Sign in

Juan Fumero

@jfumero.dev
94 followers 82 following 76 posts

Software developer @oracle Java Platform Group. Opinions my own. 🔗 jfumero.dev

PostsRepliesMedia
Reposted by Juan Fumero
Mark Reinhold @mreinhold.org · 15/09/2026
Java 27 / JDK 27: General Availability: mail.openjdk.org/archives/lis... Features: openjdk.org/projects/jdk... Downloads: jdk.java.net/27/ #Java27 #JDK27 #OpenJDK #Java
04425
Juan Fumero @jfumero.dev · 14/08/2026
Running Java workloads on GPUs means rethinking the whole software stack: APIs, types, program representation, execution and scheduling. At #DevoxxBE, I’ll dive into how we're tackling this with OpenJDK Project Babylon in "Reflect, Transform, Accelerate." See you there! #Java #OpenJDK #GPU
020
Reposted by Juan Fumero
Mark Reinhold @mreinhold.org · 10/08/2026
The first part of OpenJDK’s Project Valhalla, JEP 401 (Value Objects), has been integrated into JDK 28 as a preview feature and is now available in the early-access builds. More information: openjdk.org/projects/val... #JDK28 #OpenJDK #Java
07236
Reposted by Juan Fumero
Nicolai Parlog @nipafx.dev · 08/08/2026
Wanna have some #Java fun on the weekend? 0. download jdk.java.net/28/ EA 10 1. jshell 2. type `value class Valhallaaaa { }` (vary number of "a"s according to taste)
jdk.java.net
OpenJDK JDK 28 Early-Access Builds
1305
Juan Fumero @jfumero.dev · 04/08/2026
The recording of my #JavaOne26 session is now available! In this talk, we explore how code reflection from the #OpenJDK Project #Babylon can be used to offload #Java methods to hardware accelerators such as #GPUs. It also includes live demos. 🚀 www.youtube.com/watch?v=92ki...
youtube.com
Under the HAT: Empowering GPU Acceleration for Java
YouTube video by Java
010
Reposted by Juan Fumero
Per Minborg @pminborg.bsky.social · 29/07/2026
The Java Babylon team is #hiring in Nashville! Relocation (from inside the US to Nashville) is available. Know anyone who might be interested? Please send this along: careers.oracle.com/en/sites/job...
022
Reposted by Juan Fumero
Stefan Marr @stefan-marr.de · 22/07/2026
Are you working on language implementations and implementation research? Do you want to present your work to an enthusiastic crowed in Oakland? Submit your work to the VMIL Workshop! conf.researchr.org/home/splash-...
012
Juan Fumero @jfumero.dev · 17/07/2026
Premiere today, 21:00 CEST www.youtube.com/watch?v=ZqGS...
youtube.com
LIVE PREMIERE July 17th, 7pm UTC | The Java Story | The Official Documentary
YouTube video by CultRepo
010
Juan Fumero @jfumero.dev · 11/06/2026
We’ve just published a new article proposing an extension to Babylon about how to unlock GPU Tensor Cores directly from Java, while ensuring cross-platform portability. It also shows how Java applications can be tuned for GPUs by using HAT and NVIDIA profilers 🚀 📑 openjdk.org/projects/bab...
010
Juan Fumero @jfumero.dev · 08/06/2026
The slide deck from my last talk at the University of Salerno on Project Babylon and the Heterogeneous Accelerator Toolkit (HAT) is now available! 🚀 🔗 cr.openjdk.org/~jfumero/pre... #java #openjdk #babylon #gpus
062
Juan Fumero @jfumero.dev · 19/05/2026
Building the Latest OpenJDK from Source with Docker 🔗 jfumero.dev/posts/2026/0...
jfumero.dev
Building the Latest OpenJDK from Source with Docker
How to build OpenJDK from source in a Docker Container
071
Juan Fumero @jfumero.dev · 13/04/2026
Building The Regression Test Harness for the OpenJDK (jtreg) from Source: 🔗 jjfumero.github.io/posts/2026/0...
jjfumero.github.io
Building The Regression Test Harness for the OpenJDK (jtreg) from Source
Build JTREG
010
Reposted by Juan Fumero
𝖢𝖠𝖳 𝖡𝖴𝖳𝖫𝖤𝖱 𝖲𝗋. @catbutlersr.bsky.social · 12/04/2026
Steven Madow captured this awesome close-up shot of Artemis ll engine, using a Panasonic GH5 and a Lumix G Leica 50-200mm f/2.8-4 lens. This photo was captured at 1/8000s, f/16, and ISO 100. Beautiful (and not BS AI) petapixel.com/2026/04/03/h...
