News & Events

HyperFlex 3.5 – Cisco Announce HyperFlex 3.5 at Cisco Live

  • 21 June, 2018

Article, Cisco, Networking, News

HyperFlex 3.5

Cisco Live 2018 finished recently and some big announcements were made. One announcement that has many people in the industry excited is HyperFlex version 3.5.

Cisco HyperFlex is a hyper-converged infrastructure platform. It combines Cisco Unified Computing System (UCS) with software-defined storage and data services software. Cisco UCS is a converged infrastructure platform which integrates networking, computing and storage resources to increase efficiency and enable centralised management.

Features of HyperFlex

Independent Scaling

Independent Scaling of compute and storage capacity allows correct resources to be added incrementally in the right ratios.

Dynamic data distribution

Dynamic data distribution provides high availability, superior performance and better efficiency.

Continuous data optimisation

Continuous data optimisation, delivered through always-on online deduplication and inline compression that is layered on a log-structured file system, minimises storage needs by up to 80% without compromising on performance.

Integrated Management and Data Services

Integrated Management and Data Services enable HyperFlex systems to deliver native data services, like granular Snapshots and Clones, and to be seamlessly added to the robust UCS management ecosystem to simplify management.

What's new in HyperFlex 3.5?

Cisco has said that the new version of HyperFlex will give customers a robust and well-rounded platform in order to power even more mission-critical applications. They’ve done this by increasing the number of clouds and by increasing performance.

The strategy they’ve used in order to rapidly extend their platform is to collaborate with other technology names such as Intel, Citrix, Nvidia and SAP. This co-innovation has transformed hyperconverged infrastructure into a complete platform for multicloud. The possibilities have increased drastically:

1. Modernise SAP Applications with HyperFlex and Container Platform

Cisco recently introduced the HyperFlex SAP modernisation platform. This gives their customers a flexible common infrastructure platform to power SAP ERP Apps, SAP HANA Databases, SAP Data Hub and eventually SAP Machine Learning. The platform can be flexibly configured with HyperFlex, UCS HANA Compute Nodes, the Cisco Container Platform, and NVIDIA V100 GPUs, optimising it for their customer’s SAP environments.

2. Less complexity in VDI Deployment and management on Hyperflex with Citrix Cloud Services

This is a benefit that came from the co-innovation with Citrix Cloud services. Customers now have the simplest, fastest and most secure way to install and scale virtualised applications and desktops.

3. Cisco Hyperflex All-NVMe with Intel Optane NVMe DC SSDs

With Hyperflex 3.5 comes one of the industry’s first All-NVMe hyperconverged appliances. The system uses the ultra-fast Intel Optane NVMe drives for caching and Intel 3D NAND NVMe drives for capacity storage. This system is beginning a completely new performance class for HCI to power more advanced analytics and latency sensitive mission-critical applications.

4. Power AI/ML Workloads on HyperFlex with NVIDIA V100 GPUs

Cisco is swiftly innovating to extend the support of more workloads onto HyperFlex. They say that the feedback they received on there recently introduced Kubernetes containers support in HyperFlex 3.0 has been fantastic and that customers also wanted support for more next-gen applications on HyperFlex. Cisco worked with NVIDIA, the industry leader, to introduce HyperFlex powered by the powerful Tesla V100 GPUs to create a flexible AI/ML platform for our customers.

If you would like to learn more about HyperFlex 3.5 and how it could work in your environment then please get in touch.

Visit us on social media:

Follow us on Twitter
Follow us on Facebook
Follow us on LinkedIn


Subscribe to Newsletter

Like this article?   Share it:

Share on Twitter
Share on Facebook
Share on LinkedIn