CSE Alumnus from Oracle Addresses Database Researchers at UC San Diego

Jan 17, 2018

An early alumnus of the Computer Science and Engineering department will be back on campus Friday, January 19 to address faculty and students involved in the regular Database seminar in CSE, and then participate in a Student Roundtable Chat afterwards.

Chavan200b.jpg
Shasank Chavan, VP, Oracle

Shasank Chavan, who completed his B.S. and M.S. in Computer Science in 1997 and 1998, respectively, is now Vice President in charge of In-Memory Technologies at Oracle. Since joining the company in 2011, Chavan has been a software engineer, manager, architect and director of the Oracle RDBMS data layer team, and starting this January, he leads a team of engineers in the Database organization that is "hyper-focused on leveraging emerging hardware technologies to build the next-generation data storage engine that powers the cloud," according to Chavan

Date: Friday, January 19, 2018
Time: 2:00-2:30pm Seminar; 3:30pm-4:30pm Student Roundtable
Location: CSE 3217 (Seminar); CSE 3109 (Roundtable

Abstract:  Analytic workloads in data management systems are dominated by joins, aggregations, scan and filtering costs. In-Memory columnar databases have significantly optimized scans using compressed data formats and SIMD vectorization techniques, but have made little impact to the rest of the query execution plan. The Oracle Database In-Memory (DBIM) Option introduced new SQL execution operators that accelerate a wide range of analytic queries by optimizing aggregation over joins for star and similar schemas. Group-by expressions are pushed down into the scans of dimension tables, creating a unique key per distinct group called a Dense Grouping Key (DGK). A structure called a Key Vector is allocated that maps join keys to DGKs, which is used to filter non-matching rows during the fact table scan. Passing rows are then aggregated directly on compressed codes into DGK-indexed result buffers using SIMD and other novel aggregation techniques. 

"Our solution replaces traditional join and group-by processing (bloom filters, hash table build and probe, serial aggregation) with blazing-fast inlined scan operators," adds Chavan. "Our technique can drastically reduce query elapsed time by more than 10x, making real-time analytics truly achievable."

Chavan spent his early career at Hewlett-Packard as a software engineer, alternately focusing on databases and compilers. He joined HP immediately after receiving his M.S. degree from CSE and worked there for 13 years before joining Oracle in 2011.