{% extends "codespeed/base_site.html" %}

{% block title %}{{ block.super }}: About this site{% endblock %}

{% block body %}

<div id="sidebar">

<div id="about" class="about_content clearfix">

<h3>About this site</h3>

<p>Welcome to the speed.python.org project - this project is aimed at

constructing a shared benchmark system based on the excellent

<a href="https://speed.pypy.org/" target="_blank">speed.pypy.org</a>

project.

<p>This project will setup a common, shared instance of the benchmarking

suite and visualization tools put together by the

<a href="https://pypy.org/" target="_blank">PyPy team</a>, based on work

from the <a href="https://code.google.com/p/unladen-swallow/" target="_blank">

Unladen Swallow project</a>.

<p>Coming out of the PyCon 2011 VM and language summits, it was commonly

agreed that PyPy, CPython, IronPython and Jython should strive to move

to a common set of benchmarks and a single performance-oriented site.

This was agreed upon by the maintainers present at the conference, and

included leads from all of the major implementations. This project

would be lead by the various VM development teams, and based around

the Unladen Swallow/PyPy benchmark suite.

<p>Once set up, this site will be prominently linked on Python.org, and serve

as a resource for all Python users - both existing and potential - to evaluate

the various Python runtimes on both performance, memory usage, etc. Our goal is

to provide a resource that will both educate and assist users, maintainers and

the community as a whole.

<p>You can see the announcement, and more details at the announcement of the

machine acquisition on

<a href="https://web.archive.org/web/20170824021111/http://jessenoller.com/2011/06/29/announcing-the-new-speed-python-org-machine/" target="_blank">

Jesse Noller's blog.</a></p>

<p>For now, only CPython is being benchmarked, but we hope to expand in the future.</p>

<h3>The Benchmark Machines</h3>

<p>On speed.python.org both <b>x86</b> and <b>AArch64</b> architectures are being

measured. Below the specs of the machines used.</p>

<h4>The x86 machine</h4>

<p>Nicknamed "the beast", the machine was generously donated to the Python

Software foundation by the <a href="https://hp.com/go/linux" target="_blank">

HP Open Source Program office</a>.</p>

<p>The hardware specs are:

<li>DL380 HP DL380G7 X5670 LFF (2U)</li>

<li>Dual HP NC382i Dual Port Multifunction Gigabit Server Adapters</li>

<li>HP Smart Array P410i/1GB FBWC Controller</li>

<li>4x 4GB (1x4GB) Dual Rank x4 PC3-10600 (DDR3-1333) Registered CAS-9

Memory Kit</li>

<li>2x HP 750W Common Slot Gold Hot Plug Power Supply Kit</li>

<li>HP iLO Advanced including 1yr 24x7 Technical Support and Updates

Electronic License</li>

<li>4x HP 300GB 6G SAS 15K rpm LFF (3.5-inch) Dual Port Enterprise 3yr

Warranty Hard Drive</li>

<li>2 HP DL380 G7 Intel® Xeon® X5680 (3.33GHz/6-core/130W/12MB) FIO

Processor Kit</li>

The machine is configured with Ubuntu 18.04 LTS, HW RAID and a simple LVM setup.

HP's generous donation can not be spoken of highly enough.

<p>The racking, stacking and hardware administration and all bandwidth has been

generously donated by the <a href="https://osuosl.org/" target="_blank">

The Oregon State University Open Source Lab</a> (OSUOSL)

who have been amazing open source supporters, and supporters of the Python

Software foundation.</p>

<p>We can not thank OSUOSL enough for the hosting and administration.</p>

<h4>The AArch64 machine</h4>

<p>The machine is generously sponsored by <a href="https://www.arm.com">Arm Ltd</a>

through the <a href="https://www.arm.com/markets/computing-infrastructure/works-on-arm">

Works on Arm project</a>.</p>

<p>The hardware specs are:

<li>1xAmpere Altra ARMv8 Processor at 3Ghz (80 cores)</li>

<li>256GB RAM</li>

<li>1x960GB SSD</li>

<li>2x10Gbps</li>

The machine is configured with Ubuntu 22.04.2 LTS and administered by

<a href="https://github.com/diegorusso">Diego Russo</a> and

<a href="https://github.com/ambv">Łukasz Langa</a>.</p>

<p>The hosting, the hardware, the provisioning of the machine is all provided by

<a href="https://www.equinix.co.uk/">Equinix</a>.</p>

<h3>About the benchmarks</h3>

<p>The code can be found <a href="https://github.com/python/pyperformance">here</a>.</p>

<h3>About Python</h3>

<p>Python is a programming language that lets you work quickly and integrate systems more effectively.</p>

<p>Main website: <a href="https://python.org/">python.org</a></p>

<h3>About Codespeed</h3>

Codespeed is a web application to monitor and analyze the performance of your code.

<p>Original Code: <a href="https://github.com/tobami/codespeed">github.com/tobami/codespeed</a></p>

<p>Code for this site: <a href="https://github.com/python/codespeed/tree/speed.python.org">github.com/python/codespeed</a></p>

<p>Wiki: <a href="https://github.com/tobami/codespeed/wiki">github.com/tobami/codespeed/wiki</a></p>

<h3>Contact</h3>

<p>For problems or suggestions about this website write to us on

<a href="https://discuss.python.org/c/core-dev/23">discuss.python.org</a>.

</p>

{% endblock %}