[gcc r10-8859] Backport fix for PR/tree-optimization/97236 - fix bad use of VMAT_CONTIGUOUS

[gcc r10-8859] Backport fix for PR/tree-optimization/97236 - fix bad use of VMAT_CONTIGUOUS

[Matthias Klose]

https://gcc.gnu.org/g:1ab88985631dd2c5a5e3b5c0dce47cf8b6ed2f82

commit r10-8859-g1ab88985631dd2c5a5e3b5c0dce47cf8b6ed2f82
Author: Matthias Klose <doko@ubuntu.com>
Date:   Tue Oct 6 13:41:37 2020 +0200

    Backport fix for PR/tree-optimization/97236 - fix bad use of VMAT_CONTIGUOUS
    
    This avoids using VMAT_CONTIGUOUS with single-element interleaving
    when using V1mode vectors.  Instead keep VMAT_ELEMENTWISE but
    continue to avoid load-lanes and gathers.
    
    2020-10-01  Richard Biener  <rguenther@suse.de>
    
            PR tree-optimization/97236
            * tree-vect-stmts.c (get_group_load_store_type): Keep
            VMAT_ELEMENTWISE for single-element vectors.
    
            * gcc.dg/vect/pr97236.c: New testcase.

Diff:
---
 gcc/testsuite/gcc.dg/vect/pr97236.c | 43 +++++++++++++++++++++++++++++++++++++
 gcc/tree-vect-stmts.c               | 20 ++++++++---------
 2 files changed, 52 insertions(+), 11 deletions(-)

diff --git a/gcc/testsuite/gcc.dg/vect/pr97236.c b/gcc/testsuite/gcc.dg/vect/pr97236.c
new file mode 100644
index 00000000000..9d3dc20d953
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/pr97236.c
@@ -0,0 +1,43 @@
+typedef unsigned char __uint8_t;
+typedef __uint8_t uint8_t;
+typedef struct plane_t {
+  uint8_t *p_pixels;
+  int i_lines;
+  int i_pitch;
+} plane_t;
+
+typedef struct {
+  plane_t p[5];
+} picture_t;
+
+#define N 4
+
+void __attribute__((noipa))
+picture_Clone(picture_t *picture, picture_t *res)
+{
+  for (int i = 0; i < N; i++) {
+    res->p[i].p_pixels = picture->p[i].p_pixels;
+    res->p[i].i_lines = picture->p[i].i_lines;
+    res->p[i].i_pitch = picture->p[i].i_pitch;
+  }
+}
+
+int
+main()
+{
+  picture_t aaa, bbb;
+  uint8_t pixels[10] = {1, 1, 1, 1, 1, 1, 1, 1};
+
+  for (unsigned i = 0; i < N; i++)
+    aaa.p[i].p_pixels = pixels;
+
+  picture_Clone (&aaa, &bbb);
+
+  uint8_t c = 0;
+  for (unsigned i = 0; i < N; i++)
+    c += bbb.p[i].p_pixels[0];
+
+  if (c != N)
+    __builtin_abort ();
+  return 0;
+}
diff --git a/gcc/tree-vect-stmts.c b/gcc/tree-vect-stmts.c
index 9ace345fc5e..d8b2ff3d6ee 100644
--- a/gcc/tree-vect-stmts.c
+++ b/gcc/tree-vect-stmts.c
@@ -2413,25 +2413,23 @@ get_group_load_store_type (stmt_vec_info stmt_info, tree vectype, bool slp,
 	  /* First cope with the degenerate case of a single-element
 	     vector.  */
 	  if (known_eq (TYPE_VECTOR_SUBPARTS (vectype), 1U))
-	    *memory_access_type = VMAT_CONTIGUOUS;
+	    ;
 
 	  /* Otherwise try using LOAD/STORE_LANES.  */
-	  if (*memory_access_type == VMAT_ELEMENTWISE
-	      && (vls_type == VLS_LOAD
-		  ? vect_load_lanes_supported (vectype, group_size, masked_p)
-		  : vect_store_lanes_supported (vectype, group_size,
-						masked_p)))
+	  else if (vls_type == VLS_LOAD
+		   ? vect_load_lanes_supported (vectype, group_size, masked_p)
+		   : vect_store_lanes_supported (vectype, group_size,
+						 masked_p))
 	    {
 	      *memory_access_type = VMAT_LOAD_STORE_LANES;
 	      overrun_p = would_overrun_p;
 	    }
 
 	  /* If that fails, try using permuting loads.  */
-	  if (*memory_access_type == VMAT_ELEMENTWISE
-	      && (vls_type == VLS_LOAD
-		  ? vect_grouped_load_supported (vectype, single_element_p,
-						 group_size)
-		  : vect_grouped_store_supported (vectype, group_size)))
+	  else if (vls_type == VLS_LOAD
+		   ? vect_grouped_load_supported (vectype, single_element_p,
+						  group_size)
+		   : vect_grouped_store_supported (vectype, group_size))
 	    {
 	      *memory_access_type = VMAT_CONTIGUOUS_PERMUTE;
 	      overrun_p = would_overrun_p;