xor128
xor128(tmp, tmp, cv);
xor128(tmp, tmp, cv);
xor128(tmp, tmp, iv0);
xor128(out, in, t);
xor128(out, out, t);
xor128(out + 4*i, in + 4*i, t);
xor128(out + 4*i, in + 4*i, buf + 4*i);
xor128(buf, in, t);
xor128(buf, buf, t);
xor128(buf, buf, t);
xor128(out, in, t);
xor128(out, out, t);
xor128(out + 4*i, in + 4*i, t);
xor128(out + 4*i, in + 4*i, buf + 4*i);
xor128(buf, in, t);
xor128(buf, buf, t);
xor128(buf, buf, t);
xor128(auth, auth, in);
xor128(authctr, authctr, in);
xor128(out, in, authctr + 16);
xor128(out, authctr + 16, in);
xor128(authctr, authctr, out);