SCIENCE

AMAX will be demonstrating its GPGPU-based ServMax Series supercomputing server and personal supercomputer platforms at HPC Financial Markets 2010, booth #102. The event will take place on September 20th at The Roosevelt Hotel in New York, New York.

Until now, banks, investment firms and brokerage companies have had to live with the performance limitations of CPU-based systems. The ServMax Series, based on AMAX's 31 years of design expertise, was developed around NVIDIA's CUDA programming language and Tesla GPU (graphics processing unit) computing platform to directly address these performance shortcomings and enable financial services to gain quantum leaps in computational performance.

The high-performance GPGPU ServMax Series accelerates applications such as statistical analysis, financial simulations, trading solutions, and risk management. Financial services can now implement better forecasting, risk analysis and trading by processing much larger data sets at 8x the speed using the massive processing power of GPGPUs working in parallel to CPUs, giving firms the edge over systems utilizing CPUs only. Whereas a financial-services application might take days to complete large, complex problems using CPU computing, the GPGPU ServMax solutions allow these same processes to complete in only hours. In an industry where having an edge in speed and precision can mean the difference of millions of dollars, the GPGPU ServMax provides the necessary advantage that translates into profit.

"With the increasing volumes of data flowing through the financial markets and the pressure to execute trades first, AMAX's GPGPU-based ServMax platforms are leading the performance curve," said Jean Shih, president of AMAX. "Speed is king and from a technology standpoint, GPGPUs are going to change the way Wall Street works."

AMAX products featured at the show include:

• ServMax GPGPU Personal Supercomputer is powered by the massively parallel CUDA architecture and supports four NVIDIA Tesla 20-series GPU cards transforming a workstation into the equivalent of a small cluster at 5 percent the power consumption and 10 percent the cost. It delivers an astounding 4.12 teraflops of performance in a single chassis.
   
• ServMax GPGPU Supercomputing Server with 2.06 teraflops of computing horsepower is the fastest 1U server available. Powered by the massively parallel CUDA architecture and Tesla GPU computing processors, it can seamlessly fit into existing HPC environments and is ideal for financial services applications.

Every AMAX cluster is customizable and designed to suit your exact project requirements, from performance and budget, to delivering maximum ROI and minimum TCO. For more information on AMAX products, visit http://www.amax.com.