From: Yuri Rumyantsev <ysrumyan@gmail.com>
To: gcc-patches <gcc-patches@gcc.gnu.org>,
Igor Zamyatin <izamyatin@gmail.com>,
Richard Biener <richard.guenther@gmail.com>
Subject: [PATCH] Simple fix to enhance outer-loop vectorization.
Date: Thu, 28 May 2015 11:32:00 -0000 [thread overview]
Message-ID: <CAEoMCqQgN9=EV7vo8HnSfnEv3f762BMEeLr5egub8ioK8Zxk+A@mail.gmail.com> (raw)
[-- Attachment #1: Type: text/plain, Size: 568 bytes --]
Hi All,
Here is a simple patch which removes restriction on outer-loop
vectorization - allow references in inner-loop with zero step. This
case was found in one important benchmark.
Bootstrap and regression testing did not show any new failures.
Is it OK for trunk.
ChangeLog:
2015-05-28 Yuri Rumyantsev <ysrumyan@gmail.com>
* tree-vect-data-refs.c (vect_analyze_data_ref_access): Allow
consecutive accesses within outer-loop vectorization for references
with zero step in inner-loop.
gcc/testsuite/ChangeLog:
* gcc.dg/vect/fast-math-vect-outer-1.c: New test.
[-- Attachment #2: patch --]
[-- Type: application/octet-stream, Size: 1886 bytes --]
Index: testsuite/gcc.dg/vect/fast-math-vect-outer-1.c
===================================================================
--- testsuite/gcc.dg/vect/fast-math-vect-outer-1.c (revision 0)
+++ testsuite/gcc.dg/vect/fast-math-vect-outer-1.c (working copy)
@@ -0,0 +1,30 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target vect_float } */
+/* { dg-require-effective-target vect_simd_clones } */
+/* { dg-additional-options "-fopenmp-simd" } */
+
+extern float *px, *py, *tx, *ty, *x, *y;
+#define N 64
+static void inline bar(float cx, float cy, float *vx, float *vy)
+{
+ int j;
+ for (j = 0; j < N; ++j)
+ {
+ const float dx = cx - px[j];
+ const float dy = cy - py[j];
+ *vx += dx * tx[j];
+ *vy -= dy * ty[j];
+ }
+}
+
+void foo ()
+{
+ int i;
+
+#pragma omp simd
+ for (i = 0; i < N; i++)
+ bar(px[i],py[i],x+i,y+i);
+}
+
+/* { dg-final { scan-tree-dump "OUTER LOOP VECTORIZED" "vect" } } */
+/* { dg-final { cleanup-tree-dump "vect" } } */
Index: tree-vect-data-refs.c
===================================================================
--- tree-vect-data-refs.c (revision 223653)
+++ tree-vect-data-refs.c (working copy)
@@ -2261,7 +2261,6 @@
return true;
}
-
/* Analyze the access pattern of the data-reference DR.
In case of non-consecutive accesses call vect_analyze_group_access() to
analyze groups of accesses. */
@@ -2291,14 +2290,8 @@
if (loop_vinfo && integer_zerop (step))
{
GROUP_FIRST_ELEMENT (vinfo_for_stmt (stmt)) = NULL;
- if (nested_in_vect_loop_p (loop, stmt))
- {
- if (dump_enabled_p ())
- dump_printf_loc (MSG_NOTE, vect_location,
- "zero step in inner loop of nest\n");
- return false;
- }
- return DR_IS_READ (dr);
+ if (!nested_in_vect_loop_p (loop, stmt))
+ return DR_IS_READ (dr);
}
if (loop && nested_in_vect_loop_p (loop, stmt))
next reply other threads:[~2015-05-28 11:00 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-05-28 11:32 Yuri Rumyantsev [this message]
2015-05-28 11:56 ` Richard Biener
2015-05-28 17:15 ` Yuri Rumyantsev
2015-06-01 10:51 ` Richard Biener
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='CAEoMCqQgN9=EV7vo8HnSfnEv3f762BMEeLr5egub8ioK8Zxk+A@mail.gmail.com' \
--to=ysrumyan@gmail.com \
--cc=gcc-patches@gcc.gnu.org \
--cc=izamyatin@gmail.com \
--cc=richard.guenther@gmail.com \
/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).