diff options
| author |   Lijian.Zhang <Lijian.Zhang@arm.com> | 2019-04-04 15:26:26 +0800 |
|---|---|---|
| committer |   Damjan Marion <dmarion@me.com> | 2019-05-01 07:44:55 +0000 |
| commit | 37c83785b692145b95fe4678f7d599527157217c (patch) | |
| tree | 4a544b46e8931846672f99ec9a5a744554760966 /src/vppinfra/vector_neon.h | |
| parent | 1cff643c6549c6af026213267bed4a8eb25af55f (diff) | |
Enable NEON instructions in memcpy_le
Neon version of memcpy_le gives better performance compared with memmove on aarch64
Change-Id: I44b487bb0795a6e70dd1e55bdde4a077773ec859
Signed-off-by: Lijian Zhang <Lijian.Zhang@arm.com>
Reviewed-by: Sirshak Das <sirdas@arm.com>
Diffstat (limited to 'src/vppinfra/vector_neon.h')
| -rw-r--r-- | src/vppinfra/vector_neon.h | 8 |
1 files changed, 8 insertions, 0 deletions
diff --git a/src/vppinfra/vector_neon.h b/src/vppinfra/vector_neon.h index 90451602d2d..37bd1bb0b01 100644 --- a/src/vppinfra/vector_neon.h +++ b/src/vppinfra/vector_neon.h @@ -83,6 +83,14 @@ static_always_inline u32 \ t##s##x##c##_zero_byte_mask (t##s##x##c x) \ { uint8x16_t v = vreinterpretq_u8_u##s (vceqq_##i (vdupq_n_##i(0), x)); \ return u8x16_compare_byte_mask (v); } \ +\ +static_always_inline u##s##x##c \ +t##s##x##c##_is_greater (t##s##x##c a, t##s##x##c b) \ +{ return (u##s##x##c) vcgtq_##i (a, b); } \ +\ +static_always_inline t##s##x##c \ +t##s##x##c##_blend (t##s##x##c dst, t##s##x##c src, u##s##x##c mask) \ +{ return (t##s##x##c) vbslq_##i (mask, src, dst); } foreach_neon_vec128i foreach_neon_vec128u |