Advanced Computing in the Age of AI | Thursday, March 28, 2024

Intel and Katana Graph Team on Large-scale Graph Analytics 

Oct. 19, 2020 -- Intel and Katana Graph today announced a collaboration to port and optimize the Katana Graph engine on Intel Xeon Scalable processors, Xeon-based clusters and the upcoming line of Intel’s discrete GPUs, including the GPU (code-named “Ponte Vecchio”). Together, Intel and Katana Graph will enable customers to exploit high-performance, scale-out parallel computing to solve large-scale problems with unstructured data with unmatched efficiency.

Credit: Katana Graph

Large, unstructured datasets are typical in social network analysis, security and authentication, electronic chip design tools, biomedical and pharma applications (gene network analysis and medical knowledge graph mining), and epidemiological studies for modeling the spread of infectious diseases. Intel’s broad ecosystem of technologies enables customers to accelerate analytics at every stage of the data pipeline. For example, Intel Xeon Scalable processors make it possible to analyze massive amounts of data at high speeds while Intel Optane persistent memory technology helps customers overcome bottlenecks in how data is moved and stored.

“For deep analytics on large, unstructured data to scale into mainstream usage, it will need to be deployable and performant on both volume CPUs and GPUs. Our collaboration with Katana Graph will accelerate the adoption of graph analytics on market-leading Intel Xeon Scalable processors as well as our upcoming GPUs, enabling more customers to take advantage of graph computing,” explains Wei Li, vice president, Intel Architecture, Graphics and Software, and general manager, Machine Learning and Performance.

The Katana Graph engine is the leader in scale-up and scale-out analytics that can run on large clusters of x86 CPUs, large memory systems with Intel Optane persistent memory, single or multi-node GPU platforms, or any combination of these technologies. Additionally, it can scale to hundreds of machines in production clusters.

According to Keshav Pingali, CEO and co-founder of Katana Graph, “Computing on large, unstructured datasets is the paradigm of the future. Unlike other companies in this space, Katana has a high-level programming model and a runtime system that are specialized for applications that deal with graphs and hypergraphs. This is why our analytics libraries are orders of magnitude faster than solutions from other vendors. We are excited to be working with Intel to bring high-performance, scalable graph computing to our mutual customers.”

Customers are already utilizing the Katana Graph engine:

  • A major defense contractor is using Katana Graph to solve security problems by implementing a system for real-time intrusion detection in computer networks. The system builds online interaction graphs representing how network users interact with each other and with network resources.
  • Electronic design automation companies are evaluating Katana Graph for implementing high-performance parallel modules to solve electronic circuit design problems, including logic synthesis, hypergraph partitioning, placement and global routing. Projects that model pollution and epidemiological studies on the spread of COVID-19 used the graph engine to construct unstructured representations.
  • Katana Graph’s enterprise system is supported on various infrastructure deployment models such as on-premises, hybrid and major cloud platforms, including AWS and Microsoft Azure. It provides a full-featured graph database with scalable parallel querying, transactional execution for long-running computations and extensive support for knowledge graphs.

 

For more information, visit katanagraph.com/news.


Source: Intel Corp.

About the author: Tiffany Trader

With over a decade’s experience covering the HPC space, Tiffany Trader is one of the preeminent voices reporting on advanced scale computing today.

EnterpriseAI