Location: Room L1 – Lotus Jr (Level 4)
Track Chair: Mr Tommy Ng, NSCC
[Invited Track]
| Time | Session |
| 01:30PM – 01:50PM | HPC for the Age of AI
Democratization of HPC – Supercomputing has traditionally been an extremely time-consuming and resource-intensive undertaking. Access to GPU resources, unified tools, and AI expertise can often be difficult to attain and optimize. Many enterprises struggle with the complexity, effort, and time required to operate such infrastructure. The future trends will address such issues. – Mr SS Lim, CEO, PTC System |
| 01:50PM – 02:10PM | Leveraging Agentic AI for Advancing AI in Science To harness Agentic AI for “AI for Science,” it is essential to leverage numerous AI expert models, enable high-speed inference, and integrate existing tools beyond AI models to construct logical processes. In this session, I will demonstrate how SambaNova can simplify the creation of Agentic AI workflows, featuring live demonstrations to showcase its capabilities. – Dr Nan Hu, Senior Principal Solutions Engineer, SambaNova Systems |
| 02:10PM – 02:30PM | AMD Instinct GPU for HPC/AI
The presentation is to share the AMD GPU from Architecture and its development journey from CDNA1 to DCNA4 architecture. As to support AMD MI-Instinct GPU to be applicable for computing, AMD has been building a Software Development Environment for user since 2015. The software named ROCm, which the recently released was version 6.3 which provide additional features in supporting LLM, AI frame works and optimized Libraries which deliver more performance on the same work load as compared with earlier version 6.0. Frictionless migration path from current GPU environment to ROCm environment will be shared. – Mr Robert Sheen, Sr. Manager DCGPU Business Development, AMD |
| 02:30PM – 02:50PM |
Taking Control of Your AI Powerhouse
AI has incredible potential to change the way you engage with customers and drive value in your business, so now is the time to scale! However, as many customers have found, rapid scale can also lead to rapid problems, with escalating costs, data collection challenges and regulatory issues. Hitachi Vantara, a leader in the industrial AI space, has brought to market a solution portfolio that not only solves the technology hurdles, but addresses the afore mentioned challenges, and through that enabling you to accelerate to scalable value faster. – Mr Matthew Hardman, CTO, Asia Pacific, Hitachi Vantara |
| 02:50PM – 03:10PM | Architecting the intersection of Quantum Computing and Artificial Intelligence This session explores innovated Dell architectures for enabling the convergence of quantum simulation, artificial intelligence, and traditional computation sciences. We discuss hardware architectures, and software strategies for seamless integration, and the offloading of workflows to hybrid-quantum platforms. – Mr Andrew Underwood, APJC Field CTO, Dell Technologies |
| 03:10PM – 03:30PM | AI at Every Scale: Vertiv’s Approach to HPC AI Deployment Scenarios
Delve into the diverse scenarios and strategies of HPC/AI deployments, exploring how Vertiv’s innovative infrastructure solutions can be effectively implemented across various scenarios. From small-scale, edge scenarios to hyperscaler environments, this industry session discusses how Vertiv’s end-to-end portfolio — including advanced cooling systems and power distribution – addresses the unique challenges of each deployment. Through real-world examples and practical insights, discover how Vertiv empowers organizations to achieve efficiency, scalability, and reliability in HPC/AI operations. Let our experts equip you in choosing and implementing the right solution for every stage of your HPC/AI journey. – Mr Alvin Cheang, HPC / AI Business Director, Asia, Vertiv |
| 03:30PM – 03:40PM | Tea Break
Tea Break is served at the Exhibition Room (Orchid Ballroom). |
| 03:40PM – 04:00PM | Deploying 10,000+ GPU Clusters with VAST Data: Large-scale Model Training and Inference
As AI workloads grow in complexity, deploying and managing large-scale GPU clusters efficiently is critical for HPC/AI environments. This talk explores how VAST Data enables seamless scaling to 10,000+ GPU clusters, optimizing model training and inference with unparalleled performance and stability. VAST is widely deployed in the largest GPU environments in the world, scaling to over 100,000 GPUs; insights from this experience will also be shared. We’ll discuss key architectural considerations, real-world deployment insights, and best practices for maintaining resilience at scale — ensuring HPC teams can push the boundaries of AI innovation without compromising efficiency or reliability. – Dr Subramanian Kartik, Vice President of Systems Engineering, VAST Data |
