[PATCH] match.pd: Implement missed optimization (x << c) >> c -> -(x & 1) [PR101955]

[Drew Ross <drross@redhat.com>]

Simplifies (x << c) >> c where x is a signed integral type of
width >= int and c = precision(type) - 1 into -(x & 1). Tested successfully
on x86_64 and x86 targets.

        PR middle-end/101955

gcc/ChangeLog:

        * match.pd (x << c) >> c -> -(x & 1): New simplification.

gcc/testsuite/ChangeLog:

        * gcc.dg/pr101955.c: New test.
---
 gcc/match.pd                    | 10 +++++
 gcc/testsuite/gcc.dg/pr101955.c | 69 +++++++++++++++++++++++++++++++++
 2 files changed, 79 insertions(+)
 create mode 100644 gcc/testsuite/gcc.dg/pr101955.c

diff --git a/gcc/match.pd b/gcc/match.pd
index 8543f777a28..820fc890e8e 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -3766,6 +3766,16 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
       && (wi::ltu_p (wi::to_wide (@1), element_precision (type))))
   (bit_and @0 (rshift { build_minus_one_cst (type); } @1))))
 
+/* Optimize (X << C) >> C where C = precision(type) - 1 and X is signed
+   into -(X & 1).  */
+(simplify
+ (rshift (nop_convert? (lshift @0 uniform_integer_cst_p@1)) @@1)
+ (with { tree cst = uniform_integer_cst_p (@1); }
+ (if (ANY_INTEGRAL_TYPE_P (type)
+      && !TYPE_UNSIGNED (type)
+      && wi::eq_p (wi::to_wide (cst), element_precision (type) - 1))
+  (negate (bit_and (convert @0) { build_one_cst (type); })))))
+
 /* Optimize x >> x into 0 */
 (simplify
  (rshift @0 @0)
diff --git a/gcc/testsuite/gcc.dg/pr101955.c b/gcc/testsuite/gcc.dg/pr101955.c
new file mode 100644
index 00000000000..386154911c5
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/pr101955.c
@@ -0,0 +1,69 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -fdump-tree-dse1 -Wno-psabi" } */
+
+typedef int v4si __attribute__((vector_size(4 * sizeof(int))));
+
+__attribute__((noipa)) int
+t1 (int x)
+{
+  return (x << 31) >> 31;
+}
+
+__attribute__((noipa)) int
+t2 (int x)
+{
+  int y = x << 31;
+  int z = y >> 31;
+  return z;
+}
+
+__attribute__((noipa)) int
+t3 (int x)
+{
+  int w = 31;
+  int y = x << w;
+  int z = y >> w;
+  return z;
+}
+
+__attribute__((noipa)) long long
+t4 (long long x)
+{
+  return (x << 63) >> 63;
+}
+
+__attribute__((noipa)) long long
+t5 (long long x)
+{
+  long long y = x << 63;
+  long long z = y >> 63;
+  return z;
+}
+
+__attribute__((noipa)) long long
+t6 (long long x)
+{
+  int w = 63;
+  long long y = x << w;
+  long long z = y >> w;
+  return z;
+}
+
+__attribute__((noipa)) v4si
+t7 (v4si x)
+{
+  return (x << 31) >> 31;
+}
+
+__attribute__((noipa)) v4si
+t8 (v4si x)
+{
+  v4si t = {31,31,31,31};
+  return (x << t) >> t;
+}
+
+/* { dg-final { scan-tree-dump-not " >> " "dse1" } } */
+/* { dg-final { scan-tree-dump-not " << " "dse1" } } */
+/* { dg-final { scan-tree-dump-times " -" 8 "dse1" } } */
+/* { dg-final { scan-tree-dump-times " & " 8 "dse1" } } */
+
-- 
2.39.3