summary refs log tree commit diff stats
path: root/target/arm/tcg/translate-a64.c
diff options
context:
space:
mode:
Diffstat (limited to 'target/arm/tcg/translate-a64.c')
-rw-r--r--target/arm/tcg/translate-a64.c1362
1 files changed, 485 insertions, 877 deletions
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index 9167e4d0bd..93543da39c 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -724,19 +724,6 @@ static void gen_gvec_op3_fpst(DisasContext *s, bool is_q, int rd, int rn,
                        is_q ? 16 : 8, vec_full_reg_size(s), data, fn);
 }
 
-/* Expand a 3-operand + qc + operation using an out-of-line helper.  */
-static void gen_gvec_op3_qc(DisasContext *s, bool is_q, int rd, int rn,
-                            int rm, gen_helper_gvec_3_ptr *fn)
-{
-    TCGv_ptr qc_ptr = tcg_temp_new_ptr();
-
-    tcg_gen_addi_ptr(qc_ptr, tcg_env, offsetof(CPUARMState, vfp.qc));
-    tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, rd),
-                       vec_full_reg_offset(s, rn),
-                       vec_full_reg_offset(s, rm), qc_ptr,
-                       is_q ? 16 : 8, vec_full_reg_size(s), 0, fn);
-}
-
 /* Expand a 4-operand operation using an out-of-line helper.  */
 static void gen_gvec_op4_ool(DisasContext *s, bool is_q, int rd, int rn,
                              int rm, int ra, int data, gen_helper_gvec_4 *fn)
@@ -1363,6 +1350,14 @@ static bool do_gvec_fn3_no64(DisasContext *s, arg_qrrr_e *a, GVecGen3Fn *fn)
     return true;
 }
 
+static bool do_gvec_fn3_no8_no64(DisasContext *s, arg_qrrr_e *a, GVecGen3Fn *fn)
+{
+    if (a->esz == MO_8) {
+        return false;
+    }
+    return do_gvec_fn3_no64(s, a, fn);
+}
+
 static bool do_gvec_fn4(DisasContext *s, arg_qrrrr_e *a, GVecGen4Fn *fn)
 {
     if (!a->q && a->esz == MO_64) {
@@ -1750,6 +1745,47 @@ static bool trans_WFE(DisasContext *s, arg_WFI *a)
     return true;
 }
 
+static bool trans_WFIT(DisasContext *s, arg_WFIT *a)
+{
+    if (!dc_isar_feature(aa64_wfxt, s)) {
+        return false;
+    }
+
+    /*
+     * Because we need to pass the register value to the helper,
+     * it's easier to emit the code now, unlike trans_WFI which
+     * defers it to aarch64_tr_tb_stop(). That means we need to
+     * check ss_active so that single-stepping a WFIT doesn't halt.
+     */
+    if (s->ss_active) {
+        /* Act like a NOP under architectural singlestep */
+        return true;
+    }
+
+    gen_a64_update_pc(s, 4);
+    gen_helper_wfit(tcg_env, cpu_reg(s, a->rd));
+    /* Go back to the main loop to check for interrupts */
+    s->base.is_jmp = DISAS_EXIT;
+    return true;
+}
+
+static bool trans_WFET(DisasContext *s, arg_WFET *a)
+{
+    if (!dc_isar_feature(aa64_wfxt, s)) {
+        return false;
+    }
+
+    /*
+     * We rely here on our WFE implementation being a NOP, so we
+     * don't need to do anything different to handle the WFET timeout
+     * from what trans_WFE does.
+     */
+    if (!(tb_cflags(s->base.tb) & CF_PARALLEL)) {
+        s->base.is_jmp = DISAS_WFE;
+    }
+    return true;
+}
+
 static bool trans_XPACLRI(DisasContext *s, arg_XPACLRI *a)
 {
     if (s->pauth_active) {
@@ -5060,6 +5096,163 @@ static const FPScalar f_scalar_frsqrts = {
 };
 TRANS(FRSQRTS_s, do_fp3_scalar, a, &f_scalar_frsqrts)
 
+static bool do_satacc_s(DisasContext *s, arg_rrr_e *a,
+                MemOp sgn_n, MemOp sgn_m,
+                void (*gen_bhs)(TCGv_i64, TCGv_i64, TCGv_i64, TCGv_i64, MemOp),
+                void (*gen_d)(TCGv_i64, TCGv_i64, TCGv_i64, TCGv_i64))
+{
+    TCGv_i64 t0, t1, t2, qc;
+    MemOp esz = a->esz;
+
+    if (!fp_access_check(s)) {
+        return true;
+    }
+
+    t0 = tcg_temp_new_i64();
+    t1 = tcg_temp_new_i64();
+    t2 = tcg_temp_new_i64();
+    qc = tcg_temp_new_i64();
+    read_vec_element(s, t1, a->rn, 0, esz | sgn_n);
+    read_vec_element(s, t2, a->rm, 0, esz | sgn_m);
+    tcg_gen_ld_i64(qc, tcg_env, offsetof(CPUARMState, vfp.qc));
+
+    if (esz == MO_64) {
+        gen_d(t0, qc, t1, t2);
+    } else {
+        gen_bhs(t0, qc, t1, t2, esz);
+        tcg_gen_ext_i64(t0, t0, esz);
+    }
+
+    write_fp_dreg(s, a->rd, t0);
+    tcg_gen_st_i64(qc, tcg_env, offsetof(CPUARMState, vfp.qc));
+    return true;
+}
+
+TRANS(SQADD_s, do_satacc_s, a, MO_SIGN, MO_SIGN, gen_sqadd_bhs, gen_sqadd_d)
+TRANS(SQSUB_s, do_satacc_s, a, MO_SIGN, MO_SIGN, gen_sqsub_bhs, gen_sqsub_d)
+TRANS(UQADD_s, do_satacc_s, a, 0, 0, gen_uqadd_bhs, gen_uqadd_d)
+TRANS(UQSUB_s, do_satacc_s, a, 0, 0, gen_uqsub_bhs, gen_uqsub_d)
+TRANS(SUQADD_s, do_satacc_s, a, MO_SIGN, 0, gen_suqadd_bhs, gen_suqadd_d)
+TRANS(USQADD_s, do_satacc_s, a, 0, MO_SIGN, gen_usqadd_bhs, gen_usqadd_d)
+
+static bool do_int3_scalar_d(DisasContext *s, arg_rrr_e *a,
+                             void (*fn)(TCGv_i64, TCGv_i64, TCGv_i64))
+{
+    if (fp_access_check(s)) {
+        TCGv_i64 t0 = tcg_temp_new_i64();
+        TCGv_i64 t1 = tcg_temp_new_i64();
+
+        read_vec_element(s, t0, a->rn, 0, MO_64);
+        read_vec_element(s, t1, a->rm, 0, MO_64);
+        fn(t0, t0, t1);
+        write_fp_dreg(s, a->rd, t0);
+    }
+    return true;
+}
+
+TRANS(SSHL_s, do_int3_scalar_d, a, gen_sshl_i64)
+TRANS(USHL_s, do_int3_scalar_d, a, gen_ushl_i64)
+TRANS(SRSHL_s, do_int3_scalar_d, a, gen_helper_neon_rshl_s64)
+TRANS(URSHL_s, do_int3_scalar_d, a, gen_helper_neon_rshl_u64)
+TRANS(ADD_s, do_int3_scalar_d, a, tcg_gen_add_i64)
+TRANS(SUB_s, do_int3_scalar_d, a, tcg_gen_sub_i64)
+
+typedef struct ENVScalar2 {
+    NeonGenTwoOpEnvFn *gen_bhs[3];
+    NeonGenTwo64OpEnvFn *gen_d;
+} ENVScalar2;
+
+static bool do_env_scalar2(DisasContext *s, arg_rrr_e *a, const ENVScalar2 *f)
+{
+    if (!fp_access_check(s)) {
+        return true;
+    }
+    if (a->esz == MO_64) {
+        TCGv_i64 t0 = read_fp_dreg(s, a->rn);
+        TCGv_i64 t1 = read_fp_dreg(s, a->rm);
+        f->gen_d(t0, tcg_env, t0, t1);
+        write_fp_dreg(s, a->rd, t0);
+    } else {
+        TCGv_i32 t0 = tcg_temp_new_i32();
+        TCGv_i32 t1 = tcg_temp_new_i32();
+
+        read_vec_element_i32(s, t0, a->rn, 0, a->esz);
+        read_vec_element_i32(s, t1, a->rm, 0, a->esz);
+        f->gen_bhs[a->esz](t0, tcg_env, t0, t1);
+        write_fp_sreg(s, a->rd, t0);
+    }
+    return true;
+}
+
+static const ENVScalar2 f_scalar_sqshl = {
+    { gen_helper_neon_qshl_s8,
+      gen_helper_neon_qshl_s16,
+      gen_helper_neon_qshl_s32 },
+    gen_helper_neon_qshl_s64,
+};
+TRANS(SQSHL_s, do_env_scalar2, a, &f_scalar_sqshl)
+
+static const ENVScalar2 f_scalar_uqshl = {
+    { gen_helper_neon_qshl_u8,
+      gen_helper_neon_qshl_u16,
+      gen_helper_neon_qshl_u32 },
+    gen_helper_neon_qshl_u64,
+};
+TRANS(UQSHL_s, do_env_scalar2, a, &f_scalar_uqshl)
+
+static const ENVScalar2 f_scalar_sqrshl = {
+    { gen_helper_neon_qrshl_s8,
+      gen_helper_neon_qrshl_s16,
+      gen_helper_neon_qrshl_s32 },
+    gen_helper_neon_qrshl_s64,
+};
+TRANS(SQRSHL_s, do_env_scalar2, a, &f_scalar_sqrshl)
+
+static const ENVScalar2 f_scalar_uqrshl = {
+    { gen_helper_neon_qrshl_u8,
+      gen_helper_neon_qrshl_u16,
+      gen_helper_neon_qrshl_u32 },
+    gen_helper_neon_qrshl_u64,
+};
+TRANS(UQRSHL_s, do_env_scalar2, a, &f_scalar_uqrshl)
+
+static bool do_env_scalar2_hs(DisasContext *s, arg_rrr_e *a,
+                              const ENVScalar2 *f)
+{
+    if (a->esz == MO_16 || a->esz == MO_32) {
+        return do_env_scalar2(s, a, f);
+    }
+    return false;
+}
+
+static const ENVScalar2 f_scalar_sqdmulh = {
+    { NULL, gen_helper_neon_qdmulh_s16, gen_helper_neon_qdmulh_s32 }
+};
+TRANS(SQDMULH_s, do_env_scalar2_hs, a, &f_scalar_sqdmulh)
+
+static const ENVScalar2 f_scalar_sqrdmulh = {
+    { NULL, gen_helper_neon_qrdmulh_s16, gen_helper_neon_qrdmulh_s32 }
+};
+TRANS(SQRDMULH_s, do_env_scalar2_hs, a, &f_scalar_sqrdmulh)
+
+static bool do_cmop_d(DisasContext *s, arg_rrr_e *a, TCGCond cond)
+{
+    if (fp_access_check(s)) {
+        TCGv_i64 t0 = read_fp_dreg(s, a->rn);
+        TCGv_i64 t1 = read_fp_dreg(s, a->rm);
+        tcg_gen_negsetcond_i64(cond, t0, t0, t1);
+        write_fp_dreg(s, a->rd, t0);
+    }
+    return true;
+}
+
+TRANS(CMGT_s, do_cmop_d, a, TCG_COND_GT)
+TRANS(CMHI_s, do_cmop_d, a, TCG_COND_GTU)
+TRANS(CMGE_s, do_cmop_d, a, TCG_COND_GE)
+TRANS(CMHS_s, do_cmop_d, a, TCG_COND_GEU)
+TRANS(CMEQ_s, do_cmop_d, a, TCG_COND_EQ)
+TRANS(CMTST_s, do_cmop_d, a, TCG_COND_TSTNE)
+
 static bool do_fp3_vector(DisasContext *s, arg_qrrr_e *a,
                           gen_helper_gvec_3_ptr * const fns[3])
 {
@@ -5298,6 +5491,68 @@ TRANS(BSL_v, do_bitsel, a->q, a->rd, a->rd, a->rn, a->rm)
 TRANS(BIT_v, do_bitsel, a->q, a->rd, a->rm, a->rn, a->rd)
 TRANS(BIF_v, do_bitsel, a->q, a->rd, a->rm, a->rd, a->rn)
 
