The Penrose Triangle

By Gurpreet Singh, CEO, Pavilion Data


We live in a connected world. Millions of apps, billions of users and trillions of things. Consequently, the amount of data that is generated is exploding. Yet at the same time, we are seeing massive fragmentation of where it originates from, its key structure, where it resides, how it gets accessed and processed and how it is ultimately consumed. New-fangled clustered databases, in-memory caches, exotic massively parallel filesystems, structured to semi-structured to unstructured, modern and disparate query languages, are just a few of the technologies that are causing this significant fragmentation.

At the same time, new application architectures are evolving from monolithic three-tiered to more modern micro-services based, clustered and cloud-native.

In fact, applications themselves are becoming more data-driven by the day, and to serve modern business needs, they must process higher volumes of data in real-time to make effective decisions. Because of the nature of the internet, most modern web (transactional) and Machine Learning/AI (real-time analytics) are also built upon these massively parallel and clustered databases and filesystems because of the performance requirements of these applications.

Parallelization is everywhere.

In fact, parallelization is the very name of the game.

NVMe is a new storage technology and it inherently parallel. In fact, it is 250 times more parallel than SAS and 2000 times more parallel than SATA.

The smart minds at Pavilion have been hard at work for the past 3 years. The result is supremely differentiated technology and a system that is protected by solid intellectual property (16 Patents), one that provides massive storage bandwidth and capacity, at ultra-low latency all the way from application to the media by unshackling the benefits of NVMe technology and delivering it over Ethernet.

LIKE THE PENROSE TRIANGLE, the engineering team at Pavilion has achieved a near-impossible feat of drawing upon best practices from three DISPARATE ENGINEERING DISCIPLINES – NETWORK, STORAGE AND COMPUTE and delivered as a purpose-built system that is just right for the modern data-driven applications and rack-scale IT architecture.

This data platform is designed for processing an order of magnitude larger data sets in REAL-TIME for ANALYTICS, MACHINE LEARNING, and AI ENGINESenabling COGNITIVE LEARNING for AUTONOMOUS SYSTEMS and BETTER, FASTER DECISION MAKING for DATA SCIENTISTS. At the same time, it offers the manageability, serviceability and simplicity benefits of shared accelerated storage in rack-scale, massively parallel and clustered application environments, without compromising performance or operational agility.

Today, I am proud to be joining this esteemed technology team.

To our customers, I am sincerely grateful for the trust you have placed in us and I look forward to working with all of you in helping solve your real business and technology challenges of today and tomorrow.

To our partners, it is clear that Pavilion is the clear technology leader with the first and only true NVMe over Fabrics Storage Array. My goal is to help you serve your customers well, by extending the technology leadership position you have created over the years, and together with your help establish Pavilion as the undisputed leader as FAST DATA PLATFORM for MODERN CLOUD APPLICATIONS.