----------------------------------------------------------------------------------------------------







       Department of Systems Engineering and Engineering Management



                          The Chinese University of Hong Kong



----------------------------------------------------------------------------------------------------





Date: Wednesday, May 14, 11:00 am – 12:00 noon



Venue: ERB 513, The Chinese University of Hong Kong



Speaker: Professor Tianzheng Wang, Simon Fraser University



Title: Latency-Optimised Modern Database Engines



Abstract: Everything takes time in a database engine: I/O, memory 

stall, synchronization and scheduling all add additional delays in 

addition to running transaction logic. Reducing and hiding such 

latency has been a major goal to achieve high transaction and query 

processing performance, but prior efforts have seen limited adoption 

by missing joint optimizations that mitigate the impact of multiple 

latency sources. A prime example is software prefetching which 

interleaves memory access and compute is often at odds with 

asynchronous I/O. In this talk, we describe our recent efforts on 

reducing and hiding latencies by judiciously leveraging both hardware 

and software primitives such as prefetching instructions, asynchronous 

I/O and recent userspace interrupts. We also emphasize the effort to 

make these work in an end-to-end database engine and considerations 

beyond performance, such as programmability and backward compatibility.





Bio: Tianzheng Wang is an associate professor and director of 

dual-degree and partnerships programs in the School of Computing 

Science at Simon Fraser University in Metro Vancouver, Canada. His 

research centres around the making of database systems in the context 

of modern hardware, new programming primitives, and new applications. 

His work also often extends to related areas such as operating 

systems, parallel programming and distributed systems. Tianzheng Wang 

received his Ph.D. (2017) and M.Sc. (2014) degrees in Computer Science 

from the University of Toronto, and B.Sc. (2012) in Computing degree 

(First Class Honours) from Hong Kong Polytechnic University. His work 

has been assimilated by cloud vendors and startups, and recognized by 

two ACM SIGMOD Research Highlight Awards (2021 and 2023), a 2019 IEEE 

TCSC Award for Excellence in Scalable Computing (Early Career 

Researchers) and nominations for best paper awards.