[PATCH 2/2] net/ngbe: add vectorized functions for Rx/Tx

[Jiawen Wu <jiawenwu@trustnetic.com>]

To optimize Rx/Tx burst process, add SSE/NEON vector instructions on
x86/arm architecture.

Signed-off-by: Jiawen Wu <jiawenwu@trustnetic.com>
---
 drivers/net/ngbe/meson.build            |   6 +
 drivers/net/ngbe/ngbe_ethdev.c          |   6 +
 drivers/net/ngbe/ngbe_ethdev.h          |   1 +
 drivers/net/ngbe/ngbe_rxtx.c            | 161 +++++-
 drivers/net/ngbe/ngbe_rxtx.h            |  32 +-
 drivers/net/ngbe/ngbe_rxtx_vec_common.h | 296 ++++++++++
 drivers/net/ngbe/ngbe_rxtx_vec_neon.c   | 604 +++++++++++++++++++++
 drivers/net/ngbe/ngbe_rxtx_vec_sse.c    | 692 ++++++++++++++++++++++++
 8 files changed, 1794 insertions(+), 4 deletions(-)
 create mode 100644 drivers/net/ngbe/ngbe_rxtx_vec_common.h
 create mode 100644 drivers/net/ngbe/ngbe_rxtx_vec_neon.c
 create mode 100644 drivers/net/ngbe/ngbe_rxtx_vec_sse.c

diff --git a/drivers/net/ngbe/meson.build b/drivers/net/ngbe/meson.build
index 8b5195aab3..5d395ee17f 100644
--- a/drivers/net/ngbe/meson.build
+++ b/drivers/net/ngbe/meson.build
@@ -19,4 +19,10 @@ sources = files(
 
 deps += ['hash']
 
+if arch_subdir == 'x86'
+	sources += files('ngbe_rxtx_vec_sse.c')
+elif arch_subdir == 'arm'
+	sources += files('ngbe_rxtx_vec_neon.c')
+endif
+
 includes += include_directories('base')
diff --git a/drivers/net/ngbe/ngbe_ethdev.c b/drivers/net/ngbe/ngbe_ethdev.c
index 478da014b2..39306e353c 100644
--- a/drivers/net/ngbe/ngbe_ethdev.c
+++ b/drivers/net/ngbe/ngbe_ethdev.c
@@ -932,6 +932,7 @@ ngbe_dev_configure(struct rte_eth_dev *dev)
 	 * allocation Rx preconditions we will reset it.
 	 */
 	adapter->rx_bulk_alloc_allowed = true;
+	adapter->rx_vec_allowed = true;
 
 	return 0;
 }
@@ -1872,6 +1873,11 @@ ngbe_dev_supported_ptypes_get(struct rte_eth_dev *dev)
 	    dev->rx_pkt_burst == ngbe_recv_pkts_bulk_alloc)
 		return ngbe_get_supported_ptypes();
 
+#if defined(RTE_ARCH_X86) || defined(__ARM_NEON)
+	if (dev->rx_pkt_burst == ngbe_recv_pkts_vec ||
+	    dev->rx_pkt_burst == ngbe_recv_scattered_pkts_vec)
+		return ngbe_get_supported_ptypes();
+#endif
 	return NULL;
 }
 
diff --git a/drivers/net/ngbe/ngbe_ethdev.h b/drivers/net/ngbe/ngbe_ethdev.h
index 3cde7c8750..8aef6553a0 100644
--- a/drivers/net/ngbe/ngbe_ethdev.h
+++ b/drivers/net/ngbe/ngbe_ethdev.h
@@ -130,6 +130,7 @@ struct ngbe_adapter {
 	struct ngbe_vf_info        *vfdata;
 	struct ngbe_uta_info       uta_info;
 	bool                       rx_bulk_alloc_allowed;
+	bool                       rx_vec_allowed;
 	struct rte_timecounter     systime_tc;
 	struct rte_timecounter     rx_tstamp_tc;
 	struct rte_timecounter     tx_tstamp_tc;
diff --git a/drivers/net/ngbe/ngbe_rxtx.c b/drivers/net/ngbe/ngbe_rxtx.c
index 8a873b858e..f3e741cbad 100644
--- a/drivers/net/ngbe/ngbe_rxtx.c
+++ b/drivers/net/ngbe/ngbe_rxtx.c
@@ -10,6 +10,7 @@
 #include <ethdev_driver.h>
 #include <rte_malloc.h>
 #include <rte_net.h>
+#include <rte_vect.h>
 
 #include "ngbe_logs.h"
 #include "base/ngbe.h"
@@ -267,6 +268,27 @@ ngbe_xmit_pkts_simple(void *tx_queue, struct rte_mbuf **tx_pkts,
 	return nb_tx;
 }
 
+static uint16_t
+ngbe_xmit_pkts_vec(void *tx_queue, struct rte_mbuf **tx_pkts,
+		   uint16_t nb_pkts)
+{
+	struct ngbe_tx_queue *txq = (struct ngbe_tx_queue *)tx_queue;
+	uint16_t nb_tx = 0;
+
+	while (nb_pkts) {
+		uint16_t ret, num;
+
+		num = (uint16_t)RTE_MIN(nb_pkts, txq->tx_free_thresh);
+		ret = ngbe_xmit_fixed_burst_vec(tx_queue, &tx_pkts[nb_tx], num);
+		nb_tx += ret;
+		nb_pkts -= ret;
+		if (ret < num)
+			break;
+	}
+
+	return nb_tx;
+}
+
 static inline void
 ngbe_set_xmit_ctx(struct ngbe_tx_queue *txq,
 		volatile struct ngbe_tx_ctx_desc *ctx_txd,
@@ -1858,8 +1880,15 @@ ngbe_set_tx_function(struct rte_eth_dev *dev, struct ngbe_tx_queue *txq)
 	if (txq->offloads == 0 &&
 			txq->tx_free_thresh >= RTE_PMD_NGBE_TX_MAX_BURST) {
 		PMD_INIT_LOG(DEBUG, "Using simple tx code path");
-		dev->tx_pkt_burst = ngbe_xmit_pkts_simple;
 		dev->tx_pkt_prepare = NULL;
+		if (txq->tx_free_thresh <= RTE_NGBE_TX_MAX_FREE_BUF_SZ &&
+				(rte_eal_process_type() != RTE_PROC_PRIMARY ||
+					ngbe_txq_vec_setup(txq) == 0)) {
+			PMD_INIT_LOG(DEBUG, "Vector tx enabled.");
+			dev->tx_pkt_burst = ngbe_xmit_pkts_vec;
+		} else {
+			dev->tx_pkt_burst = ngbe_xmit_pkts_simple;
+		}
 	} else {
 		PMD_INIT_LOG(DEBUG, "Using full-featured tx code path");
 		PMD_INIT_LOG(DEBUG,
@@ -1880,6 +1909,11 @@ static const struct {
 } ngbe_tx_burst_infos[] = {
 	{ ngbe_xmit_pkts_simple,   "Scalar Simple"},
 	{ ngbe_xmit_pkts,          "Scalar"},
+#ifdef RTE_ARCH_X86
+	{ ngbe_xmit_pkts_vec,      "Vector SSE" },
+#elif defined(RTE_ARCH_ARM64)
+	{ ngbe_xmit_pkts_vec,      "Vector Neon" },
+#endif
 };
 
 int
@@ -2066,6 +2100,12 @@ ngbe_rx_queue_release_mbufs(struct ngbe_rx_queue *rxq)
 {
 	unsigned int i;
 
+	/* SSE Vector driver has a different way of releasing mbufs. */
+	if (rxq->rx_using_sse) {
+		ngbe_rx_queue_release_mbufs_vec(rxq);
+		return;
+	}
+
 	if (rxq->sw_ring != NULL) {
 		for (i = 0; i < rxq->nb_rx_desc; i++) {
 			if (rxq->sw_ring[i].mbuf != NULL) {
@@ -2189,6 +2229,11 @@ ngbe_reset_rx_queue(struct ngbe_adapter *adapter, struct ngbe_rx_queue *rxq)
 	rxq->nb_rx_hold = 0;
 	rxq->pkt_first_seg = NULL;
 	rxq->pkt_last_seg = NULL;
+
+#if defined(RTE_ARCH_X86) || defined(RTE_ARCH_ARM64)
+	rxq->rxrearm_start = 0;
+	rxq->rxrearm_nb = 0;
+#endif
 }
 
 uint64_t
@@ -2339,6 +2384,16 @@ ngbe_dev_rx_queue_setup(struct rte_eth_dev *dev,
 		     rxq->sw_ring, rxq->sw_sc_ring, rxq->rx_ring,
 		     rxq->rx_ring_phys_addr);
 
+	if (!rte_is_power_of_2(nb_desc)) {
+		PMD_INIT_LOG(DEBUG, "queue[%d] doesn't meet Vector Rx "
+				    "preconditions - canceling the feature for "
+				    "the whole port[%d]",
+			     rxq->queue_id, rxq->port_id);
+		adapter->rx_vec_allowed = false;
+	} else {
+		ngbe_rxq_vec_setup(rxq);
+	}
+
 	dev->data->rx_queues[queue_idx] = rxq;
 
 	ngbe_reset_rx_queue(adapter, rxq);
@@ -2379,7 +2434,12 @@ ngbe_dev_rx_descriptor_status(void *rx_queue, uint16_t offset)
 	if (unlikely(offset >= rxq->nb_rx_desc))
 		return -EINVAL;
 
-	nb_hold = rxq->nb_rx_hold;
+#if defined(RTE_ARCH_X86) || defined(RTE_ARCH_ARM64)
+	if (rxq->rx_using_sse)
+		nb_hold = rxq->rxrearm_nb;
+	else
+#endif
+		nb_hold = rxq->nb_rx_hold;
 	if (offset >= rxq->nb_rx_desc - nb_hold)
 		return RTE_ETH_RX_DESC_UNAVAIL;
 
@@ -2740,14 +2800,33 @@ ngbe_dev_mq_rx_configure(struct rte_eth_dev *dev)
 void
 ngbe_set_rx_function(struct rte_eth_dev *dev)
 {
+	uint16_t i, rx_using_sse;
 	struct ngbe_adapter *adapter = ngbe_dev_adapter(dev);
 
+	/*
+	 * In order to allow Vector Rx there are a few configuration
+	 * conditions to be met and Rx Bulk Allocation should be allowed.
+	 */
+	if (ngbe_rx_vec_dev_conf_condition_check(dev) ||
+	    !adapter->rx_bulk_alloc_allowed ||
+			rte_vect_get_max_simd_bitwidth() < RTE_VECT_SIMD_128) {
+		PMD_INIT_LOG(DEBUG,
+			     "Port[%d] doesn't meet Vector Rx preconditions",
+			     dev->data->port_id);
+		adapter->rx_vec_allowed = false;
+	}
+
 	if (dev->data->scattered_rx) {
 		/*
 		 * Set the scattered callback: there are bulk and
 		 * single allocation versions.
 		 */
-		if (adapter->rx_bulk_alloc_allowed) {
+		if (adapter->rx_vec_allowed) {
+			PMD_INIT_LOG(DEBUG,
+				     "Using Vector Scattered Rx callback (port=%d).",
+				     dev->data->port_id);
+			dev->rx_pkt_burst = ngbe_recv_scattered_pkts_vec;
+		} else if (adapter->rx_bulk_alloc_allowed) {
 			PMD_INIT_LOG(DEBUG, "Using a Scattered with bulk "
 					   "allocation callback (port=%d).",
 				     dev->data->port_id);
@@ -2765,9 +2844,16 @@ ngbe_set_rx_function(struct rte_eth_dev *dev)
 	 * Below we set "simple" callbacks according to port/queues parameters.
 	 * If parameters allow we are going to choose between the following
 	 * callbacks:
+	 *    - Vector
 	 *    - Bulk Allocation
 	 *    - Single buffer allocation (the simplest one)
 	 */
+	} else if (adapter->rx_vec_allowed) {
+		PMD_INIT_LOG(DEBUG, "Vector rx enabled, please make sure Rx "
+				    "burst size no less than %d (port=%d).",
+			     RTE_NGBE_DESCS_PER_LOOP,
+			     dev->data->port_id);
+		dev->rx_pkt_burst = ngbe_recv_pkts_vec;
 	} else if (adapter->rx_bulk_alloc_allowed) {
 		PMD_INIT_LOG(DEBUG, "Rx Burst Bulk Alloc Preconditions are "
 				    "satisfied. Rx Burst Bulk Alloc function "
@@ -2783,6 +2869,15 @@ ngbe_set_rx_function(struct rte_eth_dev *dev)
 
