Try to simplify (X >> C1) << (C1 + C2) -> X << C2

This patch adds a rule to simplify (X >> C1) << (C1 + C2) -> X << C2
when the low C1 bits of X are known to be zero.

Any single conversion can take place between the shifts.  E.g. for
a truncating conversion, any extra bits of X that are preserved by
truncating after the shift are immediately lost by the shift left.
And the sign bits used for an extending conversion are the same as
the sign bits used for the rshift.  (A double conversion of say
int->unsigned->uint64_t would be wrong though.)

gcc/
	* match.pd: Simplify (X >> C1) << (C1 + C2) -> X << C2 if the
	low C1 bits of X are zero.

gcc/testsuite/
	* gcc.dg/tree-ssa/shifts-1.c: New test.
	* gcc.dg/tree-ssa/shifts-2.c: Likewise.

3 files changed, 95 insertions, 0 deletions

diff --git a/gcc/match.pd b/gcc/match.pd
index b9621a4..17613ec 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -4906,6 +4906,19 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
 			- TYPE_PRECISION (TREE_TYPE (@2)))))
   (bit_and (convert @0) (lshift { build_minus_one_cst (type); } @1))))
 
+#if GIMPLE
+/* (X >> C1) << (C1 + C2) -> X << C2 if the low C1 bits of X are zero.  */
+(simplify
+ (lshift (convert? (rshift (with_possible_nonzero_bits2 @0) INTEGER_CST@1))
+         INTEGER_CST@2)
+ (if (INTEGRAL_TYPE_P (type)
+      && wi::ltu_p (wi::to_wide (@1), element_precision (type))
+      && wi::ltu_p (wi::to_wide (@2), element_precision (type))
+      && wi::to_widest (@2) >= wi::to_widest (@1)
+      && wi::to_widest (@1) <= wi::ctz (get_nonzero_bits (@0)))
+  (lshift (convert @0) (minus @2 @1))))
+#endif
+
 /* For (x << c) >> c, optimize into x & ((unsigned)-1 >> c) for
    unsigned x OR truncate into the precision(type) - c lowest bits
    of signed x (if they have mode precision or a precision of 1).  */
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/shifts-1.c b/gcc/testsuite/gcc.dg/tree-ssa/shifts-1.c
new file mode 100644
index 0000000..d88500c
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/shifts-1.c
@@ -0,0 +1,61 @@
+/* { dg-options "-O2 -fdump-tree-optimized-raw" } */
+
+unsigned int
+f1 (unsigned int x)
+{
+  if (x & 3)
+    __builtin_unreachable ();
+  x >>= 2;
+  return x << 3;
+}
+
+unsigned int
+f2 (unsigned int x)
+{
+  if (x & 3)
+    __builtin_unreachable ();
+  unsigned char y = x;
+  y >>= 2;
+  return y << 3;
+}
+
+unsigned long
+f3 (unsigned int x)
+{
+  if (x & 3)
+    __builtin_unreachable ();
+  x >>= 2;
+  return (unsigned long) x << 3;
+}
+
+int
+f4 (int x)
+{
+  if (x & 15)
+    __builtin_unreachable ();
+  x >>= 4;
+  return x << 5;
+}
+
+unsigned int
+f5 (int x)
+{
+  if (x & 31)
+    __builtin_unreachable ();
+  x >>= 5;
+  return x << 6;
+}
+
+unsigned int
+f6 (unsigned int x)
+{
+  if (x & 1)
+    __builtin_unreachable ();
+  x >>= 1;
+  return x << (sizeof (int) * __CHAR_BIT__ - 1);
+}
+
+/* { dg-final { scan-tree-dump-not {<[a-z]*_div_expr,} "optimized" } } */
+/* { dg-final { scan-tree-dump-not {<rshift_expr,} "optimized" } } */
+/* { dg-final { scan-tree-dump-times {<lshift_expr, [^,]*, [^,]*, 1,} 5 "optimized" } } */
+/* { dg-final { scan-tree-dump {<lshift_expr, [^,]*, [^,]*, 30,} "optimized" { target int32 } } } */
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/shifts-2.c b/gcc/testsuite/gcc.dg/tree-ssa/shifts-2.c
new file mode 100644
index 0000000..67ba4a7
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/shifts-2.c
@@ -0,0 +1,21 @@
+/* { dg-options "-O2 -fdump-tree-optimized-raw" } */
+
+unsigned int
+f1 (unsigned int x)
+{
+  if (x & 3)
+    __builtin_unreachable ();
+  x >>= 3;
+  return x << 4;
+}
+
+unsigned int
+f2 (unsigned int x)
+{
+  if (x & 3)
+    __builtin_unreachable ();
+  x >>= 2;
+  return x << 1;
+}
+
+/* { dg-final { scan-tree-dump-times {<rshift_expr,} 2 "optimized" } } */