[Qemu-devel] [PULL 39/54] s390x/tcg: Implement VECTOR SUBTRACT COMPUTE BORROW INDICATION

[Cornelia Huck <cohuck@redhat.com>]

From: David Hildenbrand <david@redhat.com>

Let's keep it simple for now and handle 8/16 bit elements via helpers.
Especially for 8/16, we could come up with some bit tricks.

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 | 52 +++++++++++++++++++++++++++++++++
 target/s390x/vec_int_helper.c   | 16 ++++++++++
 4 files changed, 72 insertions(+)

diff --git a/target/s390x/helper.h b/target/s390x/helper.h
index 0f411f2346fb..2cb1f369bd86 100644
--- a/target/s390x/helper.h
+++ b/target/s390x/helper.h
@@ -207,6 +207,8 @@ DEF_HELPER_FLAGS_4(gvec_verim16, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
 DEF_HELPER_FLAGS_4(gvec_vsl, TCG_CALL_NO_RWG, void, ptr, cptr, i64, i32)
 DEF_HELPER_FLAGS_4(gvec_vsra, TCG_CALL_NO_RWG, void, ptr, cptr, i64, i32)
 DEF_HELPER_FLAGS_4(gvec_vsrl, TCG_CALL_NO_RWG, void, ptr, cptr, i64, i32)
+DEF_HELPER_FLAGS_4(gvec_vscbi8, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_4(gvec_vscbi16, 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 58a61f41efeb..94de3c9c7d30 100644
--- a/target/s390x/insn-data.def
+++ b/target/s390x/insn-data.def
@@ -1176,6 +1176,8 @@
     F(0xe77d, VSRLB,   VRR_c, V,   0, 0, 0, 0, vsrl, 0, IF_VEC)
 /* VECTOR SUBTRACT */
     F(0xe7f7, VS,      VRR_c, V,   0, 0, 0, 0, vs, 0, IF_VEC)
+/* VECTOR SUBTRACT COMPUTE BORROW INDICATION */
+    F(0xe7f5, VSCBI,   VRR_c, V,   0, 0, 0, 0, vscbi, 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 5f53ae7ec546..b7052f73f8a5 100644
--- a/target/s390x/translate_vx.inc.c
+++ b/target/s390x/translate_vx.inc.c
@@ -2140,3 +2140,55 @@ static DisasJumpType op_vs(DisasContext *s, DisasOps *o)
                   get_field(s->fields, v3));
     return DISAS_NEXT;
 }
+
+static void gen_scbi_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b)
+{
+    tcg_gen_setcond_i32(TCG_COND_LTU, d, a, b);
+}
+
+static void gen_scbi_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b)
+{
+    tcg_gen_setcond_i64(TCG_COND_LTU, d, a, b);
+}
+
+static void gen_scbi2_i64(TCGv_i64 dl, TCGv_i64 dh, TCGv_i64 al,
+                          TCGv_i64 ah, TCGv_i64 bl, TCGv_i64 bh)
+{
+    TCGv_i64 th = tcg_temp_new_i64();
+    TCGv_i64 tl = tcg_temp_new_i64();
+    TCGv_i64 zero = tcg_const_i64(0);
+
+    tcg_gen_sub2_i64(tl, th, al, zero, bl, zero);
+    tcg_gen_andi_i64(th, th, 1);
+    tcg_gen_sub2_i64(tl, th, ah, zero, th, zero);
+    tcg_gen_sub2_i64(tl, th, tl, th, bh, zero);
+    tcg_gen_andi_i64(dl, th, 1);
+    tcg_gen_mov_i64(dh, zero);
+
+    tcg_temp_free_i64(th);
+    tcg_temp_free_i64(tl);
+    tcg_temp_free_i64(zero);
+}
+
+static DisasJumpType op_vscbi(DisasContext *s, DisasOps *o)
+{
+    const uint8_t es = get_field(s->fields, m4);
+    static const GVecGen3 g[4] = {
+        { .fno = gen_helper_gvec_vscbi8, },
+        { .fno = gen_helper_gvec_vscbi16, },
+        { .fni4 = gen_scbi_i32, },
+        { .fni8 = gen_scbi_i64, },
+    };
+
+    if (es > ES_128) {
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return DISAS_NORETURN;
+    } else if (es == ES_128) {
+        gen_gvec128_3_i64(gen_scbi2_i64, get_field(s->fields, v1),
+                          get_field(s->fields, v2), get_field(s->fields, v3));
+        return DISAS_NEXT;
+    }
+    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 06f8bfa30dda..09137dab996f 100644
--- a/target/s390x/vec_int_helper.c
+++ b/target/s390x/vec_int_helper.c
@@ -567,3 +567,19 @@ void HELPER(gvec_vsrl)(void *v1, const void *v2, uint64_t count,
 {
     s390_vec_shr(v1, v2, count);
 }
+
+#define DEF_VSCBI(BITS)                                                        \
+void HELPER(gvec_vscbi##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);                            \
+    }                                                                          \
+}
+DEF_VSCBI(8)
+DEF_VSCBI(16)
-- 
2.20.1