Struct OperatorGemm 

pub struct OperatorGemm {}

Implementations

impl OperatorGemm

pub fn create_outputs( &self, inputs: &[Option<Tensor>], _expand_ratio: f64, _rng: &mut impl RngExt, ) -> Result<Vec<Option<Tensor>>, SimError>

pub fn create_inputs( &self, outputs: &[Option<Tensor>], expand_ratio: f64, rng: &mut impl RngExt, ) -> Result<Vec<Option<Tensor>>, SimError>

Trait Implementations

impl Operator for OperatorGemm

fn validate_tensors( &self, inputs: &[Option<Tensor>], outputs: &[Option<Tensor>], ) -> SimResult

Validate that the input and output tensors are valid shapes and datatypes

fn compute_delay_ticks( &self, compute_capabilities: &Rc<ComputeCapabilities>, inputs: &[Option<TensorView>], outputs: &[Option<TensorView>], ) -> Result<usize, SimError>

Returns the number of clock ticks needed to perform the specified computation give the machine capabilities

fn compute_machine_ops( &self, inputs: &[Option<TensorView>], outputs: &[Option<TensorView>], ) -> Result<MachineOpCounts, SimError>

Returns the number of machine operations performed by the specified computation, broken down by operation type.

fn partition_views( &self, input_views: &[Option<TensorView>], output_views: &[Option<TensorView>], num_partitions: usize, ) -> Result<Vec<TensorPartition>, SimError>

Partition the operation into one or more views that can be executed in parallel. Implementations may return fewer than num_partitions if the operator cannot be split that finely.

fn compute_flops( &self, inputs: &[Option<TensorView>], outputs: &[Option<TensorView>], ) -> Result<usize, SimError>

Returns the total number of FLOPs performed by the specified computation.