- Community Home
- >
- Servers and Operating Systems
- >
- Servers & Systems: The Right Compute
- >
- Making supercomputing easier for HPC users
Categories
Company
Local Language
Forums
Discussions
Forums
- Data Protection and Retention
- Entry Storage Systems
- Legacy
- Midrange and Enterprise Storage
- Storage Networking
- HPE Nimble Storage
Discussions
Discussions
Discussions
Discussions
Forums
Forums
Discussions
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
- BladeSystem Infrastructure and Application Solutions
- Appliance Servers
- Alpha Servers
- BackOffice Products
- Internet Products
- HPE 9000 and HPE e3000 Servers
- Networking
- Netservers
- Secure OS Software for Linux
- Server Management (Insight Manager 7)
- Windows Server 2003
- Operating System - Tru64 Unix
- ProLiant Deployment and Provisioning
- Linux-Based Community / Regional
- Microsoft System Center Integration
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Community
Resources
Forums
Blogs
- Subscribe to RSS Feed
- Mark as New
- Mark as Read
- Bookmark
- Receive email notifications
- Printer Friendly Page
- Report Inappropriate Content
Making supercomputing easier for HPC users
HPE Cray Supercomputing User Services Software helps complete diverse workloads efficiently and seamlessly. Learn about this offering and how it can help you get more out of your HPE Cray system.
High performance computing (HPC) systems are enabling organizations to tackle the worldโs most complex challenges in manufacturing, energy, research, and more. Therefore, it should come as no surprise that it takes teams of specialists to deploy, run, and maintain the sophisticated architecture of each one of these systems.
Engineers, system administrators, IT professionals, and software developers all contribute to setting up and optimizing HPC systems as well as keeping them healthy. However, a specific group of specialists leverage the systems to run workloads: they are the users for whom the new HPE Cray Supercomputing User Services Software (HPE Cray SC User Services Software) solution is designed.
Examples of the types of people and projects include:
- Scientists recreate complicated molecular structures, simulate drug interactions, and create models with environmental data
- Data analysts process large datasets, glean insights, and train machine learning models
- Financial analysts conduct risk analysis and create financial models
- Design engineers run simulations and improve modeling
As organizations implement expanded use cases, they require high-performing systems to handle the tremendous influx of data. Thatโs where HPC systems, which can deliver exascale-class computing capabilities, come in. Hyperion Research reports that the on-premises HPC server market is expected to grow by ~8.2% per year for the next five years from approximately 15 billion in 2023.1
Examining evolutions in the HPC user base
In the past, HPC users were often government entities and research institutions performing tasks that were highly parallelizable and needed immense computational power. For example, they performed numerical simulations to forecast weather and run analyses for national security. Enterprises also leveraged HPC systems for complex tasks, and there were combined HPC and AI use cases such as building digital twins. HPC yielded the computational power to process data and run simulations while AI enabled predictive analytics and optimizations, resulting in a digital twin that not only resembled the physical models, but also could provide actionable insights.
Now, HPC systems are increasingly running โhybridโ workloads involving both HPC and AI. For example, tech startup Atomic Canyon is using Oak Ridge National Laboratoryโs Frontier (the first exascale system on the Top500) to run generative AI workloads for nuclear regulatory processes and compliance. Read more here.
Introducing HPE Cray SC User Services Software
Between running computations to advance progress on global issues and breaking new ground as they experiment with diverse use cases, HPC users certainly have a lot to consider. HPE aims to help users focus their energy on envisioning โwhatโs nextโ by launching a software solution that ensures their submitted workloads are executed efficiently and seamlessly.
HPE Cray SC User Services Software bundles together advanced features that make customersโ HPC systems more composable and fit to accommodate diverse workloads. In other words, users can customize their managed node environments and get more out of the HPE Cray systems that they have invested in. Based on their organizationsโ unique needs, customers can selectively install features for:
- Compute at scale
- File system integration
- Power management
- Workload manager integration and container support
Diving into HPE Cray SC User Services Software benefits
As HPC users grow in number and variety, HPE Cray SC User Services Software offers benefits to user experience through flexibility to run different workloads, system efficiency, and power management capabilities.
Various features expand the scope of what research users can do with existing infrastructure.
Flexibly run different types of workloads |
Included functionalities, documentation, and software enable users to run an array of HPC workloads (e.g., compiling applications, scheduling batch jobs) as well as an increasing amount of AI workloads (e.g. predictive analyses, running/tuning large language models, handling massive parallel computations with Kubernetes) |
Features also improve system efficiency, helping users have faster and more consistent runtime experiences.
Improve access to file systems |
Data Virtualization Service (DVS) enables systems to seamlessly run tasks involving data that resides on different file systems as if they are stored locally, reducing bottlenecks associated with data I/O operations. |
Efficiently manage resources |
Low noise mode focuses resources on running workloads rather than executing background activities. This optimization helps the system efficiently manage CPU cores. |
Drive scalability across multiple processes |
XPMEM streamlines communication and coordination between different processes running on the compute node, creating shared memory capabilities that enhance scalability โ especially for parallel applications. |
Features enable power management, which is especially important as new processors present even greater power requirements and energy costs for HPC sites skyrocket.
Ensure predictable power usage |
Turbo boost limiting prevents spikes in usage of power to help estimate power consumption and associated costs. Users can leverage estimates to stay within allocated power limits. |
Balance cost and performance |
Power measurement keeps users aware of power utilization and distribution by processor (CPU/GPU level) or by job so that they can make decisions on striking the balance between power and performance. |
More details about HPE Cray SC User Services Software available in the QuickSpecs.
Previewing future capabilities of HPE Cray SC User Services Software
HPE Cray SC User Services Software will continue to evolve to accommodate increasingly diverse complex workflows, pushing the boundaries on what customers can accomplish with their HPE HPC systems. It will also provide integrations with new tools and additional capabilities, helping users leverage containerization and virtualization, and ultimately, maximize utilization of hardware resources and flexibly scale their workloads.
Learn more about HPE Cray Supercomputing
Meet Evelyn Ha, Product Marketing Associate, HPC & AI
Evelyn drives product marketing initiatives for the HPC software portfolio at HPE. She is fascinated by how innovative technologies evolve and synergize to advance companies, industries, and the world. Prior to joining HPE, Evelyn performed product, content, and digital marketing roles in the technology industry. She attended the University of Southern California and is based in San Jose, California.
Compute Experts
Hewlett Packard Enterprise
twitter.com/HPE_Cray
linkedin.com/showcase/hpe-servers-and-systems/
hpe.com/supercomputing
- Back to Blog
- Newer Article
- Older Article
- PerryS on: Explore key updates and enhancements for HPE OneVi...
- Dale Brown on: Going beyond large language models with smart appl...
- alimohammadi on: How to choose the right HPE ProLiant Gen11 AMD ser...
- ComputeExperts on: Did you know that liquid cooling is currently avai...
- Jams_C_Servers on: If youโre not using Compute Ops Management yet, yo...
- AmitSharmaAPJ on: HPE servers and AMD EPYCโข 9004X CPUs accelerate te...
- AmandaC1 on: HPE Superdome Flex family earns highest availabili...
- ComputeExperts on: New release: What you need to know about HPE OneVi...
- JimLoi on: 5 things to consider before moving mission-critica...
- Jim Loiacono on: Confused with RISE with SAP S/4HANA options? Let m...
-
COMPOSABLE
77 -
CORE AND EDGE COMPUTE
146 -
CORE COMPUTE
154 -
HPC & SUPERCOMPUTING
137 -
Mission Critical
87 -
SMB
169