
Coder Survival Guide
Rapport MesoNET - GT GES
Financé par l’ANR dans le cadre du PIA3, le projet MesoNET regroupe 21 mésocentres régionaux et l’IR* GENCI en tant que partenaire coordinateur. MesoNET visant à créer une Infrastructure de Recherche nationale distribuée de type mésocentre, l’impact environnemental des investissements et activités de ce projet soulève plusieurs questions. Comment estimer l’empreinte carbone d’une infrastructure de calcul ou de stockage ? Comment permettre aux utilisateurs d’évaluer l’empreinte de leur activité calculatoire ? Afin d’y apporter des éléments de réponse, le groupe de travail GES de MesoNET s’est intéressé à une méthode d’évaluation de l’empreinte carbone globale d’un centre de calcul, résultant de travaux menés par des membres de Labos 1point5, d’EcoInfo, du GRICAD et de GENCI.
La méthodologie proposée permet d’estimer le coût carbone d’une heure de calcul sur un cœur CPU ou sur un GPU et le coût équivalent carbone pour stocker 1 Go de données / an. Cette méthodologie a ainsi été appliquée à des mésocentres régionaux du réseau MesoNET : nous en décrirons les résultats obtenus et les limites observées. Nous mettrons également en lumière quelques indicateurs clés de la méthode. Enfin, nous proposerons des recommandations pour mettre en œuvre les pratiques, outils et réflexions nécessaires à la réduction des impacts environnementaux des activités des mésocentres. Les résultats obtenus dans le cadre de MesoNET pourront alimenter l’application GES 1point5 afin de permettre aux utilisateurs d’évaluer l’empreinte carbone de leurs calculs.
Impacts environnementaux du numérique dans le monde 2025 - Asso. GreenIT
Réalisée par le groupe Etudes de l’association Green IT, cette étude porte sur les impacts environnementaux du numérique à l’échelle mondiale. Elle s’appuie sur une méthodologie d’Analyse du Cycle de Vie (ACV) multicritère. L’objectif de cette étude et d’apporter un éclairage scientifique par une évaluation quantifiée des impacts environnementaux du numérique, afin que chacun∙e d’entrePoursuivre la lecture "Impacts environnementaux du numérique dans le monde 2025"
The Ecole normale supérieure, AI & Society Institute and Capgemini launch a global Observatory on AI’s environmental impact
With the support of Capgemini, the AI and Society Institute, the Ecole normale supérieure (ENS-PLS) and the ENS Foundation have launched an Observatory dedicated to analyzing and mitigating the environmental impacts of Artificial Intelligence (AI) at all stages of its lifecycle (training, adjustment, inference and end-of-life). The new Observatory aims to establish a solid, shared methodology to encourage sustainable AI usage.
What a Web Performance Engineer Needs to Know About Cloud Cost Savings
Every line of code has a cost - but some lines cost more than others. This rather Orwellian-sounding statement might seem stark, but for web performance engineers, it's a useful perspective when considering cloud costs.
Why Should You Care About Costs?
Cost reduction directly impacts the bottom li
Putting Performance in Relatable Terms
A 300ms improvement may sound like a big win to someone immersed in web performance optimization, but for most people, mentioning milliseconds doesn't usually resonate or seem meaningful. Whenever I've mentioned how we could save a few hundred milliseconds to an executive, my proposal was often met
Not every user owns an iPhone
As software engineers and technologists its common to have access to some powerful devices and super fast bandwidths. It's highly likely that you will be developing/testing on a high end Mac (or similar) or pulling out an expensive mobile device such as an iPhone from your pocket.
But we need to be
Don't Let Your Redesign Ruin Performance: A Case Study
It's a shame that so many redesigns end up slowing down the site or dropping conversions. How to prevent this? In this text, based on one of our successful projects, you will get a framework for web redesign management.
We are a small team of web performance consultants with years of experience and
My Favorite Web Performance Graphs of the Year
As a web performance consultant, I frequently rely on visual data to prioritize optimizations and troubleshoot regressions. Over the past year, two types of graphs have stood out for their effectiveness in simplifying complex data and speeding up decision-making.
The Prioritization Graph: Where to
Wait? What? Web Performance Optimization is being studied in universities?
TL;DR:
In this article I am sharing the good news that Web Performance Optimization is being studied in universities and I am laying out the plan of teaching Real User Monitoring which I will do for the first time in front of students. My hope is to share ideas in case other fellows would be doing s
Using DevTools to Validate Web Performance Improvements
I'm passionate about Web Performance—from identifying performance issues, monitoring (synthetic and RUM), metrics, implementing product culture, training development teams and other stakeholders, speaking at meetups and conferences, tools, and snippets.
When it comes to tools, my favorite is Chrome
Digital Economy Report 2024 | United Nations iLibrary
The Digital Economy Report 2024 turns the attention to the environmental footprint of digitalization. The Report discusses environmental impacts along the life cycle of digital devices and information and communications technology infrastructure with regard to raw material extraction and processing, manufacturing, distribution; use and the end-of-life phase. The direct effects on natural resources, including transition minerals, energy and water, as well as greenhouse gas emissions and waste-related pollution can be said to constitute the “environmental footprint” of the ICT sector. There are also indirect environmental effects from the use of digital technologies and services in different sectors of the economy, and the Report includes a dedicated chapter on e-commerce. The report underlines the need to maximize the positive impact of digitalization while minimizing the negative impacts on environmental sustainability.