Skip to main content

GPU database based on PostgreSQL

The world’s fastest and most advanced GPU accelerated database and visualisation workbench!

Brytlyt 3.0 is the fastest and most advanced GPU database in the world, up to 1,000 times faster than legacy systems.

A GPU database is a database that uses a GPU (graphical processing unit) to perform some database operations and because they are throughput orientated, they are typically very fast. GPU databases are flexible and can process many different types of data, or much larger amounts of data.

GPUs are highly parallel hardware accelerators originally designed to accelerate the creation of computer graphics. More recently, businesses have been looking at GPUs to accelerate other workloads like database analytics.

Brytlyt’s GPU-accelerated database technology is transforming the way businesses use data. With Brytlyt, companies can query multi-billion row datasets in milliseconds.

Easy integration with existing systems means there’s no need for businesses to give up their current investments in code and analytics. Instead, they can accelerate them with Brytlyt with little-to-no effort. Businesses can add and remove GPU resources at will, scaling their processing capability to suit their needs, ensuring they can massively reduce data processing costs.

Functionality-rich and easy to use: Brytlyt is built on PostgreSQL, and its deep functionality is complimented by outstanding ease of use.

Brytlyt connects PostgreSQL to GPU compute using an API

  • PostgreSQL

    Is a well-used and understood enterprise grade database that supports full ANSI. Investments in SQL code and Business Intelligence and analytic visualisations will work out the box.

    Data connectors mean legacy data from many disparate sources can be easily accessed from within the Brytlyt platform.

  • Brytlyt API

    Brytlyt uses a proprietary Application Programmable Interface to integrate the PostgreSQL database engine with the power of Graphics Processor Unit compute.

    The Brytlyt API supports SQL workloads and can also support Machine Learning and Deep Neural Network workloads where necessary.

  • GPU Cluster

    The Brytlyt API allows for large numbers of Graphics Processor Units to be federated together. The available memory and compute is equal to the total number of devices in the cluster.

    Additional GPU resources can be added to the cluster as required on the fly.

Brytlyt improves agility and reduces inertia

  • Simpler ETL

    Large parts of ETL processing are dedicated to improving performance through pre-aggregating and denormalising data. This introduces cost and inertia that is unnecessary when using Brytlyt.

  • Online

    By reducing the complexity in the ETL, direct data feeds are easier to integrate into queries and close to real time analytics becomes a reality.

  • Agile

    By reducing complexity and improving performance, changes in data and analytic requirements can be implemented quickly and easily. The business can be more agile while the level of technical input is reduced.