@@ -10885,6 +10885,16 @@ expand_expr_real_1 (tree exp, rtx target, machine_mode tmode,
unsigned HOST_WIDE_INT ix;
tree field, value;
+ /* Check if it is more efficient to load the data from
+ the memory directly. FIXME: How many stores do we
+ need here if not moved by pieces? */
+ unsigned HOST_WIDE_INT bytes
+ = tree_to_uhwi (TYPE_SIZE_UNIT (type));
+ if ((bytes / UNITS_PER_WORD) > 2
+ && MOVE_MAX_PIECES > UNITS_PER_WORD
+ && can_move_by_pieces (bytes, TYPE_ALIGN (type)))
+ goto normal_inner_ref;
+
FOR_EACH_CONSTRUCTOR_ELT (CONSTRUCTOR_ELTS (init), ix,
field, value)
if (tree_int_cst_equal (field, index))
new file mode 100644
@@ -0,0 +1,22 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -march=x86-64" } */
+
+struct S
+{
+ long long s1 __attribute__ ((aligned (8)));
+ unsigned s2, s3, s4, s5, s6, s7, s8, s9, s10, s11, s12, s13, s14;
+};
+
+const struct S array[] = {
+ { 0, 60, 640, 2112543726, 39682, 48, 16, 33, 10, 96, 2, 0, 0, 4 }
+};
+
+void
+foo (struct S *x)
+{
+ x[0] = array[0];
+}
+/* { dg-final { scan-assembler-times "movups\[\\t \]%xmm\[0-9\]+, \\(%\[\^,\]+\\)" 1 } } */
+/* { dg-final { scan-assembler-times "movups\[\\t \]%xmm\[0-9\]+, 16\\(%\[\^,\]+\\)" 1 } } */
+/* { dg-final { scan-assembler-times "movups\[\\t \]%xmm\[0-9\]+, 32\\(%\[\^,\]+\\)" 1 } } */
+/* { dg-final { scan-assembler-times "movups\[\\t \]%xmm\[0-9\]+, 48\\(%\[\^,\]+\\)" 1 } } */
new file mode 100644
@@ -0,0 +1,20 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -march=skylake" } */
+
+struct S
+{
+ long long s1 __attribute__ ((aligned (8)));
+ unsigned s2, s3, s4, s5, s6, s7, s8, s9, s10, s11, s12, s13, s14;
+};
+
+const struct S array[] = {
+ { 0, 60, 640, 2112543726, 39682, 48, 16, 33, 10, 96, 2, 0, 0, 4 }
+};
+
+void
+foo (struct S *x)
+{
+ x[0] = array[0];
+}
+/* { dg-final { scan-assembler-times "vmovdqu\[\\t \]%ymm\[0-9\]+, \\(%\[\^,\]+\\)" 1 } } */
+/* { dg-final { scan-assembler-times "vmovdqu\[\\t \]%ymm\[0-9\]+, 32\\(%\[\^,\]+\\)" 1 } } */