https://gcc.gnu.org/bugzilla/show_bug.cgi?id=114814
ktkachov at gcc dot gnu.org changed:
What |Removed |Added
----------------------------------------------------------------------------
CC| |ktkachov at gcc dot gnu.org
Ever confirmed|0 |1
Status|UNCONFIRMED |NEW
Last reconfirmed| |2024-06-20
--- Comment #1 from ktkachov at gcc dot gnu.org ---
Confirmed.
The SVE2 codegen isn't much better.
-O2 -mcpu=neoverse-v2 --param aarch64-autovec-preference=2
.L3:
ld1b z3.b, p5/z, [x0, x3]
mov p5.b, p13.b
cmpeq p14.b, p5/z, z30.b, z3.b
mov z26.b, p14/z, #1
uunpklo z1.h, z26.b
whilelo p5.b, x3, x4
uunpklo z2.s, z1.h
uunpkhi z26.h, z26.b
uunpkhi z1.s, z1.h
uunpklo z0.s, z26.h
uunpklo z27.d, z2.s
uunpklo z24.d, z1.s
add z28.d, p7/m, z28.d, z27.d
uunpkhi z26.s, z26.h
mov p7.b, p15.b
uunpklo z25.d, z0.s
uunpklo z29.d, z26.s
whilelo p15.d, x3, x11
uunpkhi z2.d, z2.s
uunpkhi z1.d, z1.s
add z28.d, p6/m, z28.d, z2.d
uunpkhi z0.d, z0.s
add z28.d, p4/m, z28.d, z24.d
whilelo p6.d, x3, x5
add z28.d, p3/m, z28.d, z1.d
whilelo p4.d, x3, x6
add z28.d, p2/m, z28.d, z25.d
whilelo p3.d, x3, x7
add z28.d, p1/m, z28.d, z0.d
whilelo p2.d, x3, x8
add z28.d, p0/m, z28.d, z29.d
whilelo p1.d, x3, x9
whilelo p0.d, x3, x10
mov x1, x3
uunpkhi z26.d, z26.s
add x3, x3, x12
add z28.d, p7/m, z28.d, z26.d
whilelo p7.d, x1, x4
b.any .L3
mov p7.b, p13.b
uaddv d31, p7, z28.d
fmov x0, d31
ret
