Two days of Presto, hands-on workshops, and Prestissimo…oh my!
Happy Halloween, Presto community!
Over the last few weeks, I’ve had people reach out to ask more about PrestoCon 2023, so I figured I’d write a blog to share my thoughts. First, a quick overview:
When: December 5-6th, 2023 at the Computer History Museum in Mountain View, CA
What: Hundreds of developers and software engineers will come together at PrestoCon 2023 to support and learn more about Presto, the open-source SQL query engine for data analytics and the Open Data Lakehouse
Why: We’re excited for the future of Presto! For the first time we’ll be highlighting Prestissimo, the C++ native worker for Presto built on Velox, in a dedicated track along with other key engineering work and advancements in OS Presto.
How much is it? $50 early bird passes ends TODAY, October 31st! Register to get your pass.
So really, why should you consider coming? If you’re involved in data analytics or data infrastructure, PrestoCon is a must-attend event, and here are 3 reasons why:
- Prestissimo. Did I mention we’ll have a full track on it? 😁
If you’re not familiar, Prestissimo is next-gen Presto, the native C++ worker for Presto. A lot of work has been going into Prestissimo over the last year and we’re really excited to show you the latest advancements. Prestissimo is built on the open-source Velox project, and leading contributors from Bytedance, IBM, and Meta will be sharing their work.
This is an opportunity to see first-hand some of the cutting-edge innovation that’s going on in Prestissimo as well as some initial benchmarking results that have not yet been publicly shared with the community! If you’re new Prestissimo, IBM will present an introduction to it. Key sessions include:
- Bytedance – A Journey of Evaluating Prestissimo against PrestoDB on TPC-DS
- Meta – Prestissimo: A Year In, the Path to Veloxification
- Bytedance – Batch-size in Velox aggregation
- Free Hands-on Presto workshops
You read that right – when you purchase a pass to PrestoCon, you’ll get the chance to register for our Presto workshops for free (while availability lasts!).
This year we’ll be hosting 3 workshops:
- Getting started with Presto: Get Presto running locally on your machine, connect data sources, run queries. This is a good workshop if you’re new to the Presto project.
- Building an Open Data Lakehouse with Presto and Apache Hudi: The data lakehouse brings the flexibility, scale, and cost management benefits of the data lake together with the data management capabilities of the data warehouse. Architect the building blocks of a data lakehouse with Presto, Apache Hudi, and AWS S3 in this workshop.
- Getting started with Prestissimo on Docker: This is an intermediate-level workshop for developers and engineers who want to get their hands on Prestissimo. It’s recommended for folks who are already familiar with Presto and know how to run distributed systems.
We intentionally keep these workshops small to ensure we can provide hands-on support, so I recommend you register soon if you’re interested in these.
- Be the first to hear about new innovation in Presto and the Presto ecosystem
Presto engineers from Meta, Uber, Intel, IBM, Bytedance, Alluxio and more will be presenting some really awesome sessions. A few highlights IMO:
- Presto express – leveraging historical data to predict upcoming query execution times and optimizing cluster routing (Uber)
- Statistics with sampling using Iceberg on Presto (IBM)
- Optimizing Presto at Meta scale (Meta)
- Learned query optimization in PrestoDB (Intel/UPenn/Technical University of Munich)
- …there’s so much more, check out the full agenda
To conclude, here’s a video we put together to get you excited 👇 BTW – we’re giving out free copies of our paperback O’Reilly Presto book to the first 100 people register!
Register now! I really hope to see you in December 🥳