Home > Speakers >

Steven Graves

Mr. Graves co-founded McObject in 2001. As the company’s president and CEO, he has both spearheaded McObject’s growth and helped the company attain its goal of providing embedded database technology that makes embedded systems smarter, more reliable and more cost-effective to develop and maintain. Prior to McObject, Mr. Graves was president and chairman of Centura Solutions Corporation, and vice president of worldwide consulting for Centura Software Corporation (NASDAQ: CNTR); he also served as president and chief operating officer of Raima Corporation. Mr. Graves is a member of the advisory board for the University of Washington’s certificate program in Embedded and Real-time Systems Programming.

Database Management for Embedded Intelligence: ANN Indexes for Resource-Constrained Devices

Status: Coming up in April 2026!

Embedded devices operate under severe RAM constraints, which means both machine learning models and their search indexes often must reside in persistent storage, typically flash memory. A database management system (DBMS) with direct flash access plays a key role in this setting, offering persistence and structured access to ANN indexes while minimizing reliance on RAM. These constraints, however, expose the limits of many approximate nearest neighbor (ANN) algorithms.

One prominent example is RAM-based HNSW, which—though popular—consumes too much memory to be practical on small devices, while persistent approaches such as DiskANN, built on Vamana, are optimized for massive cloud-scale datasets and do not translate well to embedded workloads.

This paper reviews why classical database indexes such as R-trees do not scale to high-dimensional embeddings. It then outlines the evolution of ANN indexes for vector search:

  • Inverted File (IVF) structures: Exploring clustering and centroid-based search.
  • NSW, HNSW, and Vamana: Tracing the shift toward graph-based navigation.
  • Embedded Adaptations: Identifying which approaches are most disk-friendly for Edge AI.

We examine factors like Product Quantization (PQ), which reduces size at the cost of accuracy, and adaptations of the Vamana algorithm for smaller datasets, including bounded-degree constraints. We argue that flash-adapted HNSW is a practical path: it can be implemented directly on persistent storage while delivering efficient search speed and recall.

We conclude with results from real flash hardware, comparing HNSW, Vamana, and IVF-PQ in terms of accuracy, latency, and resource usage, demonstrating that DBMS-backed ANN indexes on flash are the practical choice for embedded AI.

Go to Session

Why Real-Time Systems Need a Real-Time Database

Status: Available Now

Historically, real-time systems and database systems have been like oil and water. The reason? Making an API call to a non-deterministic database system could cause a real-time task to exceed its deadline. Previously, real-time systems were not overly complex and could do without database support. Today, however, real-time systems’ tasks need to collect, aggregate, correlate and analyze data from disparate sources (sensor data fusion) and could benefit greatly from a shared repository. This MicroTalk will present a solution: adding time-cognizance to database transactions, and suitable transaction schedulers.

Go to Session