In my Monte Carlo simulation application, the key is to generate a random number from a binomial distribution with the parameters n = size and p = 0.5. Here is my current implementation
#understand
#understand
#understand
int64_t rbinom (size int64_t) {
if (! size) {
returns 0;
}
int64_t result = 0;
while (size> = 64) {
uint64_t random64;
while (! _rdrand64_step (& random64)) {
fprintf (stderr, "HW_RND_GEN not ready n");
}
result + = _popcnt64 (random64);
size - = 64;
}
uint64_t random64;
while (! _rdrand64_step (& random64)) {
fprintf (stderr, "HW_RND_GEN not ready n");
}
result + = _popcnt64 (random64 & ~ (UINT64_MAX << size));
return the result;
}
However, the result of the comparative analysis terrifies me:
I spend 99.68% of the run time on this function! How can I optimize it?
The result does not need to be cryptographically secure, as long as it is sufficient for Monte Carlo simulations.
