RAPID
RAPID provides a scale out architecture for providing very high performance for SQL analytics. This technology has been optimized for OCI Gen 2 and will be available as MySQL analytics service
RAPID
RAPID
RAPID provides a scale out architecture for providing very high performance for SQL analytics. This technology has been optimized for OCI Gen 2 and will be available as MySQL analytics service
Project Overview
Project RAPID was conceived as a hardware/software co-design project targeting large-scale data management and analysis and was targeted to provide the fastest performance for SQL analytics. The project achieved its goals and was demonstrated in a prototype system comprising custom silicon in a massively-scaled-out hardware architecture combined with a new in-memory analytic engine optimized for the custom hardware.
The goal of this project has since been augmented to deliver a system for which provides not just compelling performance for analytic workloads but optimized for performance per dollar. In order to accomplish that, the RAPID software has now been enhanced and optimized for OCI Gen 2 shapes and integrated with the MySQL database.
This technology is being offered as a cloud native MySQL analytic service called MySQL HeatWave, and provides orders of magnitude improvement in performance over MySQL for analytic queries. Several customers who have tried this service have reported significant improvement in performance and reduction in their cost compared to analytics services offered by other cloud providers.
As a part of this project, we are also exploring many machine learning based techniques for automating various aspects of this service.
Eric Sedlar is Senior Vice President & Technical Director of Oracle Labs. This position entails figuring out how to transfer research results from Labs research into Oracle products & services, as well as setting overall technical direction for new research projects in Oracle Labs. A few of the major research areas include:
- Compilers, language runtimes & frameworks: generally based on Graal technologies – see https://graal.cloud for details
- Application-Level and Cloud Operations Security
- Machine Learning, AI & Large Language Models
- Databases and large scale analytics
Eric manages over 250 fulltime researchers and developers working on over a dozen separate research areas. Eric's own research interests are in extensible database technologies, and in particular in integration of compiler technologies and database concepts.
Previously, he led the effort for XML & JSON-native storage inside Oracle. Eric has held various architecture and development management positions at Oracle since starting there in 1990. He holds over 68 patents, and has served on standards organizations for Oracle in the W3C and IETF. He co-authored the Best Paper at SIGMOD 2010 on architecture-sensitive search trees.