+TRANS(SQADD_v, do_gvec_fn3, a, gen_gvec_sqadd_qc)
+TRANS(UQADD_v, do_gvec_fn3, a, gen_gvec_uqadd_qc)
+TRANS(SQSUB_v, do_gvec_fn3, a, gen_gvec_sqsub_qc)
+TRANS(UQSUB_v, do_gvec_fn3, a, gen_gvec_uqsub_qc)
+TRANS(SUQADD_v, do_gvec_fn3, a, gen_gvec_suqadd_qc)
+TRANS(USQADD_v, do_gvec_fn3, a, gen_gvec_usqadd_qc)
+
+TRANS(SSHL_v, do_gvec_fn3, a, gen_gvec_sshl)
+TRANS(USHL_v, do_gvec_fn3, a, gen_gvec_ushl)
+TRANS(SRSHL_v, do_gvec_fn3, a, gen_gvec_srshl)
+TRANS(URSHL_v, do_gvec_fn3, a, gen_gvec_urshl)
+TRANS(SQSHL_v, do_gvec_fn3, a, gen_neon_sqshl)
+TRANS(UQSHL_v, do_gvec_fn3, a, gen_neon_uqshl)
+TRANS(SQRSHL_v, do_gvec_fn3, a, gen_neon_sqrshl)
+TRANS(UQRSHL_v, do_gvec_fn3, a, gen_neon_uqrshl)
+
+TRANS(ADD_v, do_gvec_fn3, a, tcg_gen_gvec_add)
+TRANS(SUB_v, do_gvec_fn3, a, tcg_gen_gvec_sub)
+TRANS(SHADD_v, do_gvec_fn3_no64, a, gen_gvec_shadd)
+TRANS(UHADD_v, do_gvec_fn3_no64, a, gen_gvec_uhadd)
+TRANS(SHSUB_v, do_gvec_fn3_no64, a, gen_gvec_shsub)
+TRANS(UHSUB_v, do_gvec_fn3_no64, a, gen_gvec_uhsub)
+TRANS(SRHADD_v, do_gvec_fn3_no64, a, gen_gvec_srhadd)
+TRANS(URHADD_v, do_gvec_fn3_no64, a, gen_gvec_urhadd)
+TRANS(SMAX_v, do_gvec_fn3_no64, a, tcg_gen_gvec_smax)
+TRANS(UMAX_v, do_gvec_fn3_no64, a, tcg_gen_gvec_umax)
+TRANS(SMIN_v, do_gvec_fn3_no64, a, tcg_gen_gvec_smin)
+TRANS(UMIN_v, do_gvec_fn3_no64, a, tcg_gen_gvec_umin)
+TRANS(SABA_v, do_gvec_fn3_no64, a, gen_gvec_saba)
+TRANS(UABA_v, do_gvec_fn3_no64, a, gen_gvec_uaba)
+TRANS(SABD_v, do_gvec_fn3_no64, a, gen_gvec_sabd)
+TRANS(UABD_v, do_gvec_fn3_no64, a, gen_gvec_uabd)
+TRANS(MUL_v, do_gvec_fn3_no64, a, tcg_gen_gvec_mul)
+TRANS(PMUL_v, do_gvec_op3_ool, a, 0, gen_helper_gvec_pmul_b)
+TRANS(MLA_v, do_gvec_fn3_no64, a, gen_gvec_mla)
+TRANS(MLS_v, do_gvec_fn3_no64, a, gen_gvec_mls)
+
+static bool do_cmop_v(DisasContext *s, arg_qrrr_e *a, TCGCond cond)
+{
+    if (a->esz == MO_64 && !a->q) {
+        return false;
+    }
+    if (fp_access_check(s)) {
+        tcg_gen_gvec_cmp(cond, a->esz,
+                         vec_full_reg_offset(s, a->rd),
+                         vec_full_reg_offset(s, a->rn),
+                         vec_full_reg_offset(s, a->rm),
+                         a->q ? 16 : 8, vec_full_reg_size(s));
+    }
+    return true;
+}
+
+TRANS(CMGT_v, do_cmop_v, a, TCG_COND_GT)
+TRANS(CMHI_v, do_cmop_v, a, TCG_COND_GTU)
+TRANS(CMGE_v, do_cmop_v, a, TCG_COND_GE)
+TRANS(CMHS_v, do_cmop_v, a, TCG_COND_GEU)
+TRANS(CMEQ_v, do_cmop_v, a, TCG_COND_EQ)
+TRANS(CMTST_v, do_gvec_fn3, a, gen_gvec_cmtst)
+
+TRANS(SQDMULH_v, do_gvec_fn3_no8_no64, a, gen_gvec_sqdmulh_qc)
+TRANS(SQRDMULH_v, do_gvec_fn3_no8_no64, a, gen_gvec_sqrdmulh_qc)
+
 /*
  * Advanced SIMD scalar/vector x indexed element
  */
@@ -5405,6 +5660,27 @@ static bool do_fmla_scalar_idx(DisasContext *s, arg_rrx_e *a, bool neg)
 TRANS(FMLA_si, do_fmla_scalar_idx, a, false)
 TRANS(FMLS_si, do_fmla_scalar_idx, a, true)
 
