according to ixgbe vector implementation, change the data prefetch position
Signed-off-by: Zhe Tao <zhe.tao at intel.com>
---
drivers/net/i40e/i40e_rxtx_vec.c | 14 +++++++-------
1 file changed, 7 insertions(+), 7 deletions(-)
diff --git a/drivers/net/i40e/i40e_rxtx_vec.c b/drivers/net/i40e/i40e_rxtx_vec.c
index 6f89002..f5b2db6 100644
--- a/drivers/net/i40e/i40e_rxtx_vec.c
+++ b/drivers/net/i40e/i40e_rxtx_vec.c
@@ -314,13 +314,6 @@ _recv_raw_pkts_vec(struct i40e_rx_queue *rxq, struct
rte_mbuf **rx_pkts,
__m128i zero, staterr, sterr_tmp1, sterr_tmp2;
__m128i mbp1, mbp2; /* two mbuf pointer in one XMM reg. */
- if (split_packet) {
- rte_prefetch0(&rx_pkts[pos]->cacheline1);
- rte_prefetch0(&rx_pkts[pos + 1]->cacheline1);
- rte_prefetch0(&rx_pkts[pos + 2]->cacheline1);
- rte_prefetch0(&rx_pkts[pos + 3]->cacheline1);
- }
-
/* B.1 load 1 mbuf point */
mbp1 = _mm_loadu_si128((__m128i *)&sw_ring[pos]);
/* Read desc statuses backwards to avoid race condition */
@@ -341,6 +334,13 @@ _recv_raw_pkts_vec(struct i40e_rx_queue *rxq, struct
rte_mbuf **rx_pkts,
/* B.2 copy 2 mbuf point into rx_pkts */
_mm_storeu_si128((__m128i *)&rx_pkts[pos+2], mbp2);
+ if (split_packet) {
+ rte_prefetch0(&rx_pkts[pos]->cacheline1);
+ rte_prefetch0(&rx_pkts[pos + 1]->cacheline1);
+ rte_prefetch0(&rx_pkts[pos + 2]->cacheline1);
+ rte_prefetch0(&rx_pkts[pos + 3]->cacheline1);
+ }
+
/*shift the pktlen field*/
desc_pktlen_align(descs);
--
1.9.3
