Compute

Do you need a proven 5G far-edge compute platform that’s secure and reliable, while still offering versatility of workload?

The HPE Compute Edge Server e920t  is a multi-workload edge powerhouse designed to drive your business into the future with support for virtualized RAN (vRAN) for 5G, multi-access edge computing, and retail video analytics. Designed to exceed NEBS Level 3 and perform in size-, weight-, and power-constrained environments, the HPE Compute Edge Server e920t is the server you need when rugged, dense compute is required. A bladed design allows for easy slide-in, slide-out maintenance and upgrades.

With a wide range of I/O options, industry-leading manageability, and security with HPE iLO, the HPE Compute Edge Server e920t is the compute solution to meet your workload needs at the edge in telco, retail, and more.

Do you need a powerful, dense, and rugged server at the edge? The HPE Compute Edge Server e920i s a multi-workload powerhouse designed to deploy edge compute close to where the data is being generated, conserving uplink bandwidth and connectivity cost, lowering security and data risk, and greatly reducing time to actionable insight. Designed to perform in size-, weight-, and power-constrained environments, the HPE Compute Edge Server e920 is the server you need when rugged, dense compute is required. A bladed design allows for easy slide-in, slide-out maintenance and upgrades.

Are you looking to accelerate AI workloads with a purpose-built architecture?

The HPE Cray XD675 delivers breakthrough performance with modern AMD accelerators and processors.

Powered by eight AMD Instinct™ MI300X accelerators and AMD EPYC™ 9004 Series processors, the HPE Cray XD675 provides impressive performance for running AI models, fine-tuning, and inference.

This flexible and complete AI solution features 1.5 TB of GPU memory and 10.4PFLOPs of peak FP16 performance per server that can be adapted for HPC performance with 654 TFLOPs of peak FP64 performance per server. With link speeds up to 400GbE, the HPE Cray XD675 supports NVIDIA® InfiniBand NDR to offer incredible processing power for demanding workloads and exciting adaptability for constantly-evolving demands.

Does your HPC/AI cluster need better storage performance for converged workloads of mixed and random I/O requirements for ML/AI applications while preserving the cost-effectiveness and scalability of traditional parallel HPC storage?
The HPE Cray Storage Systems C500 utilizes an open-source, parallel file system architecture for impressive performance and is ideal for entry and mid-range HPC/AI clusters with limited storage budgets that want to improve the utilization of their CPU/GPU investments. This unique, hybrid architecture exploits the strengths of different storage media (NVMe, SSD/SAS, HDD) while avoiding their respective weaknesses, allowing superb performance speeds with fewer rack units.
Utilize the HPE Cray Storage Systems C500 to experience the same price/performance benefits for storage as the largest supercomputing leadership sites.

Do you need a high performance blade server that is designed for database, Java, and technical computing applications? The HPE Integrity BL890c i6 Server Blade is an eight-socket full-height blade featuring the latest Intel® Itanium® processor 9700 series supported by up to 1.5 TB memory (96 DIMM slots) and features sixteen HPE FlexFabric Converged Network Adapter (CNA) ports standard. The HPE Integrity BL890c i6 also features the unique HPE Blade Link technology which combines multiple blades to create 4- and 8-socket systems, providing greater scalability and flexibility. The HPE Integrity BL890c i6 Server Blade can coexist with HPE ProLiant Server blades within the same HPE BladeSystem c-Class Enclosure.

HPE Cray Supercomputing Storage Systems E2000are the even faster sibling of Cray ClusterStor E1000 Storage Systems that have seen unprecedented adoption in the supercomputing market with more than half of the aggregate compute power of the world’s Top 100 supercomputers relying on Cray ClusterStor E1000 Storage Systems.¹  
The E2000 systems preserve all the value propositions that have made Cray ClusterStor E1000 Storage System the de-facto standard in high-end supercomputing, but more than doubles the performance through the use of new storage controllers.
The E2000 systems are the perfect choice for supercomputers and large compute clusters running modeling and simulation, artificial intelligence and high performance data analytics applications in integrated workflows on one machine.

Do you need a density-optimized, scale-out compute system to meet the changing demands of your workloads in high performance computing (HPC) and enterprise data centers? The HPE Cray XD2000 System provides HPC at your scale in a shared infrastructure chassis with up to four HPE Cray XD220v Servers (Intel®), four HPE Cray XD225v Servers, or two HPE Cray XD295v Servers (AMD). A shared infrastructure increases uptime by allowing individual serviceability without impacting the operation of other servers in the chassis. HPE Cray XD2000 System offers a complete, scalable solution for HPC customers, with power and cooling options, including direct liquid cooling (DLC), giving greater performance while lowering TCO. Built with exascale era-ready networking, integrated storage, support for an extensive software portfolio, management tools, and proven expertise, HPE Cray XD2000 System enables you to supercharge innovation and prepare for tomorrow’s challenges.

What sets HPE Nonstop Compute solutions apart from the rest of the industry? The HPE Nonstop Compute NS9 X5 is designed from the ground up for mission-critical and business-critical environments that demand continuous application availability and 100% fault tolerance. The reliable HPE Nonstop software has been protecting customers' vital business applications for five decades. From banking to online shopping, driving your favorite car and daily train commute, many everyday digital consumer interactions rely on these powerful, seamless and trusted HPE Nonstop Compute solutions. Introducing an x86-based, high-end system called HPE Nonstop Compute NS9 X5 with a upgraded Intel® Xeon® processors, increased memory performance and capacity, higher system interconnect bandwidth and increased networking connectivity for modern data center integration. These systems provide massive scalability with extreme performance for high-volume transaction processing (OLTP) mission-critical applications.

Does your SMB system or development environment require continuous availability? 
The HPE Nonstop Compute NS5 X5 solution is designed from the ground up for mission-critical and business-critical environments that demand continuous application availability and 100% fault tolerance. The reliable HPE Nonstop software has been protecting customers' vital applications for five decades. From banking to online shopping, driving your favorite car and everyday train commute, many everyday digital consumer interactions rely on these powerful, seamless and trusted HPE Nonstop Compute solutions. Introducing an x86-based, entry-class solution for enterprise customers called HPE Nonstop Compute NS5 X5 with upgraded Intel® Xeon® processors and increased memory capacity. These systems provide extreme performance for high-volume transaction processing (OLTP) applications and are ideal for small-enterprises, distributed computing, and development environments.

HPE Machine Learning Development System is a set of comprehensive, validated and pre-configured solutions that reduces IT complexity & provides on-prem solutions with out-of-the-box performance, allowing you to focus time and resources on model training. Solution includes a platform for distributed ML/DL model training and is integrated with HPE hardware infrastructure for standardized and configurable AI clusters, creating a faster path to more accurate modes at scale.