[Qemu-devel] [PATCH v3 07/40] s390x/tcg: Implement VECTOR AVERAGE LOGICAL

[David Hildenbrand <david@redhat.com>]

Similar to VECTOR AVERAGE but without sign extension.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: David Hildenbrand <david@redhat.com>
---
 target/s390x/helper.h           |  2 ++
 target/s390x/insn-data.def      |  2 ++
 target/s390x/translate_vx.inc.c | 48 +++++++++++++++++++++++++++++++++
 target/s390x/vec_int_helper.c   | 16 +++++++++++
 4 files changed, 68 insertions(+)

diff --git a/target/s390x/helper.h b/target/s390x/helper.h
index add1d332e5..21921397fe 100644
--- a/target/s390x/helper.h
+++ b/target/s390x/helper.h
@@ -148,6 +148,8 @@ DEF_HELPER_FLAGS_4(vstl, TCG_CALL_NO_WG, void, env, cptr, i64, i64)
 /* === Vector Integer Instructions === */
 DEF_HELPER_FLAGS_4(gvec_vavg8, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
 DEF_HELPER_FLAGS_4(gvec_vavg16, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_4(gvec_vavgl8, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_4(gvec_vavgl16, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
 
 #ifndef CONFIG_USER_ONLY
 DEF_HELPER_3(servc, i32, env, i64, i64)
diff --git a/target/s390x/insn-data.def b/target/s390x/insn-data.def
index 6f8b42e327..9889dc0b01 100644
--- a/target/s390x/insn-data.def
+++ b/target/s390x/insn-data.def
@@ -1070,6 +1070,8 @@
     F(0xe769, VNC,     VRR_c, V,   0, 0, 0, 0, vnc, 0, IF_VEC)
 /* VECTOR AVERAGE */
     F(0xe7f2, VAVG,    VRR_c, V,   0, 0, 0, 0, vavg, 0, IF_VEC)
+/* VECTOR AVERAGE LOGICAL */
+    F(0xe7f0, VAVGL,   VRR_c, V,   0, 0, 0, 0, vavgl, 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 5108025506..7e8418e585 100644
--- a/target/s390x/translate_vx.inc.c
+++ b/target/s390x/translate_vx.inc.c
@@ -1252,3 +1252,51 @@ static DisasJumpType op_vavg(DisasContext *s, DisasOps *o)
                get_field(s->fields, v3), &g[es]);
     return DISAS_NEXT;
 }
+
+static void gen_avgl_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b)
+{
+    TCGv_i64 t0 = tcg_temp_new_i64();
+    TCGv_i64 t1 = tcg_temp_new_i64();
+
+    tcg_gen_extu_i32_i64(t0, a);
+    tcg_gen_extu_i32_i64(t1, b);
+    tcg_gen_add_i64(t0, t0, t1);
+    tcg_gen_addi_i64(t0, t0, 1);
+    tcg_gen_shri_i64(t0, t0, 1);
+    tcg_gen_extrl_i64_i32(d, t0);
+
+    tcg_temp_free(t0);
+    tcg_temp_free(t1);
+}
+
+static void gen_avgl_i64(TCGv_i64 dl, TCGv_i64 al, TCGv_i64 bl)
+{
+    TCGv_i64 dh = tcg_temp_new_i64();
+    TCGv_i64 zero = tcg_const_i64(0);
+
+    tcg_gen_add2_i64(dl, dh, al, zero, bl, zero);
+    gen_addi2_i64(dl, dh, dl, dh, 1);
+    tcg_gen_extract2_i64(dl, dl, dh, 1);
+
+    tcg_temp_free_i64(dh);
+    tcg_temp_free_i64(zero);
+}
+
+static DisasJumpType op_vavgl(DisasContext *s, DisasOps *o)
+{
+    const uint8_t es = get_field(s->fields, m4);
+    static const GVecGen3 g[4] = {
+        { .fno = gen_helper_gvec_vavgl8, },
+        { .fno = gen_helper_gvec_vavgl16, },
+        { .fni4 = gen_avgl_i32, },
+        { .fni8 = gen_avgl_i64, },
+    };
+
+    if (es > ES_64) {
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return DISAS_NORETURN;
+    }
+    gen_gvec_3(get_field(s->fields, v1), get_field(s->fields, v2),
+               get_field(s->fields, v3), &g[es]);
+    return DISAS_NEXT;
+}
diff --git a/target/s390x/vec_int_helper.c b/target/s390x/vec_int_helper.c
index d964655bb8..8f97d3f466 100644
--- a/target/s390x/vec_int_helper.c
+++ b/target/s390x/vec_int_helper.c
@@ -30,3 +30,19 @@ void HELPER(gvec_vavg##BITS)(void *v1, const void *v2, const void *v3,         \
 }
 DEF_VAVG(8)
 DEF_VAVG(16)
+
+#define DEF_VAVGL(BITS)                                                        \
+void HELPER(gvec_vavgl##BITS)(void *v1, const void *v2, const void *v3,        \
+                              uint32_t desc)                                   \
+{                                                                              \
+    int i;                                                                     \
+                                                                               \
+    for (i = 0; i < (128 / BITS); i++) {                                       \
+        const uint##BITS##_t a = s390_vec_read_element##BITS(v2, i);           \
+        const uint##BITS##_t b = s390_vec_read_element##BITS(v3, i);           \
+                                                                               \
+        s390_vec_write_element##BITS(v1, i, (a + b + 1) >> 1);                 \
+    }                                                                          \
+}
+DEF_VAVGL(8)
+DEF_VAVGL(16)
-- 
2.20.1