1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
|
use crate::benchmarks::{BenchDevice, BenchDeviceHandler};
use candle_core::{DType, Device, Tensor};
use criterion::{black_box, criterion_group, Criterion, Throughput};
use std::time::Instant;
fn run(a: &Tensor) {
a.sqrt().unwrap();
}
fn run_unary_benchmark(c: &mut Criterion, device: &Device, dtype: DType, name: &str) {
let b = 1;
let m = 1024;
let k = 1024;
let tensor = Tensor::arange(0.0f32, (b * m * k) as f32, device)
.unwrap()
.to_dtype(dtype)
.unwrap()
.reshape((b, m, k))
.unwrap();
let flops = 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(&tensor));
}
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!("sqrt_{:?}", dtype);
run_unary_benchmark(c, &device, dtype, &name);
}
}
}
criterion_group!(benches, criterion_benchmark);
|