 		dev->rx_pkt_burst = ngbe_recv_pkts;
 	}
+
+	rx_using_sse = (dev->rx_pkt_burst == ngbe_recv_scattered_pkts_vec ||
+			dev->rx_pkt_burst == ngbe_recv_pkts_vec);
+
+	for (i = 0; i < dev->data->nb_rx_queues; i++) {
+		struct ngbe_rx_queue *rxq = dev->data->rx_queues[i];
+
+		rxq->rx_using_sse = rx_using_sse;
+	}
 }
 
 static const struct {
@@ -2793,6 +2888,13 @@ static const struct {
 	{ ngbe_recv_pkts_sc_bulk_alloc,      "Scalar Scattered Bulk Alloc"},
 	{ ngbe_recv_pkts_bulk_alloc,         "Scalar Bulk Alloc"},
 	{ ngbe_recv_pkts,                    "Scalar"},
+#ifdef RTE_ARCH_X86
+	{ ngbe_recv_scattered_pkts_vec,      "Vector SSE Scattered" },
+	{ ngbe_recv_pkts_vec,                "Vector SSE" },
+#elif defined(RTE_ARCH_ARM64)
+	{ ngbe_recv_scattered_pkts_vec,      "Vector Neon Scattered" },
+	{ ngbe_recv_pkts_vec,                "Vector Neon" },
+#endif
 };
 
 int
@@ -3311,3 +3413,56 @@ ngbe_txq_info_get(struct rte_eth_dev *dev, uint16_t queue_id,
 	qinfo->conf.offloads = txq->offloads;
 	qinfo->conf.tx_deferred_start = txq->tx_deferred_start;
 }
+
+/* Stubs needed for linkage when RTE_ARCH_PPC_64, RTE_ARCH_RISCV or
+ * RTE_ARCH_LOONGARCH is set.
+ */
+#if defined(RTE_ARCH_PPC_64) || defined(RTE_ARCH_RISCV) || \
+	defined(RTE_ARCH_LOONGARCH)
+int
+ngbe_rx_vec_dev_conf_condition_check(__rte_unused struct rte_eth_dev *dev)
+{
+	return -1;
+}
+
+uint16_t
+ngbe_recv_pkts_vec(__rte_unused void *rx_queue,
+		   __rte_unused struct rte_mbuf **rx_pkts,
+		   __rte_unused uint16_t nb_pkts)
+{
+	return 0;
+}
+
+uint16_t
+ngbe_recv_scattered_pkts_vec(__rte_unused void *rx_queue,
+			     __rte_unused struct rte_mbuf **rx_pkts,
+			     __rte_unused uint16_t nb_pkts)
+{
+	return 0;
+}
+
+int
+ngbe_rxq_vec_setup(__rte_unused struct ngbe_rx_queue *rxq)
+{
+	return -1;
+}
+
+uint16_t
+ngbe_xmit_fixed_burst_vec(__rte_unused void *tx_queue,
+			  __rte_unused struct rte_mbuf **tx_pkts,
+			  __rte_unused uint16_t nb_pkts)
+{
+	return 0;
+}
+
+int
+ngbe_txq_vec_setup(__rte_unused struct ngbe_tx_queue *txq)
+{
+	return -1;
+}
+
+void
+ngbe_rx_queue_release_mbufs_vec(__rte_unused struct ngbe_rx_queue *rxq)
+{
+}
+#endif
diff --git a/drivers/net/ngbe/ngbe_rxtx.h b/drivers/net/ngbe/ngbe_rxtx.h
index 9130f9d0df..41580ba0b9 100644
--- a/drivers/net/ngbe/ngbe_rxtx.h
+++ b/drivers/net/ngbe/ngbe_rxtx.h
@@ -203,6 +203,8 @@ struct ngbe_tx_desc {
 #define RTE_PMD_NGBE_RX_MAX_BURST 32
 #define RTE_NGBE_TX_MAX_FREE_BUF_SZ 64
 
+#define RTE_NGBE_DESCS_PER_LOOP    4
+
 #define RX_RING_SZ ((NGBE_RING_DESC_MAX + RTE_PMD_NGBE_RX_MAX_BURST) * \
 		    sizeof(struct ngbe_rx_desc))
 
@@ -237,6 +239,13 @@ struct ngbe_tx_entry {
 	uint16_t last_id; /**< Index of last scattered descriptor. */
 };
 
+/**
+ * Structure associated with each descriptor of the Tx ring of a Tx queue.
+ */
+struct ngbe_tx_entry_v {
+	struct rte_mbuf *mbuf; /**< mbuf associated with Tx desc, if any. */
+};
+
 /**
  * Structure associated with each Rx queue.
  */
@@ -254,6 +263,7 @@ struct ngbe_rx_queue {
 
 	struct rte_mbuf *pkt_first_seg; /**< First segment of current packet */
 	struct rte_mbuf *pkt_last_seg; /**< Last segment of current packet */
+	uint64_t        mbuf_initializer; /**< value to init mbufs */
 	uint16_t        nb_rx_desc; /**< number of Rx descriptors */
 	uint16_t        rx_tail;  /**< current value of RDT register */
 	uint16_t        nb_rx_hold; /**< number of held free Rx desc */
@@ -262,6 +272,11 @@ struct ngbe_rx_queue {
 	uint16_t rx_next_avail; /**< idx of next staged pkt to ret to app */
 	uint16_t rx_free_trigger; /**< triggers rx buffer allocation */
 
+	uint8_t         rx_using_sse;   /**< indicates that vector Rx is in use */
+#if defined(RTE_ARCH_X86) || defined(RTE_ARCH_ARM)
+	uint16_t        rxrearm_nb;     /**< number of remaining to be re-armed */
+	uint16_t        rxrearm_start;  /**< the idx we start the re-arming from */
+#endif
 	uint16_t        rx_free_thresh; /**< max free Rx desc to hold */
 	uint16_t        queue_id; /**< RX queue index */
 	uint16_t        reg_idx;  /**< RX queue register index */
@@ -325,7 +340,12 @@ struct ngbe_tx_queue {
 	volatile struct ngbe_tx_desc *tx_ring;
 
 	uint64_t             tx_ring_phys_addr; /**< Tx ring DMA address */
-	struct ngbe_tx_entry *sw_ring; /**< address of SW ring for scalar PMD */
+	union {
+		/**< address of SW ring for scalar PMD. */
+		struct ngbe_tx_entry *sw_ring;
+		/**< address of SW ring for vector PMD */
+		struct ngbe_tx_entry_v *sw_ring_v;
+	};
 	volatile uint32_t    *tdt_reg_addr; /**< Address of TDT register */
 	volatile uint32_t    *tdc_reg_addr; /**< Address of TDC register */
 	uint16_t             nb_tx_desc;    /**< number of Tx descriptors */
@@ -368,6 +388,16 @@ struct ngbe_txq_ops {
 void ngbe_set_tx_function(struct rte_eth_dev *dev, struct ngbe_tx_queue *txq);
 
 void ngbe_set_rx_function(struct rte_eth_dev *dev);
+uint16_t ngbe_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
+			    uint16_t nb_pkts);
+uint16_t ngbe_recv_scattered_pkts_vec(void *rx_queue,
+		struct rte_mbuf **rx_pkts, uint16_t nb_pkts);
+int ngbe_rx_vec_dev_conf_condition_check(struct rte_eth_dev *dev);
+int ngbe_rxq_vec_setup(struct ngbe_rx_queue *rxq);
+void ngbe_rx_queue_release_mbufs_vec(struct ngbe_rx_queue *rxq);
+uint16_t ngbe_xmit_fixed_burst_vec(void *tx_queue, struct rte_mbuf **tx_pkts,
+				   uint16_t nb_pkts);
+int ngbe_txq_vec_setup(struct ngbe_tx_queue *txq);
 int ngbe_dev_tx_done_cleanup(void *tx_queue, uint32_t free_cnt);
 
