https://gcc.gnu.org/bugzilla/show_bug.cgi?id=88834
--- Comment #8 from kugan at gcc dot gnu.org ---
(In reply to rsand...@gcc.gnu.org from comment #7)
> Thanks for looking at this.
>
> (In reply to kugan from comment #6)
> > cmp w3, 0
> > ble .L1
> > sub w3, w3, #1
> > mov x4, 0
> > cntw x5
> > ptrue p1.s, all
> > lsr w3, w3, 1
> > add w3, w3, 1
> > whilelo p0.s, xzr, x3
> > .p2align 3,,7
> > .L3:
> > ld2w {z4.s - z5.s}, p0/z, [x1, x4, lsl 2]
> > ld2w {z2.s - z3.s}, p0/z, [x2, x4, lsl 2]
> > add z0.s, z4.s, z2.s
> > sub z1.s, z5.s, z3.s
> > st2w {z0.s - z1.s}, p0, [x0, x4, lsl 2]
> > whilelo p0.s, x5, x3
> > incb x4, all, mul #2
> > incw x5
> > ptest p1, p0.b
> > bne .L3
> > .L1:
> > ret
> > .cfi_endproc
>
> This doesn't look right. x4 is an index, so it should be
> incremented by the number of words in two vectors, rather than
> the number of bytes in two vectors.
Thanks for the comments. Fixed it with the attached patch it generates
f:
.LFB0:
.cfi_startproc
cmp w3, 0
ble .L1
sub w5, w3, #1
cntw x4
mov x3, 0
ptrue p1.s, all
lsr w5, w5, 1
add w5, w5, 1
whilelo p0.s, xzr, x5
.p2align 3,,7
.L3:
ld2w {z4.s - z5.s}, p0/z, [x1, x3, lsl 2]
ld2w {z2.s - z3.s}, p0/z, [x2, x3, lsl 2]
add z0.s, z4.s, z2.s
sub z1.s, z5.s, z3.s
st2w {z0.s - z1.s}, p0, [x0, x3, lsl 2]
whilelo p0.s, x4, x5
inch x3
incw x4
ptest p1, p0.b
bne .L3
.L1:
ret
.cfi_endproc
