[Andy at Sea] Lakebases, Lakehouses, and LTAP: Unifying Transactions and Analytics on Open Storage

Speaker:

Ippokratis Pandis

System:

Databricks

Video:

YouTube

Traditionally, data architectures maintain a strict division between high-throughput operational databases and large-scale analytical lakehouses. The general wisdom for organizations seeking low-latency real-time analytics is to copy data into dedicated serving layers, which creates data redundancy, stale insights, and fragmented governance. In this talk, we explore how unifying operational and analytical workloads on open storage eliminates the need to copy... Read More

Inside Snowflake’s Query Engine: Optimizing Scans, Semi-Structured Data, and DML

Speakers:

Benjamin Owad , Jiaying Li , Bowei Chen

System:

Snowflake

How data is read, written, and stored largely determines the performance of an analytical query engine. Snowflake in particular favors adaptivity over user-facing knobs, so the engine is responsible for making many decisions at runtime. This session presents recent work in these areas, beginning with table scans. We discuss an adaptive scan parallelism technique, pruning strategies, I/O request coalescing, workload-based... Read More

[Andy at Sea] Inside the Guts of FloeScan and other Interesting Design Magic

Speaker:

Thomas Kejser

System:

Floe

Video:

YouTube

The Floe team came from on-premise databases: We wrote our own userspace, collaborative, task-based kernel. We made a database without a buffer pool and created a subsystem to issue I/O in under 1000 cycles/request, outperforming io_uring. Our execution engine maximises joins per second and runs SQL queries with 5MB of query text to completion. Of course, we needed a query... Read More

[Andy at Sea] Does Systems Engineering Matter Anymore? CANCELLED

Speaker:

David Cramer

System:

Sentry

Let’s dive into what software engineering looks like at a modern infrastructure company today, what challenges we have as engineers in this new era of software, and why systems engineering still matters. This will be a casual conversation around how Sentry - a pre-GPT company - looks at building their own engineering tools to leverage AI for code generation. We’ll... Read More

[Andy at Sea] Everything Has Bugs. Here’s How Antithesis Catches Them.

Speaker:

Marco Primi

System:

Antithesis

Video:

YouTube

Programs used to run on a single computer start to end. Today nearly all software is part of a larger distributed system. Databases were among the earliest to undergo this transition at the turn of the century, replication, fault-tolerance, consensus, scalability were the hot topics of the early cloud era, and they are still relevant today more than ever. The... Read More

[Andy at Sea] Apache Doris: Real-Time Analytics and Search Database for AI Agents

Speaker:

Owen Xiao

System:

Doris

Video:

YouTube

Apache Doris is a real-time analytical and search database built for sub-second, high-concurrency queries over fresh data and data lakes. It has been widely used for customer-facing analytics, data warehousing, and observability. As AI agents move from prototype to production, we see two new categories of workload for analytical databases: Agentic Analytics, where agents autonomously query and explore data on... Read More

Industry Affiliates Program Visit 2026 – Day 2

The second day of Carnegie Mellon University's Database Industry Affiliate Program (IAP) Visit Day, held in the Gates-Hillman Center, shifts focus to the industry side, featuring a series of informative sessions presented by member companies. These sessions offer companies the opportunity to showcase their latest innovations, products, and challenges in the database space, while also highlighting potential career opportunities for... Read More

Industry Affiliates Program Visit 2026 – Day 1

The first day of Carnegie Mellon University's Database Industry Affiliate Program (IAP) Visit Day takes place in the Gates-Hillman Center and is focused on showcasing cutting-edge research in the field of databases. The day is filled with a series of research talks delivered by faculty and students from the university's database group. These presentations provide an in-depth look at the... Read More

[Fall 2026] Bridging the Gap Between HTAP and Lakehouses for Analytics on Fresh Data

Speaker:

Nuno Faria

There has been a growing interest in systems that combine analytical performance with some form of transactions to support ever more frequent updates. On the one hand, hybrid transactional analytical processing (HTAP) systems support fine grained updates at the expense of using custom data formats and processing engines or of fully replicating data between transactional and analytical subsystems, thus limiting... Read More

Why We Created Yet Another Memory Framework: Understanding MGA’s Role in Next-Gen Database Systems

Speakers:

Vikramraj Sitpal , Shubham Kumar

System:

Oracle

Modern database engines already provide multiple memory areas, but under production constraints they often force a difficult choice: use globally shared memory (such as the SGA), with coarse visibility and lifecycle semantics, or use private process memory (such as the PGA), with stronger isolation but more copying, fragmentation, and indirect coordination when state must be shared selectively. This talk presents... Read More