diff options
| author | Michael Collison <collison@rivosinc.com> | 2022-12-02 08:40:05 +0100 |
|---|---|---|
| committer | Richard Biener <rguenther@suse.de> | 2022-12-02 09:22:01 +0100 |
| commit | 6508d5e5a1a8c08bebf83d258fad525eadc9f5d1 (patch) | |
| tree | 8799cc2dad553ed6c4f19a588ee205a416844239 | |
| parent | 5b50850c3c6f2eceb8012dcc8d3cd5ddd94fac6c (diff) | |
| download | gcc-6508d5e5a1a8c08bebf83d258fad525eadc9f5d1.zip gcc-6508d5e5a1a8c08bebf83d258fad525eadc9f5d1.tar.gz gcc-6508d5e5a1a8c08bebf83d258fad525eadc9f5d1.tar.bz2 | |
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.
| -rw-r--r-- | gcc/match.pd | 24 | ||||
| -rw-r--r-- | gcc/testsuite/gcc.dg/tree-ssa/branchless-cond.c | 26 |
2 files changed, 50 insertions, 0 deletions
diff --git a/gcc/match.pd b/gcc/match.pd index f8610e3..04d4c4c 100644 --- 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 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" } } */ |