HPE Launches New HPC Platform, Simplifies Deployment

 
 
By Chris Preimesberger  |  Posted 2016-06-21 Print this article Print
 
 
 
 
 
 
 

HPE underscores the simplification of the deployment and management of its solutions, which were often perceived to be overly complicated to deploy.

While a lot of IT companies are retooling their products and services to satisfy perceived upcoming demand for the fast-growing Internet of things and big data analytics markets, the high-performance computing market—always a substantial sector on its own—has been a bit out of the news lately.

On June 20, however, Hewlett Packard Enterprise introduced several new high-performance computing solutions that have an all-inclusive software-defined platform, improvements to its high-end Apollo servers, and new ANSYS computer-aided engineering software designed to help manufacturing organizations optimize their design simulation deployments.

Other newly released HPC components include:

--HPE Core HPC Software Stack with HPE Insight Cluster Management Utility v8.0: This is a highly flexible yet comprehensive software-defined platform for HPC that speeds up the configuration, deployment and management of server clusters.

--System architecture innovations: To accelerate the performance of customers' HPC workloads and reduce the complexity of their infrastructures, these new system improvements build upon the latest IP from the HPE Apollo technology partner ecosystem.

HPE Has Long Been an HPC Provider

HPE has been slow to take to the cloud and decided last year to abandon its public cloud plans and focus on its hybrid cloud strategy. Analysts generally are happy with the leaner HPE and its potential to dominate the hybrid cloud market.

In another major development, HPE last week announced that it will be partnering with Dropbox. Dropbox, which has more than 500,000 users, will be switching over from Amazon Web Services to the more affordable HPE Proliant and Cloudline servers. This is a big win for HPE's hybrid cloud, which provides a way for big companies to combine the best of the cloud with their own localized data centers.

HPE was never slow to move in the HPC market, however. The company continues to focus much of its research and development on companies and organizations in this sector, which has long been a fertile sales domain for HPE.

In fact, HPE is now providing HPC-based solutions for smaller enterprises. Once the exclusive domain of academics and research institutions, HPC is making its way into industries such as energy, life sciences, financial services and manufacturing, and HPE wants to be a key provider of choice.

While organizations in these industries recognize the technology's strategic importance, the perceived complexity and diversity of HPC environments may appear to outweigh the business benefits. The June 20 HPE announcement underscores the company's concern with simplification of the deployment and management of its systems.

CAE Package Designed for Large Data Sets

HPE's ANSYS solution for CAE is designed to handle large data sets and address the design prototyping needs of both large enterprises and midmarket customers. HPE, in pre-testing this on its Apollo 2000 servers, claims this package delivers improved application performance, faster resource provisioning and lower total cost of ownership. This includes completing CAE simulation in days compared to weeks. It recorded four times-higher resource utilization with HPC cluster compared to workstation-based solutions, HPE said.

HPE Core HPC Software Stack is designed to meet the needs of server cluster environments that may need to scale to thousands of compute nodes. This is a pre-integrated, pre-tested single software suite that combines open-source-based application development tools, libraries, and compilers with HPE cluster management capabilities, including HPE iLO and simple cluster setup tools.

This suite enables developers, IT administrators, engineers and researchers to quickly and easily develop, test, deploy and manage their HPC environments.

HPE has upgraded its software-defined Apollo HPC platform by introducing systems design improvements for the Apollo 6000 data center system (pictured) with new HPE ProLiant XL260a server trays based on the next generation of the Intel Xeon Phi processor family and the Intel Omni-Path Architecture (Intel OPA). These aim to reduce latency and increase bandwidth and performance.

Apollo, ProLiant Will Use Intel OPA Fabric

HPE also updated its Apollo 2000 system and ProLiant DL server platforms with Intel OPA (Omni-Path Architecture) fabric options. By combining these latest advancements in Intel Scalable System Framework with the better scalability and manageability of the HPE Apollo lineup, users can expect to gain new levels of performance, efficiency and reliability, the company said.

Additionally, users will be able to run HPC applications in a massively parallel manner with minimal code modification, the company said.

Pricing and Availability

The HPE Core HPC Software Stack with HPE Insight Cluster Management Utility V8.0 is now available for download. The ANSYS Solution for CAE is available now through HPE and worldwide channel partners. The CAE software is available through ANSYS.

HPE Apollo 6000 systems with new HPE ProLiant XL260a server trays will be available in September through HPE and worldwide channel partners. The Intel Omni-Path Architecture is now available for initial support on HPE Apollo 6000 and HPE Apollo 2000 systems.

Here is a short video overview of HPE's high-performance computing approach.

For more information, go here.

 

 
 
 
 
Chris Preimesberger

Chris Preimesberger is Editor of Features and Analysis at eWEEK. Twitter: @editingwhiz

 
 
 
 
 
 
 
 
 

Submit a Comment

Loading Comments...
 
Manage your Newsletters: Login   Register My Newsletters























 
 
 
 
 
 
 
 
 
 
 
Rocket Fuel