iiinova — where your digital self keeps evolving

Reposted by François Tessier

Fernanda Foertter @hpcprogrammer.bsky.social · 08/09/2026

Hey friends. I made public a tool I had been using for myself to keep up with what's happening in #HPC. It's called TheDailyFLOP.com Maybe it's also useful for you.

thedailyflop.com

The Daily Flop — flop around, find out

One page, one scan. Plain-language headlines and a single sentence of context on every chip, GPU, and HPC vendor announcement that matters today.

2145

Reposted by François Tessier

Brice Goglin @bgoglin.bsky.social · 09/06/2026

#hwloc 2.14.0 is released. Big improvements for ARM hybrid CPU detection, and AMD GPU management. And many other fixes. #hpc #hardware #locality sympa.inria.fr/sympa/arc/hw...

151

Reposted by François Tessier

SNCS-FSU Inria @sncs-inria.bsky.social · 17/03/2026

L'Inria essaie de défendre le fait que la ZRR ne va pas impacter les libertés académiques et le fait de la pire manière possible : en disant que de toute façon les précaires n'y auraient pas le droit (aux libertés académiques) parce qu'elles ne sont pas en poste....

Est-ce que le dispositif a un impact sur l'autonomie de la démarche scientifique et la libre circulation des idées ?

L'autonomie de la démarche scientifique et la libre circulation des idées garantit aux chercheurs d'effectuer des travaux de recherche, de publier et d’exprimer des idées sans subir de pression, de censure ou de contrainte extérieure, à condition de respecter l’éthique, l’objectivité scientifiques et plus globalement les lois et règlements en vigueur.

Ces garanties protègent les chercheurs déjà recrutés ou investis officiellement de fonctions de recherche. Elles ne sont pas accordées aux candidats à un poste.

L’exclusion d’un candidat avant sa nomination ne constitue donc pas une atteinte à l'autonomie de la démarche scientifique, à la libre circulation des idées ou à la liberté académique, par construction.

167

Reposted by François Tessier

SNCS-FSU Inria @sncs-inria.bsky.social · 04/03/2026

C'est officiel, cette année il y aura donc plus de 240 candidatures au concours Chargé·e de Recherche Inria pour seulement 6 postes (Plus d'une vingtaine de postes avant 2017). Une catastrophe. Colère pour ces jeunes chercheur·euses.

131

Reposted by François Tessier

Sarah Neuwirth 🇪🇺👩🏼‍💻👩🏻‍🏫😄 @sneuwirth.bsky.social · 23/01/2026

📢 ISPDC 2026: Call for Papers, Posters, and Talks! 📢 I am happy to announce the 25th International Symposium on Parallel and Distributed Computing (ISPDC 2026) (July 1-3, Hamburg, Germany)! Submissions are due March 23, 2026 (AoE). Further info: indico.desy.de/e/ispdc2026 #HPC #supercomputing

023

François Tessier @hephtaicie.bsky.social · 03/12/2025

📢 Call for Papers: 7th International Workshop on Extreme-Scale #Storage and #Analysis (ESSA 2026), held in conjunction with IPDPS (New Orleans, May 2026)! More info here: sites.google.com/view/essa-2026 #HPC #Cloud #IPDPS

7th Workshop on Extreme-Scale Storage and Analysis
Held in conjunction with IPDPS 2026, New Orleans, LA, USA

Paper submission deadline: January 23, 2026
Acceptance notification: February 25, 2026
Camera-ready deadline: March 6, 2026
Workshop date: May 26, 2026

021

Reposted by François Tessier

Animation Obsessive @ani-obsessive.bsky.social · 03/11/2025

It wasn't deep. It didn't have much to say. But Xiao Xiao inspired millions to try Flash animation for themselves. A Beijing artist made this series -- and turned stick fights into a phenomenon. We're exploring why and how he did it: animationobsessive.substack.com/p/when-stick...

382552871

Reposted by François Tessier

Mark A. Hanson @hansonmark.bsky.social · 11/11/2025

We wrote the Strain on scientific publishing to highlight the problems of time & trust. With a fantastic group of co-authors, we present The Drain of Scientific Publishing: a 🧵 1/n Drain: arxiv.org/abs/2511.04820 Strain: direct.mit.edu/qss/article/... Oligopoly: direct.mit.edu/qss/article/...

A table showing profit margins of major publishers. A snippet of text related to this table is below.

