New Toolkit to Support NVIDIA GPUs Coming from Platform Computing

Today's high-performance computing solutions take advantage of the latest developments in the industry, providing the level required to run some of the most demanding applications on the market. Companies such as Platform Computing, specialized in cluster, grid and cloud computing software, are trying to provide its customers with support for the latest available technologies.

On that note, the aforementioned outfit has announced today that it is providing new GPU kits for its Platform Cluster Manager and Platform HPC workgroup products, to support NVIDIA's CUDA-enabled GPUs.

“Platform and NVIDIA have complementary offerings that enable partners like Cray to provide high performance computing clusters with the right tools to solve today's challenging problems,” said Tripp Purvis, Vice President, Business Development, Platform Computing. “The GPU kits for Platform Cluster Manager and Platform HPC Workgroup Manager are designed to make NVIDIA powered GPU clusters user friendly right out of the box, so administrators can rapidly provision, manage and schedule clusters to handle increasingly intensive applications faster, more efficiently and with fewer energy requirements.”

 

The new solution coming from Platform Computing will enable customers to take advantage of the performance capabilities of NVIDIA's Tesla GPUs. These graphics cards are designed with 240 cores, enabling 1 teraflop of performance per processing GPU. GPU-based clusters are becoming increasingly important in the space of HPC solutions, as they can deliver more processing power, when compared to older CPU-only based solutions.

 

“With the market need for GPU clusters rapidly increasing, working with an HPC leader like Platform is key as it creates an easy-to-use set of tools for building clusters with NVIDIA's Tesla solutions,” said Andy Keane, General Manager of the Tesla Business Unit, NVIDIA. “Together, these products will enable commercial, academic, and research institutions to easily deploy GPU clusters, leading to revolutionary cost and power savings.”