/* Do certain trailing copies as overlapping if it's going to be
cheaper. i.e. less instructions to do so. For instance doing a 15
byte copy it's more efficient to do two overlapping 8 byte copies than
- 8 + 4 + 2 + 1. */
- if (n > 0 && n < copy_limit / 2)
+ 8 + 4 + 2 + 1. Only do this when -mstrict-align is not supplied. */
+ if (n > 0 && n < copy_limit / 2 && !STRICT_ALIGNMENT)
{
next_mode = smallest_mode_for_size (n, MODE_INT);
int n_bits = GET_MODE_BITSIZE (next_mode).to_constant ();
--- /dev/null
+/* { dg-do compile } */
+/* { dg-options "-Os -mstrict-align" } */
+
+struct s { char x[95]; };
+void foo (struct s *);
+void bar (void) { struct s s1 = {}; foo (&s1); }
+
+/* memset (s1 = {}, sizeof = 95) should be expanded out
+ such that there are no overlap stores when -mstrict-align
+ is in use.
+ so 2 pair 16 bytes stores (64 bytes).
+ 1 16 byte stores
+ 1 8 byte store
+ 1 4 byte store
+ 1 2 byte store
+ 1 1 byte store
+ */
+
+/* { dg-final { scan-assembler-times "stp\tq" 2 } } */
+/* { dg-final { scan-assembler-times "str\tq" 1 } } */
+/* { dg-final { scan-assembler-times "str\txzr" 1 } } */
+/* { dg-final { scan-assembler-times "str\twzr" 1 } } */
+/* { dg-final { scan-assembler-times "strh\twzr" 1 } } */
+/* { dg-final { scan-assembler-times "strb\twzr" 1 } } */
+
+/* Also one store pair for the frame-pointer and the LR. */
+/* { dg-final { scan-assembler-times "stp\tx" 1 } } */
+