IRUS Total

Saber: Window-based Hybrid Stream Processing for Heterogeneous Architectures

File Description SizeFormat 
saber-sigmod_accepted.pdfAccepted version932.18 kBAdobe PDFView/Open
Title: Saber: Window-based Hybrid Stream Processing for Heterogeneous Architectures
Authors: Koliousis, A
Weidlich, M
Fernandez, R
Wolf, A
Costa, P
Pietzuch, P
Item Type: Conference Paper
Abstract: Modern servers have become heterogeneous, often combining multicore CPUs with many-core GPGPUs. Such heterogeneous architectures have the potential to improve the performance of data-intensive stream processing applications, but they are not supported by current relational stream processing engines. For an engine to exploit a heterogeneous architecture, it must execute streaming SQL queries with sufficient data-parallelism to fully utilise all available heterogeneous processors, and decide how to use each in the most effective way. It must do this while respecting the semantics of streaming SQL queries, in particular with regard to window handling. We describe SABER, a hybrid high-performance relational stream processing engine for CPUs and GPGPUs. SABER executes windowbased streaming SQL queries in a data-parallel fashion using all available CPU and GPGPU cores. Instead of statically assigning query operators to heterogeneous processors, SABER employs a new adaptive heterogeneous lookahead scheduling strategy, which increases the share of queries executing on the processor that yields the highest performance. To hide data movement costs, SABER pipelines the transfer of stream data between different memory types and the CPU/GPGPU. Our experimental comparison against state-ofthe-art engines shows that SABER increases processing throughput while maintaining low latency for a wide range of streaming SQL queries with small and large windows sizes.
Issue Date: 26-Jun-2016
Date of Acceptance: 20-Sep-2015
URI: http://hdl.handle.net/10044/1/29391
Publisher: ACM
Journal / Book Title: Proceedings of the ACM SIGMOD International Conference on Management of Data
Copyright Statement: © ACM, 2016. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version has not yet been published.
Sponsor/Funder: Commission of the European Communities
Funder's Grant Number: FP7 - 318521
Conference Name: 2016 ACM SIGMOD/PODS Conference
Keywords: doc-ref21
Notes: This is a dummy significance statement.
Publication Status: Accepted
Start Date: 2016-06-26
Finish Date: 2016-07-01
Conference Place: San Francisco
Appears in Collections:Faculty of Engineering