1431 lines
No EOL
30 KiB
HTML
1431 lines
No EOL
30 KiB
HTML
|
|
<!doctype html>
|
|
<html lang="en" class="no-js">
|
|
<head>
|
|
|
|
<meta charset="utf-8">
|
|
<meta name="viewport" content="width=device-width,initial-scale=1">
|
|
|
|
|
|
|
|
|
|
<link rel="prev" href="../DEVELOPMENT/">
|
|
|
|
|
|
<link rel="next" href="../api/analysis/">
|
|
|
|
|
|
|
|
|
|
|
|
<link rel="icon" href="../assets/images/favicon.png">
|
|
<meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.7.6">
|
|
|
|
|
|
|
|
<title>HPC Guide - Brittle Star Project</title>
|
|
|
|
|
|
|
|
<link rel="stylesheet" href="../assets/stylesheets/main.484c7ddc.min.css">
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
|
|
<link rel="stylesheet" href="https://fonts.googleapis.com/css?family=Roboto:300,300i,400,400i,700,700i%7CRoboto+Mono:400,400i,700,700i&display=fallback">
|
|
<style>:root{--md-text-font:"Roboto";--md-code-font:"Roboto Mono"}</style>
|
|
|
|
|
|
|
|
<script>__md_scope=new URL("..",location),__md_hash=e=>[...e].reduce(((e,_)=>(e<<5)-e+_.charCodeAt(0)),0),__md_get=(e,_=localStorage,t=__md_scope)=>JSON.parse(_.getItem(t.pathname+"."+e)),__md_set=(e,_,t=localStorage,a=__md_scope)=>{try{t.setItem(a.pathname+"."+e,JSON.stringify(_))}catch(e){}}</script>
|
|
|
|
|
|
|
|
|
|
|
|
</head>
|
|
|
|
|
|
<body dir="ltr">
|
|
|
|
|
|
<input class="md-toggle" data-md-toggle="drawer" type="checkbox" id="__drawer" autocomplete="off">
|
|
<input class="md-toggle" data-md-toggle="search" type="checkbox" id="__search" autocomplete="off">
|
|
<label class="md-overlay" for="__drawer"></label>
|
|
<div data-md-component="skip">
|
|
|
|
|
|
<a href="#hpc-guide" class="md-skip">
|
|
Skip to content
|
|
</a>
|
|
|
|
</div>
|
|
<div data-md-component="announce">
|
|
|
|
</div>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<header class="md-header md-header--shadow" data-md-component="header">
|
|
<nav class="md-header__inner md-grid" aria-label="Header">
|
|
<a href=".." title="Brittle Star Project" class="md-header__button md-logo" aria-label="Brittle Star Project" data-md-component="logo">
|
|
|
|
|
|
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg>
|
|
|
|
</a>
|
|
<label class="md-header__button md-icon" for="__drawer">
|
|
|
|
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M3 6h18v2H3zm0 5h18v2H3zm0 5h18v2H3z"/></svg>
|
|
</label>
|
|
<div class="md-header__title" data-md-component="header-title">
|
|
<div class="md-header__ellipsis">
|
|
<div class="md-header__topic">
|
|
<span class="md-ellipsis">
|
|
Brittle Star Project
|
|
</span>
|
|
</div>
|
|
<div class="md-header__topic" data-md-component="header-topic">
|
|
<span class="md-ellipsis">
|
|
|
|
HPC Guide
|
|
|
|
</span>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
|
|
|
|
<script>var palette=__md_get("__palette");if(palette&&palette.color){if("(prefers-color-scheme)"===palette.color.media){var media=matchMedia("(prefers-color-scheme: light)"),input=document.querySelector(media.matches?"[data-md-color-media='(prefers-color-scheme: light)']":"[data-md-color-media='(prefers-color-scheme: dark)']");palette.color.media=input.getAttribute("data-md-color-media"),palette.color.scheme=input.getAttribute("data-md-color-scheme"),palette.color.primary=input.getAttribute("data-md-color-primary"),palette.color.accent=input.getAttribute("data-md-color-accent")}for(var[key,value]of Object.entries(palette.color))document.body.setAttribute("data-md-color-"+key,value)}</script>
|
|
|
|
|
|
|
|
|
|
|
|
<label class="md-header__button md-icon" for="__search">
|
|
|
|
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.52 6.52 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5"/></svg>
|
|
</label>
|
|
<div class="md-search" data-md-component="search" role="dialog">
|
|
<label class="md-search__overlay" for="__search"></label>
|
|
<div class="md-search__inner" role="search">
