Struct MixedDenseBatchResult 

pub struct MixedDenseBatchResult {
    pub outputs_q1616: Vec<i32>,
    pub overflow: Vec<bool>,
    pub underflow: Vec<bool>,
}

Per-element results of a batched mixed-precision Q8.8 × Q16.16 dense MAC.

Each vector is row-major n_batch * n_outputs; element (b, o) lives at index b * n_outputs + o.

Fields

outputs_q1616: Vec<i32>

Saturated Q16.16 accumulator codes.

overflow: Vec<bool>

true where the accumulator left the Q16.16 range.

underflow: Vec<bool>

true where a non-zero contraction rounded to zero without overflowing.

Trait Implementations

impl Clone for MixedDenseBatchResult

fn clone(&self) -> MixedDenseBatchResult

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for MixedDenseBatchResult

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

Formats the value using the given formatter.

impl Eq for MixedDenseBatchResult

impl PartialEq for MixedDenseBatchResult

fn eq(&self, other: &MixedDenseBatchResult) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl StructuralPartialEq for MixedDenseBatchResult