Steven Madow captured this awesome close-up shot of Artemis ll engine
1039370
Reposted by Juan Fumero
Adam Bien @adambien.blog · 20/03/2026
Netflix's opinion on Java👇 #java #JavaOne #netflix
1229
Reposted by Juan Fumero
Adam Bien @adambien.blog · 18/03/2026
It is now official: NVIDIA ❤️ Java 👇 #java #javaone
1195
Juan Fumero @jfumero.dev · 18/03/2026
Cheat sheet for installing and running Babylon and HAT for GPUs using JDK26 #java #codereflection #gpu
021
Juan Fumero @jfumero.dev · 15/03/2026
📸
010
Juan Fumero @jfumero.dev · 26/01/2026
Java achieving 14 TFLOP/s on an NVIDIA A10? 🚀 Is that possible? Our new article shows a PoC of how Projects Babylon and HAT use Code Reflection to achieve near-native GPU performance for matrix-multiplication. Deep-dive here: openjdk.org/projects/bab... #Java #OpenJDK #GPU #HPC #AI
openjdk.org
Optimizing GPU Programs from Java using Babylon and HAT
042
Reposted by Juan Fumero
Laurence Tratt @ltratt.bsky.social · 18/12/2025
I can't quite believe that we're now announcing the eighth Programming Language Implementation Summer School (PLISS), but we are --- in May next year, if you want to learn more about programming language implementations, this is the place to come!
1275
Juan Fumero @jfumero.dev · 10/01/2026
The fact that games such as Cyberpunk 2077 on a Pi 5 (along with the 5090) are playable is just impressive.
000
Juan Fumero @jfumero.dev · 10/01/2026
Heading to Redwood Shores for #JavaOne 2026 this March! 🚀 I’ll be speaking about what we are doing in project Babylon for programming, compiling and accelerating Java workloads on GPUs. Details: reg.rf.oracle.com/flow/oracle/... #java #babylon #gpus #ai
reg.rf.oracle.com
Session Catalog
021
Reposted by Juan Fumero
Tailscale @tailscale.com · 01/12/2025
“It’s a rite of passage to run Tailscale on weird devices": How to get easier access to a jailbroken Kindle, and drop files to it, with Tailscale. tailscale.com/blog/tailsca...
tailscale.com
How to put Tailscale on a jailbroken Kindle (and why you should)
Jailbreaking a Kindle makes it able to do much more. Adding Tailscale takes the Kindle even further.
3666
Juan Fumero @jfumero.dev · 24/11/2025
How code-model and code-reflection works in project Babylon to model Java programs for Machine Learning - presentation by Paul Sandoz www.youtube.com/watch?v=jbXo...
youtube.com
Symbolic Modeling and Transformation of Java Code #JVMLS
YouTube video by Java
020
Reposted by Juan Fumero
Ana-Maria Mihalceanu @ammbra1508.bsky.social · 08/10/2025
A big thank you to all of you who attended our @devoxx.com talk on writing #GPU ready #AI models in pure #Java!!! If you wish to revisit the concepts and run the demos, here are the slides: www.slideshare.net/slideshow/wr... Give Babylon a try and share feedback with @lizeraes.bsky.social and I!
slideshare.net
Writing GPU-Ready AI Models in Pure Java with Babylon
Project Babylon introduces the experimental Code Reflection technology that lets you define machine learning logic in plain Java code, without needing Python or external model files. It then uses Foreign Function and Memory (FFM) API to connect your code to native runtimes like ONNX Runtime for fast inference, including GPU acceleration. Furthermore, the Heterogeneous Accelerator Toolkit (HAT) provides a developer-facing programming model for writing and composing compute kernels, which can be more broadly applied-allowing Java libraries to seamlessly harness GPU power for high-performance computing tasks. Presented at Devoxx Belgium 2025 by Ana-Maria Mihalceanu and Lize Raes - Download as a PDF or view online for free
0147
Reposted by Juan Fumero
Tomas Petricek @tomasp.net · 07/10/2025
I'm teaching 𝗪𝗿𝗶𝘁𝗲 𝘆𝗼𝘂𝗿 𝗼𝘄𝗻 𝘁𝗶𝗻𝘆 𝗽𝗿𝗼𝗴𝗿𝗮𝗺𝗺𝗶𝗻𝗴 𝘀𝘆𝘀𝘁𝗲𝗺(𝘀)! again. I'll be posting the videos & tasks on YouTube too. In the first lecture, I explain what's a tiny system, why write one and show plenty of demos! 🎞️ Playlist: www.youtube.com/playlist?lis... 👉 More info: d3s.mff.cuni.cz/teaching/npr...
youtube.com
Write your own tiny programming system(s)! - YouTube
The goal of this course is to teach how fundamental programming language techniques, algorithms and systems work by writing their miniature versions. The cou...
