vect: Fix inconsistency in fully-masked lane-reducing op generation [PR116985]

To align vectorized def/use when lane-reducing op is present in loop reduction,
we may need to insert extra trivial pass-through copies, which would cause
mismatch between lane-reducing vector copy and loop mask index. This could be
fixed by computing the right index around a new counter on effective lane-
reducing vector copies.

2024-10-11 Feng Xue <fxue@os.amperecomputing.com>

gcc/
	PR tree-optimization/116985
	* tree-vect-loop.cc (vect_transform_reduction): Compute loop mask
	index based on effective vector copies for reduction op.

gcc/testsuite/
	PR tree-optimization/116985
	* gcc.dg/vect/pr116985.c: New testcase.

diff --git a/gcc/testsuite/gcc.dg/vect/pr116985.c b/gcc/testsuite/gcc.dg/vect/pr116985.c
new file mode 100644 (file)
index 0000000..e6dfdaf
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/pr116985.c
@@ -0,0 +1,23 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target vect_int } */
+/* { dg-options "--param=vect-partial-vector-usage=2 -O2" } */
+/* { dg-additional-options "-mavx512vbmi2" { target { i?86-*-* x86_64-*-* } } } */
+/* { dg-additional-options "-march=armv9-a" { target aarch64-*-* } } */
+
+signed int __attribute__ ((noipa))
+fn (signed int n,
+   signed char *restrict a,
+   signed char *restrict b,
+   signed char *restrict c,
+   signed char *restrict d)
+{
+  signed int res = 0;
+
+  for (int i = 0; i < n; ++i)
+    {
+      res += a[i] * b[i];
+      res += i + 1;
+      res += c[i] * d[i];
+    }
+  return res;
+}

diff --git a/gcc/tree-vect-loop.cc b/gcc/tree-vect-loop.cc
index ade72a5124f797feda9d0dbf451554c4ed988840..025442aabc386b79fc32a9d57c6cac4c03536780 100644 (file)
--- a/gcc/tree-vect-loop.cc
+++ b/gcc/tree-vect-loop.cc
@@ -8916,6 +8916,7 @@ vect_transform_reduction (loop_vec_info loop_vinfo,
 
   bool emulated_mixed_dot_prod = vect_is_emulated_mixed_dot_prod (stmt_info);
   unsigned num = vec_oprnds[reduc_index == 0 ? 1 : 0].length ();
+  unsigned mask_index = 0;
 
   for (unsigned i = 0; i < num; ++i)
     {
@@ -8954,7 +8955,8 @@ vect_transform_reduction (loop_vec_info loop_vinfo,
              std::swap (vop[0], vop[1]);
            }
          tree mask = vect_get_loop_mask (loop_vinfo, gsi, masks,
-                                         vec_num * ncopies, vectype_in, i);
+                                         vec_num * ncopies, vectype_in,
+                                         mask_index++);
          gcall *call = gimple_build_call_internal (cond_fn, 4, mask,
                                                    vop[0], vop[1], vop[0]);
          new_temp = make_ssa_name (vec_dest, call);
@@ -8971,7 +8973,8 @@ vect_transform_reduction (loop_vec_info loop_vinfo,
          if (masked_loop_p && mask_by_cond_expr)
            {
              tree mask = vect_get_loop_mask (loop_vinfo, gsi, masks,
-                                             vec_num * ncopies, vectype_in, i);
+                                             vec_num * ncopies, vectype_in,
+                                             mask_index++);
              build_vect_cond_expr (code, vop, mask, gsi);
            }