Add an optimised version of the in-flight flow matching algorithm
using SIMD instructions. This should give up to 1.5x over the scalar
versions performance.

Falls back to scalar version if SSE4.2 not available

Signed-off-by: David Hunt <redacted>
---
 lib/librte_distributor/Makefile                    |   7 ++
 lib/librte_distributor/rte_distributor.c           |  16 ++-
 .../rte_distributor_match_generic.c                |  43 ++++++++
 lib/librte_distributor/rte_distributor_match_sse.c | 113 +++++++++++++++++++++
 lib/librte_distributor/rte_distributor_private.h   |   5 +
 5 files changed, 182 insertions(+), 2 deletions(-)
 create mode 100644 lib/librte_distributor/rte_distributor_match_generic.c
 create mode 100644 lib/librte_distributor/rte_distributor_match_sse.c

diff --git a/lib/librte_distributor/Makefile b/lib/librte_distributor/Makefile
index 276695a..5b599c6 100644
--- a/lib/librte_distributor/Makefile
+++ b/lib/librte_distributor/Makefile

@@ -44,6 +44,13 @@ LIBABIVER := 1
 # all source are stored in SRCS-y
 SRCS-$(CONFIG_RTE_LIBRTE_DISTRIBUTOR) := rte_distributor_v20.c
 SRCS-$(CONFIG_RTE_LIBRTE_DISTRIBUTOR) += rte_distributor.c
+ifeq ($(CONFIG_RTE_ARCH_X86),y)
+SRCS-$(CONFIG_RTE_LIBRTE_DISTRIBUTOR) += rte_distributor_match_sse.c
+CFLAGS_rte_distributor_match_sse.o += -msse4.2
+else
+SRCS-$(CONFIG_RTE_LIBRTE_DISTRIBUTOR) += rte_distributor_match_generic.c
+endif
+
 
 # install this header file
 SYMLINK-$(CONFIG_RTE_LIBRTE_DISTRIBUTOR)-include := rte_distributor_v20.h

diff --git a/lib/librte_distributor/rte_distributor.c b/lib/librte_distributor/rte_distributor.c
index ae8d508..b8e171c 100644
--- a/lib/librte_distributor/rte_distributor.c
+++ b/lib/librte_distributor/rte_distributor.c

@@ -392,7 +392,13 @@ rte_distributor_process(struct rte_distributor *d,
 		for (; i < RTE_DIST_BURST_SIZE; i++)
 			flows[i] = 0;
 
-		find_match_scalar(d, &flows[0], &matches[0]);
+		switch (d->dist_match_fn) {
+		case RTE_DIST_MATCH_VECTOR:
+			find_match_vec(d, &flows[0], &matches[0]);
+			break;
+		default:
+			find_match_scalar(d, &flows[0], &matches[0]);
+		}
 
 		/*
 		 * Matches array now contain the intended worker ID (+1) of

@@ -608,7 +614,13 @@ rte_distributor_create(const char *name,
 	snprintf(d->name, sizeof(d->name), "%s", name);
 	d->num_workers = num_workers;
 	d->alg_type = alg_type;
-	d->dist_match_fn = RTE_DIST_MATCH_SCALAR;
+
+#if defined(RTE_ARCH_X86)
+	if (rte_cpu_get_flag_enabled(RTE_CPUFLAG_SSE4_2)) {
+		d->dist_match_fn = RTE_DIST_MATCH_VECTOR;
+	} else