diff --git a/aom_dsp/arm/mem_neon.h b/aom_dsp/arm/mem_neon.h
index 9e7a0cc..ad761de 100644
--- a/aom_dsp/arm/mem_neon.h
+++ b/aom_dsp/arm/mem_neon.h
@@ -98,6 +98,11 @@
   return res;
 }
 
+static inline uint16x8x2_t vld1q_u16_x2(const uint16_t *ptr) {
+  uint16x8x2_t res = { { vld1q_u16(ptr + 0 * 8), vld1q_u16(ptr + 1 * 8) } };
+  return res;
+}
+
 static inline int16x8x2_t vld1q_s16_x2(const int16_t *ptr) {
   int16x8x2_t res = { { vld1q_s16(ptr + 0 * 8), vld1q_s16(ptr + 1 * 8) } };
   return res;
@@ -136,6 +141,18 @@
   vst1_u8(ptr + 2 * 8, a.val[2]);
   vst1_u8(ptr + 3 * 8, a.val[3]);
 }
+
+static inline void vst1q_u16_x2(uint16_t *ptr, uint16x8x2_t a) {
+  vst1q_u16(ptr + 0 * 8, a.val[0]);
+  vst1q_u16(ptr + 1 * 8, a.val[1]);
+}
+
+static inline void vst1q_u16_x4(uint16_t *ptr, uint16x8x4_t a) {
+  vst1q_u16(ptr + 0 * 8, a.val[0]);
+  vst1q_u16(ptr + 1 * 8, a.val[1]);
+  vst1q_u16(ptr + 2 * 8, a.val[2]);
+  vst1q_u16(ptr + 3 * 8, a.val[3]);
+}
 #endif  // ((__GNUC__ << 8) | __GNUC_MINOR__) < 0x805
 #endif  // defined(__GNUC__) && !defined(__clang__)