--------------------------------------------------------------------------
pathos: parallel graph management and execution in heterogeneous computing
--------------------------------------------------------------------------
About the Pathos Framework
==========================
``pathos`` is a framework for heterogeneous computing. It provides a consistent
high-level interface for configuring and launching parallel computations
across heterogeneous resources. ``pathos`` provides configurable launchers for
parallel and distributed computing, where each launcher contains the
syntactic logic to configure and launch jobs in an execution environment.
Examples of launchers that plug into ``pathos`` are: a queue-less MPI-based
launcher (in ``pyina``), a ssh-based launcher (in ``pathos``), and a multi-process
launcher (in ``multiprocess``).
``pathos`` provides a consistent interface for parallel and/or distributed
versions of ``map`` and ``apply`` for each launcher, thus lowering the barrier
for users to extend their code to parallel and/or distributed resources.
The guiding design principle behind ``pathos`` is that ``map`` and ``apply``
should be drop-in replacements in otherwise serial code, and thus switching
to one or more of the ``pathos`` launchers is all that is needed to enable
code to leverage the selected parallel or distributed computing resource.
This not only greatly reduces the time to convert a code to parallel, but it
also enables a single code-base to be maintained instead of requiring
parallel, serial, and distributed versions of a code. ``pathos`` maps can be
nested, thus hierarchical heterogeneous computing is possible by merely
selecting the desired hierarchy of ``map`` and ``pipe`` (``apply``) objects.
The ``pathos`` framework is composed of several interoperating packages:
- ``dill``: serialize all of Python
- ``pox``: utilities for filesystem exploration and automated builds
- ``klepto``: persistent caching to memory, disk, or database
- ``multiprocess``: better multiprocessing and multithreading in Python
- ``ppft``: distributed and parallel Python
- ``pyina``: MPI parallel ``map`` and cluster scheduling
- ``pathos``: graph management and execution in heterogeneous computing
About Pathos
============
The ``pathos`` package provides a few basic tools to make parallel and
distributed computing more accessible to the end user. The goal of ``pathos``
is to enable the user to extend their own code to parallel and distributed
computing with minimal refactoring.
``pathos`` provides methods for configuring, launching, monitoring, and
controlling a service on a remote host. One of the most basic features
of ``pathos`` is the ability to configure and launch a RPC-based service
on a remote host. ``pathos`` seeds the remote host with the ``portpicker``
script, which allows the remote host to inform the localhost of a port
that is available for communication.
Beyond the ability to establish a RPC service, and then post requests,
is the ability to launch code in parallel. Unlike parallel computing
performed at the node level (typically with MPI), ``pathos`` enables the
user to launch jobs in parallel across heterogeneous distributed resources.
``pathos`` provides distributed ``map`` and ``pipe`` algorithms, where a mix of
local processors and distributed workers can be selected. ``pathos``
also provides a very basic automated load balancing service, as well as
the ability for the user to directly select the resources.
The high-level ``pool.map`` interface, yields a ``map`` implementation that
hides the RPC internals from the user. With ``pool.map``, the user can launch
their code in parallel, and as a distributed service, using standard Python
and without writing a line of server or parallel batch code.
RPC servers and communication in general is known to be insecure. However,
instead of attempting to make the RPC communication itself secure, ``pathos``
provides the ability to automatically wrap any distributes service or
communication in a ssh-tunnel. Ssh is a universally trusted method.
Using ssh-tunnels, ``pathos`` has launched several distributed calculations
on national lab clusters, and to date has performed test calculations
that utilize node-to-node communication between several national lab clusters
and a user's laptop. ``pathos`` allows the user to configure and launch
at a very atomistic level, through raw access to ssh and scp.
``pathos`` is the core of a Python framework for heterogeneous computing.
``pathos`` is in active development, so any user feedback, bug reports, comments,
or suggestions are highly appreciated. A list of issues is located at https://github.com/uqfoundation/pathos/issues, with a legacy list maintained at https://uqfoundation.github.io/project/pathos/query.
