Compute

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.

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.

Do you need a powerful, dense, and rugged server at the edge? The HPE Compute Edge Server e920d is an I/O-enhanced 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 e920d is the server you need when rugged, dense compute is required with I/O capability. A bladed design allows for easy slide-in, slide-out maintenance and upgrades.

Does your SMB system or development environment require continuous availability?

The HPE NonStop NS4 X4 system is a modern, x86-based, entry-class NonStop system with a discreet CPU architecture, form-factor changes, and a system interconnect with higher raw bandwidth. It is designed from the ground up for mission-critical and business-critical environments that demand continuous application availability and 100% fault tolerance. With massively parallel processing architecture, the HPE NonStop NS4 X4 system reduces the risk of downtime, while meeting growing business needs, online transaction processing, and database requirements. While this system is well suited for smaller enterprises and emerging markets, it also fits well in distributed computing and test/development environments. It serves many everyday digital consumer interactions (from banking to online shopping to communications) which have relied on always-on, always adapting HPE NonStop solutions for decades.

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.

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 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.

Does your compute environment need continuous support for OLTP, HTAP, and critical applications with unparalleled fault tolerance and scalability?

The HPE NonStop NS8 X4 system is a modern, x86-based, high-end HPE NonStop system with a discreet CPU architecture and a system interconnect with higher raw bandwidth aimed at workloads that cannot afford downtime. These systems provide virtually unlimited scalability with extreme performance for high volume OLTP, OLAP, and mission/business critical applications. They are designed from the ground up for environments that demand continuous application availability and 100% fault tolerance. HPE NonStop reduces the risk of downtime while meeting dynamic business needs and database requirements. The HPE NonStop OS has been protecting customer workloads for over 40 years. From banking to cell phone communications, payment processing, and many everyday consumer digital interactions rely on always-on, always adapting HPE NonStop solutions.

Want to multiplex server blade data on a 10G data plane?

The HPE Edgeline EL8000 Converged Edge System supports a 10G SFP+ switch and 10GbE network mezzanine option to provide a high-speed interface for faster data transfers. In addition, the storage bay and connectivity for your specific infrastructure allow high-capacity data logging and analytics on that data.

Need a rugged, far-edge server designed for extreme conditions?

The HPE Edgeline EL8000t Converged Edge System is designed to deliver high performance, low latency data ingestion, and processing in the most hostile far-edge environments. Based on open standards, the HPE Edgeline EL8000t provides the flexibility to deploy common tools and architecture from edge to cloud, reducing deployment, operational, and training costs. This open standards architecture also allows customers to choose the hardware and software that best meets their workload requirements, avoiding vendor lock-in.
Purpose-built for telco environments, the HPE Edgeline EL8000t boasts an ultra-dense, short depth chassis with size, weight, and power specifications to support rack configuration flexibility in a small footprint. This enables communication service providers to process vast amounts of data in real time directly at the edge. Redundant cooling and power supply options provide system failure protection.