[Qemu-devel] [PULL 04/35] s390x/tcg: Implement VECTOR FIND ELEMENT EQUAL

[Cornelia Huck <cohuck@redhat.com>]

From: David Hildenbrand <david@redhat.com>

Core logic courtesy of Richard H.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: David Hildenbrand <david@redhat.com>
---
 target/s390x/helper.h            |  6 ++++
 target/s390x/insn-data.def       |  2 ++
 target/s390x/translate_vx.inc.c  | 31 +++++++++++++++++
 target/s390x/vec_string_helper.c | 57 ++++++++++++++++++++++++++++++++
 4 files changed, 96 insertions(+)

diff --git a/target/s390x/helper.h b/target/s390x/helper.h
index c45328cf73c1..a1b169b666e9 100644
--- a/target/s390x/helper.h
+++ b/target/s390x/helper.h
@@ -218,6 +218,12 @@ DEF_HELPER_FLAGS_4(gvec_vfae32, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
 DEF_HELPER_5(gvec_vfae_cc8, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_5(gvec_vfae_cc16, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_5(gvec_vfae_cc32, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_4(gvec_vfee8, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_4(gvec_vfee16, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_4(gvec_vfee32, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
+DEF_HELPER_5(gvec_vfee_cc8, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_5(gvec_vfee_cc16, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_5(gvec_vfee_cc32, void, ptr, cptr, cptr, env, 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 070ce2a471e0..d8907ef6a575 100644
--- a/target/s390x/insn-data.def
+++ b/target/s390x/insn-data.def
@@ -1195,6 +1195,8 @@
 
 /* VECTOR FIND ANY ELEMENT EQUAL */
     F(0xe782, VFAE,    VRR_b, V,   0, 0, 0, 0, vfae, 0, IF_VEC)
+/* VECTOR FIND ELEMENT EQUAL */
+    F(0xe780, VFEE,    VRR_b, V,   0, 0, 0, 0, vfee, 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 ebd7a877f17d..b25afbc011b3 100644
--- a/target/s390x/translate_vx.inc.c
+++ b/target/s390x/translate_vx.inc.c
@@ -2383,3 +2383,34 @@ static DisasJumpType op_vfae(DisasContext *s, DisasOps *o)
     }
     return DISAS_NEXT;
 }
+
+static DisasJumpType op_vfee(DisasContext *s, DisasOps *o)
+{
+    const uint8_t es = get_field(s->fields, m4);
+    const uint8_t m5 = get_field(s->fields, m5);
+    static gen_helper_gvec_3 * const g[3] = {
+        gen_helper_gvec_vfee8,
+        gen_helper_gvec_vfee16,
+        gen_helper_gvec_vfee32,
+    };
+    static gen_helper_gvec_3_ptr * const g_cc[3] = {
+        gen_helper_gvec_vfee_cc8,
+        gen_helper_gvec_vfee_cc16,
+        gen_helper_gvec_vfee_cc32,
+    };
+
+    if (es > ES_32 || m5 & ~0x3) {
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return DISAS_NORETURN;
+    }
+
+    if (extract32(m5, 0, 1)) {
+        gen_gvec_3_ptr(get_field(s->fields, v1), get_field(s->fields, v2),
+                       get_field(s->fields, v3), cpu_env, m5, g_cc[es]);
+        set_cc_static(s);
+    } else {
+        gen_gvec_3_ool(get_field(s->fields, v1), get_field(s->fields, v2),
+                       get_field(s->fields, v3), m5, g[es]);
+    }
+    return DISAS_NEXT;
+}
diff --git a/target/s390x/vec_string_helper.c b/target/s390x/vec_string_helper.c
index 56dc89c824de..05ad99e17360 100644
--- a/target/s390x/vec_string_helper.c
+++ b/target/s390x/vec_string_helper.c
@@ -152,3 +152,60 @@ void HELPER(gvec_vfae_cc##BITS)(void *v1, const void *v2, const void *v3,      \
 DEF_VFAE_CC_HELPER(8)
 DEF_VFAE_CC_HELPER(16)
 DEF_VFAE_CC_HELPER(32)
+
+static int vfee(void *v1, const void *v2, const void *v3, bool zs, uint8_t es)
+{
+    const uint64_t mask = get_element_lsbs_mask(es);
+    uint64_t a0, a1, b0, b1, e0, e1, z0, z1;
+    uint64_t first_zero = 16;
+    uint64_t first_equal;
+
+    a0 = s390_vec_read_element64(v2, 0);
+    a1 = s390_vec_read_element64(v2, 1);
+    b0 = s390_vec_read_element64(v3, 0);
+    b1 = s390_vec_read_element64(v3, 1);
+    e0 = zero_search(a0 ^ b0, mask);
+    e1 = zero_search(a1 ^ b1, mask);
+    first_equal = match_index(e0, e1);
+
+    if (zs) {
+        z0 = zero_search(a0, mask);
+        z1 = zero_search(a1, mask);
+        first_zero = match_index(z0, z1);
+    }
+
+    s390_vec_write_element64(v1, 0, MIN(first_equal, first_zero));
+    s390_vec_write_element64(v1, 1, 0);
+    if (first_zero == 16 && first_equal == 16) {
+        return 3; /* no match */
+    } else if (first_zero == 16) {
+        return 1; /* matching elements, no match for zero */
+    } else if (first_equal < first_zero) {
+        return 2; /* matching elements before match for zero */
+    }
+    return 0; /* match for zero */
+}
+
+#define DEF_VFEE_HELPER(BITS)                                                  \
+void HELPER(gvec_vfee##BITS)(void *v1, const void *v2, const void *v3,         \
+                             uint32_t desc)                                    \
+{                                                                              \
+    const bool zs = extract32(simd_data(desc), 1, 1);                          \
+                                                                               \
+    vfee(v1, v2, v3, zs, MO_##BITS);                                           \
+}
+DEF_VFEE_HELPER(8)
+DEF_VFEE_HELPER(16)
+DEF_VFEE_HELPER(32)
+
+#define DEF_VFEE_CC_HELPER(BITS)                                               \
+void HELPER(gvec_vfee_cc##BITS)(void *v1, const void *v2, const void *v3,      \
+                                CPUS390XState *env, uint32_t desc)             \
+{                                                                              \
+    const bool zs = extract32(simd_data(desc), 1, 1);                          \
+                                                                               \
+    env->cc_op = vfee(v1, v2, v3, zs, MO_##BITS);                              \
+}
+DEF_VFEE_CC_HELPER(8)
+DEF_VFEE_CC_HELPER(16)
+DEF_VFEE_CC_HELPER(32)
-- 
2.20.1