Major Features
==============
``pathos`` provides a configurable distributed parallel ``map`` interface
to launching RPC service calls, with:
- a ``map`` interface that meets and extends the Python ``map`` standard
- the ability to submit service requests to a selection of servers
- the ability to tunnel server communications with ssh
The ``pathos`` core is built on low-level communication to remote hosts using
ssh. The interface to ssh, scp, and ssh-tunneled connections can:
- configure and launch remote processes with ssh
- configure and copy file objects with scp
- establish an tear-down a ssh-tunnel
To get up and running quickly, ``pathos`` also provides infrastructure to:
- easily establish a ssh-tunneled connection to a RPC server
Current Release
===============
The latest released version of ``pathos`` is available from:
https://pypi.org/project/pathos
``pathos`` is distributed under a 3-clause BSD license.
Development Version
===================
You can get the latest development version with all the shiny new features at:
https://github.com/uqfoundation
If you have a new contribution, please submit a pull request.
Installation
============
``pathos`` can be installed with ``pip``::
$ pip install pathos
Requirements
============
``pathos`` requires:
- ``python`` (or ``pypy``), **>=3.8**
- ``setuptools``, **>=42**
- ``pox``, **>=0.3.4**
- ``dill``, **>=0.3.8**
- ``ppft``, **>=1.7.6.8**
- ``multiprocess``, **>=0.70.16**
More Information
================
Probably the best way to get started is to look at the documentation at
http://pathos.rtfd.io. Also see ``pathos.tests`` and https://github.com/uqfoundation/pathos/tree/master/examples for a set of scripts that demonstrate the
configuration and launching of communications with ssh and scp, and demonstrate
the configuration and execution of jobs in a hierarchical parallel workflow.
You can run the test suite with ``python -m pathos.tests``. Tunnels and other
connections to remote servers can be established with the ``pathos_connect``
script (or with ``python -m pathos``). See ``pathos_connect --help`` for more
information. ``pathos`` also provides a ``portpicker`` script to select an
open port (also available with ``python -m pathos.portpicker``). The source
code is generally well documented, so further questions may be resolved by
inspecting the code itself. Please feel free to submit a ticket on github,
or ask a question on stackoverflow (**@Mike McKerns**). If you would like to
share how you use ``pathos`` in your work, please send an email (to **mmckerns
at uqfoundation dot org**).
Important classes and functions are found here:
- ``pathos.abstract_launcher`` [the worker pool API definition]
- ``pathos.pools`` [all of the pathos worker pools]
- ``pathos.core`` [the high-level command interface]
- ``pathos.hosts`` [the hostname registry interface]
- ``pathos.serial.SerialPool`` [the serial Python worker pool]
- ``pathos.parallel.ParallelPool`` [the parallelpython worker pool]
- ``pathos.multiprocessing.ProcessPool`` [the multiprocessing worker pool]
- ``pathos.threading.ThreadPool`` [the multithreading worker pool]
- ``pathos.connection.Pipe`` [the launcher base class]
- ``pathos.secure.Pipe`` [the secure launcher base class]
- ``pathos.secure.Copier`` [the secure copier base class]
- ``pathos.secure.Tunnel`` [the secure tunnel base class]
- ``pathos.selector.Selector`` [the selector base class]
- ``pathos.server.Server`` [the server base class]
- ``pathos.profile`` [profiling in threads and processes]
- ``pathos.maps`` [standalone map instances]
``pathos`` also provides two convenience scripts that are used to establish
secure distributed connections. These scripts are installed to a directory
on the user's ``$PATH``, and thus can be run from anywhere:
- ``portpicker`` [get the portnumber of an open port]
- ``pathos_connect`` [establish tunnel and/or RPC server]
Typing ``--help`` as an argument to any of the above scripts will print out an
instructive help message.
Citation
========
If you use ``pathos`` to do research that leads to publication, we ask that you
acknowledge use of ``pathos`` by citing the following in your publication::
M.M. McKerns, L. Strand, T. Sullivan, A. Fang, M.A.G. Aivazis,
"Building a framework for predictive science", Proceedings of
the 10th Python in Science Conference, 2011;
http://arxiv.org/pdf/1202.1056
Michael McKerns and Michael Aivazis,
"pathos: a framework for heterogeneous computing", 2010- ;
https://uqfoundation.github.io/project/pathos
Please see https://uqfoundation.github.io/project/pathos or
http://arxiv.org/pdf/1202.1056 for further information.
