oneAPI DevSummit Hosted by UXL Foundation

October 9, 2024
October 9th - 10 AM/APAC & October 10th - 10 AM/EMEA
See agenda

DESCRIPTION

Join us for an in-depth showcase of oneAPI specification along with open-source projects that implement oneAPI specification. oneAPI is designed to enable developers to use a single code base across multiple accelerators and architectures, supporting artificial intelligence, high performance computing, edge computing, automotive, and more.

 

Hosted by the UXL Foundation, this community-led conference brings together developers to explore, share, and showcase the capabilities of oneAPI through hands-on tutorials, demos, technical talks, and panel discussions.

 

We welcome you for two days across global time zones to discover how oneAPI is being used today and explore its future. Join our ever-growing community.

Agenda

October 9th APAC
October 10th EMEA

October 9th APAC

8:30 - 8:45 IST Keynote

Welcome and UXL Foundation State of the Nation

The UXL Foundation is almost one year old and the momentum is growing with increasing membership and contributions to meetings, specification and open source projects.   As Chair of the Steering Committee I will present the highlights from the past year, talk about the progress we are making to build our ecosystem, and share a vision for where the UXL Foundation is going in 2025…
Presenting

8:45 - 9:30 IST Keynote

Open source code is not enough

A discussion about how just creating an open-source project or foundation isn’t enough to drive success for a platform like oneAPI. This talk will discuss the open-source development model as opposed to just open-source code, as well as how to encourage communities, but also to engage and enable competitors’ platforms to ensure the success of the ecosystem.
Presenting

9:30 - 9:45 IST Break

9:45 - 10:30 IST Tech Talk

UXL Foundation Project Updates

UXL Foundation projects have made lots of progress in the past year, with new features and releases. Maintainers from the projects will provide an update on what’s been happening in 2024 and what to expect in the future.

10:30 - 11:15 IST Tech Talk

oneMCC: A New Programming Interface of Memory Centric Computing

In this presentation, we will provide an overview of oneMCC, a software solution for memory-centric computing proposed by Samsung, and discuss extensions to parallel programming models for effectively utilizing PIM/PNM technologies. Specifically, we will focus on introducing the SYCL extension for PIM/PNM.
Presenting

11:15 - 12:00 IST Tech Talk

Leveraging oneAPI for Industry Application: A Deep Dive focusing on predictive maintenance context

In this session, we will explore how oneAPI can be directly applied to solve real-world industrial challenges, specifically in the field of predictive maintenance. Using the example of ToolDetective, a cutting-edge predictive maintenance solution for monitoring metal cutting tool wear, we will demonstrate how integrating oneAPI-optimized AI frameworks, GPU acceleration, and advanced data processing techniques can significantly enhance performance and efficiency.
Presenting

12:00 - 12:45 IST Tech Talk

Advancing Open-Source Statistical Frameworks

Fujitsu is developing a high-performance, energy-efficient 2nm ARM-based CPU, FUJITSU-MONAKA, for next-gen data centers, focusing on optimizing performance, usability, and open-source software (OSS) development. Collaborating with the OSS community, we contribute to AI-accelerated software stacks for data-intensive workloads. This talk will highlight Fujitsu’s recent contributions to the open software ecosystem for statistical computing:   Implemented statistical kernel routines in the Vector Statistical Library (VSL) to…
Presenting

12:45 - 13:15 IST Break

13:15 - 14:00 IST Tech Talk

oneAPI Construction Kit

Bonus Session – Learn about the oneAPI Construction Kit, an open source project that allows code written in SYCL to run on custom architectures or HPC and AI.
Presenting

14:00 - 14:45 IST Tech Talk

Portable SYCL code using oneMKL on AMD, Intel and Nvidia GPUs

Across the world, there are an increasing number of centers with diverse hardware, including GPUs from vendors like AMD, Nvidia, and Intel. Many developers are sharing code across institutions and need software that runs on diverse architectures. The good news is that you can write code using a single programming model and language and deploy it across AMD, Intel, and Nvidia GPUs, as well as…
Presenting

