The fix for PR106329 needs a way of testing for a ptrue of a particular
element size. We already had such a function for svlast, so this patch
moves it to common code and generalises it to work with all kinds of
vectors.
Tested on aarch64-linux-gnu & pushed.
Richard
gcc/
* config/aarch64/aarch64-sve-builtins.h (vector_cst_all_same): Declare.
* config/aarch64/aarch64-sve-builtins.cc (vector_cst_all_same): New
function, a generalized replacement of...
* config/aarch64/aarch64-sve-builtins-base.cc
(svlast_impl::vect_all_same): ...this.
(svlast_impl::fold): Update accordingly.
---
.../aarch64/aarch64-sve-builtins-base.cc | 17 ++--------------
gcc/config/aarch64/aarch64-sve-builtins.cc | 20 +++++++++++++++++++
gcc/config/aarch64/aarch64-sve-builtins.h | 2 ++
3 files changed, 24 insertions(+), 15 deletions(-)
diff --git a/gcc/config/aarch64/aarch64-sve-builtins-base.cc
b/gcc/config/aarch64/aarch64-sve-builtins-base.cc
index 9010ecca6da..a6e527bedd1 100644
--- a/gcc/config/aarch64/aarch64-sve-builtins-base.cc
+++ b/gcc/config/aarch64/aarch64-sve-builtins-base.cc
@@ -1105,19 +1105,6 @@ public:
bool is_lasta () const { return m_unspec == UNSPEC_LASTA; }
bool is_lastb () const { return m_unspec == UNSPEC_LASTB; }
- bool vect_all_same (tree v, int step) const
- {
- int i;
- int nelts = vector_cst_encoded_nelts (v);
- tree first_el = VECTOR_CST_ENCODED_ELT (v, 0);
-
- for (i = 0; i < nelts; i += step)
- if (!operand_equal_p (VECTOR_CST_ENCODED_ELT (v, i), first_el, 0))
- return false;
-
- return true;
- }
-
/* Fold a svlast{a/b} call with constant predicate to a BIT_FIELD_REF.
BIT_FIELD_REF lowers to Advanced SIMD element extract, so we have to
ensure the index of the element being accessed is in the range of a
@@ -1142,7 +1129,7 @@ public:
without a linear search of the predicate vector:
1. LASTA if predicate is all true, return element 0.
2. LASTA if predicate all false, return element 0. */
- if (is_lasta () && vect_all_same (pred, step_1))
+ if (is_lasta () && vector_cst_all_same (pred, step_1))
{
b = build3 (BIT_FIELD_REF, TREE_TYPE (f.lhs), val,
bitsize_int (step * BITS_PER_UNIT), bitsize_int (0));
@@ -1152,7 +1139,7 @@ public:
/* Handle the all-false case for LASTB where SVE VL == 128b -
return the highest numbered element. */
if (is_lastb () && known_eq (BYTES_PER_SVE_VECTOR, 16)
- && vect_all_same (pred, step_1)
+ && vector_cst_all_same (pred, step_1)
&& integer_zerop (VECTOR_CST_ENCODED_ELT (pred, 0)))
{
b = build3 (BIT_FIELD_REF, TREE_TYPE (f.lhs), val,
diff --git a/gcc/config/aarch64/aarch64-sve-builtins.cc
b/gcc/config/aarch64/aarch64-sve-builtins.cc
index 161a14edde7..b61156302cf 100644
--- a/gcc/config/aarch64/aarch64-sve-builtins.cc
+++ b/gcc/config/aarch64/aarch64-sve-builtins.cc
@@ -2541,6 +2541,26 @@ function_checker::check ()
return shape->check (*this);
}
+/* Return true if V is a vector constant and if, for every in-range integer I,
+ element STEP*I is equal to element 0. */
+bool
+vector_cst_all_same (tree v, unsigned int step)
+{
+ if (TREE_CODE (v) != VECTOR_CST)
+ return false;
+
+ /* VECTOR_CST_NELTS_PER_PATTERN applies to any multiple of
+ VECTOR_CST_NPATTERNS. */
+ unsigned int lcm = least_common_multiple (step, VECTOR_CST_NPATTERNS (v));
+ unsigned int nelts = lcm * VECTOR_CST_NELTS_PER_PATTERN (v);
+ tree first_el = VECTOR_CST_ENCODED_ELT (v, 0);
+ for (unsigned int i = 0; i < nelts; i += step)
+ if (!operand_equal_p (VECTOR_CST_ENCODED_ELT (v, i), first_el, 0))
+ return false;
+
+ return true;
+}
+
gimple_folder::gimple_folder (const function_instance &instance, tree fndecl,
gimple_stmt_iterator *gsi_in, gcall *call_in)
: function_call_info (gimple_location (call_in), instance, fndecl),
diff --git a/gcc/config/aarch64/aarch64-sve-builtins.h
b/gcc/config/aarch64/aarch64-sve-builtins.h
index a301570b82e..d646df1c026 100644
--- a/gcc/config/aarch64/aarch64-sve-builtins.h
+++ b/gcc/config/aarch64/aarch64-sve-builtins.h
@@ -672,6 +672,8 @@ extern tree
acle_vector_types[MAX_TUPLE_SIZE][NUM_VECTOR_TYPES + 1];
extern tree acle_svpattern;
extern tree acle_svprfop;
+bool vector_cst_all_same (tree, unsigned int);
+
/* Return the ACLE type svbool_t. */
inline tree
get_svbool_t (void)
--
2.25.1
