Data analytics acceleration startup NeuroBlade Ltd. today announced that it has teamed up with Meta Platforms Inc.’s Velox community to open source hardware acceleration to the Velox execution engine by integrating NeuroBlade’s SQL Processing Unit.

The open-source hardware integration to the Velox execution engine delivers seamless integration of NeuroBlade’s SPU technology to yield acceleration of more than 10 times, on top of the threefold performance improvement already achieved by Velox using software optimizations. The joint effort aims to empower organizations to process massive datasets efficiently, setting new benchmarks in performance and efficiency.

Velox is an open-source unified execution engine that consolidates various software-based optimizations from the query engine ecosystem into a singular high-performance library. Designed for seamless integration with various query engines, such as Presto and Apache Spark, Velox provides a robust foundation. But there are issues, since conventional central processing units can struggle to manage analytical queries surpassing 2 gigabits to 3 gigabits per second efficiently because of limitations in data retrieval and query complexity.

NeuroBlade’s SPU technology overcomes the challenges with Velox by creating a dedicated analytics processor that achieves an optimal storage-to-compute balance. NeuroBlade’s SPU architecture offloads the CPU by efficiently executing sub-query operations and delivering data reduction close to storage. The SPU is also designed to execute queries at a constant throughput, eliminating query complexity as a source of variable latency.

The work with Velox includes the seamless integration of NeuroBlade’s SPU hardware acceleration into Velox. The integration is achieved through novel Velox application programming interfaces that allow arbitrary parts of query execution to be offloaded to an accelerator.

The shared effort of NeuroBlade and Velox is claimed to introduce new prospects in data analytics acceleration solutions. By meshing NeuroBlade’s hardware acceleration capabilities with Velox’s dedication to open source, the effort caters to the escalating need for performant and efficient data analytics solutions.

“Collaborating with the Velox community to open source hardware acceleration for Velox highlights our dedication to innovation in providing high-performance and efficient solutions,” Elad Sity, co-founder and chief executive of NeuroBlade, said ahead of the announcement.

The joint implementation is anticipated to be released later this year and will include a detailed white paper describing the methodology, benchmark techniques and outcomes achieved through this integrated approach.

Image: NeuroBlade