Profiling your models

Do you feel like your model is too slow? Do you want to make it faster? Instead of guessing which part of the code is responsible for the slowdown, you should profile your code to learn how much time is spent in each function and where to focus any optimization efforts.

In this tutorial you’ll learn how to profile your model using the PyTorch profiler, how to read the output of the profiler, and how to add your own labels for new functions/steps in your model’s forward function.

from typing import Dict, List, Optional

import ase.build
import matplotlib.pyplot as plt
import numpy as np
import torch
from metatensor.torch import Labels, TensorBlock, TensorMap

from metatomic.torch import (
    AtomisticModel,
    ModelCapabilities,
    ModelMetadata,
    ModelOutput,
    System,
)
from metatomic.torch.ase_calculator import MetatomicCalculator

When profiling your code, it is important to run the model on a representative system to ensure you are actually exercising the behavior of your model at the right scale. Here we’ll use a relatively large system with many atoms.

primitive = ase.build.bulk(name="C", crystalstructure="diamond", a=3.567)
atoms = ase.build.make_supercell(primitive, 10 * np.eye(3))
print(f"We have {len(atoms)} atoms in our system")
We have 2000 atoms in our system

We will use the same HarmonicModel as in the previous tutorial as our machine learning potential.

Click to see the definition of HarmonicModel
class HarmonicModel(torch.nn.Module):
    def __init__(self, force_constant: float, equilibrium_positions: torch.Tensor):
        """Create an ``HarmonicModel``.

        :param force_constant: force constant, in ``energy unit / (length unit)^2``
        :param equilibrium_positions: torch tensor with shape ``n x 3``, containing the
            equilibrium positions of all atoms
        """
        super().__init__()
        assert force_constant > 0
        self.force_constant = force_constant
        self.equilibrium_positions = equilibrium_positions

    def forward(
        self,
        systems: List[System],
        outputs: Dict[str, ModelOutput],
        selected_atoms: Optional[Labels],
    ) -> Dict[str, TensorMap]:
        if list(outputs.keys()) != ["energy"]:
            raise ValueError(
                "this model can only compute 'energy', but `outputs` contains other "
                f"keys: {', '.join(outputs.keys())}"
            )

        # we don't want to worry about selected_atoms yet
        if selected_atoms is not None:
            raise NotImplementedError("selected_atoms is not implemented")

        if outputs["energy"].per_atom:
            raise NotImplementedError("per atom energy is not implemented")

        # compute the energy for each system by adding together the energy for each atom
        energy = torch.zeros((len(systems), 1), dtype=systems[0].positions.dtype)
        for i, system in enumerate(systems):
            assert len(system) == self.equilibrium_positions.shape[0]
            r0 = self.equilibrium_positions
            energy[i] += torch.sum(self.force_constant * (system.positions - r0) ** 2)

        # add metadata to the output
        block = TensorBlock(
            values=energy,
            samples=Labels("system", torch.arange(len(systems)).reshape(-1, 1)),
            components=[],
            properties=Labels("energy", torch.tensor([[0]])),
        )
        return {
            "energy": TensorMap(keys=Labels("_", torch.tensor([[0]])), blocks=[block])
        }


model = HarmonicModel(
    force_constant=3.14159265358979323846,
    equilibrium_positions=torch.tensor(atoms.positions),
)

capabilities = ModelCapabilities(
    outputs={
        "energy": ModelOutput(quantity="energy", unit="eV", per_atom=False),
    },
    atomic_types=[6],
    interaction_range=0.0,
    length_unit="Angstrom",
    supported_devices=["cpu"],
    dtype="float32",
)

metadata = ModelMetadata()
wrapper = AtomisticModel(model.eval(), metadata, capabilities)

wrapper.export("exported-model.pt")
/home/runner/work/metatomic/metatomic/python/examples/4-profiling.py:128: DeprecationWarning: `export()` is deprecated, use `save()` instead
  wrapper.export("exported-model.pt")

If you are trying to profile your own model, you can start here and create MetatomicCalculator with your own model.

Profiling energy calculation

We will start with an energy-only calculator, which can be enabled with do_gradients_with_energy=False.

atoms.calc = MetatomicCalculator("exported-model.pt", do_gradients_with_energy=False)

Before trying to profile the code, it is a good idea to run it a couple of times to allow torch to warmup internally.

for _ in range(10):
    # force the model to re-run everytime, otherwise ASE caches calculation results
    atoms.rattle(1e-6)
    atoms.get_potential_energy()

Now we can run code using torch.profiler.profile() to collect statistic on how long each function takes to run.

