Check out our full #ISC24 special session with Codeplay Software Founder and CEO, Andrew Richards (Andrew Richards). Learn how open and scalable software is enabling scientific, academic, and industrial advancements with #HPC and #AI. Watch now. intel.ly/3XdsvP7

Teams are focused on the final day of our Intel oneAPI hackathon, receiving hands-on support from DiRAC RSEs and Intel experts from Codeplay Software

It was a pleasure to host the DiRAC Hackathon in our office last week. Some real progress was made in empowering the projects with portable, standards-based code through #SYCL and #oneAPI. Keep an eye out for our upcoming blog!

We're at the RISC-V European Summit in Munich! Come and see our talk on Thursday about bringing #SYCL and #oneAPI to your #RISCV accelerator. We'll also be by our UXLfoundation poster during the breaks, telling you all about how you can get involved! #RISCVSummitEurope

Our colleagues from Codeplay Software presenting at #RISCVSummitEurope their work on #SYCL and #oneAPI and the importance of having an #open #software ecosystem! RISC-V HaDEA Horizon Europe🇪🇺

Check out this blog and demo by CERN introducing the open-source #AdaptivePerf and how we'll use it to profile our use cases for the #SYCLOPS Project! syclops.org/updates/2024/0… #SYCL

We were glad to present our work for #oneAPI and #SYCL at the most recent ATLAS HLT workshop, led by CERN Open, portable code has many benefits for science and innovation - that's why we're also working with CERN on the SYCLOPS research project. SYCLOPS Project

"Cross-industry collaboration is the key to innovation." This article gives insight into the benefits of open source, and how open ecosystems foster collaboration. Fujitsu UK and Arm are both also members of the UXLfoundation! fujitsu.com/global/about/r…

At the RISC-V Summit in Munich, we showed how you can bring the open ecosystem of #oneAPI and #SYCL to #RISCV hardware with the oneAPI Construction Kit. The talk was recorded and is available here! youtube.com/watch?v=Jw_nEt…

In case you missed it, our founder Andrew Richards recently gave a keynote talk at #ISC. In it, they look at the ecosystem for open, standards-based acceleration with #oneAPI and the @uxlfoundation Watch it here! youtube.com/watch?v=MlvJmi…

The Intel Software Codeplay Software oneAPI Construction Kit 4.0 Brings RISC-V RISC-V Host CPU Support phoronix.com/news/oneAPI-Co…

llama.cpp is a #C++ project used to perform inference with a range of models including Meta's LLaMa. With SYCLomatic and our plugin for NVIDIA GPUs, it has been possible to convert the llama.cpp CUDA backend to #SYCL and #oneAPI Read the first blog here! codeplay.com/portal/blogs/2…

For people wanting to design their own GPU-like accelerators for AI and scientific applications, this open source project is making it very easy to solve the software challenges. Especially for the many people choosing to base the programmable part of their accelerators on RISC-V

A big milestone today as our open source #oneAPI Plugin for AMD GPUs leaves beta, and enters production. The update comes with an experimental #SYCL Graph implementation, and more support options for organizations using the plugin. Read more here! codeplay.com/portal/news/20…

Thanks to Codeplay Software and the AERO, we are able to accelerate Java programs on CPUs via the #TornadoVM framework and the oneAPI Construction Kit (OCK) . Acceleration of 3.4x over Java Streams (32 cores) using the same device for running Matrix Multiplication🤩

In our last blog we migrated CUDA code to #SYCL with the whole project migration tool, SYCLomatic. Now we're going to build and run a llama.cpp application on both an NVIDIA and Intel GPU - to demonstrate real code portability. See the second part here! codeplay.com/portal/blogs/2…

Don't miss this chance to showcase your work with #oneAPI and get involved with the UXLfoundation community. CFP open until August 30th! sessionize.com/uxldevsummit/

[Blog] Using oneAPI Construction Kit and #TornadoVM to accelerate Java Programs on #x86, #ARM and #RISCV CPUs. In this blog, we explore how OCK can be used by TornadoVM to run on different CPU architectures. 🔗jjfumero.github.io/posts/2024/09/…

The SynxFlow project broke vendor lock-in by migrating their CUDA code to #oneAPI and #SYCL This fast conversion brought open, standards based and heterogeneous code to their project which can now take advantage of Dawn, the UK's fastest AI supercomputer codeplay.com/portal/blogs/2…