@@ -1435,6 +1435,15 @@ void helper_vpmsumb(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b)
r->s128 = int128_xor(e, o);
}
+void helper_vpmsumh(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b)
+{
+ Int128 ia = a->s128;
+ Int128 ib = b->s128;
+ Int128 e = clmul_16x4_even(ia, ib);
+ Int128 o = clmul_16x4_odd(ia, ib);
+ r->s128 = int128_xor(e, o);
+}
+
#define PMSUM(name, srcfld, trgfld, trgtyp) \
void helper_##name(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b) \
{ \
@@ -1455,7 +1464,6 @@ void helper_##name(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b) \
} \
}
-PMSUM(vpmsumh, u16, u32, uint32_t)
PMSUM(vpmsumw, u32, u64, uint64_t)
void helper_VPMSUMD(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b)
Use generic routines for 16-bit carry-less multiply. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/ppc/int_helper.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-)