Raw data
{
"_id": null,
"home_page": "https://github.com/uqfoundation/pathos",
"name": "pathos",
"maintainer": "Mike McKerns",
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": "mmckerns@uqfoundation.org",
"keywords": "",
"author": "Mike McKerns",
"author_email": "mmckerns@uqfoundation.org",
"download_url": "https://files.pythonhosted.org/packages/be/99/7fcb91495e40735958a576b9bde930cc402d594e9ad5277bdc9b6326e1c8/pathos-0.3.2.tar.gz",
"platform": "Linux",
"description": "--------------------------------------------------------------------------\npathos: parallel graph management and execution in heterogeneous computing\n--------------------------------------------------------------------------\n\nAbout the Pathos Framework\n==========================\n\n``pathos`` is a framework for heterogeneous computing. It provides a consistent\nhigh-level interface for configuring and launching parallel computations\nacross heterogeneous resources. ``pathos`` provides configurable launchers for\nparallel and distributed computing, where each launcher contains the\nsyntactic logic to configure and launch jobs in an execution environment.\nExamples of launchers that plug into ``pathos`` are: a queue-less MPI-based\nlauncher (in ``pyina``), a ssh-based launcher (in ``pathos``), and a multi-process\nlauncher (in ``multiprocess``).\n\n``pathos`` provides a consistent interface for parallel and/or distributed\nversions of ``map`` and ``apply`` for each launcher, thus lowering the barrier\nfor users to extend their code to parallel and/or distributed resources.\nThe guiding design principle behind ``pathos`` is that ``map`` and ``apply``\nshould be drop-in replacements in otherwise serial code, and thus switching\nto one or more of the ``pathos`` launchers is all that is needed to enable\ncode to leverage the selected parallel or distributed computing resource.\nThis not only greatly reduces the time to convert a code to parallel, but it\nalso enables a single code-base to be maintained instead of requiring\nparallel, serial, and distributed versions of a code. ``pathos`` maps can be\nnested, thus hierarchical heterogeneous computing is possible by merely\nselecting the desired hierarchy of ``map`` and ``pipe`` (``apply``) objects.\n\nThe ``pathos`` framework is composed of several interoperating packages:\n\n - ``dill``: serialize all of Python\n - ``pox``: utilities for filesystem exploration and automated builds\n - ``klepto``: persistent caching to memory, disk, or database\n - ``multiprocess``: better multiprocessing and multithreading in Python\n - ``ppft``: distributed and parallel Python\n - ``pyina``: MPI parallel ``map`` and cluster scheduling\n - ``pathos``: graph management and execution in heterogeneous computing\n\n\nAbout Pathos\n============\n\nThe ``pathos`` package provides a few basic tools to make parallel and\ndistributed computing more accessible to the end user. The goal of ``pathos``\nis to enable the user to extend their own code to parallel and distributed\ncomputing with minimal refactoring.\n\n``pathos`` provides methods for configuring, launching, monitoring, and\ncontrolling a service on a remote host. One of the most basic features\nof ``pathos`` is the ability to configure and launch a RPC-based service\non a remote host. ``pathos`` seeds the remote host with the ``portpicker``\nscript, which allows the remote host to inform the localhost of a port\nthat is available for communication.\n\nBeyond the ability to establish a RPC service, and then post requests,\nis the ability to launch code in parallel. Unlike parallel computing\nperformed at the node level (typically with MPI), ``pathos`` enables the\nuser to launch jobs in parallel across heterogeneous distributed resources.\n``pathos`` provides distributed ``map`` and ``pipe`` algorithms, where a mix of\nlocal processors and distributed workers can be selected. ``pathos``\nalso provides a very basic automated load balancing service, as well as\nthe ability for the user to directly select the resources.