Hazelcast announced Tuesday a co-engineering and co-innovation collaboration with Intel to accelerate the performance of real-time applications, artificial intelligence (AI) and internet of things (IoT) solutions for enterprises.
At the center of this initiative is Project Veyron, which is focused on accelerating Hazelcast technologies on Intel platforms, including the second gen Intel Xeon Scalable processor and Intel Optane DC Persistent Memory.
Real-time machine learning (ML) applications require instant access to an immense flow of data from many sources. This data must be continuously compiled, processed and served to algorithms that power AI. Ultra-fast processing is critical for mobile, cloud, IoT and AI/ML-based applications that leverage both streaming data and existing data stores.
The objective of Project Veyron is to focus on optimizing the performance of the Hazelcast in-memory computing platform for the second-generation Intel Xeon scalable processor and Intel Optane DC Persistent Memory.
Project Veyron centers on cooperative engineering work to enhance the compatibility of Hazelcast and Intel offerings. The joint work will enable Hazelcast to take advantage of the high parallelism in the Intel architecture and address the higher data density and persistence needs of edge, cloud and IoT.
From this collaboration with Intel, Hazelcast intends to provide an integrated edge-to-cloud IoT processing solution. The goal is to provide enterprises with high-speed in-memory capabilities and end-to-end security. The result is a full-fledged IoT solution that achieves maximum impact for a variety of industries, including financial services, telecommunications, energy, manufacturing and entertainment.
Modern applications must process more data at a greater scale while delivering a real-time experience across online, mobile, IoT and brick-and-mortar interactions. Simultaneously, applications are expected to seamlessly incorporate advanced analytics, AI and machine learning. This challenge demands in-memory-optimized solutions that can store and process data at low-latency, as well as zero downtime reliability. This partnership will establish improved levels of performance, while increasing data density and lowering total cost of ownership (TCO).
Companies have been leveraging the Hazelcast System of Now as a low-latency data processing complement to their systems of record, such as databases. Founded in 2012, Hazelcast has continually produced the scalable in-memory data grid (IMDG) software to support applications where microseconds matter. More recently, it introduced fast event stream processing engine, Hazelcast Jet, which can run anywhere thanks to its lightweight footprint.
“Digitization is producing enormous amounts of new data every second and extracting value from it requires intelligent processing at microsecond speeds,” said Kelly Herrell, CEO of Hazelcast. “We’re honored to collaborate with Intel to drive even more powerful capability leveraging new in-memory technologies and next-generation chipsets.”
The real-time and large data set demands of AI applications require new performance advancements across all components of the data processing architecture. Intel Optane DC Persistent Memory redefines traditional architectures, offering a large and persistent memory tier at an affordable cost.
Since it has characteristics of memory and storage products, Intel Optane DC Persistent Memory enables more data to be closer to the CPU, resulting in fewer I/O trips and lower latency for accelerated performance to extract more value from larger data sets than previously possible. Project Veyron will accelerate the completion of parallel in-memory tasks, complex analyses for more sophisticated models and the use of structured and unstructured data sets.
“Intel is laser-focused on revolutionizing how organizations, regardless of size, maximize the impact of data,” said Lisa Davis, vice president and general manager of Digital Transformation & Scale Solutions at Intel. “The Hazelcast platform enables high-performance applications at extreme scale running best on Intel products. The Intel and Hazelcast collaboration will deliver platform innovations so that customers of Intel and Hazelcast will be positioned for greater success in the data-centric era.”