|
|
<form class="md-search__form" name="search">
|
|
<input type="text" class="md-search__input" name="query" aria-label="Search" placeholder="Search" autocapitalize="off" autocorrect="off" autocomplete="off" spellcheck="false" data-md-component="search-query" required>
|
|
<label class="md-search__icon md-icon" for="__search">
|
|
|
|
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.52 6.52 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5"/></svg>
|
|
|
|
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M20 11v2H8l5.5 5.5-1.42 1.42L4.16 12l7.92-7.92L13.5 5.5 8 11z"/></svg>
|
|
</label>
|
|
<nav class="md-search__options" aria-label="Search">
|
|
|
|
<button type="reset" class="md-search__icon md-icon" title="Clear" aria-label="Clear" tabindex="-1">
|
|
|
|
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M19 6.41 17.59 5 12 10.59 6.41 5 5 6.41 10.59 12 5 17.59 6.41 19 12 13.41 17.59 19 19 17.59 13.41 12z"/></svg>
|
|
</button>
|
|
</nav>
|
|
|
|
</form>
|
|
<div class="md-search__output">
|
|
<div class="md-search__scrollwrap" tabindex="0" data-md-scrollfix>
|
|
<div class="md-search-result" data-md-component="search-result">
|
|
<div class="md-search-result__meta">
|
|
Initializing search
|
|
</div>
|
|
<ol class="md-search-result__list" role="presentation"></ol>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
|
|
|
|
|
|
</nav>
|
|
|
|
</header>
|
|
|
|
<div class="md-container" data-md-component="container">
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<main class="md-main" data-md-component="main">
|
|
<div class="md-main__inner md-grid">
|
|
|
|
|
|
|
|
<div class="md-sidebar md-sidebar--primary" data-md-component="sidebar" data-md-type="navigation" >
|
|
<div class="md-sidebar__scrollwrap">
|
|
<div class="md-sidebar__inner">
|
|
|
|
|
|
|
|
|
|
<nav class="md-nav md-nav--primary" aria-label="Navigation" data-md-level="0">
|
|
<label class="md-nav__title" for="__drawer">
|
|
<a href=".." title="Brittle Star Project" class="md-nav__button md-logo" aria-label="Brittle Star Project" data-md-component="logo">
|
|
|
|
|
|
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg>
|
|
|
|
</a>
|
|
Brittle Star Project
|
|
</label>
|
|
|
|
<ul class="md-nav__list" data-md-scrollfix>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<a href=".." class="md-nav__link">
|
|
|
|
|
|
|
|
<span class="md-ellipsis">
|
|
|
|
|
|
Documentation
|
|
|
|
|
|
|
|
</span>
|
|
|
|
|
|
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<a href="../CONTRIBUTING/" class="md-nav__link">
|
|
|
|
|
|
|
|
<span class="md-ellipsis">
|
|
|
|
|
|
Contribution Guidelines
|
|
|
|
|
|
|
|
</span>
|
|
|
|
|
|
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<a href="../DEVELOPMENT/" class="md-nav__link">
|
|
|
|
|
|
|
|
<span class="md-ellipsis">
|
|
|
|
|
|
Development Guide
|
|
|
|
|
|
|
|
</span>
|
|
|
|
|
|
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item md-nav__item--active">
|
|
|
|
<input class="md-nav__toggle md-toggle" type="checkbox" id="__toc">
|
|
|
|
|
|
|
|
|
|
|
|
<label class="md-nav__link md-nav__link--active" for="__toc">
|
|
|
|
|
|
|
|
<span class="md-ellipsis">
|
|
|
|
|
|
HPC Guide
|
|
|
|
|
|
|
|
</span>
|
|
|
|
|
|
|
|
<span class="md-nav__icon md-icon"></span>
|
|
</label>
|
|
|
|
<a href="./" class="md-nav__link md-nav__link--active">
|
|
|
|
|
|
|
|
<span class="md-ellipsis">
|
|
|
|
|
|
HPC Guide
|
|
|
|
|
|
|
|
</span>
|
|
|
|
|
|
|
|
</a>
|
|
|
|
|
|
|
|
<nav class="md-nav md-nav--secondary" aria-label="Table of contents">
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<label class="md-nav__title" for="__toc">
|
|
<span class="md-nav__icon md-icon"></span>
|
|
Table of contents
|
|
</label>
|
|
<ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#storage-overview" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
