diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
index 8cc7f5db54..f6cb921573 100644
--- a/target/arm/translate-neon.inc.c
+++ b/target/arm/translate-neon.inc.c
@@ -54,6 +54,107 @@ static inline int rsub_8(DisasContext *s, int x)
 #include "decode-neon-ls.inc.c"
 #include "decode-neon-shared.inc.c"
 
+/* Return the offset of a 2**SIZE piece of a NEON register, at index ELE,
+ * where 0 is the least significant end of the register.
+ */
+static inline long
+neon_element_offset(int reg, int element, MemOp size)
+{
+    int element_size = 1 << size;
+    int ofs = element * element_size;
+#ifdef HOST_WORDS_BIGENDIAN
+    /* Calculate the offset assuming fully little-endian,
+     * then XOR to account for the order of the 8-byte units.
+     */
+    if (element_size < 8) {
+        ofs ^= 8 - element_size;
+    }
+#endif
+    return neon_reg_offset(reg, 0) + ofs;
+}
+
+static void neon_load_element(TCGv_i32 var, int reg, int ele, MemOp mop)
+{
+    long offset = neon_element_offset(reg, ele, mop & MO_SIZE);
+
+    switch (mop) {
+    case MO_UB:
+        tcg_gen_ld8u_i32(var, cpu_env, offset);
+        break;
+    case MO_UW:
+        tcg_gen_ld16u_i32(var, cpu_env, offset);
+        break;
+    case MO_UL:
+        tcg_gen_ld_i32(var, cpu_env, offset);
+        break;
+    default:
+        g_assert_not_reached();
+    }
+}
+
+static void neon_load_element64(TCGv_i64 var, int reg, int ele, MemOp mop)
+{
+    long offset = neon_element_offset(reg, ele, mop & MO_SIZE);
+
+    switch (mop) {
+    case MO_UB:
+        tcg_gen_ld8u_i64(var, cpu_env, offset);
+        break;
+    case MO_UW:
+        tcg_gen_ld16u_i64(var, cpu_env, offset);
+        break;
+    case MO_UL:
+        tcg_gen_ld32u_i64(var, cpu_env, offset);
+        break;
+    case MO_Q:
+        tcg_gen_ld_i64(var, cpu_env, offset);
+        break;
+    default:
+        g_assert_not_reached();
+    }
+}
+
+static void neon_store_element(int reg, int ele, MemOp size, TCGv_i32 var)
+{
+    long offset = neon_element_offset(reg, ele, size);
+
+    switch (size) {
+    case MO_8:
+        tcg_gen_st8_i32(var, cpu_env, offset);
+        break;
+    case MO_16:
+        tcg_gen_st16_i32(var, cpu_env, offset);
+        break;
+    case MO_32:
+        tcg_gen_st_i32(var, cpu_env, offset);
+        break;
+    default:
+        g_assert_not_reached();
+    }
+}
+
+static void neon_store_element64(int reg, int ele, MemOp size, TCGv_i64 var)
+{
+    long offset = neon_element_offset(reg, ele, size);
+
+    switch (size) {
+    case MO_8:
+        tcg_gen_st8_i64(var, cpu_env, offset);
+        break;
+    case MO_16:
+        tcg_gen_st16_i64(var, cpu_env, offset);
+        break;
+    case MO_32:
+        tcg_gen_st32_i64(var, cpu_env, offset);
+        break;
+    case MO_64:
+        tcg_gen_st_i64(var, cpu_env, offset);
+        break;
+    default:
+        g_assert_not_reached();
+    }
+}
+
 static bool trans_VCMLA(DisasContext *s, arg_VCMLA *a)
 {
     int opr_sz;
diff --git a/target/arm/translate.c b/target/arm/translate.c
index 581b0b5cde..408fb7a492 100644
--- a/target/arm/translate.c
+++ b/target/arm/translate.c
@@ -1133,25 +1133,6 @@ neon_reg_offset (int reg, int n)
     return vfp_reg_offset(0, sreg);
 }
 
