diff --git a/qemu/target/arm/neon-dp.decode b/qemu/target/arm/neon-dp.decode
index cc2ee964..105cf2b2 100644
--- a/qemu/target/arm/neon-dp.decode
+++ b/qemu/target/arm/neon-dp.decode
@@ -485,5 +485,8 @@ Vimm_1r          1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm
 
     VMUL_2sc     1111 001 . 1 . .. .... .... 1000 . 1 . 0 .... @2scalar
     VMUL_F_2sc   1111 001 . 1 . .. .... .... 1001 . 1 . 0 .... @2scalar
+
+    VQDMULH_2sc  1111 001 . 1 . .. .... .... 1100 . 1 . 0 .... @2scalar
+    VQRDMULH_2sc 1111 001 . 1 . .. .... .... 1101 . 1 . 0 .... @2scalar
   ]
 }
diff --git a/qemu/target/arm/translate-neon.inc.c b/qemu/target/arm/translate-neon.inc.c
index b8ced2a3..daf3b5ea 100644
--- a/qemu/target/arm/translate-neon.inc.c
+++ b/qemu/target/arm/translate-neon.inc.c
@@ -2576,3 +2576,32 @@ static bool trans_VMLS_F_2sc(DisasContext *s, arg_2scalar *a)
 
     return do_2scalar(s, a, opfn[a->size], accfn[a->size]);
 }
+
+WRAP_ENV_FN(gen_VQDMULH_16, gen_helper_neon_qdmulh_s16)
+WRAP_ENV_FN(gen_VQDMULH_32, gen_helper_neon_qdmulh_s32)
+WRAP_ENV_FN(gen_VQRDMULH_16, gen_helper_neon_qrdmulh_s16)
+WRAP_ENV_FN(gen_VQRDMULH_32, gen_helper_neon_qrdmulh_s32)
+
+static bool trans_VQDMULH_2sc(DisasContext *s, arg_2scalar *a)
+{
+    static NeonGenTwoOpFn * const opfn[] = {
+        NULL,
+        gen_VQDMULH_16,
+        gen_VQDMULH_32,
+        NULL,
+    };
+
+    return do_2scalar(s, a, opfn[a->size], NULL);
+}
+
+static bool trans_VQRDMULH_2sc(DisasContext *s, arg_2scalar *a)
+{
+    static NeonGenTwoOpFn * const opfn[] = {
+        NULL,
+        gen_VQRDMULH_16,
+        gen_VQRDMULH_32,
+        NULL,
+    };
+
+    return do_2scalar(s, a, opfn[a->size], NULL);
+}
diff --git a/qemu/target/arm/translate.c b/qemu/target/arm/translate.c
index 563a0c75..eaa388f8 100644
--- a/qemu/target/arm/translate.c
+++ b/qemu/target/arm/translate.c
@@ -3079,21 +3079,6 @@ static void gen_exception_return(DisasContext *s, TCGv_i32 pc)
 
 #define CPU_V001 s->V0, s->V0, s->V1
 
-static TCGv_i32 neon_load_scratch(DisasContext *s, int scratch)
-{
-    TCGContext *tcg_ctx = s->uc->tcg_ctx;
-    TCGv_i32 tmp = tcg_temp_new_i32(tcg_ctx);
-    tcg_gen_ld_i32(tcg_ctx, tmp, tcg_ctx->cpu_env, offsetof(CPUARMState, vfp.scratch[scratch]));
-    return tmp;
-}
-
-static void neon_store_scratch(DisasContext *s, int scratch, TCGv_i32 var)
-{
-    TCGContext *tcg_ctx = s->uc->tcg_ctx;
-    tcg_gen_st_i32(tcg_ctx, var, tcg_ctx->cpu_env, offsetof(CPUARMState, vfp.scratch[scratch]));
-    tcg_temp_free_i32(tcg_ctx, var);
-}
-
 static int gen_neon_unzip(DisasContext *s, int rd, int rm, int size, int q)
 {
     TCGContext *tcg_ctx = s->uc->tcg_ctx;
@@ -5310,35 +5295,10 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
                 case 1: /* Float VMLA scalar */
                 case 5: /* Floating point VMLS scalar */
                 case 9: /* Floating point VMUL scalar */
-                    return 1; /* handled by decodetree */
-
                 case 12: /* VQDMULH scalar */
                 case 13: /* VQRDMULH scalar */
-                    if (u && ((rd | rn) & 1)) {
-                        return 1;
-                    }
-                    tmp = neon_get_scalar(s, size, rm);
-                    neon_store_scratch(s, 0, tmp);
-                    for (pass = 0; pass < (u ? 4 : 2); pass++) {
-                        tmp = neon_load_scratch(s, 0);
-                        tmp2 = neon_load_reg(s, rn, pass);
-                        if (op == 12) {
-                            if (size == 1) {
-                                gen_helper_neon_qdmulh_s16(tcg_ctx, tmp, tcg_ctx->cpu_env, tmp, tmp2);
-                            } else {
-                                gen_helper_neon_qdmulh_s32(tcg_ctx, tmp, tcg_ctx->cpu_env, tmp, tmp2);
-                            }
-                        } else {
-                            if (size == 1) {
-                                gen_helper_neon_qrdmulh_s16(tcg_ctx, tmp, tcg_ctx->cpu_env, tmp, tmp2);
-                            } else {
-                                gen_helper_neon_qrdmulh_s32(tcg_ctx, tmp, tcg_ctx->cpu_env, tmp, tmp2);
-                            }
-                        }
-                        tcg_temp_free_i32(tcg_ctx, tmp2);
-                        neon_store_reg(s, rd, pass, tmp);
-                    }
-                    break;
+                    return 1; /* handled by decodetree */
+
                 case 3: /* VQDMLAL scalar */
                 case 7: /* VQDMLSL scalar */
                 case 11: /* VQDMULL scalar */