Replaced multiple neon instructions with single equivalent instruction.
This made simpler code and a bit higher performance.
Hash bulk lookup had 0.1% ~ 3% performance gain in tests on ARM A72
platforms.
Signed-off-by: Ruifeng Wang <ruifeng.w...@arm.com>
Reviewed-by: Gavin Hu <gavin...@arm.com>
---
lib/librte_hash/rte_cuckoo_hash.c | 10 +++-------
1 file changed, 3 insertions(+), 7 deletions(-)
diff --git a/lib/librte_hash/rte_cuckoo_hash.c
b/lib/librte_hash/rte_cuckoo_hash.c
index 261267b..f17819e 100644
--- a/lib/librte_hash/rte_cuckoo_hash.c
+++ b/lib/librte_hash/rte_cuckoo_hash.c
@@ -1656,7 +1656,6 @@ compare_signatures(uint32_t *prim_hash_matches, uint32_t
*sec_hash_matches,
#elif defined(RTE_MACHINE_CPUFLAG_NEON)
case RTE_HASH_COMPARE_NEON: {
uint16x8_t vmat, vsig, x;
- uint64x2_t x64;
int16x8_t shift = {-15, -13, -11, -9, -7, -5, -3, -1};
vsig = vld1q_dup_u16((uint16_t const *)&sig);
@@ -1664,16 +1663,13 @@ compare_signatures(uint32_t *prim_hash_matches,
uint32_t *sec_hash_matches,
vmat = vceqq_u16(vsig,
vld1q_u16((uint16_t const *)prim_bkt->sig_current));
x = vshlq_u16(vandq_u16(vmat, vdupq_n_u16(0x8000)), shift);
- x64 = vpaddlq_u32(vpaddlq_u16(x));
- *prim_hash_matches = (uint32_t)(vgetq_lane_u64(x64, 0) +
- vgetq_lane_u64(x64, 1));
+ *prim_hash_matches = (uint32_t)(vaddvq_u16(x));
/* Compare all signatures in the secondary bucket */
vmat = vceqq_u16(vsig,
vld1q_u16((uint16_t const *)sec_bkt->sig_current));
x = vshlq_u16(vandq_u16(vmat, vdupq_n_u16(0x8000)), shift);
- x64 = vpaddlq_u32(vpaddlq_u16(x));
- *sec_hash_matches = (uint32_t)(vgetq_lane_u64(x64, 0) +
- vgetq_lane_u64(x64, 1)); }
+ *sec_hash_matches = (uint32_t)(vaddvq_u16(x));
+ }
break;
#endif
default:
--
2.7.4
