Use generic routines for 32-bit carry-less multiply.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/ppc/int_helper.c | 26 ++++++--------------------
 1 file changed, 6 insertions(+), 20 deletions(-)

diff --git a/target/ppc/int_helper.c b/target/ppc/int_helper.c
index ebb2957fe7..1ea42b4ede 100644
--- a/target/ppc/int_helper.c
+++ b/target/ppc/int_helper.c
@@ -1445,28 +1445,14 @@ void helper_vpmsumh(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b)
     }
 }
 
-#define PMSUM(name, srcfld, trgfld, trgtyp)                   \
-void helper_##name(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b)  \
-{                                                             \
-    int i, j;                                                 \
-    trgtyp prod[sizeof(ppc_avr_t) / sizeof(a->srcfld[0])];    \
-                                                              \
-    VECTOR_FOR_INORDER_I(i, srcfld) {                         \
-        prod[i] = 0;                                          \
-        for (j = 0; j < sizeof(a->srcfld[0]) * 8; j++) {      \
-            if (a->srcfld[i] & (1ull << j)) {                 \
-                prod[i] ^= ((trgtyp)b->srcfld[i] << j);       \
-            }                                                 \
-        }                                                     \
-    }                                                         \
-                                                              \
-    VECTOR_FOR_INORDER_I(i, trgfld) {                         \
-        r->trgfld[i] = prod[2 * i] ^ prod[2 * i + 1];         \
-    }                                                         \
+void helper_vpmsumw(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_32(aa, bb) ^ clmul_32(aa >> 32, bb >> 32);
+    }
 }
 
-PMSUM(vpmsumw, u32, u64, uint64_t)
-
 void helper_VPMSUMD(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b)
 {
     int i, j;
-- 
2.34.1