https://gcc.gnu.org/bugzilla/show_bug.cgi?id=84067
--- Comment #3 from ktkachov at gcc dot gnu.org ---
(In reply to Richard Biener from comment #2)
> So any hint on whether the code after r257077 is better or worse than before?
Looks worse unfortunately:
For aarch64 at -O2 it generates:
foo:
mov w3, 44
mov w2, 40
mov w5, 1
mov w4, 2
smull x3, w1, w3
smull x2, w1, w2
str w5, [x0, x3]
add x2, x2, 400
add x1, x2, x1, sxtw 2
str w4, [x0, x1]
ret
whereas with r257077 it generates the shorter:
foo:
mov w3, 40
sxtw x2, w1
mov w4, 1
smaddl x0, w1, w3, x0
mov w3, 2
add x1, x0, x2, lsl 2
str w4, [x0, x2, lsl 2]
str w3, [x1, 400]
ret
