[Qemu-devel] [PATCH v3 37/40] s390x/tcg: Implement VECTOR SUM ACROSS DOUBLEWORD

[David Hildenbrand <david@redhat.com>]

Perform the calculations without a helper. Only 16 bit or 32 bit values
have to be added.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: David Hildenbrand <david@redhat.com>
---
 target/s390x/insn-data.def      |  2 ++
 target/s390x/translate_vx.inc.c | 29 +++++++++++++++++++++++++++++
 2 files changed, 31 insertions(+)

diff --git a/target/s390x/insn-data.def b/target/s390x/insn-data.def
index a8d90517f6..dd37003082 100644
--- a/target/s390x/insn-data.def
+++ b/target/s390x/insn-data.def
@@ -1182,6 +1182,8 @@
     F(0xe7bf, VSBI,    VRR_d, V,   0, 0, 0, 0, vsbi, 0, IF_VEC)
 /* VECTOR SUBTRACT WITH BORROW COMPUTE BORROW INDICATION */
     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)
 
 #ifndef CONFIG_USER_ONLY
 /* COMPARE AND SWAP AND PURGE */
diff --git a/target/s390x/translate_vx.inc.c b/target/s390x/translate_vx.inc.c
index b0b4d3640e..5e948ecff1 100644
--- a/target/s390x/translate_vx.inc.c
+++ b/target/s390x/translate_vx.inc.c
@@ -2248,3 +2248,32 @@ static DisasJumpType op_vsbcbi(DisasContext *s, DisasOps *o)
                       get_field(s->fields, v4));
     return DISAS_NEXT;
 }
+
+static DisasJumpType op_vsumg(DisasContext *s, DisasOps *o)
+{
+    const uint8_t es = get_field(s->fields, m4);
+    TCGv_i64 sum, tmp;
+    uint8_t dst_idx;
+
+    if (es == ES_8 || es > ES_32) {
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return DISAS_NORETURN;
+    }
+
+    sum = tcg_temp_new_i64();
+    tmp = tcg_temp_new_i64();
+    for (dst_idx = 0; dst_idx < 2; dst_idx++) {
+        uint8_t idx = dst_idx * NUM_VEC_ELEMENTS(es) / 2;
+        const uint8_t max_idx = idx + NUM_VEC_ELEMENTS(es) / 2 - 1;
+
+        read_vec_element_i64(sum, get_field(s->fields, v3), max_idx, es);
+        for (; idx <= max_idx; idx++) {
+            read_vec_element_i64(tmp, get_field(s->fields, v2), idx, es);
+            tcg_gen_add_i64(sum, sum, tmp);
+        }
+        write_vec_element_i64(sum, get_field(s->fields, v1), dst_idx, ES_64);
+    }
+    tcg_temp_free_i64(sum);
+    tcg_temp_free_i64(tmp);
+    return DISAS_NEXT;
+}
-- 
2.20.1