1. The four-fold drain
1.1 Money
Currently, academic publishing is dominated by profit-oriented, multinational companies for
whom scientific knowledge is a commodity to be sold back to the academic community who
created it. The dominant four are Elsevier, Springer Nature, Wiley and Taylor & Francis,
which collectively generated over US$7.1 billion in revenue from journal publishing in 2024
alone, and over US$12 billion in profits between 2019 and 2024 (Table 1A). Their profit
margins have always been over 30% in the last five years, and for the largest publisher
(Elsevier) always over 37%.
Against many comparators, across many sectors, scientific publishing is one of the most
consistently profitable industries (Table S1). These financial arrangements make a substantial
difference to science budgets. In 2024, 46% of Elsevier revenues and 53% of Taylor &
Francis revenues were generated in North America, meaning that North American
researchers were charged over US$2.27 billion by just two for-profit publishers. The
Canadian research councils and the US National Science Foundation were allocated US$9.3
billion in that year.

A figure detailing the drain on researcher time.

1. The four-fold drain

1.2 Time
The number of papers published each year is growing faster than the scientific workforce,
with the number of papers per researcher almost doubling between 1996 and 2022 (Figure
1A). This reflects the fact that publishers’ commercial desire to publish (sell) more material
has aligned well with the competitive prestige culture in which publications help secure jobs,
grants, promotions, and awards. To the extent that this growth is driven by a pressure for
profit, rather than scholarly imperatives, it distorts the way researchers spend their time.
The publishing system depends on unpaid reviewer labour, estimated to be over 130 million
unpaid hours annually in 2020 alone (9). Researchers have complained about the demands of
peer-review for decades, but the scale of the problem is now worse, with editors reporting
widespread difficulties recruiting reviewers. The growth in publications involves not only the
authors’ time, but that of academic editors and reviewers who are dealing with so many
review demands.
Even more seriously, the imperative to produce ever more articles reshapes the nature of
scientific inquiry. Evidence across multiple fields shows that more papers result in
‘ossification’, not new ideas (10). It may seem paradoxical that more papers can slow
progress until one considers how it affects researchers’ time. While rewards remain tied to
volume, prestige, and impact of publications, researchers will be nudged away from riskier,
local, interdisciplinary, and long-term work. The result is a treadmill of constant activity with
limited progress whereas core scholarly practices – such as reading, reflecting and engaging
with others’ contributions – is de-prioritized. What looks like productivity often masks
intellectual exhaustion built on a demoralizing, narrowing scientific vision.

A table of profit margins across industries. The section of text related to this table is below:

1. The four-fold drain
1.1 Money
Currently, academic publishing is dominated by profit-oriented, multinational companies for
whom scientific knowledge is a commodity to be sold back to the academic community who
created it. The dominant four are Elsevier, Springer Nature, Wiley and Taylor & Francis,
which collectively generated over US$7.1 billion in revenue from journal publishing in 2024
alone, and over US$12 billion in profits between 2019 and 2024 (Table 1A). Their profit
margins have always been over 30% in the last five years, and for the largest publisher
(Elsevier) always over 37%.
Against many comparators, across many sectors, scientific publishing is one of the most
consistently profitable industries (Table S1). These financial arrangements make a substantial
difference to science budgets. In 2024, 46% of Elsevier revenues and 53% of Taylor &
Francis revenues were generated in North America, meaning that North American
researchers were charged over US$2.27 billion by just two for-profit publishers. The
Canadian research councils and the US National Science Foundation were allocated US$9.3
billion in that year.

The costs of inaction are plain: wasted public funds, lost researcher time, compromised
scientific integrity and eroded public trust. Today, the system rewards commercial publishers
first, and science second. Without bold action from the funders we risk continuing to pour
resources into a system that prioritizes profit over the advancement of scientific knowledge.

8644453

Reposted by François Tessier

Suhaib Khan @suhaibkhan.bsky.social · 17/10/2025

Part 1 of the special HPCwire series about the future of #storage for #HPC and #AI lays out the current state of storage for AI and HPC and touches on some of the broad challenges that organizations are facing. www.hpcwire.com/2025/10/13/t...

hpcwire.com

The Future of Storage for HPC and AI

The AI arms race has made “GPU” and “gigawatt” household words, and for good reason: What’s happening with the scale of compute is unprecedented. But what about the underlying storage […]