 uint64_t ngbe_get_tx_port_offloads(struct rte_eth_dev *dev);
diff --git a/drivers/net/ngbe/ngbe_rxtx_vec_common.h b/drivers/net/ngbe/ngbe_rxtx_vec_common.h
new file mode 100644
index 0000000000..1ce175de52
--- /dev/null
+++ b/drivers/net/ngbe/ngbe_rxtx_vec_common.h
@@ -0,0 +1,296 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2015-2024 Beijing WangXun Technology Co., Ltd.
+ * Copyright(c) 2010-2015 Intel Corporation
+ */
+
+#ifndef _NGBE_RXTX_VEC_COMMON_H_
+#define _NGBE_RXTX_VEC_COMMON_H_
+#include <stdint.h>
+
+#include "ngbe_ethdev.h"
+#include "ngbe_rxtx.h"
+
+#define NGBE_RXD_PTID_SHIFT 9
+
+#define RTE_NGBE_RXQ_REARM_THRESH      32
+#define RTE_NGBE_MAX_RX_BURST          RTE_NGBE_RXQ_REARM_THRESH
+
+static inline uint16_t
+reassemble_packets(struct ngbe_rx_queue *rxq, struct rte_mbuf **rx_bufs,
+		   uint16_t nb_bufs, uint8_t *split_flags)
+{
+	struct rte_mbuf *pkts[nb_bufs]; /*finished pkts*/
+	struct rte_mbuf *start = rxq->pkt_first_seg;
+	struct rte_mbuf *end =  rxq->pkt_last_seg;
+	unsigned int pkt_idx, buf_idx;
+
+	for (buf_idx = 0, pkt_idx = 0; buf_idx < nb_bufs; buf_idx++) {
+		if (end != NULL) {
+			/* processing a split packet */
+			end->next = rx_bufs[buf_idx];
+			rx_bufs[buf_idx]->data_len += rxq->crc_len;
+
+			start->nb_segs++;
+			start->pkt_len += rx_bufs[buf_idx]->data_len;
+			end = end->next;
+
+			if (!split_flags[buf_idx]) {
+				/* it's the last packet of the set */
+				start->hash = end->hash;
+				start->ol_flags = end->ol_flags;
+				/* we need to strip crc for the whole packet */
+				start->pkt_len -= rxq->crc_len;
+				if (end->data_len > rxq->crc_len) {
+					end->data_len -= rxq->crc_len;
+				} else {
+					/* free up last mbuf */
+					struct rte_mbuf *secondlast = start;
+
+					start->nb_segs--;
+					while (secondlast->next != end)
+						secondlast = secondlast->next;
+					secondlast->data_len -= (rxq->crc_len -
+							end->data_len);
+					secondlast->next = NULL;
+					rte_pktmbuf_free_seg(end);
+				}
+				pkts[pkt_idx++] = start;
+				start = NULL;
+				end = NULL;
+			}
+		} else {
+			/* not processing a split packet */
+			if (!split_flags[buf_idx]) {
+				/* not a split packet, save and skip */
+				pkts[pkt_idx++] = rx_bufs[buf_idx];
+				continue;
+			}
+			start = rx_bufs[buf_idx];
+			end = start;
+			rx_bufs[buf_idx]->data_len += rxq->crc_len;
+			rx_bufs[buf_idx]->pkt_len += rxq->crc_len;
+		}
+	}
+
+	/* save the partial packet for next time */
+	rxq->pkt_first_seg = start;
+	rxq->pkt_last_seg = end;
+	memcpy(rx_bufs, pkts, pkt_idx * (sizeof(*pkts)));
+	return pkt_idx;
+}
+
+static __rte_always_inline int
+ngbe_tx_free_bufs(struct ngbe_tx_queue *txq)
+{
+	struct ngbe_tx_entry_v *txep;
+	uint32_t status;
+	uint32_t n;
+	uint32_t i;
+	int nb_free = 0;
+	struct rte_mbuf *m, *free[RTE_NGBE_TX_MAX_FREE_BUF_SZ];
+
+	/* check DD bit on threshold descriptor */
+	status = txq->tx_ring[txq->tx_next_dd].dw3;
+	if (!(status & NGBE_TXD_DD)) {
+		if (txq->nb_tx_free >> 1 < txq->tx_free_thresh)
+			ngbe_set32_masked(txq->tdc_reg_addr,
+				NGBE_TXCFG_FLUSH, NGBE_TXCFG_FLUSH);
+		return 0;
+	}
+
+	n = txq->tx_free_thresh;
+
+	/*
+	 * first buffer to free from S/W ring is at index
+	 * tx_next_dd - (tx_rs_thresh-1)
+	 */
+	txep = &txq->sw_ring_v[txq->tx_next_dd - (n - 1)];
+	m = rte_pktmbuf_prefree_seg(txep[0].mbuf);
+	if (likely(m != NULL)) {
+		free[0] = m;
+		nb_free = 1;
+		for (i = 1; i < n; i++) {
+			m = rte_pktmbuf_prefree_seg(txep[i].mbuf);
+			if (likely(m != NULL)) {
+				if (likely(m->pool == free[0]->pool)) {
+					free[nb_free++] = m;
+				} else {
+					rte_mempool_put_bulk(free[0]->pool,
+							(void *)free, nb_free);
+					free[0] = m;
+					nb_free = 1;
+				}
+			}
+		}
+		rte_mempool_put_bulk(free[0]->pool, (void **)free, nb_free);
+	} else {
+		for (i = 1; i < n; i++) {
+			m = rte_pktmbuf_prefree_seg(txep[i].mbuf);
+			if (m != NULL)
+				rte_mempool_put(m->pool, m);
+		}
+	}
+
+	/* buffers were freed, update counters */
+	txq->nb_tx_free = (uint16_t)(txq->nb_tx_free + txq->tx_free_thresh);
+	txq->tx_next_dd = (uint16_t)(txq->tx_next_dd + txq->tx_free_thresh);
+	if (txq->tx_next_dd >= txq->nb_tx_desc)
+		txq->tx_next_dd = (uint16_t)(txq->tx_free_thresh - 1);
+
+	return txq->tx_free_thresh;
+}
+
+static __rte_always_inline void
+tx_backlog_entry(struct ngbe_tx_entry_v *txep,
+		 struct rte_mbuf **tx_pkts, uint16_t nb_pkts)
+{
+	int i;
+
+	for (i = 0; i < (int)nb_pkts; ++i)
+		txep[i].mbuf = tx_pkts[i];
+}
+
+static inline void
+_ngbe_tx_queue_release_mbufs_vec(struct ngbe_tx_queue *txq)
+{
+	unsigned int i;
+	struct ngbe_tx_entry_v *txe;
+	const uint16_t max_desc = (uint16_t)(txq->nb_tx_desc - 1);
+
+	if (txq->sw_ring == NULL || txq->nb_tx_free == max_desc)
+		return;
+
+	/* release the used mbufs in sw_ring */
+	for (i = txq->tx_next_dd - (txq->tx_free_thresh - 1);
+	     i != txq->tx_tail;
+	     i = (i + 1) % txq->nb_tx_desc) {
+		txe = &txq->sw_ring_v[i];
+		rte_pktmbuf_free_seg(txe->mbuf);
+	}
+	txq->nb_tx_free = max_desc;
+
+	/* reset tx_entry */
+	for (i = 0; i < txq->nb_tx_desc; i++) {
+		txe = &txq->sw_ring_v[i];
+		txe->mbuf = NULL;
+	}
+}
+
+static inline void
+_ngbe_rx_queue_release_mbufs_vec(struct ngbe_rx_queue *rxq)
+{
+	unsigned int i;
+
+	if (rxq->sw_ring == NULL || rxq->rxrearm_nb >= rxq->nb_rx_desc)
+		return;
+
+	/* free all mbufs that are valid in the ring */
+	if (rxq->rxrearm_nb == 0) {
+		for (i = 0; i < rxq->nb_rx_desc; i++) {
+			if (rxq->sw_ring[i].mbuf != NULL)
+				rte_pktmbuf_free_seg(rxq->sw_ring[i].mbuf);
+		}
+	} else {
+		for (i = rxq->rx_tail;
+		     i != rxq->rxrearm_start;
+		     i = (i + 1) % rxq->nb_rx_desc) {
+			if (rxq->sw_ring[i].mbuf != NULL)
+				rte_pktmbuf_free_seg(rxq->sw_ring[i].mbuf);
+		}
+	}
+
+	rxq->rxrearm_nb = rxq->nb_rx_desc;
+
+	/* set all entries to NULL */
+	memset(rxq->sw_ring, 0, sizeof(rxq->sw_ring[0]) * rxq->nb_rx_desc);
+}
+
+static inline void
+_ngbe_tx_free_swring_vec(struct ngbe_tx_queue *txq)
+{
+	if (txq == NULL)
+		return;
+
+	if (txq->sw_ring != NULL) {
+		rte_free(txq->sw_ring_v - 1);
+		txq->sw_ring_v = NULL;
+	}
+}
+
+static inline void
+_ngbe_reset_tx_queue_vec(struct ngbe_tx_queue *txq)
+{
+	static const struct ngbe_tx_desc zeroed_desc = {0};
+	struct ngbe_tx_entry_v *txe = txq->sw_ring_v;
+	uint16_t i;
+
+	/* Zero out HW ring memory */
+	for (i = 0; i < txq->nb_tx_desc; i++)
+		txq->tx_ring[i] = zeroed_desc;
+
+	/* Initialize SW ring entries */
+	for (i = 0; i < txq->nb_tx_desc; i++) {
+		volatile struct ngbe_tx_desc *txd = &txq->tx_ring[i];
+
+		txd->dw3 = NGBE_TXD_DD;
+		txe[i].mbuf = NULL;
+	}
+
+	txq->tx_next_dd = (uint16_t)(txq->tx_free_thresh - 1);
+
+	txq->tx_tail = 0;
+	/*
+	 * Always allow 1 descriptor to be un-allocated to avoid
+	 * a H/W race condition
+	 */
+	txq->last_desc_cleaned = (uint16_t)(txq->nb_tx_desc - 1);
+	txq->nb_tx_free = (uint16_t)(txq->nb_tx_desc - 1);
+	txq->ctx_curr = 0;
+	memset((void *)&txq->ctx_cache, 0,
+		NGBE_CTX_NUM * sizeof(struct ngbe_ctx_info));
+}
+
+static inline int
+ngbe_rxq_vec_setup_default(struct ngbe_rx_queue *rxq)
+{
+	uintptr_t p;
+	struct rte_mbuf mb_def = { .buf_addr = 0 }; /* zeroed mbuf */
+
+	mb_def.nb_segs = 1;
+	mb_def.data_off = RTE_PKTMBUF_HEADROOM;
+	mb_def.port = rxq->port_id;
+	rte_mbuf_refcnt_set(&mb_def, 1);
+
+	/* prevent compiler reordering: rearm_data covers previous fields */
+	rte_compiler_barrier();
+	p = (uintptr_t)&mb_def.rearm_data;
+	rxq->mbuf_initializer = *(uint64_t *)p;
+	return 0;
+}
+
+static inline int
+ngbe_txq_vec_setup_default(struct ngbe_tx_queue *txq,
+			    const struct ngbe_txq_ops *txq_ops)
+{
+	if (txq->sw_ring_v == NULL)
+		return -1;
+
+	/* leave the first one for overflow */
+	txq->sw_ring_v = txq->sw_ring_v + 1;
+	txq->ops = txq_ops;
+
+	return 0;
+}
+
+static inline int
+ngbe_rx_vec_dev_conf_condition_check_default(struct rte_eth_dev *dev)
+{
+	RTE_SET_USED(dev);
+#ifndef RTE_LIBRTE_IEEE1588
+
+	return 0;
+#else
+	return -1;
+#endif
+}
+#endif
diff --git a/drivers/net/ngbe/ngbe_rxtx_vec_neon.c b/drivers/net/ngbe/ngbe_rxtx_vec_neon.c
new file mode 100644
index 0000000000..e08fa56dbd
--- /dev/null
+++ b/drivers/net/ngbe/ngbe_rxtx_vec_neon.c
@@ -0,0 +1,604 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2015-2024 Beijing WangXun Technology Co., Ltd.
+ * Copyright(c) 2010-2015 Intel Corporation
