Extend system longevity with Xeon-based industrial engines

March 14, 2017 OpenSystems Media

Industrial designers have long been handicapped by the longevity challenge, struggling to pair server-class performance with extended-life systems. The design path has primarily included traditional server systems, which can be overkill due to costly and often unnecessary certifications; Xeon-based designs have been considered too costly in contrast to Core i7, based on additional complexity in development required to fully capitalize on dual-processor capabilities. It’s been the norm to sacrifice longevity, using commercially available workstation products to accommodate steadily-increasing performance and storage needs.

New server-class industrial engines are filling this void, illustrated by Corvalent’s CorServer platform. Rugged boards and chassis are packaged into a smart, configurable design, removing obstacles such as short production life, cost, and complexity. Server boards and chassis are optimized to work together, while the cabling layout enables airflow supported by low-noise internal fans. Notably for the industrial channel, applications such as Big Data analytics, cloud or data center computing, security and surveillance, and real-time medical imaging can be developed using cost-effective, long-term deployable solutions that were not previously available.

More reliable and functional than a commercial controller deployed at the source, Xeon’s dual-processor performance is optimized for IoT and industrial number crunching applications. These data-intensive and storage-heavy applications can benefit from a high-performance server-class system that eliminates bottlenecks and better enables real-time data processing. For example, more advanced data management close to the source can reduce latency and bandwidth challenges by transmitting processed, encrypted files rather than massive amounts of raw data.

With Xeon-based server-class systems, developers have access to a dual-processor platform with no unnecessary third-party hardware certifications. Costs are reduced, even while the end-use design capitalizes on industry operating systems and advancements such as error-correcting code (ECC), optimized thermal dissipation, and robust remote access management. Xeon technology also brings new opportunity to developers working with Core i7-based systems. Applications that already take full advantage of Core i7 performance are limited to one multicore processor; Xeon lets developers optimize processing speed and compute functions, sharing resources for significantly improved overall performance, even on single-node applications.

This could become a critical advantage for certain applications currently using a dual server and potentially pushing performance boundaries—for example a medical imaging system that requires massive compute power to quickly render high-resolution images. In contrast, a Xeon-based server-class platform may divide the computing task in two, minimizing pressure on any single processor, depending on the operating system and primarily the application itself. While some developers may opt for application re-design to gain leading edge performance specifically intended for dual processors, others will find compelling performance advantages simply by using the dual-processor platform to scale up performance for single-node applications.

Xeon processors also integrate Intel Hyper-Threading Technology, enabling multiple threads to run on each core. Coupled with Intel Turbo Boost, processing dynamically adapts to the workload at hand and processes multiple threads simultaneously. Inactive cores are automatically disabled and throughput is increased on busy cores, improving overall performance for threaded applications. Because compute tasks are more efficient, systems can run the most demanding applications while remaining highly responsive. This maintains headroom for growth and new capabilities that may be required in longer deployments, essentially keeping performance longevity at the forefront of the design.

Equally as important is the longevity and availability of the system itself. Where workstation products might have even been out of production by the time an application was fully developed, platforms such as CorServer are backed by a five- to seven-year consistent supply guarantee, made possible through a combination of partnerships and design commitments. Developers and OEMs have more time to develop software applications and also benefit from ongoing cost reductions fueled by consistency.

Martin Rudloff is the Chief Technology Officer of Corvalent, where he manages all aspects of the company’s product technology, from concept to development to production, validation, and product support. Martin graduated with a BS in Electrical Engineering from Escola Politecnica in São Paulo, Brazil.

Martin Rudloff, CTO, Corvalent
Previous Article
Analytics "at" the edge, on the device, in real time
Analytics "at" the edge, on the device, in real time

It takes time for information to travel from the edge of the Internet of Things (IoT) to the cloud and back...

Next Article
Access any IoT "thing" anywhere with MQTT
Access any IoT "thing" anywhere with MQTT

Analysts forecast that up to 50 billion devices could be part of the Internet of Things (IoT) by 2020. This...

How to Develop Cross-Industry IoT Interoperability

Multi-Part Series