|
|
Storage Overview
|
|
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#initial-environment-setup" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
|
|
Initial Environment Setup
|
|
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#production-vs-debug-clusters" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
|
|
Production vs. Debug Clusters
|
|
|
|
</span>
|
|
</a>
|
|
|
|
<nav class="md-nav" aria-label="Production vs. Debug Clusters">
|
|
<ul class="md-nav__list">
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#debugging-donphan" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
|
|
Debugging (Donphan)
|
|
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#production-joltik-accelgor-litleo" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
|
|
Production (Joltik, Accelgor, Litleo)
|
|
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
</ul>
|
|
</nav>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#interactive-debugging" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
|
|
Interactive Debugging
|
|
|
|
</span>
|
|
</a>
|
|
|
|
<nav class="md-nav" aria-label="Interactive Debugging">
|
|
<ul class="md-nav__list">
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#verification-commands" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
|
|
Verification Commands
|
|
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
</ul>
|
|
</nav>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#managing-dependencies" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
|
|
Managing Dependencies
|
|
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
</ul>
|
|
|
|
</nav>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item md-nav__item--nested">
|
|
|
|
|
|
|
|
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_5" >
|
|
|
|
|
|
<label class="md-nav__link" for="__nav_5" id="__nav_5_label" tabindex="0">
|
|
|
|
|
|
|
|
<span class="md-ellipsis">
|
|
|
|
|
|
Api
|
|
|
|
|
|
|
|
</span>
|
|
|
|
|
|
|
|
<span class="md-nav__icon md-icon"></span>
|
|
</label>
|
|
|
|
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_5_label" aria-expanded="false">
|
|
<label class="md-nav__title" for="__nav_5">
|
|
<span class="md-nav__icon md-icon"></span>
|
|
|
|
|
|
Api
|
|
|
|
|
|
</label>
|
|
<ul class="md-nav__list" data-md-scrollfix>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<a href="../api/analysis/" class="md-nav__link">
|
|
|
|
|
|
|
|
<span class="md-ellipsis">
|
|
|
|
|
|
Analysis & Plotting Tools
|
|
|
|
|
|
|
|
</span>
|
|
|
|
|
|
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<a href="../api/environment/" class="md-nav__link">
|
|
|
|
|
|
|
|
<span class="md-ellipsis">
|
|
|
|
|
|
Brittle star environment
|
|
|
|
|
|
|
|
</span>
|
|
|
|
|
|
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<a href="../api/evaluation/" class="md-nav__link">
|
|
|
|
|
|
|
|
<span class="md-ellipsis">
|
|
|
|
|
|
Checkpoint & Model Evaluation
|
|
|
|
|
|
|
|
</span>
|
|
|
|
|
|
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<a href="../api/simulation/" class="md-nav__link">
|
|
|
|
|
|
|
|
<span class="md-ellipsis">
|
|
|
|
|
|
Simulation & Evaluation
|
|
|
|
|
|
|
|
</span>
|
|
|
|
|
|
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<a href="../api/tracking/" class="md-nav__link">
|
|
|
|
|
|
|
|
<span class="md-ellipsis">
|
|
|
|
|
|
Tracking & Monitoring
|
|
|
|
|
|
|
|
</span>
|
|
|
|
|
|
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<a href="../api/training/" class="md-nav__link">
|
|
|
|
|
|
|
|
<span class="md-ellipsis">
|
|
|
|
|
|
Training Models
|
|
|
|
|
|
|
|
</span>
|
|
|
|
|
|
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
</ul>
|
|
</nav>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item md-nav__item--nested">
|
|
|
|
|
|
|
|
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_6" >
|
|
|
|
|
|
