Struct Complex32 

#[repr(C)]
pub struct Complex32 {
    pub re: f32,
    pub im: f32,
}

Single-precision complex element. #[repr(C)] struct of two f32 fields (real, imag) — ABI-compatible with cuFFT’s cufftComplex (which is itself an alias for CUDA’s float2), with NumPy’s complex64, and with PyTorch’s torch.complex64.

Used by the FFT op family (Milestone 6.4) as the element type for spectrum-domain tensors. Complex arithmetic is not a kernel concern at this layer — Rust callers build / inspect complex values via the re / im fields and pass DeviceBuffer<Complex32> directly to the FFT plans, which reinterpret them as cufftComplex over the FFI boundary.

Layout invariant: Complex32 { re, im } and cufftComplex { x, y } share identical byte storage on every platform CUDA supports ((f32, f32) is 8-byte aligned, naturally padded). A DeviceBuffer<Complex32> can be reinterpreted as a DeviceBuffer<cufftComplex> via view_as without copying.

Fields

re: f32

Real component.

im: f32

Imaginary component.

Implementations

impl Complex32

pub const fn new(re: f32, im: f32) -> Complex32

Build a Complex32 from real and imaginary f32 parts.

Trait Implementations

impl Clone for Complex32

fn clone(&self) -> Complex32

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Copy for Complex32

impl Debug for Complex32

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

Formats the value using the given formatter.

impl Default for Complex32

fn default() -> Complex32

Returns the “default value” for a type.

impl DeviceRepr for Complex32

impl Element for Complex32

Single-precision complex (interleaved real/imag pair of f32) as an elementwise kernel input element. Used by the FFT family (fft, ifft, rfft output / irfft input, etc.) for spectrum-domain tensors. The Scalar projection is f32 (matches the real width).

type Scalar = f32

Scalar type used for the kernel’s alpha / beta parameters (and the epilogue compute type). f32 for f16/bf16/f32/F32Strict — the epilogue runs at f32 to match the F32 accumulator. f64 for f64 — the DGEMM path uses an F64 accumulator and f64 alpha/beta. For integer / Bool elements the projection is nominally f32 (no α/β-scaled epilogue applies).

impl KernelDtype for Complex32

const KIND: ElementKind = ElementKind::Complex32

Runtime tag for this dtype. Stable across the workspace — keyed by this same enum in crate::KernelSku::element.

impl PartialEq for Complex32

fn eq(&self, other: &Complex32) -> 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 Complex32