14:45 - 15:30 IST Tech Talk

Performance Evaluation & Benchmarking of AI Systems

AI systems, comprising application and computing components, demand efficient performance for optimal operation. Application systems focus on solving domain problems using AI techniques, while computing systems handle data-driven models. Effective performance engineering involves a deep understanding of both areas, from hardware architecture to software design. This knowledge is crucial for various roles within the AI ecosystem, including sales, marketing, computer architecture, and software development. Despite…
Presenting

15:30 - 16:15 IST Keynote

Democratizing the use of AI

Artificial intelligence (AI) is rapidly evolving, but accessibility remains a challenge. Our mission is to democratize AI by fostering open collaboration with the global community to develop human-centered, sustainable digital transformation. Japan’s NEDO has launched an initiative to achieve 40% energy savings in domestic data centers by 2030. Fujitsu’s MONAKA, a 2 nm Arm CPU arriving in 2027, focuses on energy efficiency to support carbon-neutral…
Presenting

16:15 - 16:30 IST

Closing of the First Day

Hosts will close out the APAC Day 1 of the conference.

October 10th EMEA

09:00 - 09:15 CT Keynote

Welcome and UXL Foundation State of the Nation

The UXL Foundation is almost one year old and the momentum is growing with increasing membership and contributions to meetings, specification and open source projects.   As Chair of the Steering Committee I will present the highlights from the past year, talk about the progress we are making to build our ecosystem, and share a vision for where the UXL Foundation is going in 2025…
Presenting

9:15 - 9:45 CT Keynote

GE HealthCare working with oneAPI

Presenting

9:45 - 10:15 CT Keynote

The AI Developer Journey on a Flexible, Edge Compute Platform

As the demand for accelerated computing for AI use cases continues to grow exponentially there are many challenges presented to businesses and their developers in creating software solutions for long-term deployment at the edge. In this talk we’ll explore both the new platform portability challenges and the old-persisting performance challenges for customers, looking at this from Imagination’s perspective as a provider of flexible GPU IP.…
Presenting

10:15 - 10:30 CT Lightning Talk

Ginkgo’s SYCL backend and its integration into nekRS

The increasing diversity of hardware architectures makes it harder for simulation software to get everything working on different hardware. Simulation software stacks need to rely on portability layers or software stacks that support different hardware architectures. We present Ginkgo, a math library that considers platform portability seriously and can be used for linear solvers in nekRS CFD code. We have presented nekRS with Ginkgo on…
Presenting

10:30 - 10:45 CT Lightning Talk

Making use of Level Zero with an end-to-end MLIR compiler

AI compiler support is one of the crucial enablers for any hardware system. It allows efficient mapping and execution of models on the device. The UXL interfaces enable unified access to different devices, which is a key requirement for building retargetable AI compilers. Therefore, end-to-end compiler support for the UXL ecosystem will provide the foundation for various devices. In this talk, we will present our…
Presenting

10:45 - 11:00 CT Lightning Talk

SYCLDB - cross-architecture acceleration of data analytics with SYCL

The growing popularity of AI and analytics in virtually all domains has led to an increase in the amount of data gathered. Workflows have become increasingly heterogeneous. While CPUs are not always efficient enough for the demands of modern AI and analytics workloads, GPUs, which offer greater parallelism, have largely remained closed-source. In response, two open standards have gained popularity: RISC-V, an open instruction set…
Presenting

11:00 - 11:45 CT Panel

Open standards and open source always wins

The demand for heterogeneous architectures continues to rise, driven by the exponential growth in generative AI and accelerated computing. Workloads are being spread across new and diverse hardware, such as GPUs, NPUs, and AI accelerators, allowing both traditional algorithms and new neural networks to run much faster than was previously possible. The challenge we face is in ensuring that there is a standards based way…
Presenting

11:45 - 12:30 CT Tech Talk

UXL Foundation Project Updates

The UXL Foundation projects have made lots of progress in the past year, with new features and releases. Maintainers from the projects will provide an update on what’s been happening in 2024 and what to expect in the future.