+static bool do_env_scalar2_idx_hs(DisasContext *s, arg_rrx_e *a,
+                                  const ENVScalar2 *f)
+{
+    if (a->esz < MO_16 || a->esz > MO_32) {
+        return false;
+    }
+    if (fp_access_check(s)) {
+        TCGv_i32 t0 = tcg_temp_new_i32();
+        TCGv_i32 t1 = tcg_temp_new_i32();
+
+        read_vec_element_i32(s, t0, a->rn, 0, a->esz);
+        read_vec_element_i32(s, t1, a->rm, a->idx, a->esz);
+        f->gen_bhs[a->esz](t0, tcg_env, t0, t1);
+        write_fp_sreg(s, a->rd, t0);
+    }
+    return true;
+}
+
+TRANS(SQDMULH_si, do_env_scalar2_idx_hs, a, &f_scalar_sqdmulh)
+TRANS(SQRDMULH_si, do_env_scalar2_idx_hs, a, &f_scalar_sqrdmulh)
+
 static bool do_fp3_vector_idx(DisasContext *s, arg_qrrx_e *a,
                               gen_helper_gvec_3_ptr * const fns[3])
 {
@@ -5501,6 +5777,67 @@ TRANS_FEAT(FMLSL_vi, aa64_fhm, do_fmlal_idx, a, true, false)
 TRANS_FEAT(FMLAL2_vi, aa64_fhm, do_fmlal_idx, a, false, true)
 TRANS_FEAT(FMLSL2_vi, aa64_fhm, do_fmlal_idx, a, true, true)
 
+static bool do_int3_vector_idx(DisasContext *s, arg_qrrx_e *a,
+                               gen_helper_gvec_3 * const fns[2])
+{
+    assert(a->esz == MO_16 || a->esz == MO_32);
+    if (fp_access_check(s)) {
+        gen_gvec_op3_ool(s, a->q, a->rd, a->rn, a->rm, a->idx, fns[a->esz - 1]);
+    }
+    return true;
+}
+
+static gen_helper_gvec_3 * const f_vector_idx_mul[2] = {
+    gen_helper_gvec_mul_idx_h,
+    gen_helper_gvec_mul_idx_s,
+};
+TRANS(MUL_vi, do_int3_vector_idx, a, f_vector_idx_mul)
+
+static bool do_mla_vector_idx(DisasContext *s, arg_qrrx_e *a, bool sub)
+{
+    static gen_helper_gvec_4 * const fns[2][2] = {
+        { gen_helper_gvec_mla_idx_h, gen_helper_gvec_mls_idx_h },
+        { gen_helper_gvec_mla_idx_s, gen_helper_gvec_mls_idx_s },
+    };
+
+    assert(a->esz == MO_16 || a->esz == MO_32);
+    if (fp_access_check(s)) {
+        gen_gvec_op4_ool(s, a->q, a->rd, a->rn, a->rm, a->rd,
+                         a->idx, fns[a->esz - 1][sub]);
+    }
+    return true;
+}
+
+TRANS(MLA_vi, do_mla_vector_idx, a, false)
+TRANS(MLS_vi, do_mla_vector_idx, a, true)
+
+static bool do_int3_qc_vector_idx(DisasContext *s, arg_qrrx_e *a,
+                                  gen_helper_gvec_4 * const fns[2])
+{
+    assert(a->esz == MO_16 || a->esz == MO_32);
+    if (fp_access_check(s)) {
+        tcg_gen_gvec_4_ool(vec_full_reg_offset(s, a->rd),
+                           vec_full_reg_offset(s, a->rn),
+                           vec_full_reg_offset(s, a->rm),
+                           offsetof(CPUARMState, vfp.qc),
+                           a->q ? 16 : 8, vec_full_reg_size(s),
+                           a->idx, fns[a->esz - 1]);
+    }
+    return true;
+}
+
+static gen_helper_gvec_4 * const f_vector_idx_sqdmulh[2] = {
+    gen_helper_neon_sqdmulh_idx_h,
+    gen_helper_neon_sqdmulh_idx_s,
+};
+TRANS(SQDMULH_vi, do_int3_qc_vector_idx, a, f_vector_idx_sqdmulh)
+
+static gen_helper_gvec_4 * const f_vector_idx_sqrdmulh[2] = {
+    gen_helper_neon_sqrdmulh_idx_h,
+    gen_helper_neon_sqrdmulh_idx_s,
+};
+TRANS(SQRDMULH_vi, do_int3_qc_vector_idx, a, f_vector_idx_sqrdmulh)
+
 /*
  * Advanced SIMD scalar pairwise
  */
@@ -5570,6 +5907,132 @@ static bool trans_ADDP_s(DisasContext *s, arg_rr_e *a)
     return true;
 }
 
+/*
+ * Floating-point conditional select
+ */
+
+static bool trans_FCSEL(DisasContext *s, arg_FCSEL *a)
+{
+    TCGv_i64 t_true, t_false;
+    DisasCompare64 c;
+
+    switch (a->esz) {
+    case MO_32:
+    case MO_64:
+        break;
+    case MO_16:
+        if (!dc_isar_feature(aa64_fp16, s)) {
+            return false;
+        }
+        break;
+    default:
+        return false;
+    }
+
+    if (!fp_access_check(s)) {
+        return true;
+    }
+
+    /* Zero extend sreg & hreg inputs to 64 bits now.  */
+    t_true = tcg_temp_new_i64();
+    t_false = tcg_temp_new_i64();
+    read_vec_element(s, t_true, a->rn, 0, a->esz);
+    read_vec_element(s, t_false, a->rm, 0, a->esz);
+
+    a64_test_cc(&c, a->cond);
+    tcg_gen_movcond_i64(c.cond, t_true, c.value, tcg_constant_i64(0),
+                        t_true, t_false);
+
+    /*
+     * Note that sregs & hregs write back zeros to the high bits,
+     * and we've already done the zero-extension.
+     */
+    write_fp_dreg(s, a->rd, t_true);
+    return true;
+}
+
+/*
+ * Floating-point data-processing (3 source)
+ */
+
+static bool do_fmadd(DisasContext *s, arg_rrrr_e *a, bool neg_a, bool neg_n)
+{
+    TCGv_ptr fpst;
+
+    /*
+     * These are fused multiply-add.  Note that doing the negations here
+     * as separate steps is correct: an input NaN should come out with
+     * its sign bit flipped if it is a negated-input.
+     */
+    switch (a->esz) {
+    case MO_64:
+        if (fp_access_check(s)) {
+            TCGv_i64 tn = read_fp_dreg(s, a->rn);
+            TCGv_i64 tm = read_fp_dreg(s, a->rm);
+            TCGv_i64 ta = read_fp_dreg(s, a->ra);
+
+            if (neg_a) {
+                gen_vfp_negd(ta, ta);
+            }
+            if (neg_n) {
+                gen_vfp_negd(tn, tn);
+            }
+            fpst = fpstatus_ptr(FPST_FPCR);
+            gen_helper_vfp_muladdd(ta, tn, tm, ta, fpst);
+            write_fp_dreg(s, a->rd, ta);
+        }
+        break;
+
+    case MO_32:
+        if (fp_access_check(s)) {
+            TCGv_i32 tn = read_fp_sreg(s, a->rn);
+            TCGv_i32 tm = read_fp_sreg(s, a->rm);
+            TCGv_i32 ta = read_fp_sreg(s, a->ra);
+
+            if (neg_a) {
+                gen_vfp_negs(ta, ta);
+            }
+            if (neg_n) {
+                gen_vfp_negs(tn, tn);
+            }
+            fpst = fpstatus_ptr(FPST_FPCR);
+            gen_helper_vfp_muladds(ta, tn, tm, ta, fpst);
+            write_fp_sreg(s, a->rd, ta);
+        }
+        break;
+
+    case MO_16:
+        if (!dc_isar_feature(aa64_fp16, s)) {
+            return false;
+        }
+        if (fp_access_check(s)) {
+            TCGv_i32 tn = read_fp_hreg(s, a->rn);
+            TCGv_i32 tm = read_fp_hreg(s, a->rm);
+            TCGv_i32 ta = read_fp_hreg(s, a->ra);
+
+            if (neg_a) {
+                gen_vfp_negh(ta, ta);
+            }
+            if (neg_n) {
+                gen_vfp_negh(tn, tn);
+            }
+            fpst = fpstatus_ptr(FPST_FPCR_F16);
+            gen_helper_advsimd_muladdh(ta, tn, tm, ta, fpst);
+            write_fp_sreg(s, a->rd, ta);
+        }
+        break;
+
+    default:
+        return false;
+    }
+    return true;
+}
+
+TRANS(FMADD, do_fmadd, a, false, false)
+TRANS(FNMADD, do_fmadd, a, true, true)
+TRANS(FMSUB, do_fmadd, a, false, true)
+TRANS(FNMSUB, do_fmadd, a, true, false)
+
 /* Shift a TCGv src by TCGv shift_amount, put result in dst.
  * Note that it is the caller's responsibility to ensure that the
  * shift amount is in range (ie 0..31 or 0..63) and provide the ARM
@@ -6954,68 +7417,6 @@ static void disas_fp_ccomp(DisasContext *s, uint32_t insn)
     }
 }
 
