Microway HPC Clusters and WhisperStations seamlessly integrate the AMD^® FireStream™ high performance compute processors. Solve your most important HPC challenges with a massively multi-threaded, parallel-computing architecture and the AMD Stream SDK.

AMD's next-generation stream processor, the AMD FireStream™ 9270 is specifically designed to accelerate critical algorithms in high performance computing (HPC), and enterprise applications.

The single PCI-E slot, one TeraFLOP, AMD FireStream 9270 includes 2GB GDDR5 memory enabling developers to handle large, complex problems; delivers performance of 1.2 TFLOPS single-precision and 240 GFLOPS double-precision performance.

The AMD FireStream 9270 stream processor includes a second-generation double-precision floating point hardware implementation, the industry's fastest GP-GPU with double-precision floating point support. The AMD FireStream 9270 may be configured as part of a Microway quiet WhisperStation, server or 1U compute node.

FireStream GPU computing solutions also fit seamlessly into your existing Microway workstations or clusters to enable you to solve problems orders-of-magnitude faster.

To speak with one of Microway's HPC Experts and learn more about taking advantage of the AMD FireStream GPUs, please call 508-746-7341.

An Open Systems Approach - AMD Stream SDK
AMD Stream SDK leverages open source technology and software technology partners to provide a robust, open, multi-layer development environment on 64-bit Linux and Windows.

Developers can begin with Brook+, an AMD-enhanced and supported implementation of Brook, the popular open-source C-level language and compiler. Math functions can be implemented using the AMD Core Math Library for the GPU (ACML-GPU). Tools like GPU Shader Analyzer and AMD Code Analyst help identify and correct performance issues.

AMD's Compute Abstraction Layer (CAL) provides low level access to the GPU for development and performance tuning. AMD's open systems approach allows developers access to all key APIs and specifications, enabling performance tuning at the lowest level and development of third party tools.

Massively Parallel Performance
AMD FireStream processors deliver all of the parallel processing power of the GPU to compute-intensive applications for computer scientists and engineers. Delivering 1 TFLOPS, developers can dramatically increase the performance of their data parallel task applications.

Compatible Solutions
As an industry-standard solution, FireStream easily fits into existing HPC environments. The FireStream GPUs are available for deskside workstations, computational servers and clusters. The low power consumption allows up to four GPUs to be installed in a single server.

Image Courtesy of LANL

Image Courtesy of ScienceGL