Struct rand::prng::isaac64::Isaac64Core

pub struct Isaac64Core { /* fields omitted */ }

The core of Isaac64Rng, used with BlockRng.

Methods

impl Isaac64Core

pub fn new_from_u64(seed: u64) -> Self

Create an ISAAC-64 random number generator using an u64 as seed. If seed == 0 this will produce the same stream of random numbers as the reference implementation when used unseeded.

Trait Implementations

impl Clone for Isaac64Core

fn clone(&self) -> Isaac64Core

Returns a copy of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for Isaac64Core

fn fmt(&self, f: &mut Formatter) -> Result

Formats the value using the given formatter.

impl SeedableRng for Isaac64Core

type Seed = [u8; 32]

Seed type, which is restricted to types mutably-dereferencable as u8 arrays (we recommend [u8; N] for some N).

fn from_seed(seed: Self::Seed) -> Self

Create a new PRNG using the given seed.

fn from_rng<R: RngCore>(rng: R) -> Result<Self, Error>

Create a new PRNG seeded from another Rng.

fn seed_from_u64(state: u64) -> Self

Create a new PRNG using a u64 seed.

impl BlockRngCore for Isaac64Core

type Item = u64

Results element type, e.g. u32.

type Results = IsaacArray<Self::Item>

Results type. This is the 'block' an RNG implementing BlockRngCore generates, which will usually be an array like [u32; 16].

fn generate(&mut self, results: &mut IsaacArray<Self::Item>)

Refills the output buffer, results. See also the pseudocode desciption of the algorithm in the Isaac64Rng documentation.

Optimisations used (similar to the reference implementation):

• The loop is unrolled 4 times, once for every constant of mix().
• The contents of the main loop are moved to a function rngstep, to reduce code duplication.
• We use local variables for a and b, which helps with optimisations.
• We split the main loop in two, one that operates over 0..128 and one over 128..256. This way we can optimise out the addition and modulus from s[i+128 mod 256].
• We maintain one index i and add m or m2 as base (m2 for the s[i+128 mod 256]), relying on the optimizer to turn it into pointer arithmetic.
• We fill results backwards. The reference implementation reads values from results in reverse. We read them in the normal direction, to make fill_bytes a memcopy. To maintain compatibility we fill in reverse.