+ */
+
+#include <ethdev_driver.h>
+#include <rte_malloc.h>
+#include <rte_vect.h>
+
+#include "ngbe_type.h"
+#include "ngbe_ethdev.h"
+#include "ngbe_rxtx.h"
+#include "ngbe_rxtx_vec_common.h"
+
+#pragma GCC diagnostic ignored "-Wcast-qual"
+
+static inline void
+ngbe_rxq_rearm(struct ngbe_rx_queue *rxq)
+{
+	int i;
+	uint16_t rx_id;
+	volatile struct ngbe_rx_desc *rxdp;
+	struct ngbe_rx_entry *rxep = &rxq->sw_ring[rxq->rxrearm_start];
+	struct rte_mbuf *mb0, *mb1;
+	uint64x2_t dma_addr0, dma_addr1;
+	uint64x2_t zero = vdupq_n_u64(0);
+	uint64_t paddr;
+	uint8x8_t p;
+
+	rxdp = rxq->rx_ring + rxq->rxrearm_start;
+
+	/* Pull 'n' more MBUFs into the software ring */
+	if (unlikely(rte_mempool_get_bulk(rxq->mb_pool,
+					  (void *)rxep,
+					  RTE_NGBE_RXQ_REARM_THRESH) < 0)) {
+		if (rxq->rxrearm_nb + RTE_NGBE_RXQ_REARM_THRESH >=
+		    rxq->nb_rx_desc) {
+			for (i = 0; i < RTE_NGBE_DESCS_PER_LOOP; i++) {
+				rxep[i].mbuf = &rxq->fake_mbuf;
+				vst1q_u64((uint64_t *)&rxdp[i], zero);
+			}
+		}
+		rte_eth_devices[rxq->port_id].data->rx_mbuf_alloc_failed +=
+			RTE_NGBE_RXQ_REARM_THRESH;
+		return;
+	}
+
+	p = vld1_u8((uint8_t *)&rxq->mbuf_initializer);
+
+	/* Initialize the mbufs in vector, process 2 mbufs in one loop */
+	for (i = 0; i < RTE_NGBE_RXQ_REARM_THRESH; i += 2, rxep += 2) {
+		mb0 = rxep[0].mbuf;
+		mb1 = rxep[1].mbuf;
+
+		/*
+		 * Flush mbuf with pkt template.
+		 * Data to be rearmed is 6 bytes long.
+		 */
+		vst1_u8((uint8_t *)&mb0->rearm_data, p);
+		paddr = mb0->buf_iova + RTE_PKTMBUF_HEADROOM;
+		dma_addr0 = vsetq_lane_u64(paddr, zero, 0);
+		/* flush desc with pa dma_addr */
+		vst1q_u64((uint64_t *)rxdp++, dma_addr0);
+
+		vst1_u8((uint8_t *)&mb1->rearm_data, p);
+		paddr = mb1->buf_iova + RTE_PKTMBUF_HEADROOM;
+		dma_addr1 = vsetq_lane_u64(paddr, zero, 0);
+		vst1q_u64((uint64_t *)rxdp++, dma_addr1);
+	}
+
+	rxq->rxrearm_start += RTE_NGBE_RXQ_REARM_THRESH;
+	if (rxq->rxrearm_start >= rxq->nb_rx_desc)
+		rxq->rxrearm_start = 0;
+
+	rxq->rxrearm_nb -= RTE_NGBE_RXQ_REARM_THRESH;
+
+	rx_id = (uint16_t)((rxq->rxrearm_start == 0) ?
+			     (rxq->nb_rx_desc - 1) : (rxq->rxrearm_start - 1));
+
+	/* Update the tail pointer on the NIC */
+	ngbe_set32(rxq->rdt_reg_addr, rx_id);
+}
+
+static inline void
+desc_to_olflags_v(uint8x16x2_t sterr_tmp1, uint8x16x2_t sterr_tmp2,
+		  uint8x16_t staterr, uint8_t vlan_flags,
+		  struct rte_mbuf **rx_pkts)
+{
+	uint8x16_t ptype;
+	uint8x16_t vtag_lo, vtag_hi, vtag;
+	uint8x16_t temp_csum, temp_vp;
+	uint8x16_t vtag_mask = vdupq_n_u8(0x0F);
+	uint32x4_t csum = {0, 0, 0, 0};
+
+	union {
+		uint16_t e[4];
+		uint64_t word;
+	} vol;
+
+	const uint8x16_t rsstype_msk = {
+			0x0F, 0x0F, 0x0F, 0x0F,
+			0x00, 0x00, 0x00, 0x00,
+			0x00, 0x00, 0x00, 0x00,
+			0x00, 0x00, 0x00, 0x00};
+
+	const uint8x16_t rss_flags = {
+			0, RTE_MBUF_F_RX_RSS_HASH, RTE_MBUF_F_RX_RSS_HASH, RTE_MBUF_F_RX_RSS_HASH,
+			0, RTE_MBUF_F_RX_RSS_HASH, 0, RTE_MBUF_F_RX_RSS_HASH,
+			RTE_MBUF_F_RX_RSS_HASH, 0, 0, 0,
+			0, 0, 0, RTE_MBUF_F_RX_FDIR};
+
+	/* mask everything except vlan present and l4/ip csum error */
+	const uint8x16_t vlan_csum_msk = {
+			NGBE_RXD_STAT_VLAN, NGBE_RXD_STAT_VLAN,
+			NGBE_RXD_STAT_VLAN, NGBE_RXD_STAT_VLAN,
+			0, 0, 0, 0,
+			0, 0, 0, 0,
+			(NGBE_RXD_ERR_L4CS | NGBE_RXD_ERR_IPCS) >> 24,
+			(NGBE_RXD_ERR_L4CS | NGBE_RXD_ERR_IPCS) >> 24,
+			(NGBE_RXD_ERR_L4CS | NGBE_RXD_ERR_IPCS) >> 24,
+			(NGBE_RXD_ERR_L4CS | NGBE_RXD_ERR_IPCS) >> 24};
+
+	/* map vlan present and l4/ip csum error to ol_flags */
+	const uint8x16_t vlan_csum_map_lo = {
+			RTE_MBUF_F_RX_IP_CKSUM_GOOD,
+			RTE_MBUF_F_RX_IP_CKSUM_GOOD | RTE_MBUF_F_RX_L4_CKSUM_BAD,
+			RTE_MBUF_F_RX_IP_CKSUM_BAD,
+			RTE_MBUF_F_RX_IP_CKSUM_BAD | RTE_MBUF_F_RX_L4_CKSUM_BAD,
+			0, 0, 0, 0,
+			vlan_flags | RTE_MBUF_F_RX_IP_CKSUM_GOOD,
+			vlan_flags | RTE_MBUF_F_RX_IP_CKSUM_GOOD | RTE_MBUF_F_RX_L4_CKSUM_BAD,
+			vlan_flags | RTE_MBUF_F_RX_IP_CKSUM_BAD,
+			vlan_flags | RTE_MBUF_F_RX_IP_CKSUM_BAD | RTE_MBUF_F_RX_L4_CKSUM_BAD,
+			0, 0, 0, 0};
+
+	const uint8x16_t vlan_csum_map_hi = {
+			RTE_MBUF_F_RX_L4_CKSUM_GOOD >> sizeof(uint8_t), 0,
+			RTE_MBUF_F_RX_L4_CKSUM_GOOD >> sizeof(uint8_t), 0,
+			0, 0, 0, 0,
+			RTE_MBUF_F_RX_L4_CKSUM_GOOD >> sizeof(uint8_t), 0,
+			RTE_MBUF_F_RX_L4_CKSUM_GOOD >> sizeof(uint8_t), 0,
+			0, 0, 0, 0};
+
+	ptype = vzipq_u8(sterr_tmp1.val[0], sterr_tmp2.val[0]).val[0];
+	ptype = vandq_u8(ptype, rsstype_msk);
+	ptype = vqtbl1q_u8(rss_flags, ptype);
+
+	/* extract vlan_flags and csum_error from staterr */
+	vtag = vandq_u8(staterr, vlan_csum_msk);
+
+	/* csum bits are in the most significant, to use shuffle we need to
+	 * shift them. Change mask from 0xc0 to 0x03.
+	 */
+	temp_csum = vshrq_n_u8(vtag, 6);
+
+	/* Change vlan present mask from 0x20 to 0x08.
+	 */
+	temp_vp = vshrq_n_u8(vtag, 2);
+
+	/* 'OR' the most significant 32 bits containing the checksum flags with
+	 * the vlan present flags. Then bits layout of each lane(8bits) will be
+	 * 'xxxx,VLAN,x,ERR_IPCS,ERR_L4CS'
+	 */
+	csum = vsetq_lane_u32(vgetq_lane_u32(vreinterpretq_u32_u8(temp_csum), 3), csum, 0);
+	vtag = vorrq_u8(vreinterpretq_u8_u32(csum), vtag);
+	vtag = vorrq_u8(vtag, temp_vp);
+	vtag = vandq_u8(vtag, vtag_mask);
+
+	/* convert L4 checksum correct type to vtag_hi */
+	vtag_hi = vqtbl1q_u8(vlan_csum_map_hi, vtag);
+	vtag_hi = vshrq_n_u8(vtag_hi, 7);
+
+	/* convert VP, IPE, L4E to vtag_lo */
+	vtag_lo = vqtbl1q_u8(vlan_csum_map_lo, vtag);
+	vtag_lo = vorrq_u8(ptype, vtag_lo);
+
+	vtag = vzipq_u8(vtag_lo, vtag_hi).val[0];
+	vol.word = vgetq_lane_u64(vreinterpretq_u64_u8(vtag), 0);
+
+	rx_pkts[0]->ol_flags = vol.e[0];
+	rx_pkts[1]->ol_flags = vol.e[1];
+	rx_pkts[2]->ol_flags = vol.e[2];
+	rx_pkts[3]->ol_flags = vol.e[3];
+}
+
+#define NGBE_VPMD_DESC_EOP_MASK	0x02020202
+#define NGBE_UINT8_BIT			(CHAR_BIT * sizeof(uint8_t))
+
+static inline void
+desc_to_ptype_v(uint64x2_t descs[4], uint16_t pkt_type_mask,
+		struct rte_mbuf **rx_pkts)
+{
+	uint32x4_t ptype_mask = vdupq_n_u32((uint32_t)pkt_type_mask);
+	uint32x4_t ptype0 = vzipq_u32(vreinterpretq_u32_u64(descs[0]),
+				vreinterpretq_u32_u64(descs[2])).val[0];
+	uint32x4_t ptype1 = vzipq_u32(vreinterpretq_u32_u64(descs[1]),
+				vreinterpretq_u32_u64(descs[3])).val[0];
+
+	/* interleave low 32 bits,
+	 * now we have 4 ptypes in a NEON register
+	 */
+	ptype0 = vzipq_u32(ptype0, ptype1).val[0];
+
+	/* shift right by NGBE_RXD_PTID_SHIFT, and apply ptype mask */
+	ptype0 = vandq_u32(vshrq_n_u32(ptype0, NGBE_RXD_PTID_SHIFT), ptype_mask);
+
+	rx_pkts[0]->packet_type = ngbe_decode_ptype(vgetq_lane_u32(ptype0, 0));
+	rx_pkts[1]->packet_type = ngbe_decode_ptype(vgetq_lane_u32(ptype0, 1));
+	rx_pkts[2]->packet_type = ngbe_decode_ptype(vgetq_lane_u32(ptype0, 2));
+	rx_pkts[3]->packet_type = ngbe_decode_ptype(vgetq_lane_u32(ptype0, 3));
+}
+
+/**
+ * vPMD raw receive routine, only accept(nb_pkts >= RTE_NGBE_DESCS_PER_LOOP)
+ *
+ * Notice:
+ * - nb_pkts < RTE_NGBE_DESCS_PER_LOOP, just return no packet
+ * - floor align nb_pkts to a RTE_NGBE_DESC_PER_LOOP power-of-two
+ */
+static inline uint16_t
+_recv_raw_pkts_vec(struct ngbe_rx_queue *rxq, struct rte_mbuf **rx_pkts,
+		   uint16_t nb_pkts, uint8_t *split_packet)
+{
+	volatile struct ngbe_rx_desc *rxdp;
+	struct ngbe_rx_entry *sw_ring;
+	uint16_t nb_pkts_recd;
+	int pos;
+	uint8x16_t shuf_msk = {
+		0xFF, 0xFF,
+		0xFF, 0xFF,  /* skip 32 bits pkt_type */
+		12, 13,      /* octet 12~13, low 16 bits pkt_len */
+		0xFF, 0xFF,  /* skip high 16 bits pkt_len, zero out */
+		12, 13,      /* octet 12~13, 16 bits data_len */
+		14, 15,      /* octet 14~15, low 16 bits vlan_macip */
+		4, 5, 6, 7  /* octet 4~7, 32bits rss */
+		};
+	uint16x8_t crc_adjust = {0, 0, rxq->crc_len, 0,
+				 rxq->crc_len, 0, 0, 0};
+	uint8_t vlan_flags;
+
+	/* nb_pkts has to be floor-aligned to RTE_NGBE_DESCS_PER_LOOP */
+	nb_pkts = RTE_ALIGN_FLOOR(nb_pkts, RTE_NGBE_DESCS_PER_LOOP);
+
+	/* Just the act of getting into the function from the application is
+	 * going to cost about 7 cycles
+	 */
+	rxdp = rxq->rx_ring + rxq->rx_tail;
+
+	rte_prefetch_non_temporal(rxdp);
+
+	/* See if we need to rearm the RX queue - gives the prefetch a bit
+	 * of time to act
+	 */
+	if (rxq->rxrearm_nb > RTE_NGBE_RXQ_REARM_THRESH)
+		ngbe_rxq_rearm(rxq);
+
