[PULL 13/37] s390x/tcg: Implement VECTOR MULTIPLY SUM LOGICAL

[Cornelia Huck <cohuck@redhat.com>]

From: David Hildenbrand <david@redhat.com>

Fortunately, we only need the Doubleword implementation.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: David Hildenbrand <david@redhat.com>
Message-Id: <20210608092337.12221-13-david@redhat.com>
Signed-off-by: Cornelia Huck <cohuck@redhat.com>
---
 target/s390x/insn-data.def      |  2 ++
 target/s390x/translate_vx.c.inc | 50 +++++++++++++++++++++++++++++++++
 2 files changed, 52 insertions(+)

diff --git a/target/s390x/insn-data.def b/target/s390x/insn-data.def
index 1634a6bc5aec..1a3ae7e7e77d 100644
--- a/target/s390x/insn-data.def
+++ b/target/s390x/insn-data.def
@@ -1151,6 +1151,8 @@
     F(0xe7a7, VMO,     VRR_c, V,   0, 0, 0, 0, vm, 0, IF_VEC)
 /* VECTOR MULTIPLY LOGICAL ODD */
     F(0xe7a5, VMLO,    VRR_c, V,   0, 0, 0, 0, vm, 0, IF_VEC)
+/* VECTOR MULTIPLY SUM LOGICAL */
+    F(0xe7b8, VMSL,    VRR_d, VE,  0, 0, 0, 0, vmsl, 0, IF_VEC)
 /* VECTOR NAND */
     F(0xe76e, VNN,     VRR_c, VE,  0, 0, 0, 0, vnn, 0, IF_VEC)
 /* VECTOR NOR */
diff --git a/target/s390x/translate_vx.c.inc b/target/s390x/translate_vx.c.inc
index 96283d4ddb9a..6e75b40eb8ec 100644
--- a/target/s390x/translate_vx.c.inc
+++ b/target/s390x/translate_vx.c.inc
@@ -1779,6 +1779,56 @@ static DisasJumpType op_vm(DisasContext *s, DisasOps *o)
     return DISAS_NEXT;
 }
 
+static DisasJumpType op_vmsl(DisasContext *s, DisasOps *o)
+{
+    TCGv_i64 l1, h1, l2, h2;
+
+    if (get_field(s, m4) != ES_64) {
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return DISAS_NORETURN;
+    }
+
+    l1 = tcg_temp_new_i64();
+    h1 = tcg_temp_new_i64();
+    l2 = tcg_temp_new_i64();
+    h2 = tcg_temp_new_i64();
+
+    /* Multipy both even elements from v2 and v3 */
+    read_vec_element_i64(l1, get_field(s, v2), 0, ES_64);
+    read_vec_element_i64(h1, get_field(s, v3), 0, ES_64);
+    tcg_gen_mulu2_i64(l1, h1, l1, h1);
+    /* Shift result left by one (x2) if requested */
+    if (extract32(get_field(s, m6), 3, 1)) {
+        tcg_gen_add2_i64(l1, h1, l1, h1, l1, h1);
+    }
+
+    /* Multipy both odd elements from v2 and v3 */
+    read_vec_element_i64(l2, get_field(s, v2), 1, ES_64);
+    read_vec_element_i64(h2, get_field(s, v3), 1, ES_64);
+    tcg_gen_mulu2_i64(l2, h2, l2, h2);
+    /* Shift result left by one (x2) if requested */
+    if (extract32(get_field(s, m6), 2, 1)) {
+        tcg_gen_add2_i64(l2, h2, l2, h2, l2, h2);
+    }
+
+    /* Add both intermediate results */
+    tcg_gen_add2_i64(l1, h1, l1, h1, l2, h2);
+    /* Add whole v4 */
+    read_vec_element_i64(h2, get_field(s, v4), 0, ES_64);
+    read_vec_element_i64(l2, get_field(s, v4), 1, ES_64);
+    tcg_gen_add2_i64(l1, h1, l1, h1, l2, h2);
+
+    /* Store final result into v1. */
+    write_vec_element_i64(h1, get_field(s, v1), 0, ES_64);
+    write_vec_element_i64(l1, get_field(s, v1), 1, ES_64);
+
+    tcg_temp_free_i64(l1);
+    tcg_temp_free_i64(h1);
+    tcg_temp_free_i64(l2);
+    tcg_temp_free_i64(h2);
+    return DISAS_NEXT;
+}
+
 static DisasJumpType op_vnn(DisasContext *s, DisasOps *o)
 {
     gen_gvec_fn_3(nand, ES_8, get_field(s, v1),
-- 
2.31.1