mirror of
https://github.com/hanzoai/ml.git
synced 2026-11-20 23:08:29 +00:00
58 lines
1.6 KiB
Rust
58 lines
1.6 KiB
Rust
use crate::benchmarks::{BenchDevice, BenchDeviceHandler};
|
|
use criterion::{criterion_group, Criterion, Throughput};
|
|
use hanzo_ml::{DType, Device, Tensor};
|
|
use std::hint::black_box;
|
|
use std::time::Instant;
|
|
|
|
fn run(lhs: &Tensor, rhs: &Tensor) -> Tensor {
|
|
lhs.mul(rhs).unwrap()
|
|
}
|
|
|
|
fn run_binary_benchmark(c: &mut Criterion, device: &Device, dtype: DType, name: &str) {
|
|
let b = 1;
|
|
let m = 1024;
|
|
let k = 1024;
|
|
|
|
let lhs = Tensor::arange(0.0f32, (b * m * k) as f32, device)
|
|
.unwrap()
|
|
.to_dtype(dtype)
|
|
.unwrap()
|
|
.reshape((b, m, k))
|
|
.unwrap();
|
|
|
|
let rhs = Tensor::arange(0.0f32, (b * m * k) as f32, device)
|
|
.unwrap()
|
|
.to_dtype(dtype)
|
|
.unwrap()
|
|
.reshape((b, m, k))
|
|
.unwrap();
|
|
|
|
let flops = 2 * b * m * k * dtype.size_in_bytes();
|
|
|
|
let mut group = c.benchmark_group(device.bench_name(name));
|
|
group.throughput(Throughput::Bytes(flops as u64));
|
|
group.bench_function("iter", move |b| {
|
|
b.iter_custom(|iters| {
|
|
let start = Instant::now();
|
|
for _i in 0..iters {
|
|
run(black_box(&lhs), black_box(&rhs));
|
|
}
|
|
device.sync().unwrap();
|
|
start.elapsed()
|
|
})
|
|
});
|
|
group.finish();
|
|
}
|
|
|
|
fn criterion_benchmark(c: &mut Criterion) {
|
|
let handler = BenchDeviceHandler::new().unwrap();
|
|
for device in handler.devices {
|
|
for dtype in [DType::F32, DType::BF16, DType::F16] {
|
|
let name = format!("binary_mul_{dtype:?}");
|
|
run_binary_benchmark(c, &device, dtype, &name);
|
|
}
|
|
}
|
|
}
|
|
|
|
criterion_group!(benches, criterion_benchmark);
|