DPDK patches and discussions
 help / color / mirror / Atom feed
* [dpdk-dev] [PATCH v2] app/testpmd: optimized MAC swap by using neon intrinsics
@ 2019-03-12  5:35 Ruifeng Wang
  2019-03-12 13:05 ` Honnappa Nagarahalli
  2019-03-18  3:49 ` [dpdk-dev] [PATCH] release notes: added release notes for macswap change Ruifeng Wang
  0 siblings, 2 replies; 10+ messages in thread
From: Ruifeng Wang @ 2019-03-12  5:35 UTC (permalink / raw)
  To: wenzhuo.lu, jingjing.wu, bernard.iremonger
  Cc: dev, jerinj, hemant.agrawal, Honnappa.Nagarahalli, nd, Ruifeng Wang

Improved MAC swap performance for ARM platform.
The improvement was achieved by using neon intrinsics
to save CPU cycles and doing swap for four packets
at a time.
The optimization had 15% - 20% throughput boost
in testpmd MAC swap mode.

Signed-off-by: Ruifeng Wang <ruifeng.wang@arm.com>
Reviewed-by: Gavin Hu <gavin.hu@arm.com>
Reviewed-by: Phil Yang <phil.yang@arm.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
---
v2:
* Defined idx_map as const.
* Added file header line to indicate derivation from macswap_sse.h.

 app/test-pmd/macswap.c      |  4 +-
 app/test-pmd/macswap_neon.h | 97 +++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 100 insertions(+), 1 deletion(-)
 create mode 100644 app/test-pmd/macswap_neon.h

diff --git a/app/test-pmd/macswap.c b/app/test-pmd/macswap.c
index cbb41b7..71af916 100644
--- a/app/test-pmd/macswap.c
+++ b/app/test-pmd/macswap.c
@@ -66,8 +66,10 @@
 #include <rte_flow.h>
 