+	/* Before we start moving massive data around, check to see if
+	 * there is actually a packet available
+	 */
+	if (!(rxdp->qw1.lo.status & rte_cpu_to_le_32(NGBE_RXD_STAT_DD)))
+		return 0;
+
+	/* Cache is empty -> need to scan the buffer rings, but first move
+	 * the next 'n' mbufs into the cache
+	 */
+	sw_ring = &rxq->sw_ring[rxq->rx_tail];
+
+	/* ensure these 2 flags are in the lower 8 bits */
+	RTE_BUILD_BUG_ON((RTE_MBUF_F_RX_VLAN | RTE_MBUF_F_RX_VLAN_STRIPPED) > UINT8_MAX);
+	vlan_flags = rxq->vlan_flags & UINT8_MAX;
+
+	/* A. load 4 packet in one loop
+	 * B. copy 4 mbuf point from swring to rx_pkts
+	 * C. calc the number of DD bits among the 4 packets
+	 * [C*. extract the end-of-packet bit, if requested]
+	 * D. fill info. from desc to mbuf
+	 */
+	for (pos = 0, nb_pkts_recd = 0; pos < nb_pkts;
+			pos += RTE_NGBE_DESCS_PER_LOOP,
+			rxdp += RTE_NGBE_DESCS_PER_LOOP) {
+		uint64x2_t descs[RTE_NGBE_DESCS_PER_LOOP];
+		uint8x16_t pkt_mb1, pkt_mb2, pkt_mb3, pkt_mb4;
+		uint8x16x2_t sterr_tmp1, sterr_tmp2;
+		uint64x2_t mbp1, mbp2;
+		uint8x16_t staterr;
+		uint16x8_t tmp;
+		uint32_t stat;
+
+		/* B.1 load 2 mbuf point */
+		mbp1 = vld1q_u64((uint64_t *)&sw_ring[pos]);
+
+		/* B.2 copy 2 mbuf point into rx_pkts  */
+		vst1q_u64((uint64_t *)&rx_pkts[pos], mbp1);
+
+		/* B.1 load 2 mbuf point */
+		mbp2 = vld1q_u64((uint64_t *)&sw_ring[pos + 2]);
+
+		/* A. load 4 pkts descs */
+		descs[0] =  vld1q_u64((uint64_t *)(rxdp));
+		descs[1] =  vld1q_u64((uint64_t *)(rxdp + 1));
+		descs[2] =  vld1q_u64((uint64_t *)(rxdp + 2));
+		descs[3] =  vld1q_u64((uint64_t *)(rxdp + 3));
+
+		/* B.2 copy 2 mbuf point into rx_pkts  */
+		vst1q_u64((uint64_t *)&rx_pkts[pos + 2], mbp2);
+
+		if (split_packet) {
+			rte_mbuf_prefetch_part2(rx_pkts[pos]);
+			rte_mbuf_prefetch_part2(rx_pkts[pos + 1]);
+			rte_mbuf_prefetch_part2(rx_pkts[pos + 2]);
+			rte_mbuf_prefetch_part2(rx_pkts[pos + 3]);
+		}
+
+		/* D.1 pkt 3,4 convert format from desc to pktmbuf */
+		pkt_mb4 = vqtbl1q_u8(vreinterpretq_u8_u64(descs[3]), shuf_msk);
+		pkt_mb3 = vqtbl1q_u8(vreinterpretq_u8_u64(descs[2]), shuf_msk);
+
+		/* D.1 pkt 1,2 convert format from desc to pktmbuf */
+		pkt_mb2 = vqtbl1q_u8(vreinterpretq_u8_u64(descs[1]), shuf_msk);
+		pkt_mb1 = vqtbl1q_u8(vreinterpretq_u8_u64(descs[0]), shuf_msk);
+
+		/* C.1 4=>2 filter staterr info only */
+		sterr_tmp2 = vzipq_u8(vreinterpretq_u8_u64(descs[1]),
+				      vreinterpretq_u8_u64(descs[3]));
+		/* C.1 4=>2 filter staterr info only */
+		sterr_tmp1 = vzipq_u8(vreinterpretq_u8_u64(descs[0]),
+				      vreinterpretq_u8_u64(descs[2]));
+
+		/* C.2 get 4 pkts staterr value  */
+		staterr = vzipq_u8(sterr_tmp1.val[1], sterr_tmp2.val[1]).val[0];
+
+		/* set ol_flags with vlan packet type */
+		desc_to_olflags_v(sterr_tmp1, sterr_tmp2, staterr, vlan_flags,
+				  &rx_pkts[pos]);
+
+		/* D.2 pkt 3,4 set in_port/nb_seg and remove crc */
+		tmp = vsubq_u16(vreinterpretq_u16_u8(pkt_mb4), crc_adjust);
+		pkt_mb4 = vreinterpretq_u8_u16(tmp);
+		tmp = vsubq_u16(vreinterpretq_u16_u8(pkt_mb3), crc_adjust);
+		pkt_mb3 = vreinterpretq_u8_u16(tmp);
+
+		/* D.3 copy final 3,4 data to rx_pkts */
+		vst1q_u8((void *)&rx_pkts[pos + 3]->rx_descriptor_fields1,
+			 pkt_mb4);
+		vst1q_u8((void *)&rx_pkts[pos + 2]->rx_descriptor_fields1,
+			 pkt_mb3);
+
+		/* D.2 pkt 1,2 set in_port/nb_seg and remove crc */
+		tmp = vsubq_u16(vreinterpretq_u16_u8(pkt_mb2), crc_adjust);
+		pkt_mb2 = vreinterpretq_u8_u16(tmp);
+		tmp = vsubq_u16(vreinterpretq_u16_u8(pkt_mb1), crc_adjust);
+		pkt_mb1 = vreinterpretq_u8_u16(tmp);
+
+		/* C* extract and record EOP bit */
+		if (split_packet) {
+			stat = vgetq_lane_u32(vreinterpretq_u32_u8(staterr), 0);
+			/* and with mask to extract bits, flipping 1-0 */
+			*(int *)split_packet = ~stat & NGBE_VPMD_DESC_EOP_MASK;
+
+			split_packet += RTE_NGBE_DESCS_PER_LOOP;
+		}
+
+		/* C.4 expand DD bit to saturate UINT8 */
+		staterr = vshlq_n_u8(staterr, NGBE_UINT8_BIT - 1);
+		staterr = vreinterpretq_u8_s8(vshrq_n_s8(vreinterpretq_s8_u8(staterr),
+					      NGBE_UINT8_BIT - 1));
+		stat = ~vgetq_lane_u32(vreinterpretq_u32_u8(staterr), 0);
+
+		rte_prefetch_non_temporal(rxdp + RTE_NGBE_DESCS_PER_LOOP);
+
+		/* D.3 copy final 1,2 data to rx_pkts */
+		vst1q_u8((uint8_t *)&rx_pkts[pos + 1]->rx_descriptor_fields1,
+			 pkt_mb2);
+		vst1q_u8((uint8_t *)&rx_pkts[pos]->rx_descriptor_fields1,
+			 pkt_mb1);
+
+		desc_to_ptype_v(descs, NGBE_PTID_MASK, &rx_pkts[pos]);
+
+		/* C.5 calc available number of desc */
+		if (unlikely(stat == 0)) {
+			nb_pkts_recd += RTE_NGBE_DESCS_PER_LOOP;
+		} else {
+			nb_pkts_recd += rte_ctz32(stat) / NGBE_UINT8_BIT;
+			break;
+		}
+	}
+
+	/* Update our internal tail pointer */
+	rxq->rx_tail = (uint16_t)(rxq->rx_tail + nb_pkts_recd);
+	rxq->rx_tail = (uint16_t)(rxq->rx_tail & (rxq->nb_rx_desc - 1));
+	rxq->rxrearm_nb = (uint16_t)(rxq->rxrearm_nb + nb_pkts_recd);
+
+	return nb_pkts_recd;
+}
+
+/**
+ * vPMD receive routine, only accept(nb_pkts >= RTE_IXGBE_DESCS_PER_LOOP)
+ *
+ * Notice:
+ * - nb_pkts < RTE_IXGBE_DESCS_PER_LOOP, just return no packet
+ * - floor align nb_pkts to a RTE_IXGBE_DESC_PER_LOOP power-of-two
+ */
+uint16_t
+ngbe_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
+		uint16_t nb_pkts)
+{
+	return _recv_raw_pkts_vec(rx_queue, rx_pkts, nb_pkts, NULL);
+}
+
+/**
+ * vPMD receive routine that reassembles scattered packets
+ *
+ * Notice:
+ * - nb_pkts < RTE_NGBE_DESCS_PER_LOOP, just return no packet
+ * - floor align nb_pkts to a RTE_NGBE_DESC_PER_LOOP power-of-two
+ */
+static uint16_t
+ngbe_recv_scattered_burst_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
+			      uint16_t nb_pkts)
+{
+	struct ngbe_rx_queue *rxq = rx_queue;
+	uint8_t split_flags[RTE_NGBE_MAX_RX_BURST] = {0};
+
+	/* get some new buffers */
+	uint16_t nb_bufs = _recv_raw_pkts_vec(rxq, rx_pkts, nb_pkts,
+			split_flags);
+	if (nb_bufs == 0)
+		return 0;
+
+	/* happy day case, full burst + no packets to be joined */
+	const uint64_t *split_fl64 = (uint64_t *)split_flags;
+	if (rxq->pkt_first_seg == NULL &&
+			split_fl64[0] == 0 && split_fl64[1] == 0 &&
+			split_fl64[2] == 0 && split_fl64[3] == 0)
+		return nb_bufs;
+
+	/* reassemble any packets that need reassembly*/
+	unsigned int i = 0;
+	if (rxq->pkt_first_seg == NULL) {
+		/* find the first split flag, and only reassemble then*/
+		while (i < nb_bufs && !split_flags[i])
+			i++;
+		if (i == nb_bufs)
+			return nb_bufs;
+		rxq->pkt_first_seg = rx_pkts[i];
+	}
+	return i + reassemble_packets(rxq, &rx_pkts[i], nb_bufs - i,
+		&split_flags[i]);
+}
+
+/**
+ * vPMD receive routine that reassembles scattered packets.
+ */
+uint16_t
+ngbe_recv_scattered_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
+			     uint16_t nb_pkts)
+{
+	uint16_t retval = 0;
+
+	while (nb_pkts > RTE_NGBE_MAX_RX_BURST) {
+		uint16_t burst;
+
+		burst = ngbe_recv_scattered_burst_vec(rx_queue,
+						      rx_pkts + retval,
+						      RTE_NGBE_MAX_RX_BURST);
+		retval += burst;
+		nb_pkts -= burst;
+		if (burst < RTE_NGBE_MAX_RX_BURST)
+			return retval;
+	}
+
+	return retval + ngbe_recv_scattered_burst_vec(rx_queue,
+						      rx_pkts + retval,
+						      nb_pkts);
+}
+
+static inline void
+vtx1(volatile struct ngbe_tx_desc *txdp,
+		struct rte_mbuf *pkt, uint64_t flags)
+{
+	uint64x2_t descriptor = {
+			pkt->buf_iova + pkt->data_off,
+			(uint64_t)pkt->pkt_len << 45 | flags | pkt->data_len};
+
+	vst1q_u64((uint64_t *)txdp, descriptor);
+}
+
+static inline void
+vtx(volatile struct ngbe_tx_desc *txdp,
+		struct rte_mbuf **pkt, uint16_t nb_pkts,  uint64_t flags)
+{
+	int i;
+
+	for (i = 0; i < nb_pkts; ++i, ++txdp, ++pkt)
+		vtx1(txdp, *pkt, flags);
+}
+
+uint16_t
+ngbe_xmit_fixed_burst_vec(void *tx_queue, struct rte_mbuf **tx_pkts,
+			  uint16_t nb_pkts)
+{
+	struct ngbe_tx_queue *txq = (struct ngbe_tx_queue *)tx_queue;
+	volatile struct ngbe_tx_desc *txdp;
+	struct ngbe_tx_entry_v *txep;
+	uint16_t n, nb_commit, tx_id;
+	uint64_t flags = NGBE_TXD_FLAGS;
+	uint64_t rs = NGBE_TXD_FLAGS;
+	int i;
+
+	/* cross rx_thresh boundary is not allowed */
+	nb_pkts = RTE_MIN(nb_pkts, txq->tx_free_thresh);
+
+	if (txq->nb_tx_free < txq->tx_free_thresh)
+		ngbe_tx_free_bufs(txq);
+
+	nb_pkts = (uint16_t)RTE_MIN(txq->nb_tx_free, nb_pkts);
+	if (unlikely(nb_pkts == 0))
+		return 0;
