2 files changed, 120 insertions, 0 deletions

diff --git a/meta/recipes-devtools/gcc/gcc-9.3.inc b/meta/recipes-devtools/gcc/gcc-9.3.inc
index 4c54ba250a..1c8e3df51d 100644
--- a/meta/recipes-devtools/gcc/gcc-9.3.inc
+++ b/meta/recipes-devtools/gcc/gcc-9.3.inc
@@ -72,6 +72,7 @@ SRC_URI = "\
            file://0001-aarch64-New-Straight-Line-Speculation-SLS-mitigation.patch \
            file://0002-aarch64-Introduce-SLS-mitigation-for-RET-and-BR-inst.patch \
            file://0003-aarch64-Mitigate-SLS-for-BLR-instruction.patch \
+           file://0001-Backport-fix-for-PR-tree-optimization-97236-fix-bad-.patch \
 "
 S = "${TMPDIR}/work-shared/gcc-${PV}-${PR}/gcc-${PV}"
 SRC_URI[sha256sum] = "71e197867611f6054aa1119b13a0c0abac12834765fe2d81f35ac57f84f742d1"
diff --git a/meta/recipes-devtools/gcc/gcc-9.3/0001-Backport-fix-for-PR-tree-optimization-97236-fix-bad-.patch b/meta/recipes-devtools/gcc/gcc-9.3/0001-Backport-fix-for-PR-tree-optimization-97236-fix-bad-.patch
new file mode 100644
index 0000000000..dc1039dcc8
--- /dev/null
+++ b/meta/recipes-devtools/gcc/gcc-9.3/0001-Backport-fix-for-PR-tree-optimization-97236-fix-bad-.patch
@@ -0,0 +1,119 @@
+Upstream-Status: Backport [https://gcc.gnu.org/git/?p=gcc.git;a=commit;h=97b668f9a8c6ec565c278a60e7d1492a6932e409]
+Signed-off-by: Jon Mason <jon.mason@arm.com>
+
+From 97b668f9a8c6ec565c278a60e7d1492a6932e409 Mon Sep 17 00:00:00 2001
+From: Matthias Klose <doko@ubuntu.com>
+Date: Tue, 6 Oct 2020 13:41:37 +0200
+Subject: [PATCH] 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.
+
+(cherry picked from commit 1ab88985631dd2c5a5e3b5c0dce47cf8b6ed2f82)
+---
+ gcc/testsuite/gcc.dg/vect/pr97236.c | 43 +++++++++++++++++++++++++++++
+ gcc/tree-vect-stmts.c               | 20 ++++++--------
+ 2 files changed, 52 insertions(+), 11 deletions(-)
+ create mode 100644 gcc/testsuite/gcc.dg/vect/pr97236.c
+
+diff --git a/gcc/testsuite/gcc.dg/vect/pr97236.c b/gcc/testsuite/gcc.dg/vect/pr97236.c
+new file mode 100644
+index 000000000000..9d3dc20d953d
+--- /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 507f81b0a0e8..ffbba3441de2 100644
+--- a/gcc/tree-vect-stmts.c
++++ b/gcc/tree-vect-stmts.c
+@@ -2355,25 +2355,23 @@ 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;
+-- 
+2.20.1
+