<label class="md-nav__link" for="__nav_6" id="__nav_6_label" tabindex="0">
|
|
|
|
|
|
|
|
<span class="md-ellipsis">
|
|
|
|
|
|
Design
|
|
|
|
|
|
|
|
</span>
|
|
|
|
|
|
|
|
<span class="md-nav__icon md-icon"></span>
|
|
</label>
|
|
|
|
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_6_label" aria-expanded="false">
|
|
<label class="md-nav__title" for="__nav_6">
|
|
<span class="md-nav__icon md-icon"></span>
|
|
|
|
|
|
Design
|
|
|
|
|
|
</label>
|
|
<ul class="md-nav__list" data-md-scrollfix>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<a href="../design/actor-critic/" class="md-nav__link">
|
|
|
|
|
|
|
|
<span class="md-ellipsis">
|
|
|
|
|
|
Actor-Critic Architecture
|
|
|
|
|
|
|
|
</span>
|
|
|
|
|
|
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<a href="../design/communication/" class="md-nav__link">
|
|
|
|
|
|
|
|
<span class="md-ellipsis">
|
|
|
|
|
|
Communication scheme (Message Passing)
|
|
|
|
|
|
|
|
</span>
|
|
|
|
|
|
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<a href="../design/controllers/" class="md-nav__link">
|
|
|
|
|
|
|
|
<span class="md-ellipsis">
|
|
|
|
|
|
Levels of modularity and topology
|
|
|
|
|
|
|
|
</span>
|
|
|
|
|
|
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<a href="../design/input_action_spaces/" class="md-nav__link">
|
|
|
|
|
|
|
|
<span class="md-ellipsis">
|
|
|
|
|
|
Input (state) and output (action) spaces
|
|
|
|
|
|
|
|
</span>
|
|
|
|
|
|
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<a href="../design/learning_algorithm/" class="md-nav__link">
|
|
|
|
|
|
|
|
<span class="md-ellipsis">
|
|
|
|
|
|
Reinforcement Learning Algorithm
|
|
|
|
|
|
|
|
</span>
|
|
|
|
|
|
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<a href="../design/reward_function/" class="md-nav__link">
|
|
|
|
|
|
|
|
<span class="md-ellipsis">
|
|
|
|
|
|
Reward function and observation space
|
|
|
|
|
|
|
|
</span>
|
|
|
|
|
|
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
</ul>
|
|
</nav>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item md-nav__item--nested">
|
|
|
|
|
|
|
|
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_7" >
|
|
|
|
|
|
<label class="md-nav__link" for="__nav_7" id="__nav_7_label" tabindex="0">
|
|
|
|
|
|
|
|
<span class="md-ellipsis">
|
|
|
|
|
|
Scripts
|
|
|
|
|
|
|
|
</span>
|
|
|
|
|
|
|
|
<span class="md-nav__icon md-icon"></span>
|
|
</label>
|
|
|
|
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_7_label" aria-expanded="false">
|
|
<label class="md-nav__title" for="__nav_7">
|
|
<span class="md-nav__icon md-icon"></span>
|
|
|
|
|
|
Scripts
|
|
|
|
|
|
</label>
|
|
<ul class="md-nav__list" data-md-scrollfix>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item md-nav__item--nested">
|
|
|
|
|
|
|
|
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_7_1" >
|
|
|
|
|
|
<label class="md-nav__link" for="__nav_7_1" id="__nav_7_1_label" tabindex="0">
|
|
|
|
|
|
|
|
<span class="md-ellipsis">
|
|
|
|
|
|
Analysis
|
|
|
|
|
|
|
|
</span>
|
|
|
|
|
|
|
|
<span class="md-nav__icon md-icon"></span>
|
|
</label>
|
|
|
|
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_7_1_label" aria-expanded="false">
|
|
<label class="md-nav__title" for="__nav_7_1">
|
|
<span class="md-nav__icon md-icon"></span>
|
|
|
|
|
|
Analysis
|
|
|
|
|
|
</label>
|
|
<ul class="md-nav__list" data-md-scrollfix>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<a href="../scripts/analysis/" class="md-nav__link">
|
|
|
|
|
|
|
|
<span class="md-ellipsis">
|
|
|
|
|
|
Experiment Analysis Tools
|
|
|
|
|
|
|
|
</span>
|
|
|
|
|
|
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
</ul>
|
|
</nav>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
|
|
</ul>
|
|
</nav>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item md-nav__item--nested">
|
|
|
|
|
|
|
|