+
+	tx_id = txq->tx_tail;
+	txdp = &txq->tx_ring[tx_id];
+	txep = &txq->sw_ring_v[tx_id];
+
+	txq->nb_tx_free = (uint16_t)(txq->nb_tx_free - nb_pkts);
+
+	n = (uint16_t)(txq->nb_tx_desc - tx_id);
+	nb_commit = nb_pkts;
+	if (nb_commit >= n) {
+		tx_backlog_entry(txep, tx_pkts, n);
+
+		for (i = 0; i < n - 1; ++i, ++tx_pkts, ++txdp)
+			vtx1(txdp, *tx_pkts, flags);
+
+		vtx1(txdp, *tx_pkts++, rs);
+
+		nb_commit = (uint16_t)(nb_commit - n);
+
+		tx_id = 0;
+
+		/* avoid reach the end of ring */
+		txdp = &txq->tx_ring[tx_id];
+		txep = &txq->sw_ring_v[tx_id];
+	}
+
+	tx_backlog_entry(txep, tx_pkts, nb_commit);
+
+	vtx(txdp, tx_pkts, nb_commit, flags);
+
+	tx_id = (uint16_t)(tx_id + nb_commit);
+
+	txq->tx_tail = tx_id;
+
+	ngbe_set32(txq->tdt_reg_addr, txq->tx_tail);
+
+	return nb_pkts;
+}
+
+static void __rte_cold
+ngbe_tx_queue_release_mbufs_vec(struct ngbe_tx_queue *txq)
+{
+	_ngbe_tx_queue_release_mbufs_vec(txq);
+}
+
+void __rte_cold
+ngbe_rx_queue_release_mbufs_vec(struct ngbe_rx_queue *rxq)
+{
+	_ngbe_rx_queue_release_mbufs_vec(rxq);
+}
+
+static void __rte_cold
+ngbe_tx_free_swring(struct ngbe_tx_queue *txq)
+{
+	_ngbe_tx_free_swring_vec(txq);
+}
+
+static void __rte_cold
+ngbe_reset_tx_queue(struct ngbe_tx_queue *txq)
+{
+	_ngbe_reset_tx_queue_vec(txq);
+}
+
+static const struct ngbe_txq_ops vec_txq_ops = {
+	.release_mbufs = ngbe_tx_queue_release_mbufs_vec,
+	.free_swring = ngbe_tx_free_swring,
+	.reset = ngbe_reset_tx_queue,
+};
+
+int __rte_cold
+ngbe_rxq_vec_setup(struct ngbe_rx_queue *rxq)
+{
+	return ngbe_rxq_vec_setup_default(rxq);
+}
+
+int __rte_cold
+ngbe_txq_vec_setup(struct ngbe_tx_queue *txq)
+{
+	return ngbe_txq_vec_setup_default(txq, &vec_txq_ops);
+}
+
+int __rte_cold
+ngbe_rx_vec_dev_conf_condition_check(struct rte_eth_dev *dev)
+{
+	return ngbe_rx_vec_dev_conf_condition_check_default(dev);
+}
diff --git a/drivers/net/ngbe/ngbe_rxtx_vec_sse.c b/drivers/net/ngbe/ngbe_rxtx_vec_sse.c
new file mode 100644
index 0000000000..7d9e7db615
--- /dev/null
+++ b/drivers/net/ngbe/ngbe_rxtx_vec_sse.c
@@ -0,0 +1,692 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2015-2024 Beijing WangXun Technology Co., Ltd.
+ * Copyright(c) 2010-2015 Intel Corporation
+ */
+
+#include <ethdev_driver.h>
+#include <rte_malloc.h>
+
+#include "ngbe_type.h"
+#include "ngbe_ethdev.h"
+#include "ngbe_rxtx.h"
+#include "ngbe_rxtx_vec_common.h"
+
+#include <tmmintrin.h>
+
+#ifndef __INTEL_COMPILER
+#pragma GCC diagnostic ignored "-Wcast-qual"
+#endif
+
+static inline void
+ngbe_rxq_rearm(struct ngbe_rx_queue *rxq)
+{
+	int i;
+	uint16_t rx_id;
+	volatile struct ngbe_rx_desc *rxdp;
+	struct ngbe_rx_entry *rxep = &rxq->sw_ring[rxq->rxrearm_start];
+	struct rte_mbuf *mb0, *mb1;
+	__m128i hdr_room = _mm_set_epi64x(RTE_PKTMBUF_HEADROOM,
+			RTE_PKTMBUF_HEADROOM);
+	__m128i dma_addr0, dma_addr1;
+
+	const __m128i hba_msk = _mm_set_epi64x(0, UINT64_MAX);
+
+	rxdp = rxq->rx_ring + rxq->rxrearm_start;
+
+	/* Pull 'n' more MBUFs into the software ring */
+	if (rte_mempool_get_bulk(rxq->mb_pool,
+				 (void *)rxep,
+				 RTE_NGBE_RXQ_REARM_THRESH) < 0) {
+		if (rxq->rxrearm_nb + RTE_NGBE_RXQ_REARM_THRESH >=
+		    rxq->nb_rx_desc) {
+			dma_addr0 = _mm_setzero_si128();
+			for (i = 0; i < RTE_NGBE_DESCS_PER_LOOP; i++) {
+				rxep[i].mbuf = &rxq->fake_mbuf;
+				_mm_store_si128((__m128i *)&rxdp[i],
+						dma_addr0);
+			}
+		}
+		rte_eth_devices[rxq->port_id].data->rx_mbuf_alloc_failed +=
+			RTE_NGBE_RXQ_REARM_THRESH;
+		return;
+	}
+
+	/* Initialize the mbufs in vector, process 2 mbufs in one loop */
+	for (i = 0; i < RTE_NGBE_RXQ_REARM_THRESH; i += 2, rxep += 2) {
+		__m128i vaddr0, vaddr1;
+
+		mb0 = rxep[0].mbuf;
+		mb1 = rxep[1].mbuf;
+
+		/* load buf_addr(lo 64bit) and buf_iova(hi 64bit) */
+		RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, buf_iova) !=
+				offsetof(struct rte_mbuf, buf_addr) + 8);
+		vaddr0 = _mm_loadu_si128((__m128i *)&mb0->buf_addr);
+		vaddr1 = _mm_loadu_si128((__m128i *)&mb1->buf_addr);
+
+		/* convert pa to dma_addr hdr/data */
+		dma_addr0 = _mm_unpackhi_epi64(vaddr0, vaddr0);
+		dma_addr1 = _mm_unpackhi_epi64(vaddr1, vaddr1);
+
+		/* add headroom to pa values */
+		dma_addr0 = _mm_add_epi64(dma_addr0, hdr_room);
+		dma_addr1 = _mm_add_epi64(dma_addr1, hdr_room);
+
+		/* set Header Buffer Address to zero */
+		dma_addr0 =  _mm_and_si128(dma_addr0, hba_msk);
+		dma_addr1 =  _mm_and_si128(dma_addr1, hba_msk);
+
+		/* flush desc with pa dma_addr */
+		_mm_store_si128((__m128i *)rxdp++, dma_addr0);
+		_mm_store_si128((__m128i *)rxdp++, dma_addr1);
+	}
+
+	rxq->rxrearm_start += RTE_NGBE_RXQ_REARM_THRESH;
+	if (rxq->rxrearm_start >= rxq->nb_rx_desc)
+		rxq->rxrearm_start = 0;
+
+	rxq->rxrearm_nb -= RTE_NGBE_RXQ_REARM_THRESH;
+
+	rx_id = (uint16_t)((rxq->rxrearm_start == 0) ?
+			   (rxq->nb_rx_desc - 1) : (rxq->rxrearm_start - 1));
+
+	/* Update the tail pointer on the NIC */
+	ngbe_set32(rxq->rdt_reg_addr, rx_id);
+}
+
+static inline void
+desc_to_olflags_v(__m128i descs[4], __m128i mbuf_init, uint8_t vlan_flags,
+	struct rte_mbuf **rx_pkts)
+{
+	__m128i ptype0, ptype1, vtag0, vtag1, csum, vp;
+	__m128i rearm0, rearm1, rearm2, rearm3;
+
+	/* mask everything except rss type */
+	const __m128i rsstype_msk = _mm_set_epi16(0x0000, 0x0000, 0x0000, 0x0000,
+						  0x000F, 0x000F, 0x000F, 0x000F);
+
+	/* mask the lower byte of ol_flags */
+	const __m128i ol_flags_msk = _mm_set_epi16(0x0000, 0x0000, 0x0000, 0x0000,
+						   0x00FF, 0x00FF, 0x00FF, 0x00FF);
+
+	/* map rss type to rss hash flag */
+	const __m128i rss_flags = _mm_set_epi8(RTE_MBUF_F_RX_FDIR, 0, 0, 0,
+			0, 0, 0, RTE_MBUF_F_RX_RSS_HASH,
+			RTE_MBUF_F_RX_RSS_HASH, 0, RTE_MBUF_F_RX_RSS_HASH, 0,
+			RTE_MBUF_F_RX_RSS_HASH, RTE_MBUF_F_RX_RSS_HASH, RTE_MBUF_F_RX_RSS_HASH, 0);
+
+	/* mask everything except vlan present and l4/ip csum error */
+	const __m128i vlan_csum_msk =
+		_mm_set_epi16((NGBE_RXD_ERR_L4CS | NGBE_RXD_ERR_IPCS) >> 16,
+			      (NGBE_RXD_ERR_L4CS | NGBE_RXD_ERR_IPCS) >> 16,
+			      (NGBE_RXD_ERR_L4CS | NGBE_RXD_ERR_IPCS) >> 16,
+			      (NGBE_RXD_ERR_L4CS | NGBE_RXD_ERR_IPCS) >> 16,
+			      NGBE_RXD_STAT_VLAN, NGBE_RXD_STAT_VLAN,
+			      NGBE_RXD_STAT_VLAN, NGBE_RXD_STAT_VLAN);
+
+	/* map vlan present and l4/ip csum error to ol_flags */
+	const __m128i vlan_csum_map_lo = _mm_set_epi8(0, 0, 0, 0,
+		vlan_flags | RTE_MBUF_F_RX_IP_CKSUM_BAD | RTE_MBUF_F_RX_L4_CKSUM_BAD,
+		vlan_flags | RTE_MBUF_F_RX_IP_CKSUM_BAD,
+		vlan_flags | RTE_MBUF_F_RX_IP_CKSUM_GOOD | RTE_MBUF_F_RX_L4_CKSUM_BAD,
+		vlan_flags | RTE_MBUF_F_RX_IP_CKSUM_GOOD,
+		0, 0, 0, 0,
+		RTE_MBUF_F_RX_IP_CKSUM_BAD | RTE_MBUF_F_RX_L4_CKSUM_BAD,
+		RTE_MBUF_F_RX_IP_CKSUM_BAD,
+		RTE_MBUF_F_RX_IP_CKSUM_GOOD | RTE_MBUF_F_RX_L4_CKSUM_BAD,
+		RTE_MBUF_F_RX_IP_CKSUM_GOOD);
+
+	const __m128i vlan_csum_map_hi = _mm_set_epi8(0, 0, 0, 0,
+		0, RTE_MBUF_F_RX_L4_CKSUM_GOOD >> sizeof(uint8_t), 0,
+		RTE_MBUF_F_RX_L4_CKSUM_GOOD >> sizeof(uint8_t),
+		0, 0, 0, 0,
+		0, RTE_MBUF_F_RX_L4_CKSUM_GOOD >> sizeof(uint8_t), 0,
+		RTE_MBUF_F_RX_L4_CKSUM_GOOD >> sizeof(uint8_t));
+
+	const __m128i vtag_msk = _mm_set_epi16(0x0000, 0x0000, 0x0000, 0x0000,
+					       0x000F, 0x000F, 0x000F, 0x000F);
+
+	ptype0 = _mm_unpacklo_epi16(descs[0], descs[1]);
+	ptype1 = _mm_unpacklo_epi16(descs[2], descs[3]);
+	vtag0 = _mm_unpackhi_epi16(descs[0], descs[1]);
+	vtag1 = _mm_unpackhi_epi16(descs[2], descs[3]);
+
+	ptype0 = _mm_unpacklo_epi32(ptype0, ptype1);
+	ptype0 = _mm_and_si128(ptype0, rsstype_msk);
+	ptype0 = _mm_shuffle_epi8(rss_flags, ptype0);
+
+	vtag1 = _mm_unpacklo_epi32(vtag0, vtag1);
+	vtag1 = _mm_and_si128(vtag1, vlan_csum_msk);
+
+	/* csum bits are in the most significant, to use shuffle we need to
+	 * shift them. Change mask to 0xc000 to 0x0003.
+	 */
+	csum = _mm_srli_epi16(vtag1, 14);
+
+	/* Change mask to 0x20 to 0x08. */
+	vp = _mm_srli_epi16(vtag1, 2);
+
+	/* now or the most significant 64 bits containing the checksum
+	 * flags with the vlan present flags.
+	 */
+	csum = _mm_srli_si128(csum, 8);
+	vtag1 = _mm_or_si128(csum, vtag1);
+	vtag1 = _mm_or_si128(vtag1, vp);
+	vtag1 = _mm_and_si128(vtag1, vtag_msk);
+
+	/* convert STAT_VLAN, ERR_IPCS, ERR_L4CS to ol_flags */
+	vtag0 = _mm_shuffle_epi8(vlan_csum_map_hi, vtag1);
+	vtag0 = _mm_slli_epi16(vtag0, sizeof(uint8_t));
+