| 04:00PM – 04:20PM | Standards-based Data Platforms for HPC and AI HPC and AI workloads demand high-performance access, often to multiple data sources in different storage systems and cloud instances. Traditional storage architectures struggle with data silos, proprietary file systems, and complex orchestration. Organizations need a unified global data platform that seamlessly spans edge, data centers, and cloud environments—without vendor lock-in. This session explores how pNFS and automated data orchestration enable an open, standards-based approach to parallel file system performance for AI and HPC workloads. With recent Linux kernel advancements—including contributions from Hammerspace—organizations can now achieve linear scalability in IOPS and throughput using standard NFS clients. Key topics include: • Parallel Global File Systems with NFS 4.2 – How open standards now provide high-performance, scalable access to distributed data without proprietary clients. • Automated Data Orchestration – How Hammerspace’s Flexible Files technology enables seamless, real-time data movement across storage types while ensuring continuous access. • Optimized Workflows for AI & HPC – How a unified namespace accelerates data-driven workloads and ensures compute power is fully utilized. – Mr Floyd Christofferson, Vice President of Product Marketing, Hammerspace |
| 04:20PM – 04:40PM | Quantum and Supercomputing Threats: Check Point’s Strategy for Future-Proof Security The rapid advancements in quantum computing pose both opportunities and threats to cybersecurity. Classical encryption methods, including RSA and ECC, are at risk of being rendered obsolete by quantum algorithms like Shor’s algorithm. Check Point Quantum Cryptography presents a forward-thinking approach to securing digital communications against these emerging threats. By leveraging post-quantum cryptographic algorithms, Check Point aims to ensure data integrity and confidentiality in a quantum-powered future. This presentation will explore the fundamentals of quantum cryptography, discuss the challenges of implementation, and outline Check Point’s roadmap for securing enterprises against quantum threats. The audience will gain insight into how organizations can future-proof their security infrastructures and adopt a quantum-resistant cybersecurity posture. – Mr Abhishek Kumar Singh, Sales Engineer Manager, APAC, CheckPoint Software Technologies |
| 04:40PM – 05:00PM | Accelerating Scientific Discovery with Azure Quantum
Azure Quantum is revolutionizing scientific discovery by integrating quantum computing, artificial intelligence, and high-performance computing. This presentation highlights the potential of quantum computing to address complex global challenges, particularly in chemical, materials, and drug discovery. It showcases the Azure Quantum platform’s capabilities, including the new Copilot experience, which enhances productivity for computational chemists. The presentation also emphasizes the importance of reliable logical qubits for practical quantum advantage and Microsoft’s unique approach to achieving quantum scale. Join us on this journey to unlock breakthrough value and accelerate innovation cycles with Azure Quantum. – Mr Ujjwal Kumar, Principal Architect, Office of CTO, Microsoft Asia, Microsoft |
| 05:00PM – 05:20PM | Xeon Processor Designed for HPC – Intel Xeon 6900 Series
Discover what makes Intel Xeon 6900 series processors exceptional for use in high performance computing. This includes thermal design, memory performance and Peak efficiency. – Mr Otto Chow, Technical Sales, Sales & Marketing (APAC), Intel |
| 05:20PM – 05:40PM | Quantum-centric Supercomputing: A New Perspective on Computing
As quantum systems have recently become more capable and mature, the integration of quantum systems in HPC datacenters has become more and more frequent. In this talk I will present some of our efforts along our vision of integrating quantum computing in HPC environments and will show how users can already start extracting value from quantum computers before the maturity of quantum error correction. I will also show how classical supercomputing can have a critical role at different stages of a quantum computation and how classical developers can already actively engage with heterogeneous workflows in integrated quantum and classical systems. – Dr Antonio Córcoles, Head of Quantum + HPC, Principal Research Scientist, IBM |
| 05:40PM – 06:00PM | Accelerating Scientific discovery with HPC & AI
AI and HPC are transforming scientific discovery by speeding up research processes. These technologies are applied in fields like chemistry and materials science, enabling rapid screening and accurate predictions. The integration of AI and HPC has significantly reduced discovery times, allowing scientists to achieve breakthroughs in weeks instead of years, addressing urgent challenges in various domains. – Mr Nikkesh Siva, Sr Specialist, Azure HPC, Microsoft |
