[PATCH] examples/l3fwd: optimize packet prefetch

[Dengdui Huang]

The prefetch window depending on the hardware platform. The current prefetch
policy may not be applicable to all platforms. In most cases, the number of
packets received by Rx burst is small (64 is used in most performance reports).
In L3fwd, the maximum value cannot exceed 512. Therefore, prefetching all
packets before processing can achieve better performance.

Signed-off-by: Dengdui Huang <huangdengdui at huawei.com>
---
 examples/l3fwd/l3fwd_lpm_neon.h | 42 ++++-----------------------------
 1 file changed, 5 insertions(+), 37 deletions(-)

diff --git a/examples/l3fwd/l3fwd_lpm_neon.h b/examples/l3fwd/l3fwd_lpm_neon.h
index 3c1f827424..0b51782b8c 100644
--- a/examples/l3fwd/l3fwd_lpm_neon.h
+++ b/examples/l3fwd/l3fwd_lpm_neon.h
@@ -91,53 +91,21 @@ l3fwd_lpm_process_packets(int nb_rx, struct rte_mbuf **pkts_burst,
 	const int32_t k = RTE_ALIGN_FLOOR(nb_rx, FWDSTEP);
 	const int32_t m = nb_rx % FWDSTEP;
 
-	if (k) {
-		for (i = 0; i < FWDSTEP; i++) {
-			rte_prefetch0(rte_pktmbuf_mtod(pkts_burst[i],
-							void *));
-		}
-		for (j = 0; j != k - FWDSTEP; j += FWDSTEP) {
-			for (i = 0; i < FWDSTEP; i++) {
-				rte_prefetch0(rte_pktmbuf_mtod(
-						pkts_burst[j + i + FWDSTEP],
-						void *));
-			}
+	/* The number of packets is small. Prefetch all packets. */
+	for (i = 0; i < nb_rx; i++)
+		rte_prefetch0(rte_pktmbuf_mtod(pkts_burst[i], void *));
 
+	if (k) {
+		for (j = 0; j != k; j += FWDSTEP) {
 			processx4_step1(&pkts_burst[j], &dip, &ipv4_flag);
 			processx4_step2(qconf, dip, ipv4_flag, portid,
 					&pkts_burst[j], &dst_port[j]);
 			if (do_step3)
 				processx4_step3(&pkts_burst[j], &dst_port[j]);
 		}
-
-		processx4_step1(&pkts_burst[j], &dip, &ipv4_flag);
-		processx4_step2(qconf, dip, ipv4_flag, portid, &pkts_burst[j],
-				&dst_port[j]);
-		if (do_step3)
-			processx4_step3(&pkts_burst[j], &dst_port[j]);
-
-		j += FWDSTEP;
 	}
 
 	if (m) {
-		/* Prefetch last up to 3 packets one by one */
-		switch (m) {
-		case 3:
-			rte_prefetch0(rte_pktmbuf_mtod(pkts_burst[j],
-							void *));
-			j++;
-			/* fallthrough */
-		case 2:
-			rte_prefetch0(rte_pktmbuf_mtod(pkts_burst[j],
-							void *));
-			j++;
-			/* fallthrough */
-		case 1:
-			rte_prefetch0(rte_pktmbuf_mtod(pkts_burst[j],
-							void *));
-			j++;
-		}
-		j -= m;
 		/* Classify last up to 3 packets one by one */
 		switch (m) {
 		case 3:
-- 
2.33.0