public inbox for gcc-cvs@sourceware.org
help / color / mirror / Atom feed
From: Roger Sayle <sayle@gcc.gnu.org>
To: gcc-cvs@gcc.gnu.org
Subject: [gcc r12-3073] Fold sign of LSHIFT_EXPR to eliminate no-op conversions.
Date: Mon, 23 Aug 2021 11:38:18 +0000 (GMT)	[thread overview]
Message-ID: <20210823113818.4F0963858D35@sourceware.org> (raw)

https://gcc.gnu.org/g:1d244020246cb155e4de62ca3b302b920a1f513f

commit r12-3073-g1d244020246cb155e4de62ca3b302b920a1f513f
Author: Roger Sayle <roger@nextmovesoftware.com>
Date:   Mon Aug 23 12:37:04 2021 +0100

    Fold sign of LSHIFT_EXPR to eliminate no-op conversions.
    
    This short patch teaches fold that it is "safe" to change the sign
    of a left shift, to reduce the number of type conversions in gimple.
    As an example:
    
    unsigned int foo(unsigned int i) {
      return (int)i << 8;
    }
    
    is currently optimized to:
    
    unsigned int foo (unsigned int i)
    {
      int i.0_1;
      int _2;
      unsigned int _4;
    
      <bb 2> [local count: 1073741824]:
      i.0_1 = (int) i_3(D);
      _2 = i.0_1 << 8;
      _4 = (unsigned int) _2;
      return _4;
    }
    
    with this patch, this now becomes:
    
    unsigned int foo (unsigned int i)
    {
      unsigned int _2;
    
      <bb 2> [local count: 1073741824]:
      _2 = i_1(D) << 8;
      return _2;
    }
    
    which generates exactly the same assembly language.  Aside from the
    reduced memory usage, the real benefit is that no-op conversions tend
    to interfere with many folding optimizations.  For example,
    
    unsigned int bar(unsigned char i) {
        return (i ^ (i<<16)) | (i<<8);
    }
    
    currently gets (tangled in conversions and) optimized to:
    
    unsigned int bar (unsigned char i)
    {
      unsigned int _1;
      unsigned int _2;
      int _3;
      int _4;
      unsigned int _6;
      unsigned int _8;
    
      <bb 2> [local count: 1073741824]:
      _1 = (unsigned int) i_5(D);
      _2 = _1 * 65537;
      _3 = (int) i_5(D);
      _4 = _3 << 8;
      _8 = (unsigned int) _4;
      _6 = _2 | _8;
      return _6;
    }
    
    but with this patch, bar now optimizes down to:
    
    unsigned int bar(unsigned char i)
    {
      unsigned int _1;
      unsigned int _4;
    
      <bb 2> [local count: 1073741824]:
      _1 = (unsigned int) i_3(D);
      _4 = _1 * 65793;
      return _4;
    
    }
    
    2021-08-23  Roger Sayle  <roger@nextmovesoftware.com>
    
    gcc/ChangeLog
            * match.pd (shift transformations): Change the sign of an
            LSHIFT_EXPR if it reduces the number of explicit conversions.
    
    gcc/testsuite/ChangeLog
            * gcc.dg/fold-convlshift-1.c: New test case.
            * gcc.dg/fold-convlshift-2.c: New test case.

Diff:
---
 gcc/match.pd                             |  9 +++++++++
 gcc/testsuite/gcc.dg/fold-convlshift-1.c | 20 ++++++++++++++++++++
 gcc/testsuite/gcc.dg/fold-convlshift-2.c | 20 ++++++++++++++++++++
 3 files changed, 49 insertions(+)

diff --git a/gcc/match.pd b/gcc/match.pd
index 0fcfd0ea62c..978a1b0172e 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -3385,6 +3385,15 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
     (if (integer_zerop (@2) || integer_all_onesp (@2))
      (cmp @0 @2)))))
 
+/* Both signed and unsigned lshift produce the same result, so use
+   the form that minimizes the number of conversions.  */
+(simplify
+ (convert (lshift:s@0 (convert:s@1 @2) INTEGER_CST@3))
+ (if (tree_nop_conversion_p (type, TREE_TYPE (@0))
+      && INTEGRAL_TYPE_P (TREE_TYPE (@2))
+      && TYPE_PRECISION (TREE_TYPE (@2)) <= TYPE_PRECISION (type))
+  (lshift (convert @2) @3)))
+
 /* Simplifications of conversions.  */
 
 /* Basic strip-useless-type-conversions / strip_nops.  */
diff --git a/gcc/testsuite/gcc.dg/fold-convlshift-1.c b/gcc/testsuite/gcc.dg/fold-convlshift-1.c
new file mode 100644
index 00000000000..b6f57f81e72
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/fold-convlshift-1.c
@@ -0,0 +1,20 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -fdump-tree-optimized" } */
+
+unsigned int foo(unsigned int i)
+{
+  int t1 = i;
+  int t2 = t1 << 8;
+  return t2;
+}
+
+int bar(int i)
+{
+  unsigned int t1 = i;
+  unsigned int t2 = t1 << 8;
+  return t2;
+}
+
+/* { dg-final { scan-tree-dump-not "\\(int\\)" "optimized" } } */
+/* { dg-final { scan-tree-dump-not "\\(unsigned int\\)" "optimized" } } */
+
diff --git a/gcc/testsuite/gcc.dg/fold-convlshift-2.c b/gcc/testsuite/gcc.dg/fold-convlshift-2.c
new file mode 100644
index 00000000000..f21358c4584
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/fold-convlshift-2.c
@@ -0,0 +1,20 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -fdump-tree-optimized" } */
+
+unsigned int foo(unsigned char c)
+{
+  int t1 = c;
+  int t2 = t1 << 8;
+  return t2;
+}
+
+int bar(unsigned char c)
+{
+  unsigned int t1 = c;
+  unsigned int t2 = t1 << 8;
+  return t2;
+}
+
+/* { dg-final { scan-tree-dump-times "\\(int\\)" 1 "optimized" } } */
+/* { dg-final { scan-tree-dump-times "\\(unsigned int\\)" 1 "optimized" } } */
+


                 reply	other threads:[~2021-08-23 11:38 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=20210823113818.4F0963858D35@sourceware.org \
    --to=sayle@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).