Struct TosaFp32OperatorCase 

pub struct TosaFp32OperatorCase {
    pub name: &'static str,
    pub artifact: &'static [u8],
    pub inputs: &'static [Fp32TierTensor],
    pub output: Fp32TierTensor,
    pub absolute_tolerance: f32,
    pub relative_tolerance: f32,
}

One FP32-tier operator case shared by host backends: a stable TOSA 1.0 graph over FP32 tensors with BOOL and INT32 auxiliaries, and a numerical oracle for its single output.

Float outputs follow the TosaFloat32Case rules: NaN matches any NaN, infinities and zeros compare bit-exactly (signed zero included), and finite values must fall within the absolute or relative tolerance. BOOL and INT32 outputs compare exactly.

Fields

name: &'static str

Diagnostic case name.

artifact: &'static [u8]

TOSA 1.0 FlatBuffer payload.

inputs: &'static [Fp32TierTensor]

Block inputs in declared slot order.

output: Fp32TierTensor

Single block output.

absolute_tolerance: f32

Maximum absolute error accepted for finite float values.

relative_tolerance: f32

Maximum relative error accepted for finite float values.

Implementations

impl TosaFp32OperatorCase

pub fn output_matches(self, actual: &[u8]) -> bool

Compare raw client-visible output bytes with the typed oracle.

Trait Implementations

impl Clone for TosaFp32OperatorCase

fn clone(&self) -> TosaFp32OperatorCase

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Copy for TosaFp32OperatorCase

impl Debug for TosaFp32OperatorCase

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

Formats the value using the given formatter.

impl PartialEq for TosaFp32OperatorCase

fn eq(&self, other: &TosaFp32OperatorCase) -> 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 TosaFp32OperatorCase