What is GPU Computing?
GPU computing is the use of a GPU (graphics processing unit) to do general purpose scientific and engineering
computing. The concept for GPU computing is to use a CPU and GPU together in a heterogeneous computing
model - the sequential part of the application runs on the CPU and the computationally - intensive part runs on
the GPU. From the user’s perspective, the application just runs faster because it is using the high performance of
the GPU to boost performance at 1/10th the cost and 1/20th the power consumption of the latest quad-core CPUs.

Advantages of Aberdeen GPU Servers
Aberdeen’s GPU server family provides many feature advantages of interest to the user community.

Highly Reliable Thermal Optimization
Aberdeen’s advanced thermal subsystem designs optimize the cooling elements of the server with the thermal characteristics of the GPU, CPU, motherboard, and other components. Each thermally controlled fan module is 1+1 paired in a counter rotating matched set, which maximizes the cooling effect. This design enhances system reliability and simplifies maintenance. In addition, by monitoring both CPU and GPU thermal readings though the I²C bus, Supermicro’s unique intelligent cooling control and auto fan-speed adjustment keeps the entire system in stable operation.

Direct GPU Connect Architecture
Utlizing the Supermicro design architecture provides direct Gen2 PCI-E x16 non-blocking connectivity to each GPU to take advantage of the full bandwidth of the GPU. No extra cabling is required, since the GPUs are connected directly to the server motherboard via riser cards, thus improving reliability, airflow, and maintenance, as well as reducing costs.

Industry-Leading Power Efficiency
Aberdeen’s GPU server platforms feature Gold Level (93% efficiency) power subsystems, along with high-efficiency motherboard and thermal designs to deliver breakthrough performance-per-watt and increased system reliability.

Advanced System Management
Aberdeen’s advanced IPMI capability allows the GPU system to be managed directly via the remote monitoring / controlling features. All the key elements of the server system- CPU, GPU and power supply- can be remotely monitored, along with standard onboard IPMI functionalities.

Applications and Industries
This new line of highly parallel, multi-core, multi-GPU systems is an excellent choice for an extensive range of graphics and computationally intensive applications in a wide variety of industries. In general, these systems are expected to make the fastest teraflop clusters much more affordable and accessible for users throughout the world.

Applications requiring high arithmetic intensity, such as dense linear algebra, partial differential equations, n-body problems, and finite difference formulas, can be easily accommodated using these Supermicro SuperServers. High bandwidth problems such as sequencing (virus scanning, genomics), sorting, and database problems are also potential applications. Finally, visual computing problems such as graphics, image processing, tomography, and machine vision, being original applications for GPUs, are especially accessible.

Fields where these types of problems are common and can benefit from Aberdeen's GPU servers include medical, energy, telecommunications, finance, science, and engineering in a wide array of application areas such as:

• Computational Chemistry
• Genomics
• Fluid Dynamics
• Medical Imaging
• Digital Content Creation
• Oil & Gas Exploration
• Electronic Device Automation
• Research & Scientific Computing
• Financial Markets Modeling
• Signal Processing
• Game Physics
• Weather Simulation