\n\nThe high-level ``pool.map`` interface, yields a ``map`` implementation that\nhides the RPC internals from the user. With ``pool.map``, the user can launch\ntheir code in parallel, and as a distributed service, using standard Python\nand without writing a line of server or parallel batch code.\n\nRPC servers and communication in general is known to be insecure. However,\ninstead of attempting to make the RPC communication itself secure, ``pathos``\nprovides the ability to automatically wrap any distributes service or\ncommunication in a ssh-tunnel. Ssh is a universally trusted method.\nUsing ssh-tunnels, ``pathos`` has launched several distributed calculations\non national lab clusters, and to date has performed test calculations\nthat utilize node-to-node communication between several national lab clusters\nand a user's laptop. ``pathos`` allows the user to configure and launch\nat a very atomistic level, through raw access to ssh and scp. \n\n``pathos`` is the core of a Python framework for heterogeneous computing.\n``pathos`` is in active development, so any user feedback, bug reports, comments,\nor suggestions are highly appreciated. A list of issues is located at https://github.com/uqfoundation/pathos/issues, with a legacy list maintained at https://uqfoundation.github.io/project/pathos/query.\n\n\nMajor Features\n==============\n\n``pathos`` provides a configurable distributed parallel ``map`` interface\nto launching RPC service calls, with:\n\n - a ``map`` interface that meets and extends the Python ``map`` standard\n - the ability to submit service requests to a selection of servers\n - the ability to tunnel server communications with ssh\n\nThe ``pathos`` core is built on low-level communication to remote hosts using\nssh. The interface to ssh, scp, and ssh-tunneled connections can:\n\n - configure and launch remote processes with ssh\n - configure and copy file objects with scp\n - establish an tear-down a ssh-tunnel\n\nTo get up and running quickly, ``pathos`` also provides infrastructure to:\n\n - easily establish a ssh-tunneled connection to a RPC server\n\n\nCurrent Release\n===============\n\nThe latest released version of ``pathos`` is available from:\n\n https://pypi.org/project/pathos\n\n``pathos`` is distributed under a 3-clause BSD license.\n\n\nDevelopment Version\n===================\n\nYou can get the latest development version with all the shiny new features at:\n\n https://github.com/uqfoundation\n\nIf you have a new contribution, please submit a pull request.\n\n\nInstallation\n============\n\n``pathos`` can be installed with ``pip``::\n\n $ pip install pathos\n\n\nRequirements\n============\n\n``pathos`` requires:\n\n - ``python`` (or ``pypy``), **>=3.8**\n - ``setuptools``, **>=42**\n - ``pox``, **>=0.3.4**\n - ``dill``, **>=0.3.8**\n - ``ppft``, **>=1.7.6.8**\n - ``multiprocess``, **>=0.70.16**\n\n\nMore Information\n================\n\nProbably the best way to get started is to look at the documentation at\nhttp://pathos.rtfd.io. Also see ``pathos.tests`` and https://github.com/uqfoundation/pathos/tree/master/examples for a set of scripts that demonstrate the\nconfiguration and launching of communications with ssh and scp, and demonstrate\nthe configuration and execution of jobs in a hierarchical parallel workflow.\nYou can run the test suite with ``python -m pathos.tests``. Tunnels and other\nconnections to remote servers can be established with the ``pathos_connect``\nscript (or with ``python -m pathos``). See ``pathos_connect --help`` for more\ninformation. ``pathos`` also provides a ``portpicker`` script to select an\nopen port (also available with ``python -m pathos.portpicker``). The source\ncode is generally well documented, so further questions may be resolved by\ninspecting the code itself. Please feel free to submit a ticket on github,\nor ask a question on stackoverflow (**@Mike McKerns**). If you would like to\nshare how you use ``pathos`` in your work, please send an email (to **mmckerns\nat uqfoundation dot org**).