@@ -563,14 +563,24 @@ get_store_value (gimple *stmt)
return gimple_assign_rhs1 (stmt);
}
-/* Return true if it is non-contiguous load/store. */
+/* Return true if addtional vector vars needed. */
static bool
-non_contiguous_memory_access_p (stmt_vec_info stmt_info)
+need_additional_vector_vars_p (stmt_vec_info stmt_info)
{
enum stmt_vec_info_type type
= STMT_VINFO_TYPE (vect_stmt_to_vectorize (stmt_info));
- return ((type == load_vec_info_type || type == store_vec_info_type)
- && !adjacent_dr_p (STMT_VINFO_DATA_REF (stmt_info)));
+ if (type == load_vec_info_type || type == store_vec_info_type)
+ {
+ if (STMT_VINFO_GATHER_SCATTER_P (stmt_info)
+ && STMT_VINFO_MEMORY_ACCESS_TYPE (stmt_info) == VMAT_GATHER_SCATTER)
+ return true;
+
+ machine_mode mode = TYPE_MODE (STMT_VINFO_VECTYPE (stmt_info));
+ int lmul = riscv_get_v_regno_alignment (mode);
+ if (DR_GROUP_SIZE (stmt_info) * lmul > RVV_M8)
+ return true;
+ }
+ return false;
}
/* Return the LMUL of the current analysis. */
@@ -739,10 +749,7 @@ update_local_live_ranges (
stmt_vec_info stmt_info = vinfo->lookup_stmt (gsi_stmt (si));
enum stmt_vec_info_type type
= STMT_VINFO_TYPE (vect_stmt_to_vectorize (stmt_info));
- if (non_contiguous_memory_access_p (stmt_info)
- /* LOAD_LANES/STORE_LANES doesn't need a perm indice. */
- && STMT_VINFO_MEMORY_ACCESS_TYPE (stmt_info)
- != VMAT_LOAD_STORE_LANES)
+ if (need_additional_vector_vars_p (stmt_info))
{
/* For non-adjacent load/store STMT, we will potentially
convert it into:
@@ -752,7 +759,7 @@ update_local_live_ranges (
We will be likely using one more vector variable. */
unsigned int max_point
- = (*program_points_per_bb.get (bb)).length () - 1;
+ = (*program_points_per_bb.get (bb)).length ();
auto *live_ranges = live_ranges_per_bb.get (bb);
bool existed_p = false;
tree var = type == load_vec_info_type
new file mode 100644
@@ -0,0 +1,23 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -ftree-vectorize -mrvv-max-lmul=dynamic -fdump-tree-vect-details" } */
+
+float a[32000], b[32000], c[32000], d[32000];
+float aa[256][256], bb[256][256], cc[256][256];
+
+void
+s2275 ()
+{
+ for (int i = 0; i < 256; i++)
+ {
+ for (int j = 0; j < 256; j++)
+ {
+ aa[j][i] = aa[j][i] + bb[j][i] * cc[j][i];
+ }
+ a[i] = b[i] + c[i] * d[i];
+ }
+}
+
+/* { dg-final { scan-assembler-times {e32,m8} 1 } } */
+/* { dg-final { scan-assembler-not {e32,m4} } } */
+/* { dg-final { scan-assembler-not {csrr} } } */
+/* { dg-final { scan-tree-dump-not "Preferring smaller LMUL loop because it has unexpected spills" "vect" } } */