041

Reposted by François Tessier

Torsten Hoefler 🇨🇭 @thoefler.bsky.social · 02/10/2025

Cool and impactful project led by the MPI-M: coupled simulation of the full Earth system in 1.25km resolution. Unprecedented complexity, fidelity, and performance at 82.5 simulated days per day. Accelerated by DaCe on GH200 - next generation #HPC for #climate science is here!

buff.ly

Global climate simulations achieve 1.25 km resolution—team nominated for Climate Gordon Bell Prize | CSCS

For the first time, scientists have run global coupled climate simulations at a resolution of just 1.25 kilometres. Using CSCS’s “Alps” supercomputer, the team including researchers from ETH Zürich…

082

Reposted by François Tessier

Astropierre @astropierre.com · 26/09/2025

126 millions de milliards d’opérations en virgule flottante par seconde : c’est la capacité du supercalculateur Jean Zay 4 depuis mai 2025. Une puissance énorme entièrement au service de la science. Reportage @cnrs.fr : www.youtube.com/watch?v=8Jdj...

youtube.com

Jean Zay 4 : Accélérer l'IA I Reportage CNRS

YouTube video by CNRS

36320

Reposted by François Tessier

Glenn K. Lockwood @glennklockwood.com · 25/07/2025

I wrote up some notes on how to approach I/O and storage benchmarks in RFPs. I normally don't post here about updates to my digital garden, but I think this page is tidy and useful. www.glennklockwood.com/garden/bench... #HPC

glennklockwood.com

benchmarking

There are two ways to approach benchmarking. System-level capability: This tells you the best- and worst-case performance you can get out of the system regardless of whatever workload (or mix of workl...

071

Reposted by François Tessier

Sarah Neuwirth 🇪🇺👩🏼‍💻👩🏻‍🏫😄 @sneuwirth.bsky.social · 21/07/2025

📢 [FINAL] Call for Papers for the REX-IO 2025 Workshop! 📢 REX-IO 2025 is still accepting submissions (short & full papers) and your high-quality work can make a big difference! Final deadline: July 25, 2025 11:59PM AoE. 🤩 📜 🦖 More information: sites.google.com/view/rexio/ #HPC #supercomputing

034

François Tessier @hephtaicie.bsky.social · 04/06/2025

A global power outage during an ESSA workshop is not enough to stop us from sharing our work on I/O and Storage! #IPDPS25

060

Reposted by François Tessier

Sarah Neuwirth 🇪🇺👩🏼‍💻👩🏻‍🏫😄 @sneuwirth.bsky.social · 20/05/2025

📢 [CFP] REX-IO 2025 Workshop at IEEE Cluster Conference 2025! I'm happy to announce the 5th Workshop on Re-envisioning Extreme-Scale I/O for Emerging Hybrid HPC Workloads! Submissions are due July 9, 2025 (11:59PM AoE). 🤩 📜 🦖 Further info: sites.google.com/view/rexio/ #HPC #supercomputing

075

Reposted by François Tessier

Milène Testa-Rioux @milenerioux.bsky.social · 19/05/2025

🆕Comment simuler des phénomènes naturels complexes sur ordinateur pour les rendre compréhensifs et les étudier ?🔬 Au centre #Inria de l’ @univbordeaux.bsky.social : #modélisation, #data et #HPC s’unissent dans un #continuum scientifique puissant. 🔎Sur inria.fr : www.inria.fr/fr/modelisat...

011

Reposted by François Tessier

Au Poste @auposte.media · 04/05/2025

Au Poste, c’est vous. Sans vous, c’est silence radio. Aujourd’hui, nous avons besoin de vous pour notre chaine YouTube. Moins de 5000 followers manquent pour franchir un cap, trouver des appuis, tenir la ligne, et remplir les conditions pour demandes d'aides au CNC -> www.youtube.com/@au_poste?su...

19799

Reposted by François Tessier

Glenn K. Lockwood @glennklockwood.com · 12/03/2025

Darshan now supports I/O profiling for (non-MPI) machine learning frameworks, and a new blog post explains how: www.mcs.anl.gov/research/projects/d… #HPC

mcs.anl.gov

Using Darshan with non-MPI applications (e.g., AI/ML frameworks) – Darshan

171

Reposted by François Tessier

Au Poste @auposte.media · 09/03/2025

Opération 50000 abonnés Youtube lancée: il nous manque 12.000 followers pour prétendre à traquer quelques menues aides financières ici ou là. Vous êtes 15000 ici à nous suivre sur BSKY. On serait tellement pas loin... youtube.com/@au_poste Merci de vous abonner à notre canal (gratuit)

