High Performance Computing

High Performance Computing (HPC)

For high-performance computing (HPC), iXsystems can help you build an energy efficient infrastructure with pre-tested, easy-to-deploy, easy-to-manage cluster solutions. Whether your workloads require large commodity clusters or a capability cluster in your office, iXsystems cluster solutions leverage state-of-the-art technology servers for affordable power and control. Through High-performance computing solutions, our goal is to help you maximize your resources.

Performance driven: With the needs and requirements of our customers in mind, each cluster is customized through a network topology of interconnects to gain a competitive advantage in a fully integrated cluster solution.

Energy efficient: Whether a small stand-alone system or a complex of many racks, our goal is to provide energy efficiency using the latest in energy saving technology, reducing the Total Cost of Ownership.

Space efficient: Our Twin-blade solution reduces power and cooling costs while maximizing performance density-paramount for HPC workloads.

Automated management: Our turnkey solutions come pre-configured and tested with cluster management software that is specific to the needs and requirements of each customer.

Easy to deploy: Each cluster is tested and fully integrated at our facilities, after deployment the cluster is ready to seamlessly plug into and be brought up at the customer's data center.

Scalable: Solutions can range from single rack size clusters or up to multi-rack supercomputing clusters with an open architecture that can scale out to larger units.

Rackmount Modular Servers

iXsystems' comprehensive selection of Intel and AMD-based systems can be integrated into many different configurations and switch fabrics. These servers can be deployed with Compute Cluster software in a cluster with a single head node and multiple compute nodes. The head node provides management, deployment, and job scheduling for the compute cluster.

Blade Servers

iXsystems' Triton Blade Servers offer many unique advantages that differentiate them from competitors' blade products and traditional rack-mount solutions. Customer benefits include maximum affordability, reduced management costs, lower power consumption, optimal ROI, and high scalability - and in most applications, blade servers even reduce acquisition costs.

nVidia Tesla High Performance Computing

The NVIDIA® Tesla™ 20-series (M2050/M2070/M2090) family of GPUs, the fastest parallel processors for HPC. Based on the "Fermi" GPU computing architecture, Tesla GPUs are designed from the ground up for high performance computing (HPC) to deliver up to 10X higher application performance and are ideal for seismic processing, biochemistry simulations, weather and climate modeling, signal processing, computational finance, CAE, CFD, and data analysis. iXsystems can integrate nVidia GPUs into a HPC personal supercomputing tower, or a rackmount, multi-node building block solution. Consult your Account manager today.

Infiniband Technology

InfiniBand (IB) is the industry-standard, channel-based architecture that features high-speed, low-latency interconnects for cluster computing infrastructures. InfiniBand uses a multiple-layer architecture to transfer data from one node to another. iXsystems works with leading Infiniband technology developers, such as Qlogic and Mellanox, to bring our customers the latest Infiniband technologies.