Location: Room O4 – Orchid Jr 4311-2 (Level 4)
Abstract: Transitioning to the AI-Driven Scientific Discovery Era. AI is permeating every facet of technology, heralding a transformative era in scientific research, and presenting an unprecedented opportunity to enhance simulation accuracy and drastically reduce prediction times. From traditional computing paradigms to AI-accelerated models, this shift constitutes a new industrial revolution that is reshaping the industry. We will equip students with a cutting-edge programming model that integrates both HPC and AI, and bridge the gap between academic knowledge and state-of-the-art industry applications.
Track Chair: Mr Song Qingchun, HPC-AI Advisory Council, APAC
[Invited Track]
Programme:
| Time | Session |
| 02:00pm |
Opening – Mr Qingchun Song, Chair of HPC-AI Advisory Council, Asia |
| 02:00pm – 02:20pm |
The HPC-AI Advisory Council HPC-AI Advisory Council is an organization with a vision to bridge the gap between the state of the art in HPC and AI and its practice. This is achieved through things such as workshops, student competitions, open computing laboratory and publishing best practices. The organization includes more than 450 member companies, universities, and research centers. Computationally, HPC and AI computing is towards the use of increasing amounts of accelerated system, as is reflected in the Top500 list. From a simulation perspective, with the end of Dennard Scaling, focus is shifting towards combining traditional HPC simulations with AI-based algorithms to reach the next level of simulation capabilities. These trends will be briefly discussed. – Dr Richard Graham, HPC|Scale Special Interest Group Chair, HPC-AI Advisory Council |
| 02:20pm – 02:40pm |
HPC Software Development – Challenges and the Future With new processors being introduced every one to two years, HPC software development is facing tremendous challenges to catch up and optimise for the latest architectures. A piece of software usually stays in use for a much longer period than the lifetime of a HPC system. On top of that, there are multiple competing parallel programming frameworks posting confusions to the software developers who are having hard time to pick a framework. In this talk, we walk through the current landscape of parallel programming. We share our experience and view in HPC software development, helping the audience to navigate through the challenges to the future. – Mr Chung Shin Yee, NSCC Singapore |
| 02:40pm – 03:00pm |
National Computational Infrastructure, Australia The presentation will focus on the computational capabilities of Australian NCI’s HPC Cluster, Gadi and the skills development initiatives that are helping National and International researchers leverage the high-performance capabilities. – Dr Abdullah Shaikh, Training Manager, NCI Australia |
| 03:00pm – 03:20pm |
Generative AI for 3D Generation and Editing Recent developments in Generative AI has witnessed remarkable success in synthesizing visual content, especially images and videos. In contrast, the quality of 3D generation still lags behind. In this talk, I will present several works that push the boundaries of 3D generation through efficient and scalable architecture designs. First, I will introduce how a structured 3D latent space enhances the capabilities of 3D diffusion models. Next, I will present SAR3D, an efficient framework for generating 3D objects using autoregressive next-scale prediction. Finally, I will demonstrate how we enable flexible user interaction in 3D content creation through point-dragging editing for 3D objects. – Dr Pan Xingang, Assistant Professor, National Technological University |
| 03:20pm – 03:30pm |
2024 APAC HPC-AI Competition Award Ceremony – Mr Qingchun Song, HPC-AI Advisory Council – Dr Terence Hung, NSCC – Dr Abdullah Shaikh, NCI |
| 03:30pm – 04:00pm | Tea Break |
| 04:00pm – 04:20pm |
VAST Data platform: The Data Platform for the AI Era The VAST Data Platform introduces a groundbreaking approach to AI and data analytics infrastructure through its innovative Disaggregated Shared Everything (DASE) architecture. By unifying storage, database, and containerized compute into a single, scalable software platform, it addresses critical challenges in modern data center and cloud environments. The platform’s unique capability lies in its ability to seamlessly integrate unstructured and structured data using declarative functions, creating a global data-defined computing environment. This talk will explore the platform’s technical architecture, demonstrate its transformative potential through compelling use cases, and showcase real-world customer success stories that highlight its impact on AI and deep learning workflows. – Dr James Chen, Senior Solutions Engineer, VAST |
| 04:20pm – 04:40pm |
NVIDIA Modulus Accelerates AI4S Development In this report, we will introduce NVIDIA Modulus, a physical machine learning development framework, and its application examples in computational fluid dynamics. NVIDIA Modulus is a physics-based, operator-learning environment designed to help scientists and engineers solve complex scientific and engineering problems. NVIDIA Modulus is an open-source framework for building, training, and fine-tuning physical machine learning models with a simple Python interface. NVIDIA Modulus uses neural networks to simulate physical systems that can be used for weather simulation, computational fluid dynamics, heat transfer, structural mechanics, molecular dynamics, and more. – Dr Lyulin Kuang, Solution Architect, NVIDIA |
| 04:40pm – 05:00pm |
The Blueprint for a Sustainable AI Factory The presentation details Firmus Technologies’ state of the art AI Factory. Utilizing cutting-edge liquid immersion cooling technology, Firmus achieves a 45% improvement in energy efficiency and a 30% reduction in costs compared to traditional air methods. Our scalable solution supports retrofitting legacy data centers or building new, energy-dense facilities, aligning with Singapore’s Green Plan 2030. The platform powers AI factories with NVIDIA-certified H100/H200 GPU clusters, enabling high-performance AI model training while minimizing environmental impact. – Dr Daniel Kearney, Chief Technology Officer, Firmus Technologies |
| 05:00pm – 05:20pm |
Student Competition Experience Sharing In this AI and scientific computing era, the demand of computation capability is growing drastically year after year. As a student, I’ll go through the experience of my HPC route. How I was trained, What resources should be provided when educating HPC courses, and the benefit of take part in student cluster event. And lastly, the reason why we should put more effort at colledge end to help student to catch on the trend of industry. – Mr Jason Lin, Student, National TsingHua University |
| 05:20pm – 05:40pm |
Introduction of Competition Achievements in HPC-AI 2024 Through our participation in multiple HPC-AI competitions, our team has gain invaluable insights from our seniors in large-scale HPC system. The competition provided us with access to state-of-the-art computing resources and interesting applications, enabling our hands-on experience with distributed system. We successfully implemented various optimization techniques and achieved significant performance improvements, particularly in areas of communication overhead reduction and memory utilization. Building upon this competition experience, we aim to further improve ourselves on understanding and creating novel approaches in AI system infrastructure, contributes to the broader field of HPC. – Mr Ng Woon Yee; Mr Bryan Shan, Student, Nanyang Technological University |
| 05:40pm – 06:00pm |
Growing Through HPC AI Competitions to Inspire Community Innovation Over seven years, Thammasat University’s participation in HPC-AI competitions has transformed its team, deepening HPC expertise, accessing advanced supercomputing resources, and fostering collaborations. As a coach, competition successes opened doors to prestigious opportunities, such as ACM Summer Schools and EU ASEAN HPC Schools, reclaiming missed opportunities and building a robust international network. Competition achievements help in secure funding from Thailand’s National Research Council for the HPC Ignite project. This initiative bridges HPC education and industry, empowering Northern Thailand’s economic sectors with support from local stakeholders and ThaiSC. Thammasat University Lampang Campus has transitioned from competition-based learning to impactful, community-driven initiatives, showcasing the value of global collaboration and mentorship gained through HPC-AI Advisory Council competitions. – Dr Worawan Diaz Carballo (Marurngsith), Assistant Professor, Thammasat University |
| 06:00pm |
Closing – Mr Pengzhi Zhu, Lab Manager, HPC-AI Advisory Council |
