Platform Computing Launches Platform HPC; Extends GPU Support

By DE Editors

Platform Computing has released the latest version of Platform HPC, a high-performance computing (HPC) management product. Platform HPC is designed to make it easy for technical application users to harness the power and scalability of HPC clusters. Based on Platform LSF, it features cluster provisioning, workload management, reporting and monitoring, MPI libraries and more, all of which are accessible via a web user interface. The web user interface also simplifies the application integration process so that customers can focus on their work, instead of managing their cluster.
According to the company, Platform HPC is a fully integrated, certified and supported product designed to ensure ease of use and simplified management.

Organizations across a range of industries are investing more heavily in HPC resources and application development to improve business productivity, speed up research projects and reduce infrastructure costs.

“The market for HPC application software and middleware exceeded $2.3 billion in 2009, and we expect it to approach $3 billion in 2013, says Earl Joseph, IDC program vice president for HPC. “HPC management software will become even more crucial for efficiently exploiting increasingly large, heterogeneous systems and newer environments such as grid and cloud computing. Platform Computing is well positioned to benefit from this trend.

With Platform HPC, both experienced and novice HPC users are able to deploy, run and manage their HPC clusters. They benefit from a set of cluster management capabilities that are accessible through a unified portal interface and include a simplified application integration process. New enhancements to Platform HPC include:

• Application support, including job submission templates for commonly used commercial applications and scripting guidelines for simplified job submission.
  
• GPU job scheduling and expanded GPU monitoring capabilities including ECC error detection.
  
• An enhanced design of the web-based user interface.
  
• Expanded operating system support.
 

Platform HPC has a single installer. It is pre-certified by many hardware and software vendors.

“Platform HPC removes the complexity and cost of implementing HPC clusters, which enables our customers to leverage the sophisticated simulation data and process management capabilities of SimManager to perform larger and more complex simulations and bring products to market faster, says John Janevic, vice president of Strategic Operations, MSC Software.

Expanded GPU Cluster Management
In related news, Platform Computing is extending its products to provide management of GPU clusters and GPU-aware applications. Platform’s workload scheduler products, Platform HPC, Platform LSF and Platform Symphony, now incorporate GPU-aware scheduling features for more efficient workload management. In addition, Platform is helping administrators better manage and plan GPU cluster capacity by providing access to monitoring, reporting and analysis tools. This includes new monitoring functions within the Platform HPC and Platform Symphony web-based interfaces, as well as in Platform RTM for large Platform LSF datacenters.

“Platform has a long history of supporting special purpose HPC architectures, says Ken Hertzler, vice president, Product Management, Platform Computing. “By providing enhanced support for the latest generation of Tesla GPUs, Platform is firmly establishing itself as providing premier management products for HPC data centers, offering the most complete solutions for managing GPU-based application services. By enhancing Platform HPC, Platform LSF and Platform Symphony to support GPU clusters out-of-the-box, we’re making cluster management and monitoring more simple, easy-to-use and more efficient.

Platform’s users can utilize Platform HPC management software to deploy CUDA software to compute nodes as well as allocate jobs only to resources that have GPUs. Platform products currently support NVIDIA Tesla GPUs, with plans to support future GPU accelerators when they become available.

For more information, visit Platform Computing.