match.pd: rewrite select to branchless expression

This patches transforms ((x & 0x1) == 0) ? y : z <op> y -into
(-(typeof(y))(x & 0x1) & z) <op> y, where op is a '^' or a '|'. It also
transforms (cond (and (x , 0x1) != 0), (z op y), y ) into (-(and (x ,
0x1)) & z ) op y.

Matching this patterns allows GCC to generate branchless code for one of
the functions in coremark.

	* match.pd ((x & 0x1) == 0) ? y : z <op> y
	-> (-(typeof(y))(x & 0x1) & z) <op> y.

	* gcc.dg/tree-ssa/branchless-cond.c: New test.

diff --git a/gcc/match.pd b/gcc/match.pd
index f8610e370119c477324283347d4bf94cdab3d2f9..04d4c4c054ae4a162aa8a8160cfc354b84eb9b3b 100644 (file)
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -3492,6 +3492,30 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
   (cond (le @0 integer_zerop@1) (negate@2 @0) integer_zerop@1)
   (max @2 @1))
 
+/* ((x & 0x1) == 0) ? y : z <op> y -> (-(typeof(y))(x & 0x1) & z) <op> y */
+(for op (bit_xor bit_ior)
+ (simplify
+  (cond (eq zero_one_valued_p@0
+            integer_zerop)
+        @1
+        (op:c @2 @1))
+  (if (INTEGRAL_TYPE_P (type)
+       && TYPE_PRECISION (type) > 1
+       && (INTEGRAL_TYPE_P (TREE_TYPE (@0))))
+       (op (bit_and (negate (convert:type @0)) @2) @1))))
+
+/* ((x & 0x1) == 0) ? z <op> y : y -> (-(typeof(y))(x & 0x1) & z) <op> y */
+(for op (bit_xor bit_ior)
+ (simplify
+  (cond (ne zero_one_valued_p@0
+            integer_zerop)
+       (op:c @2 @1)
+        @1)
+  (if (INTEGRAL_TYPE_P (type)
+       && TYPE_PRECISION (type) > 1
+       && (INTEGRAL_TYPE_P (TREE_TYPE (@0))))
+       (op (bit_and (negate (convert:type @0)) @2) @1))))
+
 /* Simplifications of shift and rotates.  */
 
 (for rotate (lrotate rrotate)

diff --git a/gcc/testsuite/gcc.dg/tree-ssa/branchless-cond.c b/gcc/testsuite/gcc.dg/tree-ssa/branchless-cond.c
new file mode 100644 (file)
index 0000000..68087ae
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/branchless-cond.c
@@ -0,0 +1,26 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -fdump-tree-optimized" } */
+
+int f1(unsigned int x, unsigned int y, unsigned int z)
+{
+  return ((x & 1) == 0) ? y : z ^ y;
+}
+
+int f2(unsigned int x, unsigned int y, unsigned int z)
+{
+  return ((x & 1) != 0) ? z ^ y : y;
+}
+
+int f3(unsigned int x, unsigned int y, unsigned int z)
+{
+  return ((x & 1) == 0) ? y : z | y;
+}
+
+int f4(unsigned int x, unsigned int y, unsigned int z)
+{
+  return ((x & 1) != 0) ? z | y : y;
+}
+
+/* { dg-final { scan-tree-dump-times " -" 4 "optimized" } } */
+/* { dg-final { scan-tree-dump-times " & " 8 "optimized" } } */
+/* { dg-final { scan-tree-dump-not "if" "optimized" } } */