-/* Floating point conditional select
- *   31  30  29 28       24 23  22  21 20  16 15  12 11 10 9    5 4    0
- * +---+---+---+-----------+------+---+------+------+-----+------+------+
- * | M | 0 | S | 1 1 1 1 0 | type | 1 |  Rm  | cond | 1 1 |  Rn  |  Rd  |
- * +---+---+---+-----------+------+---+------+------+-----+------+------+
- */
-static void disas_fp_csel(DisasContext *s, uint32_t insn)
-{
-    unsigned int mos, type, rm, cond, rn, rd;
-    TCGv_i64 t_true, t_false;
-    DisasCompare64 c;
-    MemOp sz;
-
-    mos = extract32(insn, 29, 3);
-    type = extract32(insn, 22, 2);
-    rm = extract32(insn, 16, 5);
-    cond = extract32(insn, 12, 4);
-    rn = extract32(insn, 5, 5);
-    rd = extract32(insn, 0, 5);
-
-    if (mos) {
-        unallocated_encoding(s);
-        return;
-    }
-
-    switch (type) {
-    case 0:
-        sz = MO_32;
-        break;
-    case 1:
-        sz = MO_64;
-        break;
-    case 3:
-        sz = MO_16;
-        if (dc_isar_feature(aa64_fp16, s)) {
-            break;
-        }
-        /* fallthru */
-    default:
-        unallocated_encoding(s);
-        return;
-    }
-
-    if (!fp_access_check(s)) {
-        return;
-    }
-
-    /* Zero extend sreg & hreg inputs to 64 bits now.  */
-    t_true = tcg_temp_new_i64();
-    t_false = tcg_temp_new_i64();
-    read_vec_element(s, t_true, rn, 0, sz);
-    read_vec_element(s, t_false, rm, 0, sz);
-
-    a64_test_cc(&c, cond);
-    tcg_gen_movcond_i64(c.cond, t_true, c.value, tcg_constant_i64(0),
-                        t_true, t_false);
-
-    /* Note that sregs & hregs write back zeros to the high bits,
-       and we've already done the zero-extension.  */
-    write_fp_dreg(s, rd, t_true);
-}
-
 /* Floating-point data-processing (1 source) - half precision */
 static void handle_fp_1src_half(DisasContext *s, int opcode, int rd, int rn)
 {
@@ -7369,152 +7770,6 @@ static void disas_fp_1src(DisasContext *s, uint32_t insn)
     }
 }
 
-/* Floating-point data-processing (3 source) - single precision */
-static void handle_fp_3src_single(DisasContext *s, bool o0, bool o1,
-                                  int rd, int rn, int rm, int ra)
-{
-    TCGv_i32 tcg_op1, tcg_op2, tcg_op3;
-    TCGv_i32 tcg_res = tcg_temp_new_i32();
-    TCGv_ptr fpst = fpstatus_ptr(FPST_FPCR);
-
-    tcg_op1 = read_fp_sreg(s, rn);
-    tcg_op2 = read_fp_sreg(s, rm);
-    tcg_op3 = read_fp_sreg(s, ra);
-
-    /* These are fused multiply-add, and must be done as one
-     * floating point operation with no rounding between the
-     * multiplication and addition steps.
-     * NB that doing the negations here as separate steps is
-     * correct : an input NaN should come out with its sign bit
-     * flipped if it is a negated-input.
-     */
-    if (o1 == true) {
-        gen_vfp_negs(tcg_op3, tcg_op3);
-    }
-
-    if (o0 != o1) {
-        gen_vfp_negs(tcg_op1, tcg_op1);
-    }
-
-    gen_helper_vfp_muladds(tcg_res, tcg_op1, tcg_op2, tcg_op3, fpst);
-
-    write_fp_sreg(s, rd, tcg_res);
-}
-
-/* Floating-point data-processing (3 source) - double precision */
-static void handle_fp_3src_double(DisasContext *s, bool o0, bool o1,
-                                  int rd, int rn, int rm, int ra)
-{
-    TCGv_i64 tcg_op1, tcg_op2, tcg_op3;
-    TCGv_i64 tcg_res = tcg_temp_new_i64();
-    TCGv_ptr fpst = fpstatus_ptr(FPST_FPCR);
-
-    tcg_op1 = read_fp_dreg(s, rn);
-    tcg_op2 = read_fp_dreg(s, rm);
-    tcg_op3 = read_fp_dreg(s, ra);
-
-    /* These are fused multiply-add, and must be done as one
-     * floating point operation with no rounding between the
-     * multiplication and addition steps.
-     * NB that doing the negations here as separate steps is
-     * correct : an input NaN should come out with its sign bit
-     * flipped if it is a negated-input.
-     */
-    if (o1 == true) {
-        gen_vfp_negd(tcg_op3, tcg_op3);
-    }
-
-    if (o0 != o1) {
-        gen_vfp_negd(tcg_op1, tcg_op1);
-    }
-
-    gen_helper_vfp_muladdd(tcg_res, tcg_op1, tcg_op2, tcg_op3, fpst);
-
-    write_fp_dreg(s, rd, tcg_res);
-}
-
-/* Floating-point data-processing (3 source) - half precision */
-static void handle_fp_3src_half(DisasContext *s, bool o0, bool o1,
-                                int rd, int rn, int rm, int ra)
-{
-    TCGv_i32 tcg_op1, tcg_op2, tcg_op3;
-    TCGv_i32 tcg_res = tcg_temp_new_i32();
-    TCGv_ptr fpst = fpstatus_ptr(FPST_FPCR_F16);
-
-    tcg_op1 = read_fp_hreg(s, rn);
-    tcg_op2 = read_fp_hreg(s, rm);
-    tcg_op3 = read_fp_hreg(s, ra);
-
-    /* These are fused multiply-add, and must be done as one
-     * floating point operation with no rounding between the
-     * multiplication and addition steps.
-     * NB that doing the negations here as separate steps is
-     * correct : an input NaN should come out with its sign bit
-     * flipped if it is a negated-input.
-     */
-    if (o1 == true) {
-        tcg_gen_xori_i32(tcg_op3, tcg_op3, 0x8000);
-    }
-
-    if (o0 != o1) {
-        tcg_gen_xori_i32(tcg_op1, tcg_op1, 0x8000);
-    }
-
-    gen_helper_advsimd_muladdh(tcg_res, tcg_op1, tcg_op2, tcg_op3, fpst);
-
-    write_fp_sreg(s, rd, tcg_res);
-}
-
-/* Floating point data-processing (3 source)
- *   31  30  29 28       24 23  22  21  20  16  15  14  10 9    5 4    0
- * +---+---+---+-----------+------+----+------+----+------+------+------+
- * | M | 0 | S | 1 1 1 1 1 | type | o1 |  Rm  | o0 |  Ra  |  Rn  |  Rd  |
- * +---+---+---+-----------+------+----+------+----+------+------+------+
- */
-static void disas_fp_3src(DisasContext *s, uint32_t insn)
-{
-    int mos = extract32(insn, 29, 3);
-    int type = extract32(insn, 22, 2);
-    int rd = extract32(insn, 0, 5);
-    int rn = extract32(insn, 5, 5);
-    int ra = extract32(insn, 10, 5);
-    int rm = extract32(insn, 16, 5);
-    bool o0 = extract32(insn, 15, 1);
-    bool o1 = extract32(insn, 21, 1);
-
-    if (mos) {
-        unallocated_encoding(s);
-        return;
-    }
-
-    switch (type) {
-    case 0:
-        if (!fp_access_check(s)) {
-            return;
-        }
-        handle_fp_3src_single(s, o0, o1, rd, rn, rm, ra);
-        break;
-    case 1:
-        if (!fp_access_check(s)) {
-            return;
-        }
-        handle_fp_3src_double(s, o0, o1, rd, rn, rm, ra);
-        break;
-    case 3:
-        if (!dc_isar_feature(aa64_fp16, s)) {
-            unallocated_encoding(s);
-            return;
-        }
-        if (!fp_access_check(s)) {
-            return;
-        }
-        handle_fp_3src_half(s, o0, o1, rd, rn, rm, ra);
-        break;
-    default:
-        unallocated_encoding(s);
-    }
-}
-
 /* Floating point immediate
  *   31  30  29 28       24 23  22  21 20        13 12   10 9    5 4    0
  * +---+---+---+-----------+------+---+------------+-------+------+------+
@@ -7959,8 +8214,7 @@ static void disas_fp_int_conv(DisasContext *s, uint32_t insn)
 static void disas_data_proc_fp(DisasContext *s, uint32_t insn)
 {
     if (extract32(insn, 24, 1)) {
-        /* Floating point data-processing (3 source) */
-        disas_fp_3src(s, insn);
+        unallocated_encoding(s); /* in decodetree */
     } else if (extract32(insn, 21, 1) == 0) {
         /* Floating point to fixed point conversions */
         disas_fp_fixed_conv(s, insn);
@@ -7976,7 +8230,7 @@ static void disas_data_proc_fp(DisasContext *s, uint32_t insn)
             break;
         case 3:
             /* Floating point conditional select */
-            disas_fp_csel(s, insn);
+            unallocated_encoding(s); /* in decodetree */
             break;
         case 0:
             switch (ctz32(extract32(insn, 12, 4))) {
@@ -9282,219 +9536,6 @@ static void disas_simd_scalar_three_reg_diff(DisasContext *s, uint32_t insn)
     }
 }
 
