/testsuite/gcc.dg/vect/pr107160.c
new file mode 100644
index 00000000000..4f9f853cafb
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/pr107160.c
@@ -0,0 +1,41 @@
+/* { dg-do run } */
+
+#include <math.h>
+
+#define N 128
+float fl[N];
+
+__attribute__ ((noipa)) void
+init ()
+{
+  for (int i = 0; i < N; i++)
+    fl[i] = i;
+}
+
+__attribute__ ((noipa)) float
+foo (int n1)
+{
+  float sum0, sum1, sum2, sum3;
+  sum0 = sum1 = sum2 = sum3 = 0.0f;
+
+  int n = (n1 / 4) * 4;
+  for (int i = 0; i < n; i += 4)
+    {
+      sum0 += fabs (fl[i]);
+      sum1 += fabs (fl[i + 1]);
+      sum2 += fabs (fl[i + 2]);
+      sum3 += fabs (fl[i + 3]);
+    }
+
+  return sum0 + sum1 + sum2 + sum3;
+}
+
+int
+main ()
+{
+  init ();
+  float res = foo (80);
+  if (res != 3160)
+    __builtin_abort ();
+  return 0;
+}
diff --git a/gcc/tree-vect-loop.cc b/gcc/tree-vect-loop.cc
index 1996ecfee7a..b1442a93581 100644
--- a/gcc/tree-vect-loop.cc
+++ b/gcc/tree-vect-loop.cc
@@ -6232,7 +6232,8 @@ vect_create_epilog_for_reduction (loop_vec_info loop_vinfo,
     }
 
   /* Record this operation if it could be reused by the epilogue loop.  */
-  if (STMT_VINFO_REDUC_TYPE (reduc_info) == TREE_CODE_REDUCTION)
+  if (STMT_VINFO_REDUC_TYPE (reduc_info) == TREE_CODE_REDUCTION
+      && vec_num == 1)
     loop_vinfo->reusable_accumulators.put (scalar_results[0],
 					   { orig_reduc_input, reduc_info });

                 reply	other threads:[~2022-10-13 13:17 UTC|newest]

Thread overview: [no followups] expand[flat|nested]  mbox.gz  Atom feed

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20221013131741.25FA03858C55@sourceware.org \
    --to=rguenth@gcc.gnu.org \
    --cc=gcc-cvs@gcc.gnu.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).