diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index d90e8661ca..3e93f6e848 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -905,15 +905,14 @@ static void do_gpr_ld(DisasContext *s, TCGv_i64 dest, TCGv_i64 tcg_addr,
 /*
  * Store from FP register to memory
  */
-static void do_fp_st(DisasContext *s, int srcidx, TCGv_i64 tcg_addr, int size)
+static void do_fp_st(DisasContext *s, int srcidx, TCGv_i64 tcg_addr, MemOp mop)
 {
     /* This writes the bottom N bits of a 128 bit wide vector to memory */
     TCGv_i64 tmplo = tcg_temp_new_i64();
-    MemOp mop = finalize_memop_asimd(s, size);
 
     tcg_gen_ld_i64(tmplo, cpu_env, fp_reg_offset(s, srcidx, MO_64));
 
-    if (size < MO_128) {
+    if ((mop & MO_SIZE) < MO_128) {
         tcg_gen_qemu_st_i64(tmplo, tcg_addr, get_mem_index(s), mop);
     } else {
         TCGv_i64 tmphi = tcg_temp_new_i64();
@@ -929,14 +928,13 @@ static void do_fp_st(DisasContext *s, int srcidx, TCGv_i64 tcg_addr, int size)
 /*
  * Load from memory to FP register
  */
-static void do_fp_ld(DisasContext *s, int destidx, TCGv_i64 tcg_addr, int size)
+static void do_fp_ld(DisasContext *s, int destidx, TCGv_i64 tcg_addr, MemOp mop)
 {
     /* This always zero-extends and writes to a full 128 bit wide vector */
     TCGv_i64 tmplo = tcg_temp_new_i64();
     TCGv_i64 tmphi = NULL;
-    MemOp mop = finalize_memop_asimd(s, size);
 
-    if (size < MO_128) {
+    if ((mop & MO_SIZE) < MO_128) {
         tcg_gen_qemu_ld_i64(tmplo, tcg_addr, get_mem_index(s), mop);
     } else {
         TCGv_i128 t16 = tcg_temp_new_i128();
@@ -2763,6 +2761,7 @@ static void disas_ld_lit(DisasContext *s, uint32_t insn)
     bool is_signed = false;
     int size = 2;
     TCGv_i64 tcg_rt, clean_addr;
+    MemOp memop;
 
     if (is_vector) {
         if (opc == 3) {
@@ -2773,6 +2772,7 @@ static void disas_ld_lit(DisasContext *s, uint32_t insn)
         if (!fp_access_check(s)) {
             return;
         }
+        memop = finalize_memop_asimd(s, size);
     } else {
         if (opc == 3) {
             /* PRFM (literal) : prefetch */
@@ -2780,19 +2780,19 @@ static void disas_ld_lit(DisasContext *s, uint32_t insn)
         }
         size = 2 + extract32(opc, 0, 1);
         is_signed = extract32(opc, 1, 1);
+        memop = finalize_memop(s, size + is_signed * MO_SIGN);
     }
 
     tcg_rt = cpu_reg(s, rt);
 
     clean_addr = tcg_temp_new_i64();
     gen_pc_plus_diff(s, clean_addr, imm);
+
     if (is_vector) {
-        do_fp_ld(s, rt, clean_addr, size);
+        do_fp_ld(s, rt, clean_addr, memop);
     } else {
         /* Only unsigned 32bit loads target 32bit registers.  */
         bool iss_sf = opc != 0;
-        MemOp memop = finalize_memop(s, size + is_signed * MO_SIGN);
-
         do_gpr_ld(s, tcg_rt, clean_addr, memop, false, true, rt, iss_sf, false);
     }
 }
@@ -2929,16 +2929,18 @@ static void disas_ldst_pair(DisasContext *s, uint32_t insn)
                                 (wback || rn != 31) && !set_tag, 2 << size);
 
     if (is_vector) {
+        MemOp mop = finalize_memop_asimd(s, size);
+
         if (is_load) {
-            do_fp_ld(s, rt, clean_addr, size);
+            do_fp_ld(s, rt, clean_addr, mop);
         } else {
-            do_fp_st(s, rt, clean_addr, size);
+            do_fp_st(s, rt, clean_addr, mop);
         }
         tcg_gen_addi_i64(clean_addr, clean_addr, 1 << size);
         if (is_load) {
-            do_fp_ld(s, rt2, clean_addr, size);
+            do_fp_ld(s, rt2, clean_addr, mop);
         } else {
-            do_fp_st(s, rt2, clean_addr, size);
+            do_fp_st(s, rt2, clean_addr, mop);
         }
     } else {
         TCGv_i64 tcg_rt = cpu_reg(s, rt);
@@ -3060,6 +3062,7 @@ static void disas_ldst_reg_imm9(DisasContext *s, uint32_t insn,
         if (!fp_access_check(s)) {
             return;
         }
+        memop = finalize_memop_asimd(s, size);
     } else {
         if (size == 3 && opc == 2) {
             /* PRFM - prefetch */
@@ -3076,6 +3079,7 @@ static void disas_ldst_reg_imm9(DisasContext *s, uint32_t insn,
         is_store = (opc == 0);
         is_signed = !is_store && extract32(opc, 1, 1);
         is_extended = (size < 3) && extract32(opc, 0, 1);
+        memop = finalize_memop(s, size + is_signed * MO_SIGN);
     }
 
     switch (idx) {
@@ -3108,7 +3112,6 @@ static void disas_ldst_reg_imm9(DisasContext *s, uint32_t insn,
     }
 
     memidx = is_unpriv ? get_a64_user_mem_index(s) : get_mem_index(s);
-    memop = finalize_memop(s, size + is_signed * MO_SIGN);
 
     clean_addr = gen_mte_check1_mmuidx(s, dirty_addr, is_store,
                                        writeback || rn != 31,
@@ -3116,9 +3119,9 @@ static void disas_ldst_reg_imm9(DisasContext *s, uint32_t insn,
 
     if (is_vector) {
         if (is_store) {
-            do_fp_st(s, rt, clean_addr, size);
+            do_fp_st(s, rt, clean_addr, memop);
         } else {
-            do_fp_ld(s, rt, clean_addr, size);
+            do_fp_ld(s, rt, clean_addr, memop);
         }
     } else {
         TCGv_i64 tcg_rt = cpu_reg(s, rt);
@@ -3224,9 +3227,9 @@ static void disas_ldst_reg_roffset(DisasContext *s, uint32_t insn,
 
     if (is_vector) {
         if (is_store) {
-            do_fp_st(s, rt, clean_addr, size);
+            do_fp_st(s, rt, clean_addr, memop);
         } else {
-            do_fp_ld(s, rt, clean_addr, size);
+            do_fp_ld(s, rt, clean_addr, memop);
         }
     } else {
         TCGv_i64 tcg_rt = cpu_reg(s, rt);
@@ -3310,9 +3313,9 @@ static void disas_ldst_reg_unsigned_imm(DisasContext *s, uint32_t insn,
 
     if (is_vector) {
         if (is_store) {
-            do_fp_st(s, rt, clean_addr, size);
+            do_fp_st(s, rt, clean_addr, memop);
         } else {
-            do_fp_ld(s, rt, clean_addr, size);
+            do_fp_ld(s, rt, clean_addr, memop);
         }
     } else {
         TCGv_i64 tcg_rt = cpu_reg(s, rt);