gcc/0060-Backport-Optimize-x-0-y-y-to-x-31-y-in-match.pd.patch

From 4352b952ba24c413697fcfc191d06165a8a31ced Mon Sep 17 00:00:00 2001
From: Andrew Pinski <apinski@marvell.com>
Date: Sat, 22 May 2021 19:49:50 +0000
Subject: [PATCH 12/35] [Backport] Optimize x < 0 ? ~y : y to (x >> 31) ^ y in
 match.pd

Reference: https://gcc.gnu.org/git/gitweb.cgi?p=gcc.git;h=1fd76b24306ed4df4cf9e797d900699ed59ce7f7

This copies the optimization that is done in phiopt for
"x < 0 ? ~y : y to (x >> 31) ^ y" into match.pd. The code
for phiopt is kept around until phiopt uses match.pd (which
I am working towards).

Note the original testcase is now optimized early on and I added a
new testcase to optimize during phiopt.

OK?  Bootstrapped and tested on x86_64-linux-gnu with no regressions.

Thanks,
Andrew Pinski

Differences from v1:
V2: Add check for integeral type to make sure vector types are not done.

gcc:
	* match.pd (x < 0 ? ~y : y): New patterns.

gcc/testsuite:
	* gcc.dg/tree-ssa/pr96928.c: Update test for slightly different IR.
	* gcc.dg/tree-ssa/pr96928-1.c: New testcase.
---
 gcc/match.pd                              | 32 +++++++++++++++
 gcc/testsuite/gcc.dg/tree-ssa/pr96928-1.c | 48 +++++++++++++++++++++++
 gcc/testsuite/gcc.dg/tree-ssa/pr96928.c   |  7 +++-
 3 files changed, 85 insertions(+), 2 deletions(-)
 create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/pr96928-1.c

diff --git a/gcc/match.pd b/gcc/match.pd
index 032830b0d..5899eea95 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -4390,6 +4390,38 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
   (cmp (bit_and@2 @0 integer_pow2p@1) @1)
   (icmp @2 { build_zero_cst (TREE_TYPE (@0)); })))
 
+(for cmp (ge lt)
+/* x < 0 ? ~y : y into (x >> (prec-1)) ^ y. */
+/* x >= 0 ? ~y : y into ~((x >> (prec-1)) ^ y). */
+ (simplify
+  (cond (cmp @0 integer_zerop) (bit_not @1) @1)
+   (if (INTEGRAL_TYPE_P (type)
+	&& INTEGRAL_TYPE_P (TREE_TYPE (@0))
+        && !TYPE_UNSIGNED (TREE_TYPE (@0))
+        && TYPE_PRECISION (TREE_TYPE (@0)) == TYPE_PRECISION (type))
+    (with
+     {
+       tree shifter = build_int_cst (integer_type_node, TYPE_PRECISION (type) - 1);
+     }
+    (if (cmp == LT_EXPR)
+     (bit_xor (convert (rshift @0 {shifter;})) @1)
+     (bit_not (bit_xor (convert (rshift @0 {shifter;})) @1))))))
+/* x < 0 ? y : ~y into ~((x >> (prec-1)) ^ y). */
+/* x >= 0 ? y : ~y into (x >> (prec-1)) ^ y. */
+ (simplify
+  (cond (cmp @0 integer_zerop) @1 (bit_not @1))
+   (if (INTEGRAL_TYPE_P (type)
+	&& INTEGRAL_TYPE_P (TREE_TYPE (@0))
+        && !TYPE_UNSIGNED (TREE_TYPE (@0))
+        && TYPE_PRECISION (TREE_TYPE (@0)) == TYPE_PRECISION (type))
+    (with
+     {
+       tree shifter = build_int_cst (integer_type_node, TYPE_PRECISION (type) - 1);
+     }
+    (if (cmp == GE_EXPR)
+     (bit_xor (convert (rshift @0 {shifter;})) @1)
+     (bit_not (bit_xor (convert (rshift @0 {shifter;})) @1)))))))
+
 /* If we have (A & C) != 0 ? D : 0 where C and D are powers of 2,
    convert this into a shift followed by ANDing with D.  */
 (simplify
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr96928-1.c b/gcc/testsuite/gcc.dg/tree-ssa/pr96928-1.c
new file mode 100644
index 000000000..a2770e5e8
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/pr96928-1.c
@@ -0,0 +1,48 @@
+/* PR tree-optimization/96928 */
+/* { dg-do compile } */
+/* { dg-options "-O2 -fdump-tree-phiopt2" } */
+/* { dg-final { scan-tree-dump-times " = a_\[0-9]*\\\(D\\\) >> " 5 "phiopt2" } } */
+/* { dg-final { scan-tree-dump-times " = ~c_\[0-9]*\\\(D\\\);" 1 "phiopt2" } } */
+/* { dg-final { scan-tree-dump-times " = ~" 1 "phiopt2" } } */
+/* { dg-final { scan-tree-dump-times " = \[abc_0-9\\\(\\\)D]* \\\^ " 5 "phiopt2" } } */
+/* { dg-final { scan-tree-dump-not "a < 0" "phiopt2" } } */
+
+int
+foo (int a)
+{
+  if (a < 0)
+    return ~a;
+  return a;
+}
+
+int
+bar (int a, int b)
+{
+  if (a < 0)
+    return ~b;
+  return b;
+}
+
+unsigned
+baz (int a, unsigned int b)
+{
+  if (a < 0)
+    return ~b;
+  return b;
+}
+
+unsigned
+qux (int a, unsigned int c)
+{
+  if (a >= 0)
+    return ~c;
+  return c;
+}
+
+int
+corge (int a, int b)
+{
+  if (a >= 0)
+    return b;
+  return ~b;
+}
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr96928.c b/gcc/testsuite/gcc.dg/tree-ssa/pr96928.c
index 209135726..e8fd82fc2 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/pr96928.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/pr96928.c
@@ -1,8 +1,11 @@
 /* PR tree-optimization/96928 */
 /* { dg-do compile } */
-/* { dg-options "-O2 -fdump-tree-phiopt2" } */
+/* { dg-options "-O2 -fdump-tree-phiopt2 -fdump-tree-optimized" } */
 /* { dg-final { scan-tree-dump-times " = a_\[0-9]*\\\(D\\\) >> " 5 "phiopt2" } } */
-/* { dg-final { scan-tree-dump-times " = ~c_\[0-9]*\\\(D\\\);" 1 "phiopt2" } } */
+/* The following check is done at optimized because a ^ (~b) is rewritten as ~(a^b)
+   and in the case of match.pd optimizing these ?:, the ~ is moved out already
+   by the time we get to phiopt2. */
+/* { dg-final { scan-tree-dump-times "\\\^ c_\[0-9]*\\\(D\\\);" 1 "optimized" } } */
 /* { dg-final { scan-tree-dump-times " = ~" 1 "phiopt2" } } */
 /* { dg-final { scan-tree-dump-times " = \[abc_0-9\\\(\\\)D]* \\\^ " 5 "phiopt2" } } */
 /* { dg-final { scan-tree-dump-not "a < 0" "phiopt2" } } */
-- 
2.27.0.windows.1