s390x/tcg: Implement VECTOR POPULATION COUNT

Similar to VECTOR COUNT TRAILING ZEROES.
Reviewed-by: NRichard Henderson <richard.henderson@linaro.org>
Signed-off-by: NDavid Hildenbrand <david@redhat.com>

target/s390x/helper.h

@@ -196,6 +196,8 @@ DEF_HELPER_FLAGS_4(gvec_vmo32, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
 DEF_HELPER_FLAGS_4(gvec_vmlo8, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
 DEF_HELPER_FLAGS_4(gvec_vmlo16, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
 DEF_HELPER_FLAGS_4(gvec_vmlo32, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_3(gvec_vpopct8, TCG_CALL_NO_RWG, void, ptr, cptr, i32)
+DEF_HELPER_FLAGS_3(gvec_vpopct16, TCG_CALL_NO_RWG, void, ptr, cptr, i32)
 
 #ifndef CONFIG_USER_ONLY
 DEF_HELPER_3(servc, i32, env, i64, i64)

target/s390x/insn-data.def

@@ -1144,6 +1144,8 @@
     F(0xe76a, VO,      VRR_c, V,   0, 0, 0, 0, vo, 0, IF_VEC)
 /* VECTOR OR WITH COMPLEMENT */
     F(0xe76f, VOC,     VRR_c, VE,  0, 0, 0, 0, voc, 0, IF_VEC)
+/* VECTOR POPULATION COUNT */
+    F(0xe750, VPOPCT,  VRR_a, V,   0, 0, 0, 0, vpopct, 0, IF_VEC)
 
 #ifndef CONFIG_USER_ONLY
 /* COMPARE AND SWAP AND PURGE */

target/s390x/translate_vx.inc.c

@@ -1826,3 +1826,22 @@ static DisasJumpType op_voc(DisasContext *s, DisasOps *o)
                   get_field(s->fields, v3));
     return DISAS_NEXT;
 }
+
+static DisasJumpType op_vpopct(DisasContext *s, DisasOps *o)
+{
+    const uint8_t es = get_field(s->fields, m3);
+    static const GVecGen2 g[4] = {
+        { .fno = gen_helper_gvec_vpopct8, },
+        { .fno = gen_helper_gvec_vpopct16, },
+        { .fni4 = tcg_gen_ctpop_i32, },
+        { .fni8 = tcg_gen_ctpop_i64, },
+    };
+
+    if (es > ES_64 || (es != ES_8 && !s390_has_feat(S390_FEAT_VECTOR_ENH))) {
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return DISAS_NORETURN;
+    }
+
+    gen_gvec_2(get_field(s->fields, v1), get_field(s->fields, v2), &g[es]);
+    return DISAS_NEXT;
+}

target/s390x/vec_int_helper.c

@@ -464,3 +464,17 @@ void HELPER(gvec_vmlo##BITS)(void *v1, const void *v2, const void *v3,         \
 DEF_VMLO(8, 16)
 DEF_VMLO(16, 32)
 DEF_VMLO(32, 64)
+
+#define DEF_VPOPCT(BITS)                                                       \
+void HELPER(gvec_vpopct##BITS)(void *v1, const void *v2, uint32_t desc)        \
+{                                                                              \
+    int i;                                                                     \
+                                                                               \
+    for (i = 0; i < (128 / BITS); i++) {                                       \
+        const uint##BITS##_t a = s390_vec_read_element##BITS(v2, i);           \
+                                                                               \
+        s390_vec_write_element##BITS(v1, i, ctpop32(a));                       \
+    }                                                                          \
+}
+DEF_VPOPCT(8)
+DEF_VPOPCT(16)