-static void handle_3same_64(DisasContext *s, int opcode, bool u,
-                            TCGv_i64 tcg_rd, TCGv_i64 tcg_rn, TCGv_i64 tcg_rm)
-{
-    /* Handle 64x64->64 opcodes which are shared between the scalar
-     * and vector 3-same groups. We cover every opcode where size == 3
-     * is valid in either the three-reg-same (integer, not pairwise)
-     * or scalar-three-reg-same groups.
-     */
-    TCGCond cond;
-
-    switch (opcode) {
-    case 0x1: /* SQADD */
-        if (u) {
-            gen_helper_neon_qadd_u64(tcg_rd, tcg_env, tcg_rn, tcg_rm);
-        } else {
-            gen_helper_neon_qadd_s64(tcg_rd, tcg_env, tcg_rn, tcg_rm);
-        }
-        break;
-    case 0x5: /* SQSUB */
-        if (u) {
-            gen_helper_neon_qsub_u64(tcg_rd, tcg_env, tcg_rn, tcg_rm);
-        } else {
-            gen_helper_neon_qsub_s64(tcg_rd, tcg_env, tcg_rn, tcg_rm);
-        }
-        break;
-    case 0x6: /* CMGT, CMHI */
-        cond = u ? TCG_COND_GTU : TCG_COND_GT;
-    do_cmop:
-        /* 64 bit integer comparison, result = test ? -1 : 0. */
-        tcg_gen_negsetcond_i64(cond, tcg_rd, tcg_rn, tcg_rm);
-        break;
-    case 0x7: /* CMGE, CMHS */
-        cond = u ? TCG_COND_GEU : TCG_COND_GE;
-        goto do_cmop;
-    case 0x11: /* CMTST, CMEQ */
-        if (u) {
-            cond = TCG_COND_EQ;
-            goto do_cmop;
-        }
-        gen_cmtst_i64(tcg_rd, tcg_rn, tcg_rm);
-        break;
-    case 0x8: /* SSHL, USHL */
-        if (u) {
-            gen_ushl_i64(tcg_rd, tcg_rn, tcg_rm);
-        } else {
-            gen_sshl_i64(tcg_rd, tcg_rn, tcg_rm);
-        }
-        break;
-    case 0x9: /* SQSHL, UQSHL */
-        if (u) {
-            gen_helper_neon_qshl_u64(tcg_rd, tcg_env, tcg_rn, tcg_rm);
-        } else {
-            gen_helper_neon_qshl_s64(tcg_rd, tcg_env, tcg_rn, tcg_rm);
-        }
-        break;
-    case 0xa: /* SRSHL, URSHL */
-        if (u) {
-            gen_helper_neon_rshl_u64(tcg_rd, tcg_rn, tcg_rm);
-        } else {
-            gen_helper_neon_rshl_s64(tcg_rd, tcg_rn, tcg_rm);
-        }
-        break;
-    case 0xb: /* SQRSHL, UQRSHL */
-        if (u) {
-            gen_helper_neon_qrshl_u64(tcg_rd, tcg_env, tcg_rn, tcg_rm);
-        } else {
-            gen_helper_neon_qrshl_s64(tcg_rd, tcg_env, tcg_rn, tcg_rm);
-        }
-        break;
-    case 0x10: /* ADD, SUB */
-        if (u) {
-            tcg_gen_sub_i64(tcg_rd, tcg_rn, tcg_rm);
-        } else {
-            tcg_gen_add_i64(tcg_rd, tcg_rn, tcg_rm);
-        }
-        break;
-    default:
-        g_assert_not_reached();
-    }
-}
-
-/* AdvSIMD scalar three same
- *  31 30  29 28       24 23  22  21 20  16 15    11  10 9    5 4    0
- * +-----+---+-----------+------+---+------+--------+---+------+------+
- * | 0 1 | U | 1 1 1 1 0 | size | 1 |  Rm  | opcode | 1 |  Rn  |  Rd  |
- * +-----+---+-----------+------+---+------+--------+---+------+------+
- */
-static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn)
-{
-    int rd = extract32(insn, 0, 5);
-    int rn = extract32(insn, 5, 5);
-    int opcode = extract32(insn, 11, 5);
-    int rm = extract32(insn, 16, 5);
-    int size = extract32(insn, 22, 2);
-    bool u = extract32(insn, 29, 1);
-    TCGv_i64 tcg_rd;
-
-    switch (opcode) {
-    case 0x1: /* SQADD, UQADD */
-    case 0x5: /* SQSUB, UQSUB */
-    case 0x9: /* SQSHL, UQSHL */
-    case 0xb: /* SQRSHL, UQRSHL */
-        break;
-    case 0x8: /* SSHL, USHL */
-    case 0xa: /* SRSHL, URSHL */
-    case 0x6: /* CMGT, CMHI */
-    case 0x7: /* CMGE, CMHS */
-    case 0x11: /* CMTST, CMEQ */
-    case 0x10: /* ADD, SUB (vector) */
-        if (size != 3) {
-            unallocated_encoding(s);
-            return;
-        }
-        break;
-    case 0x16: /* SQDMULH, SQRDMULH (vector) */
-        if (size != 1 && size != 2) {
-            unallocated_encoding(s);
-            return;
-        }
-        break;
-    default:
-        unallocated_encoding(s);
-        return;
-    }
-
-    if (!fp_access_check(s)) {
-        return;
-    }
-
-    tcg_rd = tcg_temp_new_i64();
-
-    if (size == 3) {
-        TCGv_i64 tcg_rn = read_fp_dreg(s, rn);
-        TCGv_i64 tcg_rm = read_fp_dreg(s, rm);
-
-        handle_3same_64(s, opcode, u, tcg_rd, tcg_rn, tcg_rm);
-    } else {
-        /* Do a single operation on the lowest element in the vector.
-         * We use the standard Neon helpers and rely on 0 OP 0 == 0 with
-         * no side effects for all these operations.
-         * OPTME: special-purpose helpers would avoid doing some
-         * unnecessary work in the helper for the 8 and 16 bit cases.
-         */
-        NeonGenTwoOpEnvFn *genenvfn;
-        TCGv_i32 tcg_rn = tcg_temp_new_i32();
-        TCGv_i32 tcg_rm = tcg_temp_new_i32();
-        TCGv_i32 tcg_rd32 = tcg_temp_new_i32();
-
-        read_vec_element_i32(s, tcg_rn, rn, 0, size);
-        read_vec_element_i32(s, tcg_rm, rm, 0, size);
-
-        switch (opcode) {
-        case 0x1: /* SQADD, UQADD */
-        {
-            static NeonGenTwoOpEnvFn * const fns[3][2] = {
-                { gen_helper_neon_qadd_s8, gen_helper_neon_qadd_u8 },
-                { gen_helper_neon_qadd_s16, gen_helper_neon_qadd_u16 },
-                { gen_helper_neon_qadd_s32, gen_helper_neon_qadd_u32 },
-            };
-            genenvfn = fns[size][u];
-            break;
-        }
-        case 0x5: /* SQSUB, UQSUB */
-        {
-            static NeonGenTwoOpEnvFn * const fns[3][2] = {
-                { gen_helper_neon_qsub_s8, gen_helper_neon_qsub_u8 },
-                { gen_helper_neon_qsub_s16, gen_helper_neon_qsub_u16 },
-                { gen_helper_neon_qsub_s32, gen_helper_neon_qsub_u32 },
-            };
-            genenvfn = fns[size][u];
-            break;
-        }
-        case 0x9: /* SQSHL, UQSHL */
-        {
-            static NeonGenTwoOpEnvFn * const fns[3][2] = {
-                { gen_helper_neon_qshl_s8, gen_helper_neon_qshl_u8 },
-                { gen_helper_neon_qshl_s16, gen_helper_neon_qshl_u16 },
-                { gen_helper_neon_qshl_s32, gen_helper_neon_qshl_u32 },
-            };
-            genenvfn = fns[size][u];
-            break;
-        }
-        case 0xb: /* SQRSHL, UQRSHL */
-        {
-            static NeonGenTwoOpEnvFn * const fns[3][2] = {
-                { gen_helper_neon_qrshl_s8, gen_helper_neon_qrshl_u8 },
-                { gen_helper_neon_qrshl_s16, gen_helper_neon_qrshl_u16 },
-                { gen_helper_neon_qrshl_s32, gen_helper_neon_qrshl_u32 },
-            };
-            genenvfn = fns[size][u];
-            break;
-        }
-        case 0x16: /* SQDMULH, SQRDMULH */
-        {
-            static NeonGenTwoOpEnvFn * const fns[2][2] = {
-                { gen_helper_neon_qdmulh_s16, gen_helper_neon_qrdmulh_s16 },
-                { gen_helper_neon_qdmulh_s32, gen_helper_neon_qrdmulh_s32 },
-            };
-            assert(size == 1 || size == 2);
-            genenvfn = fns[size - 1][u];
-            break;
-        }
-        default:
-            g_assert_not_reached();
-        }
-
-        genenvfn(tcg_rd32, tcg_env, tcg_rn, tcg_rm);
-        tcg_gen_extu_i32_i64(tcg_rd, tcg_rd32);
-    }
-
-    write_fp_dreg(s, rd, tcg_rd);
-}
-
 /* AdvSIMD scalar three same extra
  *  31 30  29 28       24 23  22  21 20  16  15 14    11  10 9  5 4  0
  * +-----+---+-----------+------+---+------+---+--------+---+----+----+
@@ -9981,88 +10022,6 @@ static void handle_2misc_narrow(DisasContext *s, bool scalar,
     clear_vec_high(s, is_q, rd);
 }
 