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_8" >
|
|
|
|
|
|
<label class="md-nav__link" for="__nav_8" id="__nav_8_label" tabindex="0">
|
|
|
|
|
|
|
|
<span class="md-ellipsis">
|
|
|
|
|
|
Src
|
|
|
|
|
|
|
|
</span>
|
|
|
|
|
|
|
|
<span class="md-nav__icon md-icon"></span>
|
|
</label>
|
|
|
|
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_8_label" aria-expanded="false">
|
|
<label class="md-nav__title" for="__nav_8">
|
|
<span class="md-nav__icon md-icon"></span>
|
|
|
|
|
|
Src
|
|
|
|
|
|
</label>
|
|
<ul class="md-nav__list" data-md-scrollfix>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item md-nav__item--nested">
|
|
|
|
|
|
|
|
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_8_1" >
|
|
|
|
|
|
<label class="md-nav__link" for="__nav_8_1" id="__nav_8_1_label" tabindex="0">
|
|
|
|
|
|
|
|
<span class="md-ellipsis">
|
|
|
|
|
|
Experiment logger
|
|
|
|
|
|
|
|
</span>
|
|
|
|
|
|
|
|
<span class="md-nav__icon md-icon"></span>
|
|
</label>
|
|
|
|
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_8_1_label" aria-expanded="false">
|
|
<label class="md-nav__title" for="__nav_8_1">
|
|
<span class="md-nav__icon md-icon"></span>
|
|
|
|
|
|
Experiment logger
|
|
|
|
|
|
</label>
|
|
<ul class="md-nav__list" data-md-scrollfix>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<a href="../src/experiment_logger/" class="md-nav__link">
|
|
|
|
|
|
|
|
<span class="md-ellipsis">
|
|
|
|
|
|
Experiment Logger
|
|
|
|
|
|
|
|
</span>
|
|
|
|
|
|
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
</ul>
|
|
</nav>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
|
|
</ul>
|
|
</nav>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
</ul>
|
|
</nav>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
|
|
|
|
|
|
<div class="md-sidebar md-sidebar--secondary" data-md-component="sidebar" data-md-type="toc" >
|
|
<div class="md-sidebar__scrollwrap">
|
|
<div class="md-sidebar__inner">
|
|
|
|
|
|
<nav class="md-nav md-nav--secondary" aria-label="Table of contents">
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<label class="md-nav__title" for="__toc">
|
|
<span class="md-nav__icon md-icon"></span>
|
|
Table of contents
|
|
</label>
|
|
<ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#storage-overview" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
|
|
Storage Overview
|
|
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#initial-environment-setup" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
|
|
Initial Environment Setup
|
|
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#production-vs-debug-clusters" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
|
|
Production vs. Debug Clusters
|
|
|
|
</span>
|
|
</a>
|
|
|
|
<nav class="md-nav" aria-label="Production vs. Debug Clusters">
|
|
<ul class="md-nav__list">
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#debugging-donphan" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
|
|
Debugging (Donphan)
|
|
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#production-joltik-accelgor-litleo" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
|
|
Production (Joltik, Accelgor, Litleo)
|
|
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
</ul>
|
|
</nav>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#interactive-debugging" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
|
|
Interactive Debugging
|
|
|
|
</span>
|
|
</a>
|
|
|
|
<nav class="md-nav" aria-label="Interactive Debugging">
|
|
<ul class="md-nav__list">
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#verification-commands" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
|
|
Verification Commands
|
|
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
</ul>
|
|
</nav>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#managing-dependencies" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
|
