This allows the backend to generate movcc instructions, if target
machine has movcc pattern.
branchless-cond.c needs to be updated since some target machines have
conditional move instructions, and the experssion will not change to
branchless expression.
gcc/ChangeLog:
PR target/113095
* match.pd (`(zero_one == 0) ? y : z <op> y`,
`(zero_one != 0) ? z <op> y : y`): Do not match to branchless
expression, if target machine has conditional move pattern.
gcc/testsuite/ChangeLog:
* gcc.dg/tree-ssa/branchless-cond.c: Update testcase.
---
gcc/match.pd | 30 +++++++++++++++++--
.../gcc.dg/tree-ssa/branchless-cond.c | 6 ++--
2 files changed, 31 insertions(+), 5 deletions(-)
diff --git a/gcc/match.pd b/gcc/match.pd
index e42ecaf9ec7..a1f90b1cd41 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -4231,7 +4231,20 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
(if (INTEGRAL_TYPE_P (type)
&& TYPE_PRECISION (type) > 1
&& (INTEGRAL_TYPE_P (TREE_TYPE (@0))))
- (op (mult (convert:type @0) @2) @1))))
+ (with {
+ bool can_movecc_p = false;
+ if (can_conditionally_move_p (TYPE_MODE (type)))
+ can_movecc_p = true;
+
+ /* Some target only support word_mode for movcc pattern, if type can
+ extend to word_mode then use conditional move. Even if there is a
+ extend instruction, the cost is lower than branchless. */
+ if (can_extend_p (word_mode, TYPE_MODE (type), TYPE_UNSIGNED (type))
+ && can_conditionally_move_p (word_mode))
+ can_movecc_p = true;
+ }
+ (if (!can_movecc_p)
+ (op (mult (convert:type @0) @2) @1))))))
/* (zero_one != 0) ? z <op> y : y -> ((typeof(y))zero_one * z) <op> y */
(for op (bit_xor bit_ior plus)
@@ -4243,7 +4256,20 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
(if (INTEGRAL_TYPE_P (type)
&& TYPE_PRECISION (type) > 1
&& (INTEGRAL_TYPE_P (TREE_TYPE (@0))))
- (op (mult (convert:type @0) @2) @1))))
+ (with {
+ bool can_movecc_p = false;
+ if (can_conditionally_move_p (TYPE_MODE (type)))
+ can_movecc_p = true;
+
+ /* Some target only support word_mode for movcc pattern, if type can
+ extend to word_mode then use conditional move. Even if there is a
+ extend instruction, the cost is lower than branchless. */
+ if (can_extend_p (word_mode, TYPE_MODE (type), TYPE_UNSIGNED (type))
+ && can_conditionally_move_p (word_mode))
+ can_movecc_p = true;
+ }
+ (if (!can_movecc_p)
+ (op (mult (convert:type @0) @2) @1))))))
/* ?: Value replacement. */
/* a == 0 ? b : b + a -> b + a */
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/branchless-cond.c
b/gcc/testsuite/gcc.dg/tree-ssa/branchless-cond.c
index e063dc4bb5f..c002ed97364 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/branchless-cond.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/branchless-cond.c
@@ -21,6 +21,6 @@ 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 " & " 4 "optimized" } } */
-/* { dg-final { scan-tree-dump-not "if " "optimized" } } */
+/* { dg-final { scan-tree-dump-times " \\\*" 4 "optimized" { xfail {
"aarch64*-*-* alpha*-*-* bfin*-*-* epiphany-*-* i?86-*-* x86_64-*-* nds32*-*-*"
} } } } */
+/* { dg-final { scan-tree-dump-times " & " 4 "optimized" { xfail {
"aarch64*-*-* alpha*-*-* bfin*-*-* epiphany-*-* i?86-*-* x86_64-*-* nds32*-*-*"
} } } } */
+/* { dg-final { scan-tree-dump-not "if " "optimized" { xfail { "aarch64*-*-*
alpha*-*-* bfin*-*-* epiphany-*-* i?86-*-* x86_64-*-* nds32*-*-*" } } } } */
--
2.40.1
