Blazing Fast SQL on RAPIDS



Blazing fast SQL on Rapids

BlazingSQL is an incredibly fast distributed SQL engine on GPUs. BlazingSQL enables data scientists to easily connect large-scale data lakes to GPU-accelerated analytics. With a few lines of code, you can directly query raw file formats such as CSV and Apache Parquet inside Data Lakes like HDSF and AWS S3, and directly pipe the results into GPU memory.

ETL at Scale

Distributed architecture scales to thousands of GPUs. Relative performance improvements of engine continue to increase with scale of cluster.

BLazing Fast ETL

BlazingSQL currently runs ETL 20x faster than an Apache Spark cluster at price parity on a single node. With BlazingSQL, enterprise scale workloads run in seconds rather than hours. Read more on our blog

Built on RAPIDS

BlazingSQL is built on the GPU DataFrame, a shared memory model that enables libraries in the RAPIDS AI ecosystem to seamlessly interoperate with each other. Read more on our blog


It’s easy to get started with BlazingSQL + RAPIDS

Try Now In Colab

The fastest way to get up and running is with Google Colab, a free web-based interface similar to a Jupyter Notebook that lets you quickly run BlazingSQL + RAPIDS on T4 GPUs. Try now in Colabratory

Learn More

Learn more about Colab, our Docker Container, and getting started. More on BlazingSQL

Access BlazingSQL Docs

See the latest documentation from BlazingSQL

BlazingSQL Demos

Get started with BlazingSQL + RAPIDS and try all the demos free on Google CoLab.

Getting Started Demo

Walk through the process for getting BlazingSQL and cuDF running. Then go through a basic ETL process and query.


Federated Query Demo

In a single query, join an Apache Parquet Gilem a CSV, and a GPU DataFrame (GDF) in GPU memory. Try now in Colabratory

Netflow Demo

Query 65M rows of network security data (netflow) with BlazingSQL. Try now in Colabratory

Taxi Demo

Train a linear regression model with cuML on 55 million rows of public NYC Taxi Data loaded with BlazingSQL. Try now in Colabratory

BlazingSQL vs Apache Spark Demo

Analyze 20 million rows of net flow data. Compare BlazingSQL and Apache Spark timings for the same workload. Try now in Colabratory

Get Started With BlazingSQL