mov dst, dstin /* Preserve dstin, we need to return it. */
cmp count, #64
- bge .Lcpy_not_short
+ bhs .Lcpy_not_short
/* Deal with small copies quickly by dropping straight into the
exit block. */
1:
subs tmp2, count, #64 /* Use tmp2 for count. */
- blt .Ltail63aligned
+ blo .Ltail63aligned
cmp tmp2, #512
- bge .Lcpy_body_long
+ bhs .Lcpy_body_long
.Lcpy_body_medium: /* Count in tmp2. */
#ifdef USE_VFP
add src, src, #64
vstr d1, [dst, #56]
add dst, dst, #64
- bge 1b
+ bhs 1b
tst tmp2, #0x3f
beq .Ldone
ldrd A_l, A_h, [src, #64]!
strd A_l, A_h, [dst, #64]!
subs tmp2, tmp2, #64
- bge 1b
+ bhs 1b
tst tmp2, #0x3f
bne 1f
ldr tmp2,[sp], #FRAME_SIZE
add src, src, #32
subs tmp2, tmp2, #prefetch_lines * 64 * 2
- blt 2f
+ blo 2f
1:
cpy_line_vfp d3, 0
cpy_line_vfp d4, 64
add dst, dst, #2 * 64
add src, src, #2 * 64
subs tmp2, tmp2, #prefetch_lines * 64
- bge 1b
+ bhs 1b
2:
cpy_tail_vfp d3, 0
1:
pld [src, #(3 * 64)]
subs count, count, #64
- ldrmi tmp2, [sp], #FRAME_SIZE
- bmi .Ltail63unaligned
+ ldrlo tmp2, [sp], #FRAME_SIZE
+ blo .Ltail63unaligned
pld [src, #(4 * 64)]
#ifdef USE_NEON
neon_load_multi d0-d3, src
neon_load_multi d4-d7, src
subs count, count, #64
- bmi 2f
+ blo 2f
1:
pld [src, #(4 * 64)]
neon_store_multi d0-d3, dst
neon_store_multi d4-d7, dst
neon_load_multi d4-d7, src
subs count, count, #64
- bpl 1b
+ bhs 1b
2:
neon_store_multi d0-d3, dst
neon_store_multi d4-d7, dst