vppinfra: add u64x2_gather/u32x4_gather

Add u64x2_gather/u32x4_gather in vector_neon.h. u64x2_gather/u32x4_gather
gathers data from scattered memory locations to a SIMD register.

Type: feature

Change-Id: I1dd27e38af28b9bed85143014c86197ee549fede
Signed-off-by: Lijian Zhang <Lijian.Zhang@arm.com>
Reviewed-by: Sirshak Das <Sirshak.Das@arm.com>
Reviewed-by: Honnappa Nagarahalli <Honnappa.Nagarahalli@arm.com>
diff --git a/src/vppinfra/vector_neon.h b/src/vppinfra/vector_neon.h
index 37bd1bb..4e911ac 100644
--- a/src/vppinfra/vector_neon.h
+++ b/src/vppinfra/vector_neon.h
@@ -142,6 +142,24 @@
   return (u16) (vgetq_lane_u64 (x64, 0) + (vgetq_lane_u64 (x64, 1) << 8));
 }
 
+static_always_inline u64x2
+u64x2_gather (void *p0, void *p1)
+{
+  u64x2 r = vdupq_n_u64 (*(u64 *) p0);
+  r = vsetq_lane_u64 (*(u64 *) p1, r, 1);
+  return r;
+}
+
+static_always_inline u32x4
+u32x4_gather (void *p0, void *p1, void *p2, void *p3)
+{
+  u32x4 r = vdupq_n_u32 (*(u32 *) p0);
+  r = vsetq_lane_u32 (*(u32 *) p1, r, 1);
+  r = vsetq_lane_u32 (*(u32 *) p2, r, 2);
+  r = vsetq_lane_u32 (*(u32 *) p3, r, 3);
+  return r;
+}
+
 #define CLIB_HAVE_VEC128_MSB_MASK
 
 #define CLIB_HAVE_VEC128_UNALIGNED_LOAD_STORE