[dpdk-dev] [PATCH] app/testpmd: improve MAC swap performance

[Qi Zhang <qi.z.zhang@intel.com>]

The patch optimizes the mac swap operation by taking advantage
of SSE instructions, it only impacts x86 platform.

Cc: stable@dpdk.org

Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
---
 app/test-pmd/macswap.c | 16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)

diff --git a/app/test-pmd/macswap.c b/app/test-pmd/macswap.c
index a8384d5b8..0722782b0 100644
--- a/app/test-pmd/macswap.c
+++ b/app/test-pmd/macswap.c
@@ -78,7 +78,6 @@ pkt_burst_mac_swap(struct fwd_stream *fs)
 	struct rte_port  *txp;
 	struct rte_mbuf  *mb;
 	struct ether_hdr *eth_hdr;
-	struct ether_addr addr;
 	uint16_t nb_rx;
 	uint16_t nb_tx;
 	uint16_t i;
@@ -95,6 +94,15 @@ pkt_burst_mac_swap(struct fwd_stream *fs)
 	start_tsc = rte_rdtsc();
 #endif
 
+#ifdef RTE_ARCH_X86
+	__m128i addr;
+	__m128i shfl_msk = _mm_set_epi8(15, 14, 13, 12,
+					5, 4, 3, 2,
+					1, 0, 11, 10,
+					9, 8, 7, 6);
+#else
+	struct ether_addr addr;
+#endif
 	/*
 	 * Receive a burst of packets and forward them.
 	 */
@@ -123,9 +131,15 @@ pkt_burst_mac_swap(struct fwd_stream *fs)
 		eth_hdr = rte_pktmbuf_mtod(mb, struct ether_hdr *);
 
 		/* Swap dest and src mac addresses. */
+#ifdef RTE_ARCH_X86
+		addr = _mm_loadu_si128((__m128i *)eth_hdr);
+		addr = _mm_shuffle_epi8(addr, shfl_msk);
+		_mm_storeu_si128((__m128i *)eth_hdr, addr);
+#else
 		ether_addr_copy(&eth_hdr->d_addr, &addr);
 		ether_addr_copy(&eth_hdr->s_addr, &eth_hdr->d_addr);
 		ether_addr_copy(&addr, &eth_hdr->s_addr);
+#endif
 
 		mb->ol_flags &= IND_ATTACHED_MBUF | EXT_ATTACHED_MBUF;
 		mb->ol_flags |= ol_flags;
-- 
2.13.6