[Qemu-devel] [PULL SUBSYSTEM s390x 39/40] s390x/tcg: Implement VECTOR SUM ACROSS WORD

[David Hildenbrand <david@redhat.com>]

Similar to VECTOR SUM ACROSS DOUBLEWORD.

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 2483ee01d7..a52db41388 100644
--- a/target/s390x/insn-data.def
+++ b/target/s390x/insn-data.def
@@ -1186,6 +1186,8 @@
     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)
+/* VECTOR SUM ACROSS WORD */
+    F(0xe764, VSUM,    VRR_c, V,   0, 0, 0, 0, vsum, 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 16bfbfce57..52ab8562e6 100644
--- a/target/s390x/translate_vx.inc.c
+++ b/target/s390x/translate_vx.inc.c
@@ -2313,3 +2313,32 @@ static DisasJumpType op_vsumq(DisasContext *s, DisasOps *o)
     tcg_temp_free_i64(tmpl);
     return DISAS_NEXT;
 }
+
+static DisasJumpType op_vsum(DisasContext *s, DisasOps *o)
+{
+    const uint8_t es = get_field(s->fields, m4);
+    TCGv_i32 sum, tmp;
+    uint8_t dst_idx;
+
+    if (es > ES_16) {
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return DISAS_NORETURN;
+    }
+
+    sum = tcg_temp_new_i32();
+    tmp = tcg_temp_new_i32();
+    for (dst_idx = 0; dst_idx < 4; dst_idx++) {
+        uint8_t idx = dst_idx * NUM_VEC_ELEMENTS(es) / 4;
+        const uint8_t max_idx = idx + NUM_VEC_ELEMENTS(es) / 4 - 1;
+
+        read_vec_element_i32(sum, get_field(s->fields, v3), max_idx, es);
+        for (; idx <= max_idx; idx++) {
+            read_vec_element_i32(tmp, get_field(s->fields, v2), idx, es);
+            tcg_gen_add_i32(sum, sum, tmp);
+        }
+        write_vec_element_i32(sum, get_field(s->fields, v1), dst_idx, ES_32);
+    }
+    tcg_temp_free_i32(sum);
+    tcg_temp_free_i32(tmp);
+    return DISAS_NEXT;
+}
-- 
2.20.1