|
Managing Dependencies
|
|
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
</ul>
|
|
|
|
</nav>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
|
|
|
|
|
|
<div class="md-content" data-md-component="content">
|
|
|
|
<article class="md-content__inner md-typeset">
|
|
|
|
|
|
|
|
|
|
|
|
<h1 id="hpc-guide">HPC Guide</h1>
|
|
<p>Full documentation: <a href="https://docs.hpc.ugent.be/">https://docs.hpc.ugent.be/</a></p>
|
|
<h2 id="storage-overview">Storage Overview</h2>
|
|
<ul>
|
|
<li><strong>Run Outputs</strong>: Written to <code>$VSC_SCRATCH</code> during the job (fast I/O) and copied to <code>$VSC_DATA</code> at the end for persistence.</li>
|
|
<li><strong>Virtual Environments</strong>: Managed on <strong><code>$VSC_DATA</code></strong> by mirroring configuration files. This avoids the 3GB home quota without requiring symlinks in the project root.</li>
|
|
</ul>
|
|
<h2 id="initial-environment-setup">Initial Environment Setup</h2>
|
|
<p>Run <strong>once</strong> after cloning the repository. This script handles all modules, mirroring, and environment synchronization.</p>
|
|
<div class="highlight"><pre><span></span><code><span class="c1"># Option A: Interactive (on a compute node)</span>
|
|
module<span class="w"> </span>swap<span class="w"> </span>cluster/donphan<span class="w"> </span><span class="c1"># Debug cluster (CPU only)</span>
|
|
<span class="c1"># OR for GPU clusters:</span>
|
|
<span class="c1"># module swap cluster/joltik</span>
|
|
<span class="c1"># module swap cluster/accelgor</span>
|
|
<span class="c1"># module swap cluster/litleo</span>
|
|
|
|
qsub<span class="w"> </span>-I<span class="w"> </span>-l<span class="w"> </span><span class="nv">nodes</span><span class="o">=</span><span class="m">1</span>:gpus<span class="o">=</span><span class="m">1</span><span class="w"> </span><span class="c1"># Only for GPU clusters</span>
|
|
<span class="nb">cd</span><span class="w"> </span><span class="s2">"</span><span class="si">${</span><span class="nv">PBS_O_WORKDIR</span><span class="si">}</span><span class="s2">"</span>
|
|
bash<span class="w"> </span>scripts/hpc/install.sh
|
|
|
|
<span class="c1"># Option B: Batch (Run in background)</span>
|
|
<span class="c1"># NOTE: GPU clusters (joltik/accelgor/litleo) require -l gpus=1 at runtime</span>
|
|
qsub<span class="w"> </span>-l<span class="w"> </span><span class="nv">gpus</span><span class="o">=</span><span class="m">1</span><span class="w"> </span>scripts/hpc/install.sh
|
|
</code></pre></div>
|
|
<h2 id="production-vs-debug-clusters">Production vs. Debug Clusters</h2>
|
|
<p>Our scripts are cluster-agnostic and do <strong>not</strong> have hardcoded GPU requirements. Instead, you must request GPUs at runtime using the <code>-l gpus=1</code> flag when submitting to a production GPU cluster.</p>
|
|
<h3 id="debugging-donphan">Debugging (Donphan)</h3>
|
|
<p>The <code>donphan</code> cluster does not support GPUs. Simply run the scripts without extra resource flags:
|
|
<div class="highlight"><pre><span></span><code>module<span class="w"> </span>swap<span class="w"> </span>cluster/donphan
|
|
qsub<span class="w"> </span>scripts/hpc/train.pbs
|
|
</code></pre></div></p>
|
|
<h3 id="production-joltik-accelgor-litleo">Production (Joltik, Accelgor, Litleo)</h3>
|
|
<p>These clusters provide GPU acceleration and <strong>require</strong> a GPU request at runtime:
|
|
<div class="highlight"><pre><span></span><code>module<span class="w"> </span>swap<span class="w"> </span>cluster/joltik<span class="w"> </span><span class="c1"># or accelgor/litleo</span>
|
|
qsub<span class="w"> </span>-l<span class="w"> </span><span class="nv">gpus</span><span class="o">=</span><span class="m">1</span><span class="w"> </span>scripts/hpc/train.pbs
|
|
</code></pre></div></p>
|
|
<h2 id="interactive-debugging">Interactive Debugging</h2>
|
|
