https://gcc.gnu.org/bugzilla/show_bug.cgi?id=109885
--- Comment #1 from Andrew Pinski <pinskia at gcc dot gnu.org> ---
Just FYI, GCC does better on aarch64 with sum.
GCC:
ldp q29, q30, [x0]
movi v31.4s, 0x1
fcmeq v29.4s, v29.4s, 0
fcmeq v30.4s, v30.4s, 0
and v31.16b, v31.16b, v29.16b
sub v31.4s, v31.4s, v30.4s
addv s31, v31.4s
fmov w0, s31
ret
vs this mess:
sub sp, sp, #16
ldp q1, q0, [x0]
adrp x8, .LCPI0_0
fcmeq v1.4s, v1.4s, #0.0
fcmeq v0.4s, v0.4s, #0.0
uzp1 v0.8h, v1.8h, v0.8h
ldr q1, [x8, :lo12:.LCPI0_0]
and v0.16b, v0.16b, v1.16b
addv h0, v0.8h
fmov w8, s0
and w8, w8, #0xff
fmov s0, w8
cnt v0.8b, v0.8b
uaddlv h0, v0.8b
fmov w0, s0
add sp, sp, #16
ret
The reason is it looks like clang/LLVM is tuned to try to use movmskps/testps
while GCC is tuned to do just a sum reduction in general.
Though I think GCC could be slightly better here too.
ldp q29, q30, [x0]
fcmeq v29.4s, v29.4s, 0
fcmeq v30.4s, v30.4s, 0
add v31.16b, v29.16b, v30.16b
addv s31, v31.4s
fmov w0, s31
neg w0, w0
ret
I think might be the best code for aarch64 reduction of bools
