Hi,
This patch addresses the issue reported in PR target/112787 by improving the
compute type selection. We do this by not considering types with more
elements
than the type we are lowering since we'd reject such types anyway.
gcc/ChangeLog:
PR target/112787
* tree-vect-generic (type_for_widest_vector_mode): Add a parameter to
control maximum amount of elements in resulting vector mode.
(get_compute_type): Restrict vector_compute_type to a mode no wider
than the original compute type.
gcc/testsuite/ChangeLog:
* gcc.target/aarch64/pr112787.c: New test.
Bootstrapped and regression tested on aarch64-unknown-linux-gnu and
x86_64-pc-linux-gnu.
Is this OK for trunk?
Kind regards,
Andre Vieira
diff --git a/gcc/testsuite/gcc.target/aarch64/pr112787.c
b/gcc/testsuite/gcc.target/aarch64/pr112787.c
new file mode 100644
index
0000000000000000000000000000000000000000..caca1bf7ef447e4489b2c134d7200a4afd16763f
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/pr112787.c
@@ -0,0 +1,11 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-O2 -march=armv8-a+sve -mcpu=neoverse-n2" } */
+
+typedef int __attribute__((__vector_size__ (64))) vec;
+
+vec fn (vec a, vec b)
+{
+ return a + b;
+}
+
+/* { dg-final { scan-assembler-times {add\tv[0-9]+} 4 } } */
diff --git a/gcc/tree-vect-generic.cc b/gcc/tree-vect-generic.cc
index
a7e6cb87a5e31e3dd2a893ea5652eeebf8d5d214..2dbf3c8f5f64f2623944110dbc371fe0944198f0
100644
--- a/gcc/tree-vect-generic.cc
+++ b/gcc/tree-vect-generic.cc
@@ -1347,7 +1347,7 @@ optimize_vector_constructor (gimple_stmt_iterator *gsi)
TYPE, or NULL_TREE if none is found. */
static tree
-type_for_widest_vector_mode (tree type, optab op)
+type_for_widest_vector_mode (tree type, optab op, poly_int64 max_nunits = 0)
{
machine_mode inner_mode = TYPE_MODE (type);
machine_mode best_mode = VOIDmode, mode;
@@ -1371,7 +1371,9 @@ type_for_widest_vector_mode (tree type, optab op)
FOR_EACH_MODE_FROM (mode, mode)
if (GET_MODE_INNER (mode) == inner_mode
&& maybe_gt (GET_MODE_NUNITS (mode), best_nunits)
- && optab_handler (op, mode) != CODE_FOR_nothing)
+ && optab_handler (op, mode) != CODE_FOR_nothing
+ && (known_eq (max_nunits, 0)
+ || known_lt (GET_MODE_NUNITS (mode), max_nunits)))
best_mode = mode, best_nunits = GET_MODE_NUNITS (mode);
if (best_mode == VOIDmode)
@@ -1702,7 +1704,8 @@ get_compute_type (enum tree_code code, optab op, tree
type)
|| optab_handler (op, TYPE_MODE (type)) == CODE_FOR_nothing))
{
tree vector_compute_type
- = type_for_widest_vector_mode (TREE_TYPE (type), op);
+ = type_for_widest_vector_mode (TREE_TYPE (type), op,
+ TYPE_VECTOR_SUBPARTS (compute_type));
if (vector_compute_type != NULL_TREE
&& subparts_gt (compute_type, vector_compute_type)
&& maybe_ne (TYPE_VECTOR_SUBPARTS (vector_compute_type), 1U)