-/* Remaining saturating accumulating ops */
-static void handle_2misc_satacc(DisasContext *s, bool is_scalar, bool is_u,
-                                bool is_q, int size, int rn, int rd)
-{
-    bool is_double = (size == 3);
-
-    if (is_double) {
-        TCGv_i64 tcg_rn = tcg_temp_new_i64();
-        TCGv_i64 tcg_rd = tcg_temp_new_i64();
-        int pass;
-
-        for (pass = 0; pass < (is_scalar ? 1 : 2); pass++) {
-            read_vec_element(s, tcg_rn, rn, pass, MO_64);
-            read_vec_element(s, tcg_rd, rd, pass, MO_64);
-
-            if (is_u) { /* USQADD */
-                gen_helper_neon_uqadd_s64(tcg_rd, tcg_env, tcg_rn, tcg_rd);
-            } else { /* SUQADD */
-                gen_helper_neon_sqadd_u64(tcg_rd, tcg_env, tcg_rn, tcg_rd);
-            }
-            write_vec_element(s, tcg_rd, rd, pass, MO_64);
-        }
-        clear_vec_high(s, !is_scalar, rd);
-    } else {
-        TCGv_i32 tcg_rn = tcg_temp_new_i32();
-        TCGv_i32 tcg_rd = tcg_temp_new_i32();
-        int pass, maxpasses;
-
-        if (is_scalar) {
-            maxpasses = 1;
-        } else {
-            maxpasses = is_q ? 4 : 2;
-        }
-
-        for (pass = 0; pass < maxpasses; pass++) {
-            if (is_scalar) {
-                read_vec_element_i32(s, tcg_rn, rn, pass, size);
-                read_vec_element_i32(s, tcg_rd, rd, pass, size);
-            } else {
-                read_vec_element_i32(s, tcg_rn, rn, pass, MO_32);
-                read_vec_element_i32(s, tcg_rd, rd, pass, MO_32);
-            }
-
-            if (is_u) { /* USQADD */
-                switch (size) {
-                case 0:
-                    gen_helper_neon_uqadd_s8(tcg_rd, tcg_env, tcg_rn, tcg_rd);
-                    break;
-                case 1:
-                    gen_helper_neon_uqadd_s16(tcg_rd, tcg_env, tcg_rn, tcg_rd);
-                    break;
-                case 2:
-                    gen_helper_neon_uqadd_s32(tcg_rd, tcg_env, tcg_rn, tcg_rd);
-                    break;
-                default:
-                    g_assert_not_reached();
-                }
-            } else { /* SUQADD */
-                switch (size) {
-                case 0:
-                    gen_helper_neon_sqadd_u8(tcg_rd, tcg_env, tcg_rn, tcg_rd);
-                    break;
-                case 1:
-                    gen_helper_neon_sqadd_u16(tcg_rd, tcg_env, tcg_rn, tcg_rd);
-                    break;
-                case 2:
-                    gen_helper_neon_sqadd_u32(tcg_rd, tcg_env, tcg_rn, tcg_rd);
-                    break;
-                default:
-                    g_assert_not_reached();
-                }
-            }
-
-            if (is_scalar) {
-                write_vec_element(s, tcg_constant_i64(0), rd, 0, MO_64);
-            }
-            write_vec_element_i32(s, tcg_rd, rd, pass, MO_32);
-        }
-        clear_vec_high(s, is_q, rd);
-    }
-}
-
 /* AdvSIMD scalar two reg misc
  *  31 30  29 28       24 23  22 21       17 16    12 11 10 9    5 4    0
  * +-----+---+-----------+------+-----------+--------+-----+------+------+
@@ -10082,12 +10041,6 @@ static void disas_simd_scalar_two_reg_misc(DisasContext *s, uint32_t insn)
     TCGv_ptr tcg_fpstatus;
 
     switch (opcode) {
-    case 0x3: /* USQADD / SUQADD*/
-        if (!fp_access_check(s)) {
-            return;
-        }
-        handle_2misc_satacc(s, true, u, false, size, rn, rd);
-        return;
     case 0x7: /* SQABS / SQNEG */
         break;
     case 0xa: /* CMLT */
@@ -10187,6 +10140,7 @@ static void disas_simd_scalar_two_reg_misc(DisasContext *s, uint32_t insn)
         }
         break;
     default:
+    case 0x3: /* USQADD / SUQADD */
         unallocated_encoding(s);
         return;
     }
@@ -10919,284 +10873,6 @@ static void disas_simd_three_reg_diff(DisasContext *s, uint32_t insn)
     }
 }
 
