The goal of greater performance at lower costs has propelled clusters to the forefront of High-Performance Computing (HPC). Still, HPC users are demanding better reliability, availability, flexibility, compatibility and power efficiency. Responding to these demands, Appro has introduced Xtreme-X™ Supercomputer Series based on scalable cluster architecture. These clusters are grouped together to make a fully integrated Scalable Unit (SU) that can be provisioned and managed as a stand-alone supercomputer system to deliver sustained capacity computing performance.

Appro Xtreme-X2 System Highlights:
- Improved power and cooling efficiency
- Support for Quad-Core AMD Opteron processors
- Fully integrated, tested solution with a variety of system configurations
- 64 nodes/128 CPUs/512 cores
- Peak Performance/Rack: 4TF
- Memory Capacity/Rack: 4TB
- Scales up to 1000TF of computing power
- Balanced Architecture (CPU, Memory, Network)
- Scalability (SW & Network)
- Reliability (Real RAS: Network, Node, SW)
- Facilities (30% less space, 28% less power)
- Single or Dual Rail Management Network and IPC networks
- Single or dual rail QDR IB on board for best network performance
- Hot-swappable redundant components
- Redundant PSU 90% Efficiency, 5+1, PFC
- Appro’s Fault-tolerant System Architecture
- Appro Cluster Engine™ System Management Software
- Advanced Intel compilers and development tools included
- Appro Directed Airflow™ cooling architecture cabinet options
- Rear Door Heat Exchanger for standard cabinet options

Appro Reference Architecture Designs
Appro demonstrates performance and scalability using building block reference architecture designs based on customer requirements. The Appro Reference Architecture Designs are based on a 42U Standard Rack Cabinet.
It enables a supercomputing environment to be built with up to 1000TF.
It offers a complete stack of management software: network, servers, cluster and storage.

Scalable and Balanced Architecture
The usable performance of a large cluster depends on a balanced architecture and well designed support software. The memory and I/O system must support the performance of the processors or the entire machine will run no faster than the slowest components.

Directed Airflow™ Cabinet Cooling Options
The Appro Xtreme-X supercomputer offers a Directed Airflow™ cooling configuration designed to take cold air form the datacenter AC under floor directly to the equipment for optimum rack cooling efficiency. This cooling system features front access for maintenance, allowing racks to be mounted back-to-back to take advantage of the under-floor cooling available in most datacenters. Delivering the cold air directly to the equipment to be cooled eliminates the need for an aisle between the racks. This improves density and saves 30% on floor space.

Water Cooled Rear Cabinet Door Options
It provides up to 35kW of cooling using a passive design with no fans, moving parts or electrical connections. It is 100% sensible cooling with no condensation. It installs in minutes with no rearrangement of enclosures required while allowing 8x more compute power versus other type of solutions.

Appro Cluster Engine™ Management Software
Appro Cluster Engine™ (ACE) Management Software features a complete lights-out management solution that comes pre-installed with every system. This software suite offers a web-based management interface that is easy-to-use, making it possible to control the Xtreme-X1 from any location. The management modules include Network Management, Server Management, Cluster Management and Storage Management. In addition, ACE supports multiple networking topologies to achieve maximum reliability, performance and high availability. It supports root file systems offering instant provisioning for rapid, standard Linux installs on large diskless systems allowing them to boot 64 to 6,400 blades in about the same time. ACE offers a complete, reliable, highly available and serviceable architecture in a total software management package.

Ideal environment
For demanding applications that require higher reliability and better system management delivering a balanced highly-available supercomputer for a wide range of HPC applications such as Computational Fluid Dynamics, aerospace and automotive engineering simulations, petroleum exploration and production, scientific visualization for oil discovery and recovery, research in seismic, weather and environmental sciences, defense and classified research production.