Title: Efficient Data Processing on Modern Hardware

Speaker: Sebastian Breß

Affiliation: TU Berlin

Date and location: Friday, April 12, 12:30-1:30pm; Wozniak Lounge (430 Soda Hall)

Abstract: Processor manufacturers build increasingly specialized processors to mitigate the effects of the power wall in order to deliver improved performance. Currently, database engines have to be manually optimized for each processor which is a costly and error prone process. In this talk, we provide an overview of our research on automatic performance tuning in Hawk, a hardware-tailored code generator [1]. Our key idea is to create processor-specific code variants and to learn a well-performing code variant for each processor. These code variants leverage various parallelization strategies and apply both generic and processor-specific code transformations. We observe that performance of different code variants may diverge up to two orders of magnitude. Thus, we need to generate custom code for each processor for peak performance. To this end, Hawk automatically finds efficient code variants for CPUs, GPUs, and MICs.

[1] https://github.com/TU-Berlin-DIMA/Hawk-VLDBJ

Bio: Sebastian Breß received his PhD (Dr.-Ing.) from University of Magdeburg, Germany in 2015, under the supervision of Gunter Saake (University of Magdeburg) and Jens Teubner (TU Dortmund). He is the the initiator and system architect of the research database system CoGaDB and the Hawk Code Generator. Currently, Sebastian is a Senior Researcher at German Research Center for Artificial Intelligence (DFKI) and a PostDoc at Technische Universität Berlin, working with Prof. Dr. Volker Markl and Prof. Dr. Tilmann Rabl. Sebastian‘s research interests include data management on modern hardware, query compilation, stream processing, and optimizing data management systems for heterogeneous processors. Sebastian has been selected as a Distinguished Program Committee Member at SIGMOD 2018.