https://gcc.gnu.org/bugzilla/show_bug.cgi?id=18438
--- Comment #10 from Maxim Kuvyrkov <mkuvyrkov at gcc dot gnu.org> ---
(In reply to Maxim Kuvyrkov from comment #9)
> which then becomes for aarch64:
> .L4:
> ld2 {v0.2d - v1.2d}, [x1]
> add w2, w2, 1
> cmp w2, w7
> eor v0.16b, v2.16b, v0.16b
> umov x4, v0.d[1]
> st1 {v0.d}[0], [x1]
> add x1, x1, 32
> str x4, [x1, -16]
> bcc .L4
IIUC,
umov x4, v0.d[1]
st1 {v0.d}[0], [x1]
str x4, [x1, -16]
could become just
st2 {v0.d - v1.2d}, [x1]
