KIT Karlsruhe, the research University in the Helmholtz Association, located in Karlsruhe Germany, installed one of the first HPC Systems with the new SD650 v2 water-cooled nodes in combination with die SD650-N v2 water-cooled GPU Nodes. How did they do? Here’s the report.

Nor-Tech provides turnkey Lenovo HPC Solutions. We take the complexity of deploying and managing a cluster out of the equation. By partnering with Lenovo, we provide a rock-solid hardware foundation to deploy our turnkey integration services--from the cluster management suite, workload manager, application software to after deployment support. Nor-Tech has 20-years of experience in HPC applications integration including many open source applications and most commercial simulation and modeling applications.

Learn about the latest HPC technologies from Intel, AMD, and Mellanox for CAE from Lenovo, and how TotalCAE makes these advancements accessible and easy to use for the CAE engineering community

ManagedHPC from X-ISS & Lenovo enables customers to get the best of both worlds: a customized, well-engineered HPC cluster, and a world-class, fully managed service to take care of any issues on the system—from hardware to applications. This allows users to focus on their research and feel confident that the cluster is running optimally at all times

In this session, we will cover two tightly related Professional Services from Lenovo:

• Tackling the special needs of your high power / high heat HPC environment
• Full stack deployment of your HPC & AI cluster, from filesystem to scheduler, including tuning and optimization services

How to reduce electricity consumption by up to 80% vs. conventional cooling by using adsorption chillers in data centers

• Working Principle: Adsorption chillers use heat to produce cold
• Waste heat from a liquid cooled computer can be utilized to run the adsorption chiller
• Required prerequisites to run an adsorption chiller
• Reference “Adsorption Chillers in Leibniz Supercomputing Centre”
• View into the future: rack integrated adsorption chillers simplify planning and installation

In this session you will learn what Ceph storage is and which protocols it uses. We'll also show scenarios in which Ceph is used and how you can start exploring it today.

In this talk, we'll share what shaped our decisions to make the switch to water cooling and how this journey has changed research computing at Harvard. We will give several examples of the impacts on specific faculty research projects.

This session will discuss real world scenarios in Life Sciences, Higher Education, and other research computing industries that leverage existing customer HPC investments in order to boost GPU AI/ML performance. Cambridge Computer's HPC/AI experts will discuss how AI, Machine Learning, and Deep Learning solutions can integrate into existing HPC infrastructure and leverage new enhancements like GPU Direct and GDS (Magnum IO).

While there is continued hype in the media around public blockchain, the enterprise blockchain technology adoption continues to march forward. This private, permissioned type of blockchain platform enables increased transparency and trust based on a shared, distributed, consensus-based and immutable transaction ledger. Participants in the private blockchain network benefit from enhanced automation of their critical business processes and a significantly faster pace of business. This session with provide an overview of enterprise blockchain adoption across industries and highlight key use-cases and examples of enterprise blockchain usage in Lenovo.

Hear how the key supercomputing leaders came together to architect the Leibniz Supercomputing Center’s (LRZ) SuperMUC-NG’s phase II. This upgrade will see the addition of 240 new nodes of the upcoming Intel Xeon “Sapphire Rapids” CPUs and Intel’s planned “Ponte Vecchio” GPU, integrated in Lenovo’s soon-to-be-launched SD650-I v3 server platform. Learn how the upgrade will integrate AI into the research toolbox available to SuperMUC-NG users, enabling much faster Time to Answer in disciplines from climate science to seismic research to genetics. The power of SuperMUC-NG Phase II will deliver a new era where compute cycles no longer limit scientific imagination.

During this session, we will present the process and motivations that led to the heterogeneous solution for the upcoming Dutch National Supercomputer. Specific attention will be given to the compute, communication, and storage aspects and design decisions to efficiently support the emerging HPC and AI workloads.

Learn how Lenovo end-to-end data management solutions provide the necessary framework at the edge, core, and cloud to enable more efficient data collection, faster AI workloads, and transparent cloud integration. By leveraging the reference architecture using Lenovo ThinkSystem servers with ThinkSystem DM ONTAP-powered storage systems for edge and data center ML/DL use cases, including the Lenovo LiCO software platform, organizations will benefit from faster Data Insights to further accelerate their growth and aspiration for innovation.

With our first discrete GPU for the data center, Intel is further expanding its rich suite of platform innovations for enhanced cloud gaming and media experiences. The combination of Intel^® Xeon^® Scalable processors, open-sourced and licensed software ingredients and the new Intel Server GPU offers a high-density, low-latency solution at lower total cost of ownership (TCO) for Android cloud gaming and high-density media transcode and encode for real-time over-the-top video streaming1. By using Intel Server GPUs alongside Intel Xeon Scalable processors, service providers can scale graphics capacity separately from the server count, supporting larger numbers of streams and subscribers per system, while still achieving low TCO.

Intel Optane SSDs, Intel Optane Persistent Memory and the new DAOS scale-out object store are transforming storage performance. Learn how Intel technologies help traditional HPC, AI and High Performance Data Analytics customers overcome their memory and storage bottlenecks, unlocking new levels of performance and scalability.

Artificial intelligence has become a pillar of modern enterprise applications in recent years. Successful enterprises will become "AI powered" - not just because they can but because they must. Enterprise AI supports companies on their AI adoption journey and harnesses advanced artificial intelligence techniques to drive digital transformation. Join Dr. Feiyu Xu, Global Head of Artificial Intelligence at SAP, to get firsthand insights into Enterprise AI, and how SAP delivers value by making end-to-end business processes more intelligent.

NVIDIA AI Enterprise is an end-to-end, cloud-native suite of AI and data analytics software. Optimized, certified, and supported by NVIDIA to run on VMware vSphere  with  NVIDIA-Certified  Systems™, it includes key enabling technologies from NVIDIA for  rapid deployment, management, and scaling of AI workloads  in the modern datacenter. 

Object storage can scale massively! And today’s analytics and AI/ML workloads need access to huge amounts of data. The flat organization of objects versus a hierarchical architecture makes it easier for data engineers to amass data stores in-situ, accessible to data scientists without the need to copy to file or block protocols. The proliferation of technologies like GPUs that accelerate compute functions, while faster networks and NVMe devices speed access to data, makes object data not only highly scalable, but delivers deterministic performance for myriad workloads not considered a decade ago.
Come hear about the scalability and economics of file, block, and object storage, for High Performance Computing and how the growth in objects is driving a new way to respond to a data tsunami!

High performance computing and artificial intelligence supercomputers have evolved to be the primary data processing engines for wide commercial use, hosting a variety of users and applications. While providing the highest possible performance, supercomputers must also offer multi-tenancy security, therefore, they need to be designed as cloud-native supercomputing platforms. The key element that enables this architecture transition is the Data Processing Unit (DPU). DPU is a fully integrated data center on a chip platform that can manage the data center infrastructure instead of the host processor, enabling security and orchestration of the supercomputer. This architecture enables supercomputing platforms that will deliver optimal bare metal performance, while natively supporting multi-node tenant isolation.