atoms.rattle(1e-6)
with torch.profiler.profile() as energy_profiler:
    atoms.get_potential_energy()

print(energy_profiler.key_averages().table(sort_by="self_cpu_time_total", row_limit=10))
------------------------------------------  ------------  ------------  ------------  ------------  ------------  ------------
                                      Name    Self CPU %      Self CPU   CPU total %     CPU total  CPU time avg    # of Calls
------------------------------------------  ------------  ------------  ------------  ------------  ------------  ------------
       MetatomicCalculator::prepare_inputs        21.33%     338.053us        31.11%     493.015us     493.015us             1
                                   forward        11.57%     183.263us        20.00%     316.985us     316.985us             1
                            Model::forward         9.22%     146.134us        29.23%     463.119us     463.119us             1
        AtomisticModel::check_atomic_types         6.68%     105.847us        11.37%     180.128us     180.128us             1
      AtomisticModel::convert_units_output         5.25%      83.116us         5.37%      85.140us      85.140us             1
         MetatomicCalculator::sum_energies         4.93%      78.056us         4.93%      78.056us      78.056us             1
       AtomisticModel::convert_units_input         4.36%      69.139us         4.52%      71.664us      71.664us             1
    MetatomicCalculator::compute_neighbors         3.97%      62.949us         7.49%     118.623us     118.623us             1
      MetatomicCalculator::convert_outputs         3.92%      62.067us         5.07%      80.341us      80.341us             1
                               aten::copy_         3.67%      58.179us         3.67%      58.179us       5.289us            11
------------------------------------------  ------------  ------------  ------------  ------------  ------------  ------------
Self CPU time total: 1.585ms

There are a couple of interesting things to see here. First the total runtime of the code is shown in the bottom; and then the most costly functions are visible on top, one line per function. For each function, Self CPU refers to the time spent in this function excluding any called functions; and CPU total refers to the time spent in this function, including called functions.

For more options to record operations and display outputs, please refer to the official documentation for PyTorch profiler.

Here, Model::forward indicates the time taken by your model’s forward(). Anything starting with aten:: comes from operations on torch tensors, typically with the same function name as the corresponding torch functions (e.g. aten::arange is torch.arange()). We can also see some internal functions from metatomic, with the name staring with AtomisticModel:: for AtomisticModel; and MetatomicCalculator:: for ase_calculator.MetatomicCalculator.

If you want to see more details on the internal steps taken by your model, you can add torch.profiler.record_function() (https://pytorch.org/docs/stable/generated/torch.autograd.profiler.record_function.html) inside your model code to give names to different steps in the calculation. This is how we internally set names such as Model::forward or MetatomicCalculator::prepare_inputs above.

Profiling forces calculation

Let us now do the same, but while also computing the forces for this system. This mean we should now see some time spent in the backward() function, on top of everything else.

atoms.calc = MetatomicCalculator("exported-model.pt")

# warmup
for _ in range(10):
    atoms.rattle(1e-6)
    atoms.get_forces()

atoms.rattle(1e-6)
with torch.profiler.profile() as forces_profiler:
    atoms.get_forces()

print(forces_profiler.key_averages().table(sort_by="self_cpu_time_total", row_limit=10))
-------------------------------------------------------  ------------  ------------  ------------  ------------  ------------  ------------
                                                   Name    Self CPU %      Self CPU   CPU total %     CPU total  CPU time avg    # of Calls
-------------------------------------------------------  ------------  ------------  ------------  ------------  ------------  ------------
                    MetatomicCalculator::prepare_inputs        12.91%     205.407us        19.52%     310.703us     310.703us             1
                   MetatomicCalculator::convert_outputs         9.36%     148.999us        12.46%     198.343us     198.343us             1
                      MetatomicCalculator::run_backward         8.79%     139.893us        22.92%     364.734us     364.734us             1
                                         Model::forward         6.78%     107.923us        18.36%     292.199us     292.199us             1
                                                forward         5.70%      90.789us        11.58%     184.276us     184.276us             1
                                               aten::mm         5.06%      80.553us         5.11%      81.364us      20.341us             4
                   AtomisticModel::convert_units_output         4.77%      75.943us         4.88%      77.636us      77.636us             1
                     AtomisticModel::check_atomic_types         4.56%      72.636us         7.91%     125.936us     125.936us             1
                      MetatomicCalculator::sum_energies         4.37%      69.611us         4.37%      69.611us      69.611us             1
                    AtomisticModel::convert_units_input         3.71%      59.021us         3.84%      61.085us      61.085us             1
-------------------------------------------------------  ------------  ------------  ------------  ------------  ------------  ------------
Self CPU time total: 1.591ms

Let’s visualize this data in another way:

events = forces_profiler.key_averages()
events = sorted(events, key=lambda u: u.self_cpu_time_total, reverse=True)
total_cpu_time = sum(map(lambda u: u.self_cpu_time_total, events))

bottom = 0.0
for event in events:
    self_time = event.self_cpu_time_total
    name = event.key
    if len(name) > 30:
        name = name[:12] + "[...]" + name[-12:]

    if self_time > 0.03 * total_cpu_time:
        plt.bar(0, self_time, bottom=bottom, label=name)
        bottom += self_time
    else:
        plt.bar(0, total_cpu_time - bottom, bottom=bottom, label="others")
        break

plt.legend()
plt.xticks([])
plt.xlim(0, 1)
plt.ylabel("self time / µs")
plt.show()
4 profiling

Total running time of the script: (0 minutes 1.359 seconds)

Gallery generated by Sphinx-Gallery