+	vtag1 = _mm_shuffle_epi8(vlan_csum_map_lo, vtag1);
+	vtag1 = _mm_and_si128(vtag1, ol_flags_msk);
+	vtag1 = _mm_or_si128(vtag0, vtag1);
+
+	vtag1 = _mm_or_si128(ptype0, vtag1);
+
+	/*
+	 * At this point, we have the 4 sets of flags in the low 64-bits
+	 * of vtag1 (4x16).
+	 * We want to extract these, and merge them with the mbuf init data
+	 * so we can do a single 16-byte write to the mbuf to set the flags
+	 * and all the other initialization fields. Extracting the
+	 * appropriate flags means that we have to do a shift and blend for
+	 * each mbuf before we do the write.
+	 */
+	rearm0 = _mm_blend_epi16(mbuf_init, _mm_slli_si128(vtag1, 8), 0x10);
+	rearm1 = _mm_blend_epi16(mbuf_init, _mm_slli_si128(vtag1, 6), 0x10);
+	rearm2 = _mm_blend_epi16(mbuf_init, _mm_slli_si128(vtag1, 4), 0x10);
+	rearm3 = _mm_blend_epi16(mbuf_init, _mm_slli_si128(vtag1, 2), 0x10);
+
+	/* write the rearm data and the olflags in one write */
+	RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, ol_flags) !=
+			offsetof(struct rte_mbuf, rearm_data) + 8);
+	RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, rearm_data) !=
+			RTE_ALIGN(offsetof(struct rte_mbuf, rearm_data), 16));
+	_mm_store_si128((__m128i *)&rx_pkts[0]->rearm_data, rearm0);
+	_mm_store_si128((__m128i *)&rx_pkts[1]->rearm_data, rearm1);
+	_mm_store_si128((__m128i *)&rx_pkts[2]->rearm_data, rearm2);
+	_mm_store_si128((__m128i *)&rx_pkts[3]->rearm_data, rearm3);
+}
+
+static inline void
+desc_to_ptype_v(__m128i descs[4], uint16_t pkt_type_mask,
+		struct rte_mbuf **rx_pkts)
+{
+	__m128i ptype_mask = _mm_set_epi32(pkt_type_mask, pkt_type_mask,
+					pkt_type_mask, pkt_type_mask);
+
+	__m128i ptype0 = _mm_unpacklo_epi32(descs[0], descs[2]);
+	__m128i ptype1 = _mm_unpacklo_epi32(descs[1], descs[3]);
+
+	/* interleave low 32 bits,
+	 * now we have 4 ptypes in a XMM register
+	 */
+	ptype0 = _mm_unpacklo_epi32(ptype0, ptype1);
+
+	/* shift left by NGBE_RXD_PTID_SHIFT, and apply ptype mask */
+	ptype0 = _mm_and_si128(_mm_srli_epi32(ptype0, NGBE_RXD_PTID_SHIFT),
+			       ptype_mask);
+
+	rx_pkts[0]->packet_type = ngbe_decode_ptype(_mm_extract_epi32(ptype0, 0));
+	rx_pkts[1]->packet_type = ngbe_decode_ptype(_mm_extract_epi32(ptype0, 1));
+	rx_pkts[2]->packet_type = ngbe_decode_ptype(_mm_extract_epi32(ptype0, 2));
+	rx_pkts[3]->packet_type = ngbe_decode_ptype(_mm_extract_epi32(ptype0, 3));
+}
+
+/*
+ * vPMD raw receive routine, only accept(nb_pkts >= RTE_NGBE_DESCS_PER_LOOP)
+ *
+ * Notice:
+ * - nb_pkts < RTE_NGBE_DESCS_PER_LOOP, just return no packet
+ * - floor align nb_pkts to a RTE_NGBE_DESC_PER_LOOP power-of-two
+ */
+static inline uint16_t
+_recv_raw_pkts_vec(struct ngbe_rx_queue *rxq, struct rte_mbuf **rx_pkts,
+		uint16_t nb_pkts, uint8_t *split_packet)
+{
+	volatile struct ngbe_rx_desc *rxdp;
+	struct ngbe_rx_entry *sw_ring;
+	uint16_t nb_pkts_recd;
+	int pos;
+	uint64_t var;
+	__m128i shuf_msk;
+	__m128i crc_adjust = _mm_set_epi16(0, 0, 0, /* ignore non-length fields */
+				-rxq->crc_len, /* sub crc on data_len */
+				0,             /* ignore high-16bits of pkt_len */
+				-rxq->crc_len, /* sub crc on pkt_len */
+				0, 0);         /* ignore pkt_type field */
+
+	/*
+	 * compile-time check the above crc_adjust layout is correct.
+	 * NOTE: the first field (lowest address) is given last in set_epi16
+	 * call above.
+	 */
+	RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, pkt_len) !=
+			offsetof(struct rte_mbuf, rx_descriptor_fields1) + 4);
+	RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, data_len) !=
+			offsetof(struct rte_mbuf, rx_descriptor_fields1) + 8);
+	__m128i dd_check, eop_check;
+	__m128i mbuf_init;
+	uint8_t vlan_flags;
+
+	/*
+	 * Under the circumstance that `rx_tail` wrap back to zero
+	 * and the advance speed of `rx_tail` is greater than `rxrearm_start`,
+	 * `rx_tail` will catch up with `rxrearm_start` and surpass it.
+	 * This may cause some mbufs be reused by application.
+	 *
+	 * So we need to make some restrictions to ensure that
+	 * `rx_tail` will not exceed `rxrearm_start`.
+	 */
+	nb_pkts = RTE_MIN(nb_pkts, RTE_NGBE_RXQ_REARM_THRESH);
+
+	/* nb_pkts has to be floor-aligned to RTE_NGBE_DESCS_PER_LOOP */
+	nb_pkts = RTE_ALIGN_FLOOR(nb_pkts, RTE_NGBE_DESCS_PER_LOOP);
+
+	/* Just the act of getting into the function from the application is
+	 * going to cost about 7 cycles
+	 */
+	rxdp = rxq->rx_ring + rxq->rx_tail;
+
+	rte_prefetch0(rxdp);
+
+	/* See if we need to rearm the RX queue - gives the prefetch a bit
+	 * of time to act
+	 */
+	if (rxq->rxrearm_nb > RTE_NGBE_RXQ_REARM_THRESH)
+		ngbe_rxq_rearm(rxq);
+
+	/* Before we start moving massive data around, check to see if
+	 * there is actually a packet available
+	 */
+	if (!(rxdp->qw1.lo.status &
+				rte_cpu_to_le_32(NGBE_RXD_STAT_DD)))
+		return 0;
+
+	/* 4 packets DD mask */
+	dd_check = _mm_set_epi64x(0x0000000100000001LL, 0x0000000100000001LL);
+
+	/* 4 packets EOP mask */
+	eop_check = _mm_set_epi64x(0x0000000200000002LL, 0x0000000200000002LL);
+
+	/* mask to shuffle from desc. to mbuf */
+	shuf_msk = _mm_set_epi8(7, 6, 5, 4,  /* octet 4~7, 32bits rss */
+		15, 14,      /* octet 14~15, low 16 bits vlan_macip */
+		13, 12,      /* octet 12~13, 16 bits data_len */
+		0xFF, 0xFF,  /* skip high 16 bits pkt_len, zero out */
+		13, 12,      /* octet 12~13, low 16 bits pkt_len */
+		0xFF, 0xFF,  /* skip 32 bit pkt_type */
+		0xFF, 0xFF);
+	/*
+	 * Compile-time verify the shuffle mask
+	 * NOTE: some field positions already verified above, but duplicated
+	 * here for completeness in case of future modifications.
+	 */
+	RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, pkt_len) !=
+			offsetof(struct rte_mbuf, rx_descriptor_fields1) + 4);
+	RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, data_len) !=
+			offsetof(struct rte_mbuf, rx_descriptor_fields1) + 8);
+	RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, vlan_tci) !=
+			offsetof(struct rte_mbuf, rx_descriptor_fields1) + 10);
+	RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, hash) !=
+			offsetof(struct rte_mbuf, rx_descriptor_fields1) + 12);
+
+	mbuf_init = _mm_set_epi64x(0, rxq->mbuf_initializer);
+
+	/* Cache is empty -> need to scan the buffer rings, but first move
+	 * the next 'n' mbufs into the cache
+	 */
+	sw_ring = &rxq->sw_ring[rxq->rx_tail];
+
+	/* ensure these 2 flags are in the lower 8 bits */
+	RTE_BUILD_BUG_ON((RTE_MBUF_F_RX_VLAN | RTE_MBUF_F_RX_VLAN_STRIPPED) > UINT8_MAX);
+	vlan_flags = rxq->vlan_flags & UINT8_MAX;
+
+	/* A. load 4 packet in one loop
+	 * [A*. mask out 4 unused dirty field in desc]
+	 * B. copy 4 mbuf point from swring to rx_pkts
+	 * C. calc the number of DD bits among the 4 packets
+	 * [C*. extract the end-of-packet bit, if requested]
+	 * D. fill info. from desc to mbuf
+	 */
+	for (pos = 0, nb_pkts_recd = 0; pos < nb_pkts;
+			pos += RTE_NGBE_DESCS_PER_LOOP,
+			rxdp += RTE_NGBE_DESCS_PER_LOOP) {
+		__m128i descs[RTE_NGBE_DESCS_PER_LOOP];
+		__m128i pkt_mb1, pkt_mb2, pkt_mb3, pkt_mb4;
+		__m128i zero, staterr, sterr_tmp1, sterr_tmp2;
+		/* 2 64 bit or 4 32 bit mbuf pointers in one XMM reg. */
+		__m128i mbp1;
+#if defined(RTE_ARCH_X86_64)
+		__m128i mbp2;
+#endif
+
+		/* B.1 load 2 (64 bit) or 4 (32 bit) mbuf points */
+		mbp1 = _mm_loadu_si128((__m128i *)&sw_ring[pos]);
+
+		/* Read desc statuses backwards to avoid race condition */
+		/* A.1 load desc[3] */
+		descs[3] = _mm_loadu_si128((__m128i *)(rxdp + 3));
+		rte_compiler_barrier();
+
+		/* B.2 copy 2 64 bit or 4 32 bit mbuf point into rx_pkts */
+		_mm_storeu_si128((__m128i *)&rx_pkts[pos], mbp1);
+
+#if defined(RTE_ARCH_X86_64)
+		/* B.1 load 2 64 bit mbuf points */
+		mbp2 = _mm_loadu_si128((__m128i *)&sw_ring[pos + 2]);
+#endif
+
+		/* A.1 load desc[2-0] */
+		descs[2] = _mm_loadu_si128((__m128i *)(rxdp + 2));
+		rte_compiler_barrier();
+		descs[1] = _mm_loadu_si128((__m128i *)(rxdp + 1));
+		rte_compiler_barrier();
+		descs[0] = _mm_loadu_si128((__m128i *)(rxdp));
+
+#if defined(RTE_ARCH_X86_64)
+		/* B.2 copy 2 mbuf point into rx_pkts  */
+		_mm_storeu_si128((__m128i *)&rx_pkts[pos + 2], mbp2);
+#endif
+
+		if (split_packet) {
+			rte_mbuf_prefetch_part2(rx_pkts[pos]);
+			rte_mbuf_prefetch_part2(rx_pkts[pos + 1]);
+			rte_mbuf_prefetch_part2(rx_pkts[pos + 2]);
+			rte_mbuf_prefetch_part2(rx_pkts[pos + 3]);