46217179

Reposted by François Tessier

Ryohei Kobayashi @ryohei-kobayashi.bsky.social · 08/02/2025

🚀 𝐈𝐄𝐄𝐄 𝐂𝐥𝐮𝐬𝐭𝐞𝐫 𝟐𝟎𝟐𝟓 – 𝐂𝐚𝐥𝐥 𝐟𝐨𝐫 𝐏𝐚𝐩𝐞𝐫𝐬! 📢 Submission Deadline: April 25, 2025 📍 Location: Edinburgh, United Kingdom 📅 Dates: September 2-5, 2025 📢 The CFP is open! Submit your paper by April 25, 2025: clustercomp.org/2025/papers/

clustercomp.org

Welcome!

Website for IEEE Cluster 2025. The latest news is also shown in Twitter/ieeecluster

055

François Tessier @hephtaicie.bsky.social · 31/01/2025

ECLAT, the Extreme Computing Lab for Astronomical Telescopes, now has an English website! eclat-lab.fr/en/ Next week will also be organized the first hackathon at the Paris Observatory. A great opportunity for the #HPC and #Astro communities to work together on scaling up #SKA processing pipelines.

eclat-lab.fr

Homepage - ECLAT

Introducing ECLAT, a laboratory of excellence dedicated to high-performance computing (HPC) and artificial intelligence (AI) for astronomical instrumentation. Created as a result of France's contribut...

011

Reposted by François Tessier

Nicolas Berrod @nicolasberrod.bsky.social · 27/01/2025

La communauté scientifique a massivement migré sur le ciel bleu, la preuve en chiffres : parmi 5 300 répondants à Nature... • 52,5 % ont quitté X • 14,9 % utilisent toujours X mais davantage Bsky • Seuls 13,6 % utilisent toujours davantage X que Bsky 1/3

14725229

Reposted by François Tessier

Stéphane @molloy.bsky.social · 28/01/2025

A review of the world scientific literature shows the number of supercomputer articles, growing rapidly after 1980. An Informal Survey of the Scientific and Social Impact of a Soda Can-Sized Super-Supercomputer doi: 10.1063/1.4822988 #supercomputer #HPC #retrocomputer #vintagecomputiong #research

Supercomputer articles. A review of the world scientific literature shows the number of supercomputer articles, growing rapidly after 1980.
1981 : 11
85 : 47
89 : 103
90 : 120

011

François Tessier @hephtaicie.bsky.social · 23/01/2025

We have extended the deadline for ESSA! You still have a bit of time to submit your work on I/O, storage and data analytics at extreme scale, and join us in June in Milano, Italy. #HPC

052

François Tessier @hephtaicie.bsky.social · 23/01/2025

Bye bye #PizDaint 🇨🇭. It was a real pleasure working with you for a while. #HPC

142

Reposted by François Tessier

seb(astien) @nseb.bsky.social · 23/01/2025

To kick start this account let's repost something I worked on last year at @epcc.bsky.social. Wind turbine flow simulation done with @xcompact3d.bsky.social by Andrew Mole and render and animation by me using @blender.org #hpc #blender #sc24 #cfd

1152

Reposted by François Tessier

Michael Papka @mpapka.bsky.social · 05/01/2025

The Argonne Leadership Computing Facility has released its 2024 Science report (bit.ly/3BTyEHW) highlighting some of the work of our great users. #hpc

alcf.anl.gov

1173

Reposted by François Tessier

David Monniaux @monniauxd.bsky.social · 03/01/2025

(This is mostly for young academics, though science journalists might find it interesting.) I often receive suspicious advertisements about scientific journals and conferences. Why do I consider them suspicious?

11110

François Tessier @hephtaicie.bsky.social · 21/12/2024

Today, we present our work on simulation of #HPC storage systems at HiPC, India, ... remotely! I didn't get my visa on time, and had to give up boarding 1 hour before departure while standing in front of the check-in desk. Not my best travel experience, I have to say 😅

140

Reposted by François Tessier

v @vsoch.bsky.social · 09/12/2024

We are pleased to announce an #IEEE Computing in Science and Engineering (CiSE) Special Issue on Converged Computing! ☁️ www.computer.org/csdl/magazin... Discussion of the best of both worlds, #cloud and #HPC, on the level of technology and culture, is of utmost importance.

