Struct Product 

pub struct Product;

Multiplicative reduction: computes ∏ data[i].

Identity element is T::ONE. Uses SIMD mul to accumulate lane products, then reduces horizontally via a scalar lane-extraction loop (no prod_reduce on SimdKernel — the hardware does not expose one universally).

Zero-Cost Guarantee

size_of::<Product>() == 0. All branching over Product vs other ops is eliminated via DCE during monomorphization.

Trait Implementations

impl Clone for Product

fn clone(&self) -> Product

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Copy for Product

impl Debug for Product

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

Formats the value using the given formatter.

impl Eq for Product

impl PartialEq for Product

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

Equality operator ==.

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

Inequality operator !=.

impl<T> ReductionOp<T> for Product

where T: NumericElement,

unsafe fn accumulate<Arch>( acc: <Arch as SimdKernel<T>>::Vector, v: <Arch as SimdKernel<T>>::Vector, ) -> <Arch as SimdKernel<T>>::Vector

where Arch: SimdKernel<T>,

Accumulate: acc = acc * v (lane-wise multiply).

Safety

Processor must support the target feature of Arch.

unsafe fn finalize<Arch>(acc: <Arch as SimdKernel<T>>::Vector) -> T

where Arch: SimdKernel<T>,

Finalize: store the accumulated product vector and reduce over lanes.

There is no universal prod_reduce intrinsic, so this falls back to:

1. Store the LANE_COUNT partial products into a local stack array.
2. Scalar-fold with *.

For Scalar arch this is always a single-element store + identity.

Safety

Processor must support the target feature of Arch.

fn identity_scalar() -> T

The identity element for this reduction as a scalar.

fn scalar_combine(a: T, b: T) -> T

Combine two scalar partial results using this reduction.

unsafe fn fma_pair_accumulate<Arch>( acc: <Arch as SimdKernel<T>>::Vector, a: <Arch as SimdKernel<T>>::Vector, b: <Arch as SimdKernel<T>>::Vector, ) -> <Arch as SimdKernel<T>>::Vector

where Arch: SimdKernel<T>,

FMA-aware pairwise accumulation: acc = fuse(acc, a, b) where fuse may use a single fused multiply-add instruction rather than a separate mul + accumulate.

fn scalar_accumulate(acc: T, elem: T) -> T

Accumulate a single scalar element elem into a scalar accumulator acc.

unsafe fn identity_vector<Arch>() -> <Arch as SimdKernel<T>>::Vector

where Arch: SimdKernel<T>,

Splat the identity element into a vector register.

unsafe fn transform_vector<Arch>( v: <Arch as SimdKernel<T>>::Vector, ) -> <Arch as SimdKernel<T>>::Vector

where Arch: SimdKernel<T>,

Per-element lane transform applied before combining (identity by default).

unsafe fn combine_vectors<Arch>( a: <Arch as SimdKernel<T>>::Vector, b: <Arch as SimdKernel<T>>::Vector, ) -> <Arch as SimdKernel<T>>::Vector

where Arch: SimdKernel<T>,

Merge two partial accumulators WITHOUT the per-element transform.

impl StructuralPartialEq for Product