+		}
+
+		/* avoid compiler reorder optimization */
+		rte_compiler_barrier();
+
+		/* D.1 pkt 3,4 convert format from desc to pktmbuf */
+		pkt_mb4 = _mm_shuffle_epi8(descs[3], shuf_msk);
+		pkt_mb3 = _mm_shuffle_epi8(descs[2], shuf_msk);
+
+		/* D.1 pkt 1,2 convert format from desc to pktmbuf */
+		pkt_mb2 = _mm_shuffle_epi8(descs[1], shuf_msk);
+		pkt_mb1 = _mm_shuffle_epi8(descs[0], shuf_msk);
+
+		/* C.1 4=>2 filter staterr info only */
+		sterr_tmp2 = _mm_unpackhi_epi32(descs[3], descs[2]);
+		/* C.1 4=>2 filter staterr info only */
+		sterr_tmp1 = _mm_unpackhi_epi32(descs[1], descs[0]);
+
+		/* set ol_flags with vlan packet type */
+		desc_to_olflags_v(descs, mbuf_init, vlan_flags, &rx_pkts[pos]);
+
+		/* D.2 pkt 3,4 set in_port/nb_seg and remove crc */
+		pkt_mb4 = _mm_add_epi16(pkt_mb4, crc_adjust);
+		pkt_mb3 = _mm_add_epi16(pkt_mb3, crc_adjust);
+
+		/* C.2 get 4 pkts staterr value  */
+		zero = _mm_xor_si128(dd_check, dd_check);
+		staterr = _mm_unpacklo_epi32(sterr_tmp1, sterr_tmp2);
+
+		/* D.3 copy final 3,4 data to rx_pkts */
+		_mm_storeu_si128((void *)&rx_pkts[pos + 3]->rx_descriptor_fields1,
+				pkt_mb4);
+		_mm_storeu_si128((void *)&rx_pkts[pos + 2]->rx_descriptor_fields1,
+				pkt_mb3);
+
+		/* D.2 pkt 1,2 set in_port/nb_seg and remove crc */
+		pkt_mb2 = _mm_add_epi16(pkt_mb2, crc_adjust);
+		pkt_mb1 = _mm_add_epi16(pkt_mb1, crc_adjust);
+
+		/* C* extract and record EOP bit */
+		if (split_packet) {
+			__m128i eop_shuf_mask =
+				_mm_set_epi8(0xFF, 0xFF, 0xFF, 0xFF,
+					     0xFF, 0xFF, 0xFF, 0xFF,
+					     0xFF, 0xFF, 0xFF, 0xFF,
+					     0x04, 0x0C, 0x00, 0x08);
+
+			/* and with mask to extract bits, flipping 1-0 */
+			__m128i eop_bits = _mm_andnot_si128(staterr, eop_check);
+			/* the staterr values are not in order, as the count
+			 * of dd bits doesn't care. However, for end of
+			 * packet tracking, we do care, so shuffle. This also
+			 * compresses the 32-bit values to 8-bit
+			 */
+			eop_bits = _mm_shuffle_epi8(eop_bits, eop_shuf_mask);
+			/* store the resulting 32-bit value */
+			*(int *)split_packet = _mm_cvtsi128_si32(eop_bits);
+			split_packet += RTE_NGBE_DESCS_PER_LOOP;
+		}
+
+		/* C.3 calc available number of desc */
+		staterr = _mm_and_si128(staterr, dd_check);
+		staterr = _mm_packs_epi32(staterr, zero);
+
+		/* D.3 copy final 1,2 data to rx_pkts */
+		_mm_storeu_si128((void *)&rx_pkts[pos + 1]->rx_descriptor_fields1,
+				pkt_mb2);
+		_mm_storeu_si128((void *)&rx_pkts[pos]->rx_descriptor_fields1,
+				pkt_mb1);
+
+		desc_to_ptype_v(descs, NGBE_PTID_MASK, &rx_pkts[pos]);
+
+		/* C.4 calc available number of desc */
+		var = rte_popcount64(_mm_cvtsi128_si64(staterr));
+		nb_pkts_recd += var;
+		if (likely(var != RTE_NGBE_DESCS_PER_LOOP))
+			break;
+	}
+
+	/* Update our internal tail pointer */
+	rxq->rx_tail = (uint16_t)(rxq->rx_tail + nb_pkts_recd);
+	rxq->rx_tail = (uint16_t)(rxq->rx_tail & (rxq->nb_rx_desc - 1));
+	rxq->rxrearm_nb = (uint16_t)(rxq->rxrearm_nb + nb_pkts_recd);
+
+	return nb_pkts_recd;
+}
+
+/*
+ * vPMD receive routine, only accept(nb_pkts >= RTE_NGBE_DESCS_PER_LOOP)
+ *
+ * Notice:
+ * - nb_pkts < RTE_NGBE_DESCS_PER_LOOP, just return no packet
+ * - floor align nb_pkts to a RTE_NGBE_DESC_PER_LOOP power-of-two
+ */
+uint16_t
+ngbe_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
+		uint16_t nb_pkts)
+{
+	return _recv_raw_pkts_vec(rx_queue, rx_pkts, nb_pkts, NULL);
+}
+
+/**
+ * vPMD receive routine that reassembles scattered packets
+ *
+ * Notice:
+ * - nb_pkts < RTE_NGBE_DESCS_PER_LOOP, just return no packet
+ * - floor align nb_pkts to a RTE_NGBE_DESC_PER_LOOP power-of-two
+ */
+static uint16_t
+ngbe_recv_scattered_burst_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
+			       uint16_t nb_pkts)
+{
+	struct ngbe_rx_queue *rxq = rx_queue;
+	uint8_t split_flags[RTE_NGBE_MAX_RX_BURST] = {0};
+
+	/* get some new buffers */
+	uint16_t nb_bufs = _recv_raw_pkts_vec(rxq, rx_pkts, nb_pkts,
+			split_flags);
+	if (nb_bufs == 0)
+		return 0;
+
+	/* happy day case, full burst + no packets to be joined */
+	const uint64_t *split_fl64 = (uint64_t *)split_flags;
+	if (rxq->pkt_first_seg == NULL &&
+			split_fl64[0] == 0 && split_fl64[1] == 0 &&
+			split_fl64[2] == 0 && split_fl64[3] == 0)
+		return nb_bufs;
+
+	/* reassemble any packets that need reassembly*/
+	unsigned int i = 0;
+	if (rxq->pkt_first_seg == NULL) {
+		/* find the first split flag, and only reassemble then*/
+		while (i < nb_bufs && !split_flags[i])
+			i++;
+		if (i == nb_bufs)
+			return nb_bufs;
+		rxq->pkt_first_seg = rx_pkts[i];
+	}
+	return i + reassemble_packets(rxq, &rx_pkts[i], nb_bufs - i,
+		&split_flags[i]);
+}
+
+/**
+ * vPMD receive routine that reassembles scattered packets.
+ */
+uint16_t
+ngbe_recv_scattered_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
+			     uint16_t nb_pkts)
+{
+	uint16_t retval = 0;
+
+	while (nb_pkts > RTE_NGBE_MAX_RX_BURST) {
+		uint16_t burst;
+
+		burst = ngbe_recv_scattered_burst_vec(rx_queue,
+						      rx_pkts + retval,
+						      RTE_NGBE_MAX_RX_BURST);
+		retval += burst;
+		nb_pkts -= burst;
+		if (burst < RTE_NGBE_MAX_RX_BURST)
+			return retval;
+	}
+
+	return retval + ngbe_recv_scattered_burst_vec(rx_queue,
+						      rx_pkts + retval,
+						      nb_pkts);
+}
+
+static inline void
+vtx1(volatile struct ngbe_tx_desc *txdp,
+		struct rte_mbuf *pkt, uint64_t flags)
+{
+	__m128i descriptor = _mm_set_epi64x((uint64_t)pkt->pkt_len << 45 |
+			flags | pkt->data_len,
+			pkt->buf_iova + pkt->data_off);
+	_mm_store_si128((__m128i *)txdp, descriptor);
+}
+
+static inline void
+vtx(volatile struct ngbe_tx_desc *txdp,
+		struct rte_mbuf **pkt, uint16_t nb_pkts,  uint64_t flags)
+{
+	int i;
+
+	for (i = 0; i < nb_pkts; ++i, ++txdp, ++pkt)
+		vtx1(txdp, *pkt, flags);
+}
+
+uint16_t
+ngbe_xmit_fixed_burst_vec(void *tx_queue, struct rte_mbuf **tx_pkts,
+			  uint16_t nb_pkts)
+{
+	struct ngbe_tx_queue *txq = (struct ngbe_tx_queue *)tx_queue;
+	volatile struct ngbe_tx_desc *txdp;
+	struct ngbe_tx_entry_v *txep;
+	uint16_t n, nb_commit, tx_id;
+	uint64_t flags = NGBE_TXD_FLAGS;
+	uint64_t rs = NGBE_TXD_FLAGS;
+	int i;
+
+	/* cross rx_thresh boundary is not allowed */
+	nb_pkts = RTE_MIN(nb_pkts, txq->tx_free_thresh);
+
+	if (txq->nb_tx_free < txq->tx_free_thresh)
+		ngbe_tx_free_bufs(txq);
+
+	nb_pkts = (uint16_t)RTE_MIN(txq->nb_tx_free, nb_pkts);
+	if (unlikely(nb_pkts == 0))
+		return 0;
+
+	tx_id = txq->tx_tail;
+	txdp = &txq->tx_ring[tx_id];
+	txep = &txq->sw_ring_v[tx_id];
+
+	txq->nb_tx_free = (uint16_t)(txq->nb_tx_free - nb_pkts);
+
+	n = (uint16_t)(txq->nb_tx_desc - tx_id);
+	nb_commit = nb_pkts;
+	if (nb_commit >= n) {
+		tx_backlog_entry(txep, tx_pkts, n);
+
+		for (i = 0; i < n - 1; ++i, ++tx_pkts, ++txdp)
+			vtx1(txdp, *tx_pkts, flags);
+
+		vtx1(txdp, *tx_pkts++, rs);
+
+		nb_commit = (uint16_t)(nb_commit - n);
+
+		tx_id = 0;
+
+		/* avoid reach the end of ring */
+		txdp = &txq->tx_ring[tx_id];
+		txep = &txq->sw_ring_v[tx_id];
+	}
+
+	tx_backlog_entry(txep, tx_pkts, nb_commit);
+
+	vtx(txdp, tx_pkts, nb_commit, flags);
+
+	tx_id = (uint16_t)(tx_id + nb_commit);
+
+	txq->tx_tail = tx_id;
+
+	ngbe_set32(txq->tdt_reg_addr, txq->tx_tail);
+
+	return nb_pkts;
+}
+
+static void __rte_cold
+ngbe_tx_queue_release_mbufs_vec(struct ngbe_tx_queue *txq)
+{
+	_ngbe_tx_queue_release_mbufs_vec(txq);
+}
+
+void __rte_cold
+ngbe_rx_queue_release_mbufs_vec(struct ngbe_rx_queue *rxq)
+{
+	_ngbe_rx_queue_release_mbufs_vec(rxq);
+}
+
+static void __rte_cold
+ngbe_tx_free_swring(struct ngbe_tx_queue *txq)
+{
+	_ngbe_tx_free_swring_vec(txq);
+}
+
+static void __rte_cold
+ngbe_reset_tx_queue(struct ngbe_tx_queue *txq)
+{
+	_ngbe_reset_tx_queue_vec(txq);
+}
+
+static const struct ngbe_txq_ops vec_txq_ops = {
+	.release_mbufs = ngbe_tx_queue_release_mbufs_vec,
+	.free_swring = ngbe_tx_free_swring,
+	.reset = ngbe_reset_tx_queue,
+};
+
+int __rte_cold
+ngbe_rxq_vec_setup(struct ngbe_rx_queue *rxq)
+{
+	return ngbe_rxq_vec_setup_default(rxq);
+}
+
+int __rte_cold
+ngbe_txq_vec_setup(struct ngbe_tx_queue *txq)
+{
+	return ngbe_txq_vec_setup_default(txq, &vec_txq_ops);
+}
+
+int __rte_cold
+ngbe_rx_vec_dev_conf_condition_check(struct rte_eth_dev *dev)
+{
+	return ngbe_rx_vec_dev_conf_condition_check_default(dev);
+}
-- 
2.27.0