From: Kyrylo Tkachov <[email protected]>
A lane of A | B is zero exactly when the corresponding lanes of A and of B
are both zero, so
(A == 0) & (B == 0) -> (A | B) == 0
and the De Morgan dual for inequality. The existing scalar rule already
implements this identity. Extend it to vector integers and use a view
conversion when the operands differ only in element signedness. Extend the
related all-ones rule in the same way.
typedef int v4si __attribute__((vector_size (16)));
v4si f (v4si a, v4si b) { return (a == 0) & (b == 0); }
aarch64 -O3 before:
cmeq v0.4s, v0.4s, #0
cmeq v1.4s, v1.4s, #0
and v0.16b, v0.16b, v1.16b
after:
orr v0.16b, v0.16b, v1.16b
cmeq v0.4s, v0.4s, #0
Add vector_nop_conversion_p for the element-wise property shared by these
rules and the existing nop_convert matcher.
Bootstrapped and tested on aarch64-none-linux-gnu.
Ok for trunk?
Thanks,
Kyrill
gcc/ChangeLog:
* match.pd (nop_convert): Use vector_nop_conversion_p.
((A == 0) & (B == 0), (A != 0) | (B != 0)): Extend the
existing simplifications to vector operands.
((A == -1) & (B == -1), (A != -1) | (B != -1)): Likewise.
* tree.cc (vector_nop_conversion_p): New function.
* tree.h (vector_nop_conversion_p): Declare.
gcc/testsuite/ChangeLog:
* gcc.dg/tree-ssa/vec-mask-zero-1.c: New test.
Signed-off-by: Kyrylo Tkachov <[email protected]>
---
gcc/match.pd | 26 +++++++++++++------
.../gcc.dg/tree-ssa/vec-mask-zero-1.c | 17 ++++++++++++
gcc/tree.cc | 15 +++++++++++
gcc/tree.h | 1 +
4 files changed, 51 insertions(+), 8 deletions(-)
create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/vec-mask-zero-1.c
diff --git a/gcc/match.pd b/gcc/match.pd
index da002001399..efa821bff59 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -161,10 +161,7 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
(if (tree_nop_conversion_p (type, TREE_TYPE (@0)))))
(match (nop_convert @0)
(view_convert @0)
- (if (VECTOR_TYPE_P (type) && VECTOR_TYPE_P (TREE_TYPE (@0))
- && known_eq (TYPE_VECTOR_SUBPARTS (type),
- TYPE_VECTOR_SUBPARTS (TREE_TYPE (@0)))
- && tree_nop_conversion_p (TREE_TYPE (type), TREE_TYPE (TREE_TYPE
(@0))))))
+ (if (vector_nop_conversion_p (type, TREE_TYPE (@0)))))
/* These are used by gimple_bitwise_inverted_equal_p to simplify
detection of BIT_NOT and comparisons. */
@@ -1560,20 +1557,33 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
(x == 0 & y == 0) -> (x | typeof(x)(y)) == 0.
(x != 0 | y != 0) -> (x | typeof(x)(y)) != 0. */
(simplify
- (bitop (cmp @0 integer_zerop@2) (cmp @1 integer_zerop))
+ (bitop (cmp@3 @0 integer_zerop@2) (cmp@4 @1 integer_zerop))
+ (switch
(if (INTEGRAL_TYPE_P (TREE_TYPE (@0))
&& INTEGRAL_TYPE_P (TREE_TYPE (@1))
&& TYPE_PRECISION (TREE_TYPE (@0)) == TYPE_PRECISION (TREE_TYPE (@1)))
- (cmp (bit_ior @0 (convert @1)) @2)))
+ (cmp (bit_ior @0 (convert @1)) @2))
+ (if (VECTOR_INTEGER_TYPE_P (TREE_TYPE (@0))
+ && VECTOR_INTEGER_TYPE_P (TREE_TYPE (@1))
+ && vector_nop_conversion_p (TREE_TYPE (@0), TREE_TYPE (@1))
+ && single_use (@3) && single_use (@4))
+ (cmp (bit_ior @0 (view_convert @1)) @2))))
/* Transform:
(x == -1 & y == -1) -> (x & typeof(x)(y)) == -1.
