HPE Superdome Flex enables a massive leap in processing performance

Hewlett Packard Enterprise recently unveiled the world’s most scalable and modular in-memory computing platform, the HPE Superdome Flex.

It elevates high-performance data analytics for mission-critical workloads. The platform enables enterprises of any size to process and analyze massive amounts of data and turn it into real-time business insights.

Vikram K, Senior Director, Data Center and Hybrid Cloud, HPE India, tells us more. Excerpts:

BW CIO: What are the unique features of the HPE Superdome Flex?

Vikram K: HPE Superdome Flex combines the reliability of HPE Integrity Superdome X with the scalable technology for high-performance data analytics that HPE gained with its acquisition of SGI.

This latest mission-critical in-memory computing platform has been designed with memory-driven computing principles, thereby providing a shared pool of memory over an ultra-fast fabric that’s capable of scaling from 768GB to 48TB in a single system, which enables customers to turn data into actionable insights at unparalleled scale and in real-time.

Additionally, the platform has a unique modular design that scales from 4 to 32 sockets in 4-socket increments. This equips customer environments of all sizes with in-memory computing that can expand seamlessly and cost-efficiently as their business needs increase.

HPE Superdome Flex also offers proven reliability, availability and serviceability capabilities not present in other standard x86 platforms to provide 99.999 percent single-system availability.

BW CIO: How is the HPE Superdome Flex designed to harness the full value of in-memory computing, thus enabling businesses to achieve real-time insights?

Vikram K: Organizations today face a complex dilemma on how to harness all of their data to derive actionable insights in real time in order to make more impactful business decisions. One way businesses are tackling this challenge is by leveraging in-memory databases, such as SAP HANA, Oracle Database In-Memory and Microsoft SQL Server.

However, to harness the full value of in-memory computing, the underlying infrastructure must be capable of addressing large data sets and process analytics without slowing transactions to achieve real-time insights.

HPE Superdome Flex enables customers to capitalize on in-memory data analytics for their most critical workloads while its unique modular design scales seamlessly so enterprises can keep pace with evolving data demands.

BW CIO: Can you share details on HPE’s focus on Memory-Driven Computing?

Vikram K: The computers that we currently rely on, from smartphones to supercomputers, are hitting a wall, both in terms of physical size, efficiency and computing capacity. That’s because today’s computers are based on an architecture that’s more than 60 years old. These just can’t keep up with the exponential increase in data we are generating from solving complex data problems to advanced AI, autonomous cars to smart cities.

As the volume of data we create, grows, insufficient computational power will become the key limiting factor stunting innovation in technology. This has implications for fields as diverse as healthcare, transportation and research.

HPE believes that only by redesigning the computing architecture from the ground up will we be able to overcome the limitations of today’s technologies. HPE envisions a world where memory will replace the processor at the center of all technologies, which we call Memory-Driven Computing.

BW CIO: Elaborate upon Memory-Driven Computing architecture.

Vikram K: At the core of the Memory-Driven Computing architecture is a complete rethink of the relationship between processors and memory. Memory-Driven Computing creates a vast, shared pool of memory that can be accessed by multiple processors, a sharp departure from today’s systems, where relatively small amount of memory are tethered to each processor.

By eliminating the gap between memory and storage, HPE’s Memory-Driven Computing system is capable of shrinking the time needed to process complex problems from days to hours, hours to minutes, and minutes to seconds and deliver real-time intelligence.

This architecture will enable a massive and essential leap in processing performance and allow us to develop new ways to extract knowledge and insights from large, complex data sources. Every computing field, from analytics to artificial intelligence, to machine learning, stands to benefit from the evolution to Memory-Driven Computing.

In fact, HPE believes a memory-centric approach, rather than a processor-centric approach, is key to meet the challenge of ever increasing data rates and sizes, from the data center to the edge, from microsystems to the next supercomputers, to enable significant advances in the value technology can bring to business.