If you're going to go there, maybe emulate the hardware cascade approach instead?
uint8_t xor (uint8_t *inputs, uint8_t input_count) {
uint8_t i; // Loop counter
uint8_t tmp; // Running value
tmp = inputs[0];
for (i = 1; i < input_count; i++) {
tmp = (tmp != inputs[i]);
if (tmp) return 1;
}
return 0;
}
uint8_t xnor (uint8_t *inputs, uint8_t input_count) {
uint8_t i; // Loop counter
uint8_t tmp; // Running value
tmp = inputs[0];
for (i = 1; i < input_count; i++) {
tmp = (tmp == inputs[i]);
if (!tmp) return 1;
}
return 0;
}
Would that do the trick? (Haven't tested it... might be overlooking an obvious snafu.) Not quite as fast as hard-coded conditionals, but scalable to the width of the counter... 