Some operations on mask are redundant and can be removed.
The change yielded 1.6% performance gain on N1SDP.
On ThunderX2, slight performance uplift was also observed.
Fixes: 570acdb1da8a ("net/mlx5: add vectorized Rx/Tx burst for ARM")
Cc: sta...@dpdk.org
Signed-off-by: Ruifeng Wang <ruifeng.w...@arm.com>
---
drivers/net/mlx5/mlx5_rxtx_vec_neon.h | 9 +--------
1 file changed, 1 insertion(+), 8 deletions(-)
diff --git a/drivers/net/mlx5/mlx5_rxtx_vec_neon.h
b/drivers/net/mlx5/mlx5_rxtx_vec_neon.h
index 2234fbe6b2..98a75b09c6 100644
--- a/drivers/net/mlx5/mlx5_rxtx_vec_neon.h
+++ b/drivers/net/mlx5/mlx5_rxtx_vec_neon.h
@@ -768,18 +768,11 @@ rxq_cq_process_v(struct mlx5_rxq_data *rxq, volatile
struct mlx5_cqe *cq,
comp_mask), 0)) /
(sizeof(uint16_t) * 8);
/* D.6 mask out entries after the compressed CQE. */
- mask = vcreate_u16(comp_idx < MLX5_VPMD_DESCS_PER_LOOP ?
- -1UL >> (comp_idx * sizeof(uint16_t) * 8) :
- 0);
- invalid_mask = vorr_u16(invalid_mask, mask);
+ invalid_mask = vorr_u16(invalid_mask, comp_mask);
/* D.7 count non-compressed valid CQEs. */
n = __builtin_clzl(vget_lane_u64(vreinterpret_u64_u16(
invalid_mask), 0)) / (sizeof(uint16_t) * 8);
nocmp_n += n;
- /* D.2 get the final invalid mask. */
- mask = vcreate_u16(n < MLX5_VPMD_DESCS_PER_LOOP ?
- -1UL >> (n * sizeof(uint16_t) * 8) : 0);
- invalid_mask = vorr_u16(invalid_mask, mask);
/* D.3 check error in opcode. */
opcode = vceq_u16(resp_err_check, opcode);
opcode = vbic_u16(opcode, invalid_mask);
--
2.25.1
