vect: Account for unused IFN_LOAD_LANES results

At the moment, if we use only one vector of an LD4 result,
we'll treat the LD4 as having the cost of a single load.
But all 4 loads and any associated permutes take place
regardless of which results are actually used.

This patch therefore counts the cost of unused LOAD_LANES
results against the first statement in a group.  An alternative
would be to multiply the ncopies of the first stmt by the group
size and treat other stmts in the group as having zero cost,
but I thought that might be more surprising when reading dumps.

gcc/
	* tree-vect-stmts.c (vect_model_load_cost): Account for unused
	IFN_LOAD_LANES results.

gcc/testsuite/
	* gcc.target/aarch64/sve/cost_model_11.c: New test.
	* gcc.target/aarch64/sve/mask_struct_load_5.c: Use
	-fno-vect-cost-model.

3 files changed, 37 insertions, 1 deletions

diff --git a/gcc/testsuite/gcc.target/aarch64/sve/cost_model_11.c b/gcc/testsuite/gcc.target/aarch64/sve/cost_model_11.c
new file mode 100644
index 0000000..d9f4ccc
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/cost_model_11.c
@@ -0,0 +1,12 @@
+/* { dg-options "-O2 -ftree-vectorize -msve-vector-bits=128" } */
+
+long
+f (long *x, long *y, long *z, long n)
+{
+  long res = 0;
+  for (long i = 0; i < n; ++i)
+    z[i] = x[i * 4] + y[i * 4];
+  return res;
+}
+
+/* { dg-final { scan-assembler-not {\tld4d\t} } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/mask_struct_load_5.c b/gcc/testsuite/gcc.target/aarch64/sve/mask_struct_load_5.c
index da367e4..2a33ee8 100644
--- a/gcc/testsuite/gcc.target/aarch64/sve/mask_struct_load_5.c
+++ b/gcc/testsuite/gcc.target/aarch64/sve/mask_struct_load_5.c
@@ -1,5 +1,5 @@
 /* { dg-do compile } */
-/* { dg-options "-O2 -ftree-vectorize -ffast-math --param aarch64-sve-compare-costs=0" } */
+/* { dg-options "-O2 -ftree-vectorize -ffast-math -fno-vect-cost-model" } */
 
 #include <stdint.h>
 
diff --git a/gcc/tree-vect-stmts.c b/gcc/tree-vect-stmts.c
index 068e498..4d72c4d 100644
--- a/gcc/tree-vect-stmts.c
+++ b/gcc/tree-vect-stmts.c
@@ -1120,6 +1120,30 @@ vect_model_load_cost (vec_info *vinfo,
      once per group anyhow.  */
   bool first_stmt_p = (first_stmt_info == stmt_info);
 
+  /* An IFN_LOAD_LANES will load all its vector results, regardless of which
+     ones we actually need.  Account for the cost of unused results.  */
+  if (first_stmt_p && !slp_node && memory_access_type == VMAT_LOAD_STORE_LANES)
+    {
+      unsigned int gaps = DR_GROUP_SIZE (first_stmt_info);
+      stmt_vec_info next_stmt_info = first_stmt_info;
+      do
+	{
+	  gaps -= 1;
+	  next_stmt_info = DR_GROUP_NEXT_ELEMENT (next_stmt_info);
+	}
+      while (next_stmt_info);
+      if (gaps)
+	{
+	  if (dump_enabled_p ())
+	    dump_printf_loc (MSG_NOTE, vect_location,
+			     "vect_model_load_cost: %d unused vectors.\n",
+			     gaps);
+	  vect_get_load_cost (vinfo, stmt_info, ncopies * gaps, false,
+			      &inside_cost, &prologue_cost,
+			      cost_vec, cost_vec, true);
+	}
+    }
+
   /* We assume that the cost of a single load-lanes instruction is
      equivalent to the cost of DR_GROUP_SIZE separate loads.  If a grouped
      access is instead being provided by a load-and-permute operation,