14918
Reposted by Juan Fumero
Ana-Maria Mihalceanu @ammbra1508.bsky.social · 07/10/2025
Hey #Java devs! At @devoxx.com, the Java Team at #Oracle is hosting an "Ask The Architects" panel. Post your questions here by Wed 23:00 UTC! Then check out the recording to hear the experts’ answers (as many as we can). 📝 Please read the questions others have suggested to prevent double-posting.
31310
Reposted by Juan Fumero
Sharat (Shar) Chander - 🟦🌊 @sharatchander.bsky.social · 29/08/2025
📢Announcement📢 #Java peers...the #Oracle Java VSCode extension 24.1.0 is now available with support for #JDK25 language features. Download now from the @microsoft.com #VSCode marketplace: marketplace.visualstudio.com/items?itemNa...
marketplace.visualstudio.com
Java - Visual Studio Marketplace
Extension for Visual Studio Code - Java Platform Extension for Visual Studio Code
0102
Juan Fumero @jfumero.dev · 15/08/2025
New blog post: How to Install NVIDIA Drivers and CUDA Toolkit on Oracle Linux 10 - Desktops jjfumero.github.io/posts/2025/0... #ol10 #linux #nvidia #cuda
jjfumero.github.io
How to Install NVIDIA Drivers and CUDA Toolkit on Oracle Linux 10
How to install NVIDIA 580 Drivers and CUDA 13.0 Toolkit on Oracle Linux 10
021
Juan Fumero @jfumero.dev · 09/07/2025
Today's my last day at @officialuom.bsky.social ! After almost 8 incredible years, it feels like a second home. Huge thanks to everyone for the amazing memories, especially developing #TornadoVM into a world-class open-source platform. So proud of what we achieved! Excited for what's next!
230
Juan Fumero @jfumero.dev · 08/07/2025
Updating open WebUI to run local models with CUDA gist: gist.github.com/jjfumero/a30...
000
Juan Fumero @jfumero.dev · 04/07/2025
New blogpost: How to enable NVIDIA Nsight Compute CLI in Fedora/Linux. 🔗https://jjfumero.github.io/posts/2025/07/04/nvidia-ncu-enable-fedora #profiling #cuda #configuration
120
Juan Fumero @jfumero.dev · 25/06/2025
Thanks to @mukel.bsky.social for the llama2.java port and Roger Allen (github.com/rogerallen/l...) for the CUDA port, we were able to understand and shape TornadoVM for running LLMs and transformers architectures.
llama2.java
010
Juan Fumero @jfumero.dev · 20/06/2025
This is pretty cool: switching between NVIDIA Driver Module Flavors at any time. docs.nvidia.com/datacenter/t...
docs.nvidia.com
1. Introduction — NVIDIA Driver Installation Guide r575 documentation
NVIDIA Driver Installation Guide for Linux
000
Reposted by Juan Fumero
Ana-Maria Mihalceanu @ammbra1508.bsky.social · 20/05/2025
🎉 Java is turning 30! ☕️ On 22 May, join the celebration of three decades of innovation, code, and community! 📺 www.youtube.com/live/LHHPbI7... 🗓️ Checkout the schedule dev.java/community/ja... Don't miss it! See what's brewing next and be part of Java's joy! #JavaTurns30 #HappyBirthday
youtube.com
Java's 30th Birthday
YouTube video by Java
0207
Juan Fumero @jfumero.dev · 20/05/2025
Really fun and interesting podcast with @adambien.blog. In this one we talk about the status of TornadoVM and all new changes, API design and optimisations we had to do to run LLMs more efficiently on integrated and discrete GPUs. 🎧https://airhacks.fm/#episode_346
airhacks.fm
airhacks.fm podcast
podcast with adam bien
042
Juan Fumero @jfumero.dev · 11/05/2025
Really interesting article about Google's hybrid approach to research by combining engineering from day one. Engineering at Google has always intrigued me. Google makes stronger research by proving it at scale. I wish Universities have similar resources. dl.acm.org/doi/10.1145/...
dl.acm.org
Google's hybrid approach to research | Communications of the ACM
By closely connecting research and development Google is able to conduct experiments on an unprecedented scale, often resulting in new capabilities for the company.
010
Juan Fumero @jfumero.dev · 17/04/2025
Guidelines to install and configure @unsloth.ai , a framework for optimising fine tuning of large language models. This guide details the configuration for Linux systems to run with NVIDIA GPUs. jjfumero.github.io/posts/2025/0... #llm #ai #linux
jjfumero.github.io
Configuring Unsloth on Linux for LLM Fine Tuning
This guide details the configuration of Unsloth to build fine-tuned LLM models on NVIDIA GPUs on Linux systems.
