Commit 8dc69a19 authored by David Hildenbrand's avatar David Hildenbrand
Browse files

s390x/tcg: Implement VECTOR SUM ACROSS QUADWORD



Similar to VECTOR SUM ACROSS DOUBLEWORD, however without a loop and
using 128-bit calculations.

Reviewed-by: default avatarRichard Henderson <richard.henderson@linaro.org>
Signed-off-by: default avatarDavid Hildenbrand <david@redhat.com>
parent fe2be36d
Loading
Loading
Loading
Loading
+2 −0
Original line number Diff line number Diff line
@@ -1184,6 +1184,8 @@
    F(0xe7bd, VSBCBI,  VRR_d, V,   0, 0, 0, 0, vsbcbi, 0, IF_VEC)
/* VECTOR SUM ACROSS DOUBLEWORD */
    F(0xe765, VSUMG,   VRR_c, V,   0, 0, 0, 0, vsumg, 0, IF_VEC)
/* VECTOR SUM ACROSS QUADWORD */
    F(0xe767, VSUMQ,   VRR_c, V,   0, 0, 0, 0, vsumq, 0, IF_VEC)

#ifndef CONFIG_USER_ONLY
/* COMPARE AND SWAP AND PURGE */
+32 −0
Original line number Diff line number Diff line
@@ -2281,3 +2281,35 @@ static DisasJumpType op_vsumg(DisasContext *s, DisasOps *o)
    tcg_temp_free_i64(tmp);
    return DISAS_NEXT;
}

static DisasJumpType op_vsumq(DisasContext *s, DisasOps *o)
{
    const uint8_t es = get_field(s->fields, m4);
    const uint8_t max_idx = NUM_VEC_ELEMENTS(es) - 1;
    TCGv_i64 sumh, suml, zero, tmpl;
    uint8_t idx;

    if (es < ES_32 || es > ES_64) {
        gen_program_exception(s, PGM_SPECIFICATION);
        return DISAS_NORETURN;
    }

    sumh = tcg_const_i64(0);
    suml = tcg_temp_new_i64();
    zero = tcg_const_i64(0);
    tmpl = tcg_temp_new_i64();

    read_vec_element_i64(suml, get_field(s->fields, v3), max_idx, es);
    for (idx = 0; idx <= max_idx; idx++) {
        read_vec_element_i64(tmpl, get_field(s->fields, v2), idx, es);
        tcg_gen_add2_i64(suml, sumh, suml, sumh, tmpl, zero);
    }
    write_vec_element_i64(sumh, get_field(s->fields, v1), 0, ES_64);
    write_vec_element_i64(suml, get_field(s->fields, v1), 1, ES_64);

    tcg_temp_free_i64(sumh);
    tcg_temp_free_i64(suml);
    tcg_temp_free_i64(zero);
    tcg_temp_free_i64(tmpl);
    return DISAS_NEXT;
}