node: choose vector path at runtime

When choosing the vector path, max SIMD bitwidth is now checked to
ensure the vector path is suitable. To do this, the scalar function is
chosen by default in the struct, but at node initialisation time, this
function pointer is updated to the vector version if supported, and
if it is within the max SIMD bitwidth limit.

Signed-off-by: Ciara Power <ciara.power@intel.com>
Acked-by: Nithin Dabilpuram <ndabilpuram@marvell.com>

diff --git a/lib/librte_node/ip4_lookup.c b/lib/librte_node/ip4_lookup.c
index 293c77f..8835aab 100644 (file)
--- a/lib/librte_node/ip4_lookup.c
+++ b/lib/librte_node/ip4_lookup.c
@@ -15,6 +15,7 @@
 #include <rte_mbuf.h>
 #include <rte_tcp.h>
 #include <rte_udp.h>
+#include <rte_vect.h>
 
 #include "rte_node_ip4_api.h"
 
@@ -34,10 +35,10 @@ static struct ip4_lookup_node_main ip4_lookup_nm;
 #include "ip4_lookup_neon.h"
 #elif defined(RTE_ARCH_X86)
 #include "ip4_lookup_sse.h"
-#else
+#endif
 
 static uint16_t
-ip4_lookup_node_process(struct rte_graph *graph, struct rte_node *node,
+ip4_lookup_node_process_scalar(struct rte_graph *graph, struct rte_node *node,
                        void **objs, uint16_t nb_objs)
 {
        struct rte_ipv4_hdr *ipv4_hdr;
@@ -109,8 +110,6 @@ ip4_lookup_node_process(struct rte_graph *graph, struct rte_node *node,
        return nb_objs;
 }
 
-#endif
-
 int
 rte_node_ip4_route_add(uint32_t ip, uint8_t depth, uint16_t next_hop,
                       enum rte_node_ip4_lookup_next next_node)
@@ -194,13 +193,19 @@ ip4_lookup_node_init(const struct rte_graph *graph, struct rte_node *node)
                init_once = 1;
        }
        *lpm_p = ip4_lookup_nm.lpm_tbl[graph->socket];
+
+#if defined(__ARM_NEON) || defined(RTE_ARCH_X86)
+       if (rte_vect_get_max_simd_bitwidth() >= RTE_VECT_SIMD_128)
+               node->process = ip4_lookup_node_process_vec;
+#endif
+
        node_dbg("ip4_lookup", "Initialized ip4_lookup node");
 
        return 0;
 }
 
 static struct rte_node_register ip4_lookup_node = {
-       .process = ip4_lookup_node_process,
+       .process = ip4_lookup_node_process_scalar,
        .name = "ip4_lookup",
 
        .init = ip4_lookup_node_init,

diff --git a/lib/librte_node/ip4_lookup_neon.h b/lib/librte_node/ip4_lookup_neon.h
index 5e5a7d8..0ad2763 100644 (file)
--- a/lib/librte_node/ip4_lookup_neon.h
+++ b/lib/librte_node/ip4_lookup_neon.h
@@ -7,7 +7,7 @@
 
 /* ARM64 NEON */
 static uint16_t
-ip4_lookup_node_process(struct rte_graph *graph, struct rte_node *node,
+ip4_lookup_node_process_vec(struct rte_graph *graph, struct rte_node *node,
                        void **objs, uint16_t nb_objs)
 {
        struct rte_mbuf *mbuf0, *mbuf1, *mbuf2, *mbuf3, **pkts;

diff --git a/lib/librte_node/ip4_lookup_sse.h b/lib/librte_node/ip4_lookup_sse.h
index a071cc5..264c986 100644 (file)
--- a/lib/librte_node/ip4_lookup_sse.h
+++ b/lib/librte_node/ip4_lookup_sse.h
@@ -7,7 +7,7 @@
 
 /* X86 SSE */
 static uint16_t
-ip4_lookup_node_process(struct rte_graph *graph, struct rte_node *node,
+ip4_lookup_node_process_vec(struct rte_graph *graph, struct rte_node *node,
                        void **objs, uint16_t nb_objs)
 {
        struct rte_mbuf *mbuf0, *mbuf1, *mbuf2, *mbuf3, **pkts;