<p>To activate your environment for interactive work, simply run the same <code>install.sh</code> script.</p>
|
|
<div class="highlight"><pre><span></span><code>qsub<span class="w"> </span>-I<span class="w"> </span>-l<span class="w"> </span><span class="nv">nodes</span><span class="o">=</span><span class="m">1</span>:ppn<span class="o">=</span><span class="m">4</span><span class="w"> </span>-l<span class="w"> </span><span class="nv">walltime</span><span class="o">=</span><span class="m">1</span>:00:00
|
|
<span class="nb">cd</span><span class="w"> </span><span class="s2">"</span><span class="nv">$PBS_O_WORKDIR</span><span class="s2">"</span>
|
|
bash<span class="w"> </span>scripts/hpc/install.sh
|
|
</code></pre></div>
|
|
<h3 id="verification-commands">Verification Commands</h3>
|
|
<p>After installation, run these commands to ensure your environment is set up correctly:</p>
|
|
<ol>
|
|
<li>
|
|
<p><strong>Verify Quota Safety</strong>:
|
|
<div class="highlight"><pre><span></span><code>ls<span class="w"> </span>-d<span class="w"> </span>venvs<span class="w"> </span><span class="m">2</span>>/dev/null<span class="w"> </span><span class="o">&&</span><span class="w"> </span><span class="nb">echo</span><span class="w"> </span><span class="s2">"FAIL"</span><span class="w"> </span><span class="o">||</span><span class="w"> </span><span class="nb">echo</span><span class="w"> </span><span class="s2">">>> PASS: Project root is clean."</span>
|
|
</code></pre></div></p>
|
|
</li>
|
|
<li>
|
|
<p><strong>Verify Library Versions (NumPy Fix)</strong>:
|
|
<div class="highlight"><pre><span></span><code>python<span class="w"> </span>-c<span class="w"> </span><span class="s2">"import numpy; print(f'NumPy: {numpy.__version__}')"</span>
|
|
<span class="c1"># Expected: 2.x.x (Venv version), not 1.2x (System version)</span>
|
|
</code></pre></div></p>
|
|
</li>
|
|
<li>
|
|
<p><strong>Verify GPU Access</strong>:
|
|
<div class="highlight"><pre><span></span><code>python<span class="w"> </span>-c<span class="w"> </span><span class="s2">"import torch, jax; print(f'GPU: {torch.cuda.is_available()}'); print(f'JAX: {jax.devices()}')"</span>
|
|
</code></pre></div></p>
|
|
</li>
|
|
</ol>
|
|
<h2 id="managing-dependencies">Managing Dependencies</h2>
|
|
<p><code>env/hpc/requirements.txt</code> is auto-generated from <code>pyproject.toml</code>. To regenerate:</p>
|
|
<div class="highlight"><pre><span></span><code>uv<span class="w"> </span>run<span class="w"> </span>scripts/hpc/export_requirements.py
|
|
</code></pre></div>
|
|
<p>Modules listed in <code>env/hpc/modules.txt</code> are automatically excluded from the pip requirements to save space and use HPC-optimized binaries.</p>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
</article>
|
|
</div>
|
|
|
|
|
|
<script>var target=document.getElementById(location.hash.slice(1));target&&target.name&&(target.checked=target.name.startsWith("__tabbed_"))</script>
|
|
</div>
|
|
|
|
</main>
|
|
|
|
<footer class="md-footer">
|
|
|
|
<div class="md-footer-meta md-typeset">
|
|
<div class="md-footer-meta__inner md-grid">
|
|
<div class="md-copyright">
|
|
|
|
|
|
Made with
|
|
<a href="https://squidfunk.github.io/mkdocs-material/" target="_blank" rel="noopener">
|
|
Material for MkDocs
|
|
</a>
|
|
|
|
</div>
|
|
|
|
</div>
|
|
</div>
|
|
</footer>
|
|
|
|
</div>
|
|
<div class="md-dialog" data-md-component="dialog">
|
|
<div class="md-dialog__inner md-typeset"></div>
|
|
</div>
|
|
|
|
|
|
|
|
|
|
|
|
<script id="__config" type="application/json">{"annotate": null, "base": "..", "features": [], "search": "../assets/javascripts/workers/search.2c215733.min.js", "tags": null, "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}, "version": null}</script>
|
|
|
|
|
|
<script src="../assets/javascripts/bundle.79ae519e.min.js"></script>
|
|
|
|
|
|
</body>
|
|
</html> |