-/* Integer op subgroup of C3.6.16. */
-static void disas_simd_3same_int(DisasContext *s, uint32_t insn)
-{
-    int is_q = extract32(insn, 30, 1);
-    int u = extract32(insn, 29, 1);
-    int size = extract32(insn, 22, 2);
-    int opcode = extract32(insn, 11, 5);
-    int rm = extract32(insn, 16, 5);
-    int rn = extract32(insn, 5, 5);
-    int rd = extract32(insn, 0, 5);
-    int pass;
-    TCGCond cond;
-
-    switch (opcode) {
-    case 0x13: /* MUL, PMUL */
-        if (u && size != 0) {
-            unallocated_encoding(s);
-            return;
-        }
-        /* fall through */
-    case 0x0: /* SHADD, UHADD */
-    case 0x2: /* SRHADD, URHADD */
-    case 0x4: /* SHSUB, UHSUB */
-    case 0xc: /* SMAX, UMAX */
-    case 0xd: /* SMIN, UMIN */
-    case 0xe: /* SABD, UABD */
-    case 0xf: /* SABA, UABA */
-    case 0x12: /* MLA, MLS */
-        if (size == 3) {
-            unallocated_encoding(s);
-            return;
-        }
-        break;
-    case 0x16: /* SQDMULH, SQRDMULH */
-        if (size == 0 || size == 3) {
-            unallocated_encoding(s);
-            return;
-        }
-        break;
-    default:
-        if (size == 3 && !is_q) {
-            unallocated_encoding(s);
-            return;
-        }
-        break;
-    }
-
-    if (!fp_access_check(s)) {
-        return;
-    }
-
-    switch (opcode) {
-    case 0x01: /* SQADD, UQADD */
-        if (u) {
-            gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_uqadd_qc, size);
-        } else {
-            gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_sqadd_qc, size);
-        }
-        return;
-    case 0x05: /* SQSUB, UQSUB */
-        if (u) {
-            gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_uqsub_qc, size);
-        } else {
-            gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_sqsub_qc, size);
-        }
-        return;
-    case 0x08: /* SSHL, USHL */
-        if (u) {
-            gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_ushl, size);
-        } else {
-            gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_sshl, size);
-        }
-        return;
-    case 0x0c: /* SMAX, UMAX */
-        if (u) {
-            gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_umax, size);
-        } else {
-            gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_smax, size);
-        }
-        return;
-    case 0x0d: /* SMIN, UMIN */
-        if (u) {
-            gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_umin, size);
-        } else {
-            gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_smin, size);
-        }
-        return;
-    case 0xe: /* SABD, UABD */
-        if (u) {
-            gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_uabd, size);
-        } else {
-            gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_sabd, size);
-        }
-        return;
-    case 0xf: /* SABA, UABA */
-        if (u) {
-            gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_uaba, size);
-        } else {
-            gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_saba, size);
-        }
-        return;
-    case 0x10: /* ADD, SUB */
-        if (u) {
-            gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_sub, size);
-        } else {
-            gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_add, size);
-        }
-        return;
-    case 0x13: /* MUL, PMUL */
-        if (!u) { /* MUL */
-            gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_mul, size);
-        } else {  /* PMUL */
-            gen_gvec_op3_ool(s, is_q, rd, rn, rm, 0, gen_helper_gvec_pmul_b);
-        }
-        return;
-    case 0x12: /* MLA, MLS */
-        if (u) {
-            gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_mls, size);
-        } else {
-            gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_mla, size);
-        }
-        return;
-    case 0x16: /* SQDMULH, SQRDMULH */
-        {
-            static gen_helper_gvec_3_ptr * const fns[2][2] = {
-                { gen_helper_neon_sqdmulh_h, gen_helper_neon_sqrdmulh_h },
-                { gen_helper_neon_sqdmulh_s, gen_helper_neon_sqrdmulh_s },
-            };
-            gen_gvec_op3_qc(s, is_q, rd, rn, rm, fns[size - 1][u]);
-        }
-        return;
-    case 0x11:
-        if (!u) { /* CMTST */
-            gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_cmtst, size);
-            return;
-        }
-        /* else CMEQ */
-        cond = TCG_COND_EQ;
-        goto do_gvec_cmp;
-    case 0x06: /* CMGT, CMHI */
-        cond = u ? TCG_COND_GTU : TCG_COND_GT;
-        goto do_gvec_cmp;
-    case 0x07: /* CMGE, CMHS */
-        cond = u ? TCG_COND_GEU : TCG_COND_GE;
-    do_gvec_cmp:
-        tcg_gen_gvec_cmp(cond, size, vec_full_reg_offset(s, rd),
-                         vec_full_reg_offset(s, rn),
-                         vec_full_reg_offset(s, rm),
-                         is_q ? 16 : 8, vec_full_reg_size(s));
-        return;
-    }
-
-    if (size == 3) {
-        assert(is_q);
-        for (pass = 0; pass < 2; pass++) {
-            TCGv_i64 tcg_op1 = tcg_temp_new_i64();
-            TCGv_i64 tcg_op2 = tcg_temp_new_i64();
-            TCGv_i64 tcg_res = tcg_temp_new_i64();
-
-            read_vec_element(s, tcg_op1, rn, pass, MO_64);
-            read_vec_element(s, tcg_op2, rm, pass, MO_64);
-
-            handle_3same_64(s, opcode, u, tcg_res, tcg_op1, tcg_op2);
-
-            write_vec_element(s, tcg_res, rd, pass, MO_64);
-        }
-    } else {
-        for (pass = 0; pass < (is_q ? 4 : 2); pass++) {
-            TCGv_i32 tcg_op1 = tcg_temp_new_i32();
-            TCGv_i32 tcg_op2 = tcg_temp_new_i32();
-            TCGv_i32 tcg_res = tcg_temp_new_i32();
-            NeonGenTwoOpFn *genfn = NULL;
-            NeonGenTwoOpEnvFn *genenvfn = NULL;
-
-            read_vec_element_i32(s, tcg_op1, rn, pass, MO_32);
-            read_vec_element_i32(s, tcg_op2, rm, pass, MO_32);
-
-            switch (opcode) {
-            case 0x0: /* SHADD, UHADD */
-            {
-                static NeonGenTwoOpFn * const fns[3][2] = {
-                    { gen_helper_neon_hadd_s8, gen_helper_neon_hadd_u8 },
-                    { gen_helper_neon_hadd_s16, gen_helper_neon_hadd_u16 },
-                    { gen_helper_neon_hadd_s32, gen_helper_neon_hadd_u32 },
-                };
-                genfn = fns[size][u];
-                break;
-            }
-            case 0x2: /* SRHADD, URHADD */
-            {
-                static NeonGenTwoOpFn * const fns[3][2] = {
-                    { gen_helper_neon_rhadd_s8, gen_helper_neon_rhadd_u8 },
-                    { gen_helper_neon_rhadd_s16, gen_helper_neon_rhadd_u16 },
-                    { gen_helper_neon_rhadd_s32, gen_helper_neon_rhadd_u32 },
-                };
-                genfn = fns[size][u];
-                break;
-            }
-            case 0x4: /* SHSUB, UHSUB */
-            {
-                static NeonGenTwoOpFn * const fns[3][2] = {
-                    { gen_helper_neon_hsub_s8, gen_helper_neon_hsub_u8 },
-                    { gen_helper_neon_hsub_s16, gen_helper_neon_hsub_u16 },
-                    { gen_helper_neon_hsub_s32, gen_helper_neon_hsub_u32 },
-                };
-                genfn = fns[size][u];
-                break;
-            }
-            case 0x9: /* SQSHL, UQSHL */
-            {
-                static NeonGenTwoOpEnvFn * const fns[3][2] = {
-                    { gen_helper_neon_qshl_s8, gen_helper_neon_qshl_u8 },
-                    { gen_helper_neon_qshl_s16, gen_helper_neon_qshl_u16 },
-                    { gen_helper_neon_qshl_s32, gen_helper_neon_qshl_u32 },
-                };
-                genenvfn = fns[size][u];
-                break;
-            }
-            case 0xa: /* SRSHL, URSHL */
-            {
-                static NeonGenTwoOpFn * const fns[3][2] = {
-                    { gen_helper_neon_rshl_s8, gen_helper_neon_rshl_u8 },
-                    { gen_helper_neon_rshl_s16, gen_helper_neon_rshl_u16 },
-                    { gen_helper_neon_rshl_s32, gen_helper_neon_rshl_u32 },
-                };
-                genfn = fns[size][u];
-                break;
-            }
-            case 0xb: /* SQRSHL, UQRSHL */
-            {
-                static NeonGenTwoOpEnvFn * const fns[3][2] = {
-                    { gen_helper_neon_qrshl_s8, gen_helper_neon_qrshl_u8 },
-                    { gen_helper_neon_qrshl_s16, gen_helper_neon_qrshl_u16 },
-                    { gen_helper_neon_qrshl_s32, gen_helper_neon_qrshl_u32 },
-                };
-                genenvfn = fns[size][u];
-                break;
-            }
-            default:
-                g_assert_not_reached();
-            }
-
-            if (genenvfn) {
-                genenvfn(tcg_res, tcg_env, tcg_op1, tcg_op2);
-            } else {
-                genfn(tcg_res, tcg_op1, tcg_op2);
-            }
-
-            write_vec_element_i32(s, tcg_res, rd, pass, MO_32);
-        }
-    }
-    clear_vec_high(s, is_q, rd);
-}
-
-/* AdvSIMD three same
- *  31  30  29  28       24 23  22  21 20  16 15    11  10 9    5 4    0
- * +---+---+---+-----------+------+---+------+--------+---+------+------+
- * | 0 | Q | U | 0 1 1 1 0 | size | 1 |  Rm  | opcode | 1 |  Rn  |  Rd  |
- * +---+---+---+-----------+------+---+------+--------+---+------+------+
- */
-static void disas_simd_three_reg_same(DisasContext *s, uint32_t insn)
-{
-    int opcode = extract32(insn, 11, 5);
-
-    switch (opcode) {
-    default:
-        disas_simd_3same_int(s, insn);
-        break;
-    case 0x3: /* logic ops */
-    case 0x14: /* SMAXP, UMAXP */
-    case 0x15: /* SMINP, UMINP */
-    case 0x17: /* ADDP */
-    case 0x18 ... 0x31: /* floating point ops */
-        unallocated_encoding(s);
-        break;
-    }
-}
-
 /* AdvSIMD three same extra
  *  31   30  29 28       24 23  22  21 20  16  15 14    11  10 9  5 4  0
  * +---+---+---+-----------+------+---+------+---+--------+---+----+----+
@@ -11683,16 +11359,6 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn)
             return;
         }
         break;
-    case 0x3: /* SUQADD, USQADD */
-        if (size == 3 && !is_q) {
-            unallocated_encoding(s);
-            return;
-        }
-        if (!fp_access_check(s)) {
-            return;
-        }
-        handle_2misc_satacc(s, false, u, is_q, size, rn, rd);
-        return;
     case 0x7: /* SQABS, SQNEG */
         if (size == 3 && !is_q) {
             unallocated_encoding(s);
@@ -11867,6 +11533,7 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn)
         break;
     }
     default:
+    case 0x3: /* SUQADD, USQADD */
         unallocated_encoding(s);
         return;
     }
@@ -12375,14 +12042,6 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn)
     TCGv_ptr fpst;
 
