https://gcc.gnu.org/bugzilla/show_bug.cgi?id=88963
--- Comment #9 from Devin Hussey <husseydevin at gmail dot com> ---
(In reply to Andrew Pinski from comment #6)
> Try using 128 (or 256) and you might see that aarch64 falls down similarly.
yup. Oof.
test:
sub sp, sp, #560
stp x29, x30, [sp]
mov x29, sp
stp x19, x20, [sp, 16]
mov x19, 128
mov x20, x0
add x0, sp, 176
str x21, [sp, 32]
mov x21, x2
mov x2, x19
bl memcpy
mov x2, x19
mov x1, x21
add x0, sp, 304
bl memcpy
ldr q7, [sp, 176]
mov x2, x19
ldr q6, [sp, 192]
add x1, sp, 48
ldr q5, [sp, 208]
mov x0, x20
ldr q4, [sp, 224]
ldr q3, [sp, 240]
ldr q2, [sp, 256]
ldr q1, [sp, 272]
ldr q0, [sp, 288]
ldr q23, [sp, 304]
ldr q22, [sp, 320]
ldr q21, [sp, 336]
ldr q20, [sp, 352]
ldr q19, [sp, 368]
ldr q18, [sp, 384]
ldr q17, [sp, 400]
ldr q16, [sp, 416]
add v7.4s, v7.4s, v23.4s
add v6.4s, v6.4s, v22.4s
add v5.4s, v5.4s, v21.4s
add v4.4s, v4.4s, v20.4s
add v3.4s, v3.4s, v19.4s
str q7, [sp, 48]
add v2.4s, v2.4s, v18.4s
str q6, [sp, 64]
add v1.4s, v1.4s, v17.4s
str q5, [sp, 80]
add v0.4s, v0.4s, v16.4s
str q4, [sp, 96]
str q3, [sp, 112]
str q2, [sp, 128]
str q1, [sp, 144]
str q0, [sp, 160]
bl memcpy
ldp x29, x30, [sp]
ldp x19, x20, [sp, 16]
ldr x21, [sp, 32]
add sp, sp, 560
ret
