Open Source GPU-Accelerated Analytics

Platform for Lightning-Fast SQL, Visualization and Machine Learning

Join us on Thursday, October 5, 2017 6pm PDT at MapD HQ in San Francisco, CA for our MapD & H20.ai: GPU-powered Visualization and Machine Learning Meetup. RSVP HERE

MapD Customers
Supercharge your Analytics

Lightning-fast SQL

The open source MapD Core database leverages the parallelism of GPUs with a state-of-the-art query compilation engine to achieve orders-of-magnitude speedups for analytic SQL queries, powering exploration of big datasets with near zero-latency. In independent tests a single node of MapD has been shown to be 74X to 3500X faster than clustered CPU database solutions.

See Details
Hide Details
Data source: Summary of the 1.1 Billion Taxi Rides Benchmarks at http://tech.marksblogg.com/benchmarks.html
Query 1 SELECT cab_type, count() FROM trips GROUP BY cab_type;
Query 2 SELECT passenger_count, avg(total_amount) FROM trips GROUP BY passenger_count;
Query 3 SELECT passenger_count, extract(year from pickup_datetime) AS pickup_year, count() FROM trips GROUP BY passenger_count, pickup_year;
Query 4 SELECT passenger_count, extract(year from pickup_datetime) AS pickup_year, cast(trip_distance as int) AS distance, count(*) AS the_count FROM trips GROUP BY passenger_count, pickup_year, distance ORDER BY pickup_year, the_count desc;
System configurations
MapD: 1 machine (16 cores, 512 GB RAM, 2 x 1TB SSD, 8 Nvidia Pascal Titan X GPUs)
Redshift: 6 machines (36 cores, 244 GB RAM, 16TB HDD, AWS ds2.8xlarge)
Presto: 50 machines (4 cores, 15 GB RAM, 100GB SSD, GCP n1-standard-4)
Spark: 11 machines (4 cores, 15 GB RAM, 2 X 40GB storage, AWS m3.xlarge)

Interactive
Visualization at Scale

The MapD Immerse visual analytics client leverages both the speed of the MapD Core database and its unique ability to render granular visualizations on server-side GPUs to allow analysts and data scientists to explore large datasets in full detail without lag.

Data Engine for
Machine Learning

By using the GPU Data Frame (GDF), MapD allows query results to be seamlessly outputted to other processes on the GPU without the overhead of moving data to the CPU. Data scientists use MapD as an efficient pre-processing engine to feed data into their machine learning pipelines.

MapD… was the world’s first to create basically a database engine on top of GPUs… it's just completely amazing, to be able to access databases so large completely in-memory and be able to interact with it, create graphs out of it, query it with AI, visualize it, all in real time. Completely revolutionary stuff.
— Jensen Huang, CEO
MapD has taken commodity GPUs and turned them into a solution that can transform the analytics industry.
— Mark Smith
Information and analytics leaders struggling with situational awareness on large amounts of high velocity data should consider MapD. The company is experiencing early success in telecommunications, retail and social media use cases.
— 2016 Cool Vendors Report
I view MapD as a game changer in enabling businesses to derive insights from large amounts of data. The speed at which their GPU database queries billions of rows of data, paired with the killer app of their Immerse front end, enabled us at Jam City to take journeys through our data with quickness and ease that was not possible before. This led to a new kind of spontaneous insight generation and a true form of data democratization. It is akin to gaining an extra sense.
— Rami Safadi
See for Yourself
Play with and instantly visualize hundreds of millions of realtime tweets, from the global level all the way down to your neighborhood.
Follow ships through US coastal waters using a distributed cluster of the MapD Core database to visualize over 11 billion rows of geospatial data.
Explore every taxi ride in NYC over the last 7 years, constituting 1.2 billion records in total. We've also joined every NYC store within 30 meters of a pickup or dropoff, data courtesy of Factual.