.. DO NOT EDIT.
.. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY.
.. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE:
.. "examples/benchmarks/plot_modal.py"
.. LINE NUMBERS ARE GIVEN BELOW.

.. only:: html

    .. note::
        :class: sphx-glr-download-link-note

        :ref:`Go to the end <sphx_glr_download_examples_benchmarks_plot_modal.py>`
        to download the full example code. or to run this example in your browser via Binder

.. rst-class:: sphx-glr-example-title

.. _sphx_glr_examples_benchmarks_plot_modal.py:


Benchmark Modal
===============

Numerical backends performace comparison, with GPU acceleration, as run on Modal (https://modal.com)

.. GENERATED FROM PYTHON SOURCE LINES 13-57



.. rst-class:: sphx-glr-horizontal


    *

      .. image-sg:: /examples/benchmarks/images/sphx_glr_plot_modal_001.png
         :alt: plot modal
         :srcset: /examples/benchmarks/images/sphx_glr_plot_modal_001.png
         :class: sphx-glr-multi-img

    *

      .. image-sg:: /examples/benchmarks/images/sphx_glr_plot_modal_002.png
         :alt: plot modal
         :srcset: /examples/benchmarks/images/sphx_glr_plot_modal_002.png
         :class: sphx-glr-multi-img





.. code-block:: Python



    import os

    import matplotlib.pyplot as plt
    import numpy as np

    backends = ["numpy", "scipy", "autograd", "jax", "torch"]
    inputs = [(b, "cpu") for b in backends]
    inputs += [(b, "gpu") for b in ["jax", "torch"]]


    t = []

    plt.figure()

    for i in inputs:
        backend, device = i
        fname = f"modal/benchmark_{backend}_{device}.npz"
        arch = np.load(fname)
        times = arch["times"]
        times_all = arch["times_all"]
        real_nh = arch["real_nh"]
        nh = arch["nh"]

        t.append(times_all)

        plt.plot(real_nh, times_all, "-o", label=f"{backend} {device}")
    plt.legend()
    plt.xlabel("number of harmonics")
    plt.ylabel("time [s]")
    plt.xscale("log")
    plt.yscale("log")


    plt.figure()
    for j, i in enumerate(inputs):
        backend, device = i
        plt.plot(real_nh, t[0] / t[j], "-o", label=f"{backend} {device}")
    plt.legend()
    plt.xlabel("number of harmonics")
    plt.ylabel("speedup vs numpy")
    plt.xscale("log")
    # plt.yscale("log")


.. rst-class:: sphx-glr-timing

   **Total running time of the script:** (0 minutes 0.622 seconds)

**Estimated memory usage:**  519 MB


.. _sphx_glr_download_examples_benchmarks_plot_modal.py:

.. only:: html

  .. container:: sphx-glr-footer sphx-glr-footer-example

    .. container:: binder-badge

      .. image:: images/binder_badge_logo.svg
        :target: https://mybinder.org/v2/gh/nannos/nannos.gitlab.io/doc?filepath=notebooks/examples/benchmarks/plot_modal.ipynb
        :alt: Launch binder
        :width: 150 px

    .. container:: sphx-glr-download sphx-glr-download-jupyter

      :download:`Download Jupyter notebook: plot_modal.ipynb <plot_modal.ipynb>`

    .. container:: sphx-glr-download sphx-glr-download-python

      :download:`Download Python source code: plot_modal.py <plot_modal.py>`

    .. container:: sphx-glr-download sphx-glr-download-zip

      :download:`Download zipped: plot_modal.zip <plot_modal.zip>`


.. only:: html

 .. rst-class:: sphx-glr-signature

    `Gallery generated by Sphinx-Gallery <https://sphinx-gallery.github.io>`_