View page source

warp.poisson#

warp.poisson(state: uint32, lam: float32) → uint32#

  • Kernel

  • Python

Generate a random sample from a Poisson distribution.

In a kernel, advances state in place when lam > 0 (and returns 0 without consuming RNG state when lam == 0); called from the Python scope, it does not modify state, so repeated calls with the same state return the same count (see rand_init()). The returned count has mean and variance both equal to lam.

@wp.kernel
def counts(seed: int, rate: float, out: wp.array[wp.uint32]):
    i = wp.tid()
    rng = wp.rand_init(seed, i)
    out[i] = wp.poisson(rng, rate)
Parameters:

  • state – RNG state; advanced in place when called in a kernel (see rand_init()).

  • lam – Expected value (rate) of the distribution; must be non-negative.

Returns:

A uint32 sample drawn from Poisson(lam).