Associate Professor at The University of Manchester | Chief Engineer at KTM Innovation | Project Lead TornadoVM
This year's DLS Most Notable Paper award goes to:
Compiling for Multi-language Task Migration
by Marc Feeley
This paper is motivated by the challenges of implementing continuations for an uncooperative environment, and worth a read!
Congratulations to the author!
A great milestone achieved by our team. Just released #GPULlama3.java, the first Java implementation of Llama3 inference accelerated on GPUs via #TornadoVM.
GitHub v0.1.0-beta: https://github.com/beehive-lab/GPULlama3.java
Looking forward to your feedback.
#opensource #Java #AI #LLM #GPUs
New #TornadoVM v1.1.0 release!
👉 Improved profiling and logging.
👉 New memory and buffer management features to persist and reuse data.
👉 Support for more atomic operations.
Work done under #horizoneurope and UK Research and Innovation funded projects: AERO Project, TANGO EU, P2CODE project, ENCRYPT Project!
hanks to all our contributors! 👏
Hardware #Acceleration for #Java Ray Tracing: #TornadoVM in Action
The President & Vice President of the United States are a disgrace to our country.
Ukraine deserves better.
America deserves better.
DeepComputing's developer-focused RISC-V Mainboard for Framework Laptop 13 is now shipping!
Note that pricing for the US reflects tariffs🥲
The #Java YouTube channel just passed 200.000 subscribers. Woot! 🥳 Thank you, everybody, for watching, commenting, sharing, and just in general for being an active member of this awesome community. 🧡💙
New post: Learn how to setup WSL for GPU compute, including TornadoVM
Finally found the downtime to complete this fantastic survey of managed runtimes (e.g. the JVM) and heterogeneous hardware (e.g. CPUs and GPUs or FPGAs) by @snatverk@mastodon.online, @thanos_str@mastodon.sdf.org, and @kotselidis@mastodon.online.
Required reading for those who want a look at the future of software development.
#TornadoVM #JOCL #OpenCL #CUDA
(comment on "Programming Heterogeneous Hardware via Managed Runtime Systems")
Is #Java ready to run on #RISC-V accelerators? If so, how? Juan Fumero shows a possible way by using open-source solutions integrating TornadoVM with the oneAPI Construction Kit:
#Java 23 is now available! Your: FREE, Multi-Platform, Production-Ready, Open Source, Binary Release ...made available by Oracle.
Learn more: https://blogs.oracle.com/java/post/the-arrival-of-java-23
I'm currently recruiting Java educators for a study evaluating potential hints for Java novices. Will take ~30 minutes total to do a solo online task+survey, can be done whenever and wherever you like. If you're interested to participate, email me at neil.c.c.brown@kcl.ac.uk Sharing is appreciated.
#Java developers:
The third recording from the 14th #JVM Language Summit is now available on the official Java YouTube page. "Code Reflection in Action - Translating Java to SPIR-V" by Steve Dohrmann, Intel
Click to view ➡️ https://youtu.be/GQLBzrbkiKA?si=8fxh0EFlvnOI4Fg9
With every major Cloud provider now offering #Armprocessor-based instances, it’s time to start migrating your #Java applications to #Aarch64. Michael Hall from ARM, Principal Engineer and Developer Evangelist, reports on :foojay: :
https://foojay.io/today/is-your-java-application-ready-for-the-next-generation-of-server-cpus/
Closing every JIRA ticket I get assigned tomorrow with “Will Not Fix - probably a solar storm-induced bitflip"
My copy of @snatverk, @thanos_str, and @kotselidis's new book "Programming Heterogeneous Hardware via Managed Runtime Systems" just arrived! Can't wait to read it! #TornadoVM
TornadoVM reaching 8500 GLOPS on NVIDIA #GH200 #GraceHopper GPU for Matrix Multiplication of size 2048x2048. This is the naive matrix multiplication offloaded and optimised by the #TornadoVM + #GraalVM JIT compilers and the TornadoVM runtime. Stay tuned for more experiments on this platform. 🚀
Thank you to the University of Pisa for giving us access to this system via the AERO Project 🙏
We just drop a new release for TornadoVM - version 1.0.4. This one includes new features such as Tensor types based on the Panama Memory API, connection with ONNX, better memory management and power metrics in the profiler + plenty of bug fixes.
Our mission is to provide acceleration as easy as possible, as transparent as possible, and run as fast as possible using the latest technologies, hardware and software.
Release notes: 🔗 https://github.com/beehive-lab/TornadoVM/releases/tag/v1.0.4
🌿 Let's embrace the 4 R's: Reduce, reuse, recycle... and repair!
Today, the European Parliament adopted the 'Right to Repair' Directive. By promoting repairs both within and beyond the legal guarantee, it will soon mean:
🟢 Easier product fixes
🟢 Money saved
🟢 Less waste
By repairing and using our goods for longer, EU consumers can not only practice sustainable consumption but also save a significant amount of money in the process!