000
Juan Fumero @jfumero.dev · 04/04/2025
🚀 Learn how to accelerate performance on RISC-V CPUs using TornadoVM & vector instructions with OCK in my latest article. #Java #RISCV #Performance #OpenSource 🔗 jjfumero.github.io/posts/2025/0...
064
Juan Fumero @jfumero.dev · 31/03/2025
We just released a new version of #TornadoVM: v1.1.0 Highlights: - New API calls to share and optimise device buffers - Multi-task graphs fine-grained executions - Support for FP16 and mixed precision computations - Memory management improvements - Extended Math library and much more!
043
Juan Fumero @jfumero.dev · 24/03/2025
Preprint is now available: 🔗 research.manchester.ac.uk/en/publicati... #riscv #java #acceleration #vectorization #tornadovm
research.manchester.ac.uk
Leveraging RISC-V Vectorization: Accelerating Java Programs with TornadoVM and OCK
094
Reposted by Juan Fumero
Suresh @suresh.dev · 21/03/2025
Nice. If you want to use a pre-compiled library with an existing JVM, I used it from, chriswhocodes.com/hsdis/ and builds.shipilev.net/hsdis/
chriswhocodes.com
hsdis HotSpot Disassembly Plugin Downloads
011
Juan Fumero @jfumero.dev · 20/03/2025
Hoy voy a exponer mi trabajo como postdoc en la Universidad de Manchester y mi trayectoria como investigador en la universidad en la que estudié, La Laguna, Tenerife! Siempre un placer!
011
Juan Fumero @jfumero.dev · 19/03/2025
NVIDIA DGX Spark: raspberrypi-ish size with 1000 TOPS AI performance (in FP4) www.nvidia.com/en-us/produc...
nvidia.com
NVIDIA DGX Spark
A Grace Blackwell AI supercomputer on your desk.
040
Juan Fumero @jfumero.dev · 07/03/2025
Our last paper is accepted at the #RISCV Summit Europe 2025! We evaluated Java parallel workloads expressed with #TornadoVM on real RISC-V CPUs using vector instructions generated by the oneAPI Construction Kit. How cool is this? Pre-print coming soon!
094
Juan Fumero @jfumero.dev · 05/03/2025
Last week @kotselidis.net and myself presented the work we are doing to run and optimise Java/ #TornadoVM applications for RISC-V hardware accelerators in the #RISCV J-Group. See the slides: github.com/jjfumero/jjf... If you are interested in the topic, stay tune!
054
Juan Fumero @jfumero.dev · 28/02/2025
Hardware Acceleration for Java Ray Tracing: TornadoVM in Action www.youtube.com/watch?v=7q9A...
youtube.com
Hardware Acceleration for Java Ray Tracing: TornadoVM in Action #tornadovm #java #raytracer
YouTube video by Juan Fumero
052
Reposted by Juan Fumero
Stefan Marr @stefan-marr.de · 26/02/2025
The MoreVMs deadline is in a month! We're looking forward to your talk proposals, blog posts, or extended abstracts. New this year: we ask you to submit a description of a planed experiment. Benchmarking is hard, and we're happy to help with feedback! 2025.programming-conference.org/home/MoreVMs...
2025.programming-conference.org
MoreVMs 2025 - 9th International Workshop on Modern Language Runtimes, Ecosystems, and VMs - ‹Programming› 2025
The 9th MoreVMs workshop aims to bring together industrial and academic programmers to discuss the design, implementation, and usage of modern languages and runtimes. This includes aspects such as re...
0115
Juan Fumero @jfumero.dev · 14/02/2025
Java folks: What are the reasons hsdis is not built-in into the JDK? I'm genuinely interested in understanding the technical or logistical considerations that led to this choice.
100
Juan Fumero @jfumero.dev · 14/02/2025
New blogpost: Learn how to build JDK 21 and JDK 25 with the HotSpot Disassembler (HSDIS) plugin enabled for Linux. `hsdis` is a tool to inspect the JVM’s JIT-compiled assembly code, and this post explains how to configure it: 🔗 jjfumero.github.io/posts/2025/0... #java #jdk #jit #disassembler
jjfumero.github.io
Building JDK with HSDIS on Linux
Learn how to build a JDK with the HotSpot Disassembler (HSDIS) plugin enabled on Linux to inspect the JVM’s JIT-compiled assembly code.
151
Juan Fumero @jfumero.dev · 11/02/2025
Upgrading to Bianbu 2.0 to 2.1 for RISC-V Lichee Pi 3A SBC ... Let's see! #riscv
100