12:30 - 12:45 CT Break

12:45 - 13:30 CT Tech Talk

TornadoVM: Harnessing the XPU Power from Java

The demand for heterogeneous architectures continues to rise, driven by the exponential growth in generative AI and accelerated computing. Workloads are being spread across new and diverse hardware, such as GPUs, NPUs, and AI accelerators, allowing both traditional algorithms and new neural networks to run much faster than was previously possible. The challenge we face is in ensuring that there is a standards based way…
Presenting

13:30 - 14:15 CT Panel

Accelerating Software on the Edge

The rise of edge computing has increased the need for portable hardware acceleration for AI and image processing, especially where power consumption matters or cloud connectivity is unreliable. Automotive is driving software innovation in vehicles, particularly for driver assist and self-driving features, motivating the use of neural networks like Llama and GPT. Traditional algorithms like BLAS and FFT also benefit, running much faster on GPU-like…
Presenting

14:15 - 15:00 CT Tech Talk

UXL Security strategy as an adoption of the best industry practices

Open-source runs the world. That’s why we at the Linux Foundation and UXL genuinely believe in establishing and transparently sharing the best ecosystem practices, staying at the forefront of modern collaborative software development. Recognizing the level of responsibility entrusted to us by millions of users who consume LF and UXL projects, we must make sure our repos are as resilient as possible to the next…
Presenting

15:00 - 15:15 CT Break

15:15 - 16:00 CT Tech Talk

Add Jet Fuel to your SYCL* Application - Profiling and Optimizing Your Code

SYCL*, a standards-based unified programming model, offers ground-breaking performance across different hardware targets, including CPUs, GPUs, and FPGAs. However, to achieve maximum performance from the SYCL* workloads running on various platforms, we need to ensure maximum utilization of Hardware resources and Software capabilities. Profilers can play a significant role in harnessing the maximum computational power and memory bandwidth of the target Hardware. In this session,…
Presenting

16:00 - 16:45 CT Tech Talk

Data-flow parallelism for high-energy and nuclear physics computing frameworks

The processing tasks of a scientific workflow in high-energy and nuclear physics (HENP) can typically be represented as a directed acyclic graph formed according to the data flow—i.e., the data dependencies among algorithms executed as part of the workflow. With this representation, an HENP computing framework can optimally execute a workflow, exploiting the parallelism inherent in independent tasks. Despite such a natural description of a…
Presenting

16:45 - 17:00 CT Lightning Talk

NAMD Molecular Dynamics Simulations

Molecular dynamics simulations with NAMD serve as a bridge between structural data and biological function, providing a “computational microscope” that offers an atomic-scale view of the mechanistic foundations of life. This talk will discuss the use of oneAPI in NAMD to support Intel PVC GPUs for fast, scalable simulations on ALCF Aurora and TACC Stampede 3 supercomputers. Development has included porting CUDA kernels to SYCL,…
Presenting

17:00 - 17:15 CT Lightning Talk

Experiences with Cross-platform Portability of NWChemEx using SYCL on Exascale Supercomputers

The advent of exascale computing presents significant opportunities for advancing computational chemistry, particularly in the accurate modeling of molecular systems. We explore the integration of a gold standard quantum chemistry algorithm—Coupled Cluster with Single, Double, and Perturbative Triple excitations [CCSD(T)] method developed within the NWChemEx library using SYCL and the oneMKL library to enable portability and performance across diverse exascale hardware architectures. Our work specifically…
Presenting

17:15 - 17:30 CT

Closing Ceremonies

×


Watch the oneAPI DevSummit hosted by UXL:

Watch Now