GPU-accelerated Analytics for Big Data

The OmniSci platform is designed to overcome the scalability and performance limitations of legacy analytics tools faced with the scale, velocity and location attributes of today’s big datasets. Those tools are collapsing, becoming too slow and too hardware-intensive to be effective in big data analytics. OmniSci is a breakthrough technology, originating from MIT, designed to leverage the massively parallel processing of GPUs alongside traditional CPU compute, for extraordinary performance at scale.


OmniSci GPU-accelerated Analytics Platform

OmniSci Core

Open source SQL engine

The foundation of the platform is OmniSci Core, the world’s fastest open-source, GPU-accelerated analytics database. OmniSci Core harnesses the GPU’s parallel processing power and returns SQL query results in milliseconds, even on tables with many billions of rows. OmniSci Core delivers that extreme big data analytics performance with a combination of support for native SQL, rapid query compilation, query vectorization and advanced three-tier memory management.

Learn More About OmniSci Core

OmniSci Render

Server-side visual rendering

OmniSci Render is a server-side engine designed for rendering pointmap, scatterplot and polygon visualizations of massive datasets. This gives users zero-latency, exploratory interaction with complex visualizations, something never before possible. For geospatial visualization, the Vega rendering engine API allows users to visualize up to billions of points, lines, or polygons.

Learn More About OmniSci Render

OmniSci Immerse

Interactive visual analytics

OmniSci Immerse is a web-based data visualization interface, leveraging the GPU-accelerated speed and rendering capabilities of OmniSci Core and OmniSci Render for unparalleled visual interaction. OmniSci Immerse is incredibly intuitive and easy to use, providing standard visualizations, such as line, bar, and pie charts, as well as complex data visualizations, such as geo-point maps, geo heat maps, choropleths, and scatter plots. Dashboards automatically cross-filter when interacting with data, and refresh with zero latency.

Learn More About OmniSci Immerse

Data Integration

Connecting data sources to OmniSci

OmniSci Core stores very large structured datasets, and it does not require data pre-aggregation or indexing. This means data can ingest dramatically faster than with other systems - ideal for streaming data or large, frequently changing datasets. OmniSci supports standard data ingest connectors like Apache Kafka, Apache Sqoop and JDBC, and can ingest data at rates as fast as millions of records per second.

Learn More About Data Integration With OmniSci

Develop with OmniSci

Build and connect applications to OmniSci

Because OmniSci Core is open-source, many individual developers and technology vendors are choosing to connect to OmniSci Core or OmniSci Render for SQL acceleration and visual rendering. OmniSci is also a founder of the GPU Open Analytics Initiative (GOAI), whose mission is to enable data scientists to rapidly and efficiently pass data between analytics processes and machine learning model training processes, without the data leaving GPUs.

Learn More About Developing With OmniSci

Get the OmniSci Whitepaper

Learn more about the platform that delivers zero-latency querying and visual exploration of big data.