Please note: This PhD seminar will be given online.
Mustafa
Korkmaz, PhD
candidate
David
R.
Cheriton
School
of
Computer
Science
Supervisor: Professor Ken Salem
Data centers consume significant amounts of energy, and consumption is growing each year. Alongside efforts in the hardware domain, there are some mechanisms in the software domain to reduce energy consumption. One of these mechanisms is dynamic voltage and frequency scaling (DVFS) and modern servers, which are equipped with multi-core CPUs. In this multi-processor, multi-core setting, a scheduler must address several new problems in addition to the single-processor scheduling problem. For example, it must consider which and how many cores to use or how to distribute transaction executions across those cores. In this talk, we present how we address multi-processor specific scheduling problems and route requests across CPU cores for a better energy-efficiency in transactional data systems.
To join this PhD seminar on Zoom, please go to https://us02web.zoom.us/j/83326411204?pwd=Z3dNVUxIK01PMXY3MTlXaHNVckJqdz09.