This patches transforms (cond (and (x , 0x1) == 0), y, (z op y)) into
(-(and (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.
Bootstrapped and tested on x86 and RISC-V. Okay?
Michael.
2022-11-08 Michael Collison <colli...@rivosinc.com>
* match.pd ((cond (and (x , 0x1) == 0), y, (z op y) )
-> (-(and (x , 0x1)) & z ) op y)
2022-11-08 Michael Collison <colli...@rivosinc.com>
* gcc.dg/tree-ssa/branchless-cond.c: New test.
---
gcc/match.pd | 22 ++++++++++++++++
.../gcc.dg/tree-ssa/branchless-cond.c | 26 +++++++++++++++++++
2 files changed, 48 insertions(+)
create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/branchless-cond.c
diff --git a/gcc/match.pd b/gcc/match.pd
index 194ba8f5188..722f517ac6d 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -3486,6 +3486,28 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
(cond (le @0 integer_zerop@1) (negate@2 @0) integer_zerop@1)
(max @2 @1))
+/* (cond (and (x , 0x1) == 0), y, (z ^ y) ) -> (-(and (x , 0x1)) & z )
^ y */
+(for op (bit_xor bit_ior)
+ (simplify
+ (cond (eq (bit_and @0 integer_onep@1)
+ integer_zerop)
+ @2
+ (op:c @3 @2))
+ (if (INTEGRAL_TYPE_P (type)
+ && (INTEGRAL_TYPE_P (TREE_TYPE (@0))))
+ (op (bit_and (negate (convert:type (bit_and @0 @1))) @3) @2))))
+
+/* (cond (and (x , 0x1) != 0), (z ^ y), y ) -> (-(and (x , 0x1)) & z )
^ y */
+(for op (bit_xor bit_ior)
+ (simplify
+ (cond (ne (bit_and @0 integer_onep@1)
+ integer_zerop)
+ (op:c @3 @2)
+ @2)
+ (if (INTEGRAL_TYPE_P (type)
+ && (INTEGRAL_TYPE_P (TREE_TYPE (@0))))
+ (op (bit_and (negate (convert:type (bit_and @0 @1))) @3) @2))))
+
/* 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
index 00000000000..68087ae6568
--- /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" } } */
--
2.34.1
