Remove unroll32 code since it doesn't improve performance.
Reviewed-by: Naohiro Tamura <naohirot@fujitsu.com>
ccmp vector_length, tmp1, 0, cs
b.eq L(L1_prefetch)
-L(unroll32):
- lsl tmp1, vector_length, 3 // vector_length * 8
- lsl tmp2, vector_length, 5 // vector_length * 32
- .p2align 3
-1: cmp rest, tmp2
- b.cc L(unroll8)
- st1b_unroll
- add dst, dst, tmp1
- st1b_unroll
- add dst, dst, tmp1
- st1b_unroll
- add dst, dst, tmp1
- st1b_unroll
- add dst, dst, tmp1
- sub rest, rest, tmp2
- b 1b
L(unroll8):
lsl tmp1, vector_length, 3
sub rest, rest, CACHE_LINE_SIZE * 2
cmp rest, L1_SIZE
b.ge 1b
- cbnz rest, L(unroll32)
+ cbnz rest, L(unroll8)
ret
// count >= L2_SIZE