 #include "testpmd.h"
-#ifdef RTE_ARCH_X86
+#if defined(RTE_ARCH_X86)
 #include "macswap_sse.h"
+#elif defined(RTE_MACHINE_CPUFLAG_NEON)
+#include "macswap_neon.h"
 #else
 #include "macswap.h"
 #endif
diff --git a/app/test-pmd/macswap_neon.h b/app/test-pmd/macswap_neon.h
new file mode 100644
index 0000000..bdf416a
--- /dev/null
+++ b/app/test-pmd/macswap_neon.h
@@ -0,0 +1,97 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2019 Arm Limited
+ *
+ * Copyright(c) 2019 Intel Corporation
+ *
+ * Derived do_macswap implementation from app/test-pmd/macswap_sse.h
+ */
+
+#ifndef _MACSWAP_NEON_H_
+#define _MACSWAP_NEON_H_
+
+#include "macswap_common.h"
+#include "rte_vect.h"
+
+static inline void
+do_macswap(struct rte_mbuf *pkts[], uint16_t nb,
+		struct rte_port *txp)
+{
+	struct ether_hdr *eth_hdr[4];
+	struct rte_mbuf *mb[4];
+	uint64_t ol_flags;
+	int i;
+	int r;
+	uint8x16_t v0, v1, v2, v3;
+	/**
+	 * Index map be used to shuffle the 16 bytes.
+	 * byte 0-5 will be swapped with byte 6-11.
+	 * byte 12-15 will keep unchanged.
+	 */
+	const uint8x16_t idx_map = {6, 7, 8, 9, 10, 11, 0, 1, 2, 3, 4, 5,
+				12, 13, 14, 15};
+
+	ol_flags = ol_flags_init(txp->dev_conf.txmode.offloads);
+	vlan_qinq_set(pkts, nb, ol_flags,
+			txp->tx_vlan_id, txp->tx_vlan_id_outer);
+
+	i = 0;
+	r = nb;
+
+	while (r >= 4) {
+		if (r >= 8) {
+			rte_prefetch0(rte_pktmbuf_mtod(pkts[i + 4], void *));
+			rte_prefetch0(rte_pktmbuf_mtod(pkts[i + 5], void *));
+			rte_prefetch0(rte_pktmbuf_mtod(pkts[i + 6], void *));
+			rte_prefetch0(rte_pktmbuf_mtod(pkts[i + 7], void *));
+		}
+
+		mb[0] = pkts[i++];
+		eth_hdr[0] = rte_pktmbuf_mtod(mb[0], struct ether_hdr *);
+
+		mb[1] = pkts[i++];
+		eth_hdr[1] = rte_pktmbuf_mtod(mb[1], struct ether_hdr *);
+
+		mb[2] = pkts[i++];
+		eth_hdr[2] = rte_pktmbuf_mtod(mb[2], struct ether_hdr *);
+
+		mb[3] = pkts[i++];
+		eth_hdr[3] = rte_pktmbuf_mtod(mb[3], struct ether_hdr *);
+
+		v0 = vld1q_u8((uint8_t const *)eth_hdr[0]);
+		v1 = vld1q_u8((uint8_t const *)eth_hdr[1]);
+		v2 = vld1q_u8((uint8_t const *)eth_hdr[2]);
+		v3 = vld1q_u8((uint8_t const *)eth_hdr[3]);
+
+		v0 = vqtbl1q_u8(v0, idx_map);
+		v1 = vqtbl1q_u8(v1, idx_map);
+		v2 = vqtbl1q_u8(v2, idx_map);
+		v3 = vqtbl1q_u8(v3, idx_map);
+
+		vst1q_u8((uint8_t *)eth_hdr[0], v0);
+		vst1q_u8((uint8_t *)eth_hdr[1], v1);
+		vst1q_u8((uint8_t *)eth_hdr[2], v2);
+		vst1q_u8((uint8_t *)eth_hdr[3], v3);
+
+		mbuf_field_set(mb[0], ol_flags);
+		mbuf_field_set(mb[1], ol_flags);
+		mbuf_field_set(mb[2], ol_flags);
+		mbuf_field_set(mb[3], ol_flags);
+		r -= 4;
+	}
+
+	for ( ; i < nb; i++) {
+		if (i < nb - 1)
+			rte_prefetch0(rte_pktmbuf_mtod(pkts[i+1], void *));
+		mb[0] = pkts[i];
+		eth_hdr[0] = rte_pktmbuf_mtod(mb[0], struct ether_hdr *);
+
+		/* Swap dest and src mac addresses. */
+		v0 = vld1q_u8((uint8_t const *)eth_hdr[0]);
+		v0 = vqtbl1q_u8(v0, idx_map);
+		vst1q_u8((uint8_t *)eth_hdr[0], v0);
+
+		mbuf_field_set(mb[0], ol_flags);
+	}
+}
+
+#endif /* _MACSWAP_NEON_H_ */
-- 
2.7.4

^ permalink raw reply	[flat|nested] 10+ messages in thread

end of thread, other threads:[~2019-03-20 17:14 UTC | newest]

Thread overview: 10+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2019-03-12  5:35 [dpdk-dev] [PATCH v2] app/testpmd: optimized MAC swap by using neon intrinsics Ruifeng Wang
2019-03-12 13:05 ` Honnappa Nagarahalli
2019-03-15 18:38   ` Ferruh Yigit
2019-03-15 18:38     ` Ferruh Yigit
2019-03-18  5:45     ` Ruifeng Wang (Arm Technology China)
2019-03-18  5:45       ` Ruifeng Wang (Arm Technology China)
2019-03-18  3:49 ` [dpdk-dev] [PATCH] release notes: added release notes for macswap change Ruifeng Wang
2019-03-18  3:49   ` Ruifeng Wang
2019-03-20 17:14   ` Ferruh Yigit
2019-03-20 17:14     ` Ferruh Yigit

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).