1208

François Tessier @hephtaicie.bsky.social · 06/12/2024

A priceless quote from @sneuwirth.bsky.social's talk today at the Inria center in Rennes: "Benchmarking can be benchmarketing at times". I think I'm going to frame it for my office 😅

1206

François Tessier @hephtaicie.bsky.social · 06/12/2024

Today is the Day! Julien Monniot, my first PhD student, is defending his PhD entitled "Enabling Accurate Simulation of #HPC Storage Systems: Methodology and Practical Techniques". So proud of him!

2122

Reposted by François Tessier

David Ho @davidho.bsky.social · 29/11/2024

Ahem…do y'all know about sci-hub? 🌊🧪 sci-hub.se

1512224

François Tessier @hephtaicie.bsky.social · 28/11/2024

Lots of newcomers to the #HPC community on Bluesky! I am therefore taking this opportunity to repost our CFP for the ESSA workshop which will be organized jointly with IPDPS next June. ESSA is dedicated to I/O challenges, storage management and analysis of large volumes of data.

063

François Tessier @hephtaicie.bsky.social · 27/11/2024

HPE/Cray recently open the source code of the support library for Slingshot network (github.com/HewlettPacka...). Thanks to a Guix-HPC package, it's now possible to seamlessly deploy a Slingshot-capable MPI stack with performance on par with native MPI! #HPC hpc.guix.info/blog/2024/11...

hpc.guix.info

Guix-HPC — Targeting the Cray/HPE Slingshot interconnect

0143

François Tessier @hephtaicie.bsky.social · 27/11/2024

Today starts the first technical workshop of the Extreme Computing Laboratory for Astronomical Telescopes (ECLAT) in Bordeaux, France. Several of us will take turns to present our work on the very large-scale transition of SKA's operational workflow. #HPC 🖥️ and #radioastronomy 🔭 on the program 😎

071

François Tessier @hephtaicie.bsky.social · 25/11/2024

I'm launching the hashtag #HPCTales to share ridiculous articles about #HPC. I'm starting with news from a French defense (!!) website that headlines: "The 2nd most powerful supercomputer in the world (Frontier) is now able to create its own Matrix-like universe thanks to Exascale" 🤦

2106

François Tessier @hephtaicie.bsky.social · 22/11/2024

We had a great program this morning at the #SC24 SuperCompCloud workshop ranging from cloud-based software ecosystem for radioastronomy workload to open platform for micro-services deployment. See you (hopefully) next year for SC25 😎

050

François Tessier @hephtaicie.bsky.social · 22/11/2024

Even after living in the US for three years, one mystery remains: chicken and waffles. Why guys?! #SC24

231

François Tessier @hephtaicie.bsky.social · 21/11/2024

⚠️ If you plan to attend the #SC24 reception tonight at the Aquarium, drop off your backpack beforehand! I just got that info from a SC Organizing Committee member. It will be way more complicated to get in with a bag. The Aquarium staff insisted a lot on that point during a meeting today.

087

François Tessier @hephtaicie.bsky.social · 21/11/2024

Best #SC24 party though. Or should I say "best accelerated party"?

000

François Tessier @hephtaicie.bsky.social · 21/11/2024

Everything is "accelerated" at Weka. They got a discount on the word. #SC24

181

Reposted by François Tessier

Sunita Chandrasekaran @sunitachandra.bsky.social · 20/11/2024

We are hiring!!! #RSE #SC24 #HPC #UDEL 🥁 🥁 🥁 🥁 🥁 careers.udel.edu/cw/en-us/job... Here you go with a project summary - www.udel.edu/udaily/2024/... #NSF Democratizing access to #RSE DARSE sites.udel.edu/darse/ #NSF SCIPE award www.nsf.gov/awardsearch/...

udel.edu

Building a data-intensive research workforce for the Mid-Atlantic | UDaily

University of Delaware program to create pipeline for new professionals

0157

François Tessier @hephtaicie.bsky.social · 19/11/2024

Marketing is getting out of control this year at the #SC24 exhibition! Everything is AI-enabled. I saw AI-ready network cables or AI-compatible cooling systems to name a few. I find it a bit AI-ridiculous.

3163

François Tessier @hephtaicie.bsky.social · 19/11/2024

Attending a nice #SC24 talk about managing I/O interference on supercomputers. However, the authors claim that part of the interference is due to non-exclusive node allocation. My experience with large-scale #HPC systems is that nodes are largely allocated exclusively. Thoughts?

320