void, ptr, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_6(sme_usmopa_d, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_6(sme2_bmopa_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, ptr, i32)
DEF_IMOP_64(sumopa_d, int16_t, uint16_t)
DEF_IMOP_64(usmopa_d, uint16_t, int16_t)
-#define DEF_IMOPH(NAME, S) \
- void HELPER(sme_##NAME##_##S)(void *vza, void *vzn, void *vzm, \
+#define DEF_IMOPH(P, NAME, S) \
+ void HELPER(P##_##NAME##_##S)(void *vza, void *vzn, void *vzm, \
void *vpn, void *vpm, uint32_t desc) \
{ do_imopa_##S(vza, vzn, vzm, vpn, vpm, desc, NAME##_##S); }
-DEF_IMOPH(smopa, s)
-DEF_IMOPH(umopa, s)
-DEF_IMOPH(sumopa, s)
-DEF_IMOPH(usmopa, s)
+DEF_IMOPH(sme, smopa, s)
+DEF_IMOPH(sme, umopa, s)
+DEF_IMOPH(sme, sumopa, s)
+DEF_IMOPH(sme, usmopa, s)
-DEF_IMOPH(smopa, d)
-DEF_IMOPH(umopa, d)
-DEF_IMOPH(sumopa, d)
-DEF_IMOPH(usmopa, d)
+DEF_IMOPH(sme, smopa, d)
+DEF_IMOPH(sme, umopa, d)
+DEF_IMOPH(sme, sumopa, d)
+DEF_IMOPH(sme, usmopa, d)
+
+static uint32_t bmopa_s(uint32_t n, uint32_t m, uint32_t a, uint8_t p, bool neg)
+{
+ uint32_t sum = ctpop32(~(n ^ m));
+ if (neg) {
+ sum = -sum;
+ }
+ if (!(p & 1)) {
+ sum = 0;
+ }
+ return a + sum;
+}
+
+DEF_IMOPH(sme2, bmopa, s)
TRANS_FEAT(UMOPA_d, aa64_sme_i16i64, do_outprod, a, MO_64, gen_helper_sme_umopa_d)
TRANS_FEAT(SUMOPA_d, aa64_sme_i16i64, do_outprod, a, MO_64, gen_helper_sme_sumopa_d)
TRANS_FEAT(USMOPA_d, aa64_sme_i16i64, do_outprod, a, MO_64, gen_helper_sme_usmopa_d)
+
+TRANS_FEAT(BMOPA, aa64_sme2, do_outprod, a, MO_32, gen_helper_sme2_bmopa_s)