@@ -1438,6 +1438,14 @@ void helper_vpmsumb(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b)
}
}
+void helper_vpmsumh(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b)
+{
+ for (int i = 0; i < 2; ++i) {
+ uint64_t aa = a->u64[i], bb = b->u64[i];
+ r->u64[i] = clmul_16x2_even(aa, bb) ^ clmul_16x2_odd(aa, bb);
+ }
+}
+
#define PMSUM(name, srcfld, trgfld, trgtyp) \
void helper_##name(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b) \
{ \
@@ -1458,7 +1466,6 @@ 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 | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-)