https://gcc.gnu.org/bugzilla/show_bug.cgi?id=93771
Andrew Pinski <pinskia at gcc dot gnu.org> changed:
What |Removed |Added
----------------------------------------------------------------------------
Resolution|--- |FIXED
Status|NEW |RESOLVED
Target Milestone|--- |11.0
--- Comment #5 from Andrew Pinski <pinskia at gcc dot gnu.org> ---
Note the aarch64 code generation for this code is not so bad right now:
ldp q0, q2, [x1]
ldr q1, [x2]
ins v0.d[1], v2.d[1]
fadd v0.2d, v0.2d, v1.2d
str q0, [x0]
Because the PERM
vect__1.7_17 = VEC_PERM_EXPR <vect__1.5_14, vect__1.6_16, { 0, 3 }>;
does the correct thing of doing just the ins now (by
r11-2192-gc9c87e6f9c795bb36e4570a07 )
x86_64 code generation is not bad either:
movupd 16(%rsi), %xmm0
movupd (%rdx), %xmm1
movlpd (%rsi), %xmm0
addpd %xmm1, %xmm0
movups %xmm0, (%rdi)
So I am just going to close this as fixed really.
