Achievement unlocked:
Compressing *and* computing right in the browser ✅
10.03.2026 16:40
👍 0
🔁 0
💬 0
📌 0
Achievement unlocked:
Compressing *and* computing right in the browser ✅
New DSL kernels in Python-Blosc2, being parallelizable and JIT-compiling capable, can accelerate code quite a bit 🚀
For example, linspace() has been rewritten to use DSL kernels, and performance boost is well beyond expectations.
JIT-compiled DSL kernels: a major step forward for a minor release number! 🥳🥳
DSL kernels are gonna be a pretty wild thing.
The new engine in Python-Blosc2 4.0 delivers quite awesome performance results. Processing a 400 MB array can be up to 9.6x faster than NumPy 🤯
The best part is that it fully supports NumPy's array and ufunc interfaces. High performance with zero friction! 🏎️💨
ironarray.io/blog/miniexp...
Enjoy!
So glad to see v4.0 in the wild! 🥳🥳.
Thanks to all the ironArray team; you did an outstanding job in putting together top-class compression with high performance computing 💯
Really exciting news! 🥳🥳
🚀 Our #PyDataGlobal 2025 tutorial on modern #Blosc2 & #Caterva2 features is out!
Learn how compression boosts array performance & enables cloud computing without downloads. ☁️
Watch here: 👇 www.youtube.com/watch?v=tUvS...
#Python #HPC #DataScience #BigData
Run live data analysis and visualizations on your phone in seconds! 💻👁️
Blosc2 + Caterva2 + Numba = ⚡⚡
🤔 Can a library that computes on compressed data actually outperform performance heavyweights like NumPy and NumExpr?
Find some surprising answers 👉 www.blosc.org/posts/roofli...
During the walk, I'm also introducing a funny anecdote back when NumPy was a 👶
Enjoy!
#Blosc2 #HPC #NumPy #Numexpr
A la comunitat local de Python en Castelló de la Plana: aquest divendres dia 28 a les 7:30 ens reunirem al local de Nayar Systems en Avinguda Casalduch, 9.
Parlarem de Cat2Cloud ☁️ : ironarray.io/cat2cloud
Com que és Black Friday, tenim un regalet preparat per als asistents! 🎁
Us esperem!
Downloading big data is not only boring, but also consumes immense resources. Handle and extract value right where your data is! 💚
#sdlm Me parece muy bien que incluyan obras de mujeres en el concierto de año nuevo este año, pero... para cuando una directora mujer?
Don't let this opportunity slip away! 💨
Slice and compute with HDF5 in the cloud as easy as pie! 🥧
Slice and compute with HDF5 in the cloud as easy as pie! 🥧
It's Friday, and apparently bluesky is ready for this fun revelation:
Dinosaurs lived on the other side the Galaxy.
Data browsing and computing right in your phone.
I've built a demo Jupyter notebook that connects to a Cat2Cloud server from an Android phone and slices into an 8 TB dataset, downloading a 1 MB chunk in under 100 milliseconds. ⚡
Interact with your vasts remote datasets right in your phone!
cat2.cloud/demo/roots/@...
#Cat2Cloud #Blosc2 #BigData
ironArray is on a roll 🚅!
With Cat2Cloud released this week we continue our 💊ironPill series with another video, showing you how to browse your cloud-hosted data ☁️ in the bespoke web client!
Visualise and manage all kinds of data formats - from arrays to jpgs 🖼️, markdown to PDFs 📄 !
Yay! 🥳
So happy to see the beast out of the cage! 🥳
Stop downloading. Start computing.
Everything changes on November 18, 2025.
#Cat2Cloud is coming.
Haha, this from the New Yorker is getting passed around the math dork community. I did a comic about this kind of thought a few years ago: www.smbc-comics.com/comic/commut...
Our Blosc2 tutorial for @euroscipy.bsky.social 2025 is up! Learn how compression boosts tensor data handling, sharing & computing.
www.youtube.com/watch?v=BdpT... #DataScience #BigData #HPC #OpenSource
📢🚨Blosc2 3.11.0 Released! 🚨 📢
Blosc2 is part of the NumPy array library ecosystem: numpy.org
In v3.11, Blosc2 has become even more flexible; all functions can accept basically any array object:
𝚋𝚕𝚘𝚜𝚌𝟸.𝚖𝚊𝚝𝚖𝚞𝚕(𝙰, 𝙱)
for 𝙰, 𝙱 PyTorch, Jax, Tensorflow, Zarr... arrays!
#Compute
#Tensor
#PyTorch
The importance of linear algebra in modern computing is undeniable 📐.
Equally crucial is vertical integration. When SSD storage, memory hierarchies, compression, and computation are seamlessly orchestrated 💃, the performance gains can be transformative. 🚀
💊 IronPill 1💊
Blosc2 calculates Fourier approximations:
⚡5x faster than NumPy
👣 fraction of the memory footprint
🐍 one-line syntax 𝚜𝚞𝚖(𝚊 * 𝚌𝚘𝚜(𝚝) + 𝚋 * 𝚜𝚒𝚗(𝚝), 𝚊𝚡𝚒𝚜=𝟷)
Full notebook: github.com/Blosc/python...
(inspiration: towardsdatascience.com/numexpr-the-...)
#Blosc2
#Data
#SignalProcessing
From a programmer's virtue to a computational powerhouse: laziness transforms a developer's best practice into the engine of modern computing.
Inspired by the ESA's Gaia Milky Way map 🌌!
At SciPy 2023, we showcased visualizing a massive 7.3 TB Gaia dataset on a standard laptop by compressing it to 1.8 GB using #Blosc2. Big data analysis for everyone! 🚀
Dataset: digistorage.es/links/652403...
Paper: www.blosc.org/docs/Explori...
#napari
