Imperial College London
Portrait Picture

ProfessorPeterPietzuch

Faculty of Engineering, Department of Computing

Professor of Distributed Systems
 
 
 
//

Contact

 

+44 (0)20 7594 8314prp Website

 
 
//

Location

 

442Huxley BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@inproceedings{Koliousis:2016:10.1145/2882903.2882906,
author = {Koliousis, A and Weidlich, M and Fernandez, R and Wolf, A and Costa, P and Pietzuch, P},
doi = {10.1145/2882903.2882906},
pages = {555--569},
publisher = {ACM},
title = {Saber: window-based hybrid stream processing for heterogeneous architectures},
url = {http://dx.doi.org/10.1145/2882903.2882906},
year = {2016}
}
Download

RIS format (EndNote, RefMan)

TY  - CPAPER
AB  - Modern servers have become heterogeneous, often combining multicoreCPUs with many-core GPGPUs. Such heterogeneous architectureshave the potential to improve the performance of data-intensivestream processing applications, but they are not supported by currentrelational stream processing engines. For an engine to exploit aheterogeneous architecture, it must execute streaming SQL querieswith sufficient data-parallelism to fully utilise all available heterogeneousprocessors, and decide how to use each in the most effectiveway. It must do this while respecting the semantics of streamingSQL queries, in particular with regard to window handling.We describe SABER, a hybrid high-performance relational streamprocessing engine for CPUs and GPGPUs. SABER executes windowbasedstreaming SQL queries in a data-parallel fashion using allavailable CPU and GPGPU cores. Instead of statically assigningquery operators to heterogeneous processors, SABER employs anew adaptive heterogeneous lookahead scheduling strategy, whichincreases the share of queries executing on the processor that yieldsthe highest performance. To hide data movement costs, SABERpipelines the transfer of stream data between different memory typesand the CPU/GPGPU. Our experimental comparison against state-ofthe-artengines shows that SABER increases processing throughputwhile maintaining low latency for a wide range of streaming SQLqueries with small and large windows sizes.
AU  - Koliousis,A
AU  - Weidlich,M
AU  - Fernandez,R
AU  - Wolf,A
AU  - Costa,P
AU  - Pietzuch,P
DO  - 10.1145/2882903.2882906
EP  - 569
PB  - ACM
PY  - 2016///
SP  - 555
TI  - Saber: window-based hybrid stream processing for heterogeneous architectures
UR  - http://dx.doi.org/10.1145/2882903.2882906
UR  - http://hdl.handle.net/10044/1/29391
ER  -
Download