(x != -1 | y != -1) -> (x & typeof(x)(y)) != -1. */
(simplify
- (bitop (cmp @0 integer_all_onesp@2) (cmp @1 integer_all_onesp))
+ (bitop (cmp@3 @0 integer_all_onesp@2)
+ (cmp@4 @1 integer_all_onesp))
+ (switch
(if (INTEGRAL_TYPE_P (TREE_TYPE (@0))
&& INTEGRAL_TYPE_P (TREE_TYPE (@1))
&& TYPE_PRECISION (TREE_TYPE (@0)) == TYPE_PRECISION (TREE_TYPE (@1)))
- (cmp (bit_and @0 (convert @1)) @2))))
+ (cmp (bit_and @0 (convert @1)) @2))
+ (if (VECTOR_INTEGER_TYPE_P (TREE_TYPE (@0))
+ && VECTOR_INTEGER_TYPE_P (TREE_TYPE (@1))
+ && vector_nop_conversion_p (TREE_TYPE (@0), TREE_TYPE (@1))
+ && single_use (@3) && single_use (@4))
+ (cmp (bit_and @0 (view_convert @1)) @2)))))
/* Fold (A & ~B) - (A & B) into (A ^ B) - B. */
(simplify
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/vec-mask-zero-1.c
b/gcc/testsuite/gcc.dg/tree-ssa/vec-mask-zero-1.c
new file mode 100644
index 00000000000..1b31f727488
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/vec-mask-zero-1.c
@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -fdump-tree-optimized" } */
+/* Combine pairs of vector comparisons against zero or all-ones. Use
+ different signedness for the operands to exercise the view conversion. */
+typedef int v4si __attribute__((vector_size (16)));
+typedef unsigned int v4ui __attribute__((vector_size (16)));
+
+v4si f1 (v4si a, v4ui b) { return (a == 0) & (b == 0); }
+v4si f2 (v4si a, v4ui b) { return (a != 0) | (b != 0); }
+v4si f3 (v4si a, v4ui b) { return (a == -1) & (b == -1u); }
+v4si f4 (v4si a, v4ui b) { return (a != -1) | (b != -1u); }
+
+/* Each function keeps one bitwise operation and one comparison. */
+/* { dg-final { scan-tree-dump-times " == " 2 "optimized" } } */
+/* { dg-final { scan-tree-dump-times " != " 2 "optimized" } } */
+/* { dg-final { scan-tree-dump-times " \\| " 2 "optimized" } } */
+/* { dg-final { scan-tree-dump-times " & " 2 "optimized" } } */
diff --git a/gcc/tree.cc b/gcc/tree.cc
index c8aa42b3e10..157f453e49c 100644
--- a/gcc/tree.cc
+++ b/gcc/tree.cc
@@ -12384,6 +12384,21 @@ tree_nop_conversion_p (const_tree outer_type,
const_tree inner_type)
return TYPE_MODE (outer_type) == TYPE_MODE (inner_type);
}
+/* Return true iff a view conversion from vector type INNER_TYPE to vector
+ type OUTER_TYPE has the same number of elements and does not change the
+ representation of an element. */
+
+bool
+vector_nop_conversion_p (const_tree outer_type, const_tree inner_type)
+{
+ return (VECTOR_TYPE_P (outer_type)
+ && VECTOR_TYPE_P (inner_type)
+ && known_eq (TYPE_VECTOR_SUBPARTS (outer_type),
+ TYPE_VECTOR_SUBPARTS (inner_type))
+ && tree_nop_conversion_p (TREE_TYPE (outer_type),
+ TREE_TYPE (inner_type)));
+}
+
/* Return true iff conversion in EXP generates no instruction. Mark
it inline so that we fully inline into the stripping functions even
though we have two uses of this function. */
diff --git a/gcc/tree.h b/gcc/tree.h
index 1ccbf848d9b..56863bdfc18 100644
--- a/gcc/tree.h
+++ b/gcc/tree.h
@@ -5784,6 +5784,7 @@ extern bool auto_var_p (const_tree);
extern bool auto_var_in_fn_p (const_tree, const_tree);
extern tree build_low_bits_mask (tree, unsigned);
extern bool tree_nop_conversion_p (const_tree, const_tree);
+extern bool vector_nop_conversion_p (const_tree, const_tree);
extern tree tree_strip_nop_conversions (tree);
extern tree tree_strip_sign_nop_conversions (tree);
extern const_tree strip_invariant_refs (const_tree);
--
2.50.1 (Apple Git-155)