\n\nImportant classes and functions are found here:\n\n - ``pathos.abstract_launcher`` [the worker pool API definition]\n - ``pathos.pools`` [all of the pathos worker pools]\n - ``pathos.core`` [the high-level command interface] \n - ``pathos.hosts`` [the hostname registry interface] \n - ``pathos.serial.SerialPool`` [the serial Python worker pool]\n - ``pathos.parallel.ParallelPool`` [the parallelpython worker pool]\n - ``pathos.multiprocessing.ProcessPool`` [the multiprocessing worker pool]\n - ``pathos.threading.ThreadPool`` [the multithreading worker pool]\n - ``pathos.connection.Pipe`` [the launcher base class]\n - ``pathos.secure.Pipe`` [the secure launcher base class]\n - ``pathos.secure.Copier`` [the secure copier base class]\n - ``pathos.secure.Tunnel`` [the secure tunnel base class]\n - ``pathos.selector.Selector`` [the selector base class]\n - ``pathos.server.Server`` [the server base class]\n - ``pathos.profile`` [profiling in threads and processes]\n - ``pathos.maps`` [standalone map instances]\n\n``pathos`` also provides two convenience scripts that are used to establish\nsecure distributed connections. These scripts are installed to a directory\non the user's ``$PATH``, and thus can be run from anywhere:\n\n - ``portpicker`` [get the portnumber of an open port]\n - ``pathos_connect`` [establish tunnel and/or RPC server]\n\nTyping ``--help`` as an argument to any of the above scripts will print out an\ninstructive help message.\n\n\nCitation\n========\n\nIf you use ``pathos`` to do research that leads to publication, we ask that you\nacknowledge use of ``pathos`` by citing the following in your publication::\n\n M.M. McKerns, L. Strand, T. Sullivan, A. Fang, M.A.G. Aivazis,\n \"Building a framework for predictive science\", Proceedings of\n the 10th Python in Science Conference, 2011;\n http://arxiv.org/pdf/1202.1056\n\n Michael McKerns and Michael Aivazis,\n \"pathos: a framework for heterogeneous computing\", 2010- ;\n https://uqfoundation.github.io/project/pathos\n\nPlease see https://uqfoundation.github.io/project/pathos or\nhttp://arxiv.org/pdf/1202.1056 for further information.\n\n",
"bugtrack_url": null,
"license": "BSD-3-Clause",
"summary": "parallel graph management and execution in heterogeneous computing",
"version": "0.3.2",
"project_urls": {
"Bug Tracker": "https://github.com/uqfoundation/pathos/issues",
"Documentation": "http://pathos.rtfd.io",
"Download": "https://pypi.org/project/pathos/#files",
"Homepage": "https://github.com/uqfoundation/pathos",
"Source Code": "https://github.com/uqfoundation/pathos"
},
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "f47fcea34872c000d17972dad998575d14656d7c6bcf1a08a8d66d73c1ef2cca",
"md5": "a230bc90a6749727c76d9ea3e289dd3b",
"sha256": "d669275e6eb4b3fbcd2846d7a6d1bba315fe23add0c614445ba1408d8b38bafe"
},
"downloads": -1,
"filename": "pathos-0.3.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "a230bc90a6749727c76d9ea3e289dd3b",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 82075,
"upload_time": "2024-01-28T19:11:25",
"upload_time_iso_8601": "2024-01-28T19:11:25.560123Z",
"url": "https://files.pythonhosted.org/packages/f4/7f/cea34872c000d17972dad998575d14656d7c6bcf1a08a8d66d73c1ef2cca/pathos-0.3.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "be997fcb91495e40735958a576b9bde930cc402d594e9ad5277bdc9b6326e1c8",
"md5": "4ed63e18f27a5dd164455ecf8a79c52e",
"sha256": "4f2a42bc1e10ccf0fe71961e7145fc1437018b6b21bd93b2446abc3983e49a7a"
},
"downloads": -1,
"filename": "pathos-0.3.2.tar.gz",
"has_sig": false,
"md5_digest": "4ed63e18f27a5dd164455ecf8a79c52e",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 166506,
"upload_time": "2024-01-28T19:11:27",
"upload_time_iso_8601": "2024-01-28T19:11:27.603203Z",
"url": "https://files.pythonhosted.org/packages/be/99/7fcb91495e40735958a576b9bde930cc402d594e9ad5277bdc9b6326e1c8/pathos-0.3.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-01-28 19:11:27",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "uqfoundation",
"github_project": "pathos",
"travis_ci": true,
"coveralls": true,
"github_actions": false,
"tox": true,
"lcname": "pathos"
}
JSON
