Struct burn_wgpu::kernel::reduce::MeanDimAutotuneOperationSet

pub struct MeanDimAutotuneOperationSet<E: WgpuElement, const D: usize> { /* private fields */ }

Set of mean_dim implementations available for autotune Autotune key is given by concatenating the closest upper power of 2 of dim to reduce, and product of others

Trait Implementations

impl<E: WgpuElement + Element, const D: usize> AutotuneOperationSet<WgpuAutotuneKey> for MeanDimAutotuneOperationSet<E, D>

fn key(&self) -> WgpuAutotuneKey

The key used in the tune cache

fn autotunables(&self) -> Vec<Box<dyn AutotuneOperation>>

All candidate operations for autotuning this operation type Operations can run on toy tensors of relevant size

fn fastest(self: Box<Self>, fastest_index: usize) -> Box<dyn AutotuneOperation>

Returns the operation for the given index, matching the order returned by autotunables. Operation obtained here runs on original tensors