High Performance Computing Solutions with Great Return of Investment (ROI)
Here at CAD2 our vast range of high performance computing clusters can help solve some of the most challenging computational intensive tasks available. By integrating the very latest advances in industry standard multi-core processor technology, ultra high performance error correction memory (ECC). high speed interconnects and leading open source/commercial software, our unique HPC clusters can deliver the performance and stability required by today's leading design, engineering and scientific professionals.

CAD2's High Performance Computing (HPC) Solutions with Streamlined Deployment and Management
Our vast range of High Performance Computing (HPC) systems are designed to simplify the overall HPC deploy/management process. A standard infrastructure stack from CAD2 is designed using individually custom built 1U ultra high performance cluster nodes (these are available in a variety of specifications and feature 1, 2, 4, 8 or 16x cpu ores) that feature only the very latest multi-core microprocessor technologies. The result is a highly scalable HPC solution that can deliver exceptional performance and manageability, whilst still providing a great return of investment (ROI).

We then streamline the implementation process by validating and pre-configuring each cluster node to meet a wide variety of application needs (CAD/CAM/CAE Analysis, 3D Image REndering, Oil/Gas, Scientific Calculations etc). Our unique HPC solutions deliver supercomputing performance to business's of any size, while driving down cost and complexity of ownership.

CAD2 High Performance Computing (HPC): How it Works...
Our High Performance Computing Clusters (or HPCC for short) are designed to enable high performance parallel computing and consist of one or more master nodes (the Master) and one or more compute nodes (the Slaves) interconnected by a private ultra high performance infiniband network infrastructure. Each HPCC (or stacks as they are more commonly known) are built using standard 1U sized server clusters. This includes all hardware, interconnects (networking) and software.

The 'master' node is designed to provide the stack with its main gateway to external resources and supports the Network File System (NFS). The compute 'slave' nodes are the cluster workhorses and are designed to perform parallel computing tasks (deployed by the parallel software applications). Typically, access and management of slave nodes are provided via remote interfaces, such as Microsoft Windows Remote Desktop (RDP) or serial port connections through the 'master' node.

We offer FOUR main HPC Cluster Nodes, each housed in a standard 19" 1U rack mountable chassis (excluding SuperBlade). Brief technical specifications can be found below. For further information please speak with one of our HPC product specialists on +44 (0) 800 180 4801 or e-mail sales@cad2.com

CAD2 Blade HPC-4
Our Blade HPC-4 is a fully featured 1U rack mountable SINGLE CPU cluster server. Brimming with cutting edge computer and micro processing technology (Single CPU support only); designed to provide great computing performance with an entry level price point. Specification is as follows: -

• 64Bit Quad Core Microprocessor (AMD™ Opteron™ or Intel® Xeon®)
• Up to 12GB of ECC Registered DDR2 667MHz Memory
• Dual Gigabit Network Interface Cards (10/100/1000 NIC)
• Up to 4TB of Hard Disk Drive Storage (Available via 1 > 4 SATA Hard Disk Drives)
• Optional Remote Management
• Optional High Speed Infiniband Interconnect

CAD2 Blade HPC-8 (and HPC-8x2)
Our Blade HPC-8 is a fully featured 1U rack mountable, DUAL CPU cluster server. Brimming with cutting edge computer and micro processing technology; designed to provide ultimate computing performance with a mid to high end price point. Specification is as follows: -

• Dual 64Bit Quad Core Microprocessors (AMD™ Opteron™ or Intel® Xeon®)
• Up to 32GB of ECC Registered DDR2 667MHz Memory
• Dual Gigabit Network Interface Cards (10/100/1000 NIC)
• Up to 4TB of Hard Disk Drive Storage (Available via 1 > 4 SATA Hard Disk Drives)
• Optional Remote Management
• Optional High Speed Infiniband Interconnect
• Optional Blade HPC-8x2 (Dual HPC-8 Cluster Nodes in ONE) - Call for full details

CAD2 Blade HPC-16
Our Blade HPC-16 is a fully featured 1U rack mountable, QUAD CPU cluster server. Brimming with cutting edge computer and micro processing technology; designed to provide the world's fastest, most powerful computer clustering solution, designed for the ultra high end scientific analysis and 3D image rendering applications. Specification is as follows: -

• Quad 64Bit Quad Core Microprocessors (AMD™ Opteron™ 64 )
• Up to 64GB of ECC Registered DDR2 667MHz Memory
• Dual Gigabit Network Interface Cards (10/100/1000 NIC)
• Up to 4TB of Hard Disk Drive Storage (Available via 1 > 4 SATA Hard Disk Drives)
• Optional Remote Management
• Optional High Speed Infiniband Interconnect

CAD2 SuperBlade HPC-80/160
Our Superblade Blade HPC-80/160 is an all-in-one HPC cluster server centre designed to further simplify the implementation of high performance computer clusters. A complete 7U blade centre fully equipped with either 80 or 160 CPU core, full remote management, ultra high speed infiniband network connection, combined KVM, cables, power supplies and enclosure. The definitive blade solution. Specification is as follows: -

• Up to 160x Quad 64Bit Quad Core Microprocessors (AMD™ Opteron™ 64 ) or
• Up to 80x Dual 64Bit Quad Core Microprocessors (Intel® Xeon®)
• Up to 640GB of ECC Registered DDR2 667MHz Memory (320GB on Intel® Xeon® System)
• 20x Gigabit Network Interface Cards (10x Dual 10/100/1000 NIC)
• Up to 20TB of Hard Disk Drive Storage
• Full IPMI Remote Management
• Full High Speed Infiniband Interconnect

For further information on any of our high performance computing (HPC) solutions speak with one of our product specialists on +44 (0) 800 180 4801. Alternatively you can e-mail sales@cad2.com or click below.