On 17 February 2018 at 18:23, Richard Henderson
<[email protected]> wrote:
> Signed-off-by: Richard Henderson <[email protected]>
> ---
> target/arm/helper-sve.h | 5 +++++
> target/arm/sve_helper.c | 43 ++++++++++++++++++++++++++++++++++++
> target/arm/translate-sve.c | 55
> +++++++++++++++++++++++++++++++++++++++++++++-
> target/arm/sve.decode | 5 +++++
> 4 files changed, 107 insertions(+), 1 deletion(-)
>
>
> +/* Load and broadcast element. */
> +static void trans_LD1R_zpri(DisasContext *s, arg_rpri_load *a, uint32_t insn)
> +{
> + unsigned vsz = vec_full_reg_size(s);
> + unsigned psz = pred_full_reg_size(s);
> + unsigned esz = dtype_esz[a->dtype];
> + TCGLabel *over = gen_new_label();
> + TCGv_i64 temp;
> +
> + /* If the guarding predicate has no bits set, no load occurs. */
> + if (psz <= 8) {
> + temp = tcg_temp_new_i64();
> + tcg_gen_ld_i64(temp, cpu_env, pred_full_reg_offset(s, a->pg));
> + tcg_gen_andi_i64(temp, temp,
> + deposit64(0, 0, psz * 8, pred_esz_masks[esz]));
> + tcg_gen_brcondi_i64(TCG_COND_EQ, temp, 0, over);
> + tcg_temp_free_i64(temp);
> + } else {
> + TCGv_i32 t32 = tcg_temp_new_i32();
> + find_last_active(s, t32, esz, a->pg);
> + tcg_gen_brcondi_i32(TCG_COND_LT, t32, 0, over);
> + tcg_temp_free_i32(t32);
> + }
> +
> + /* Load the data. */
> + temp = tcg_temp_new_i64();
> + tcg_gen_addi_i64(temp, cpu_reg_sp(s, a->rn), a->imm);
Isn't the immediate offset supposed to be scaled by mbytes ?
> + tcg_gen_qemu_ld_i64(temp, temp, get_mem_index(s),
> + s->be_data | dtype_mop[a->dtype]);
> +
> + /* Broadcast to *all* elements. */
> + tcg_gen_gvec_dup_i64(esz, vec_full_reg_offset(s, a->rd),
> + vsz, vsz, temp);
> + tcg_temp_free_i64(temp);
> +
> + /* Zero the inactive elements. */
> + gen_set_label(over);
> + do_clr_inactive_zp(s, a->rd, a->pg, esz);
> +}
> +
Otherwise
Reviewed-by: Peter Maydell <[email protected]>
thanks
-- PMM