     switch (16 * u + opcode) {
-    case 0x08: /* MUL */
-    case 0x10: /* MLA */
-    case 0x14: /* MLS */
-        if (is_scalar) {
-            unallocated_encoding(s);
-            return;
-        }
-        break;
     case 0x02: /* SMLAL, SMLAL2 */
     case 0x12: /* UMLAL, UMLAL2 */
     case 0x06: /* SMLSL, SMLSL2 */
@@ -12400,9 +12059,6 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn)
     case 0x0b: /* SQDMULL, SQDMULL2 */
         is_long = true;
         break;
-    case 0x0c: /* SQDMULH */
-    case 0x0d: /* SQRDMULH */
-        break;
     case 0x1d: /* SQRDMLAH */
     case 0x1f: /* SQRDMLSH */
         if (!dc_isar_feature(aa64_rdm, s)) {
@@ -12462,7 +12118,12 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn)
     case 0x01: /* FMLA */
     case 0x04: /* FMLSL */
     case 0x05: /* FMLS */
+    case 0x08: /* MUL */
     case 0x09: /* FMUL */
+    case 0x0c: /* SQDMULH */
+    case 0x0d: /* SQRDMULH */
+    case 0x10: /* MLA */
+    case 0x14: /* MLS */
     case 0x18: /* FMLAL2 */
     case 0x19: /* FMULX */
     case 0x1c: /* FMLSL2 */
@@ -12583,56 +12244,6 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn)
                                : gen_helper_gvec_fcmlah_idx);
         }
         return;
-
-    case 0x08: /* MUL */
-        if (!is_long && !is_scalar) {
-            static gen_helper_gvec_3 * const fns[3] = {
-                gen_helper_gvec_mul_idx_h,
-                gen_helper_gvec_mul_idx_s,
-                gen_helper_gvec_mul_idx_d,
-            };
-            tcg_gen_gvec_3_ool(vec_full_reg_offset(s, rd),
-                               vec_full_reg_offset(s, rn),
-                               vec_full_reg_offset(s, rm),
-                               is_q ? 16 : 8, vec_full_reg_size(s),
-                               index, fns[size - 1]);
-            return;
-        }
-        break;
-
-    case 0x10: /* MLA */
-        if (!is_long && !is_scalar) {
-            static gen_helper_gvec_4 * const fns[3] = {
-                gen_helper_gvec_mla_idx_h,
-                gen_helper_gvec_mla_idx_s,
-                gen_helper_gvec_mla_idx_d,
-            };
-            tcg_gen_gvec_4_ool(vec_full_reg_offset(s, rd),
-                               vec_full_reg_offset(s, rn),
-                               vec_full_reg_offset(s, rm),
-                               vec_full_reg_offset(s, rd),
-                               is_q ? 16 : 8, vec_full_reg_size(s),
-                               index, fns[size - 1]);
-            return;
-        }
-        break;
-
-    case 0x14: /* MLS */
-        if (!is_long && !is_scalar) {
-            static gen_helper_gvec_4 * const fns[3] = {
-                gen_helper_gvec_mls_idx_h,
-                gen_helper_gvec_mls_idx_s,
-                gen_helper_gvec_mls_idx_d,
-            };
-            tcg_gen_gvec_4_ool(vec_full_reg_offset(s, rd),
-                               vec_full_reg_offset(s, rn),
-                               vec_full_reg_offset(s, rm),
-                               vec_full_reg_offset(s, rd),
-                               is_q ? 16 : 8, vec_full_reg_size(s),
-                               index, fns[size - 1]);
-            return;
-        }
-        break;
     }
 
     if (size == 3) {
@@ -12668,7 +12279,6 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn)
             read_vec_element_i32(s, tcg_op, rn, pass, is_scalar ? size : MO_32);
 
             switch (16 * u + opcode) {
-            case 0x08: /* MUL */
             case 0x10: /* MLA */
             case 0x14: /* MLS */
             {
@@ -12917,7 +12527,6 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn)
  */
 static const AArch64DecodeTable data_proc_simd[] = {
     /* pattern  ,  mask     ,  fn                        */
-    { 0x0e200400, 0x9f200400, disas_simd_three_reg_same },
     { 0x0e008400, 0x9f208400, disas_simd_three_reg_same_extra },
     { 0x0e200000, 0x9f200c00, disas_simd_three_reg_diff },
     { 0x0e200800, 0x9f3e0c00, disas_simd_two_reg_misc },
@@ -12929,7 +12538,6 @@ static const AArch64DecodeTable data_proc_simd[] = {
     { 0x0e000000, 0xbf208c00, disas_simd_tb },
     { 0x0e000800, 0xbf208c00, disas_simd_zip_trn },
     { 0x2e000000, 0xbf208400, disas_simd_ext },
-    { 0x5e200400, 0xdf200400, disas_simd_scalar_three_reg_same },
     { 0x5e008400, 0xdf208400, disas_simd_scalar_three_reg_same_extra },
     { 0x5e200000, 0xdf200c00, disas_simd_scalar_three_reg_diff },
     { 0x5e200800, 0xdf3e0c00, disas_simd_scalar_two_reg_misc },