-/* Return the offset of a 2**SIZE piece of a NEON register, at index ELE,
- * where 0 is the least significant end of the register.
- */
-static inline long
-neon_element_offset(int reg, int element, MemOp size)
-{
-    int element_size = 1 << size;
-    int ofs = element * element_size;
-#ifdef HOST_WORDS_BIGENDIAN
-    /* Calculate the offset assuming fully little-endian,
-     * then XOR to account for the order of the 8-byte units.
-     */
-    if (element_size < 8) {
-        ofs ^= 8 - element_size;
-    }
-#endif
-    return neon_reg_offset(reg, 0) + ofs;
-}
-
 static TCGv_i32 neon_load_reg(int reg, int pass)
 {
     TCGv_i32 tmp = tcg_temp_new_i32();
@@ -1159,94 +1140,12 @@ static TCGv_i32 neon_load_reg(int reg, int pass)
     return tmp;
 }
 
-static void neon_load_element(TCGv_i32 var, int reg, int ele, MemOp mop)
-{
-    long offset = neon_element_offset(reg, ele, mop & MO_SIZE);
-
-    switch (mop) {
-    case MO_UB:
-        tcg_gen_ld8u_i32(var, cpu_env, offset);
-        break;
-    case MO_UW:
-        tcg_gen_ld16u_i32(var, cpu_env, offset);
-        break;
-    case MO_UL:
-        tcg_gen_ld_i32(var, cpu_env, offset);
-        break;
-    default:
-        g_assert_not_reached();
-    }
-}
-
-static void neon_load_element64(TCGv_i64 var, int reg, int ele, MemOp mop)
-{
-    long offset = neon_element_offset(reg, ele, mop & MO_SIZE);
-
-    switch (mop) {
-    case MO_UB:
-        tcg_gen_ld8u_i64(var, cpu_env, offset);
-        break;
-    case MO_UW:
-        tcg_gen_ld16u_i64(var, cpu_env, offset);
-        break;
-    case MO_UL:
-        tcg_gen_ld32u_i64(var, cpu_env, offset);
-        break;
-    case MO_Q:
-        tcg_gen_ld_i64(var, cpu_env, offset);
-        break;
-    default:
-        g_assert_not_reached();
-    }
-}
-
 static void neon_store_reg(int reg, int pass, TCGv_i32 var)
 {
     tcg_gen_st_i32(var, cpu_env, neon_reg_offset(reg, pass));
     tcg_temp_free_i32(var);
 }
 
-static void neon_store_element(int reg, int ele, MemOp size, TCGv_i32 var)
-{
-    long offset = neon_element_offset(reg, ele, size);
-
-    switch (size) {
-    case MO_8:
-        tcg_gen_st8_i32(var, cpu_env, offset);
-        break;
-    case MO_16:
-        tcg_gen_st16_i32(var, cpu_env, offset);
-        break;
-    case MO_32:
-        tcg_gen_st_i32(var, cpu_env, offset);
-        break;
-    default:
-        g_assert_not_reached();
-    }
-}
-
-static void neon_store_element64(int reg, int ele, MemOp size, TCGv_i64 var)
-{
-    long offset = neon_element_offset(reg, ele, size);
-
-    switch (size) {
-    case MO_8:
-        tcg_gen_st8_i64(var, cpu_env, offset);
-        break;
-    case MO_16:
-        tcg_gen_st16_i64(var, cpu_env, offset);
-        break;
-    case MO_32:
-        tcg_gen_st32_i64(var, cpu_env, offset);
-        break;
-    case MO_64:
-        tcg_gen_st_i64(var, cpu_env, offset);
-        break;
-    default:
-        g_assert_not_reached();
-    }
-}
-
 static inline void neon_load_reg64(TCGv_i64 var, int reg)
 {
     tcg_gen_ld_i64(var, cpu_env, vfp_reg_offset(1, reg));