Trait cubecl_runtime::benchmark::Benchmark

pub trait Benchmark {
    type Args: Clone;

    // Required methods
    fn prepare(&self) -> Self::Args;
    fn execute(&self, args: Self::Args);
    fn name(&self) -> String;
    fn sync(&self);

    // Provided methods
    fn num_samples(&self) -> usize { ... }
    fn options(&self) -> Option<String> { ... }
    fn shapes(&self) -> Vec<Vec<usize>> { ... }
    fn run(&self) -> BenchmarkDurations { ... }
}

Benchmark trait.

Required Associated Types

type Args: Clone

Benchmark arguments.

Required Methods

fn prepare(&self) -> Self::Args

Prepare the benchmark, run anything that is essential for the benchmark, but shouldn’t count as included in the duration.

Notes

This should not include warmup, the benchmark will be run at least one time without measuring the execution time.

fn execute(&self, args: Self::Args)

Execute the benchmark and returns the time it took to complete.

fn name(&self) -> String

Name of the benchmark, should be short and it should match the name defined in the crate Cargo.toml

fn sync(&self)

Wait for computed to be over

Provided Methods

fn num_samples(&self) -> usize

Number of samples per run required to have a statistical significance.

fn options(&self) -> Option<String>

The options passed to the benchmark.

fn shapes(&self) -> Vec<Vec<usize>>

Shapes dimensions

fn run(&self) -> BenchmarkDurations

Run the benchmark a number of times.

Implementors

impl<S: ComputeServer, C: ComputeChannel<S>, Out> Benchmark for TuneBenchmark<S, C, Out>

type Args = Box<dyn AutotuneOperation<Out>>