Difference between revisions of "Vol-3194/invited1"

From BITPlan ceur-ws Wiki
Jump to navigation Jump to search
(edited by wikiedit)
 
(modified through wikirestore by wf)
Line 1: Line 1:
−
 
+
=Paper=
 
{{Paper
 
{{Paper
−
|wikidataid=Q117344885
+
|id=Vol-3194/invited1
 +
|storemode=property
 +
|title=Runtime-Optimized Analytics
 +
|pdfUrl=https://ceur-ws.org/Vol-3194/invited1.pdf
 +
|volume=Vol-3194
 +
|authors=Anastasia Ailamaki
 +
|dblpUrl=https://dblp.org/rec/conf/sebd/Ailamaki22
 
}}
 
}}
 +
==Runtime-Optimized Analytics==
 +
<pdf width="1500px">https://ceur-ws.org/Vol-3194/invited1.pdf</pdf>
 +
<pre>
 +
Runtime-Optimized Analytics
 +
Anastasia Ailamaki1,2
 +
1
 +
    Ecole Polytechnique Federale de Lausanne (EPFL), Switzerland
 +
2
 +
    RAW Labs SA, Switzerland
 +
 +
 +
                                        Abstract
 +
                                        The ever-increasing demand for diverse real-time analysis on exponentially growing data has brought a
 +
                                        series of new system design challenges: First, we can no longer afford to pre-load the data in a database
 +
                                        in order to support interactive analytics. Second, with the semiconductor advancement predicted by the
 +
                                        end of Dennard scaling, hardware in servers becomes increasingly heterogeneous. Third, the need for
 +
                                        throughput is increased as a function of the number of concurrent queries issued by applications and
 +
                                        users, but current work sharing techniques do not scale. Fourth, data pipelines are made of heterogeneous
 +
                                        tools, each optimized for each processing step, but cross-tool communication introduces high overheads.
 +
                                        Finally, we need real-time processing over fresh data (aka Hybrid Transactional Analytical Processing
 +
                                        or HTAP), but interference between heterogeneous workloads results in suboptimal performance. The
 +
                                        common theme is increasing heterogeneity which is impossible to address efficiently with system design
 +
                                        decision made ahead of time, as at design time we know too little too early. Runtime decisions about
 +
                                        both mechanisms and heuristics, on the other hand, always lead to efficient processing because optimal
 +
                                        processing depends on the use case properties (dat, workload, hardware, concurrency). I will discuss
 +
                                        novel just-in-time (JIT) systems which make and actuate decisions at runtime, and explain how the
 +
                                        individual JIT solutions synthesise a real-time intelligence paradigm that helps resolve most system
 +
                                        performance challenges.
 +
 +
 +
 +
 +
SEBD 2022: The 30th Italian Symposium on Advanced Database Systems, June 19-22, 2022, Tirrenia (PI), Italy
 +
                                      © 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
 +
    CEUR
 +
    Workshop
 +
    Proceedings
 +
                  http://ceur-ws.org
 +
                  ISSN 1613-0073
 +
                                      CEUR Workshop Proceedings (CEUR-WS.org)
 +
�
 +
</pre>

Revision as of 17:53, 30 March 2023

Paper

Paper
edit
description  
id  Vol-3194/invited1
wikidataid  →Q117344885
title  Runtime-Optimized Analytics
pdfUrl  https://ceur-ws.org/Vol-3194/invited1.pdf
dblpUrl  https://dblp.org/rec/conf/sebd/Ailamaki22
volume  Vol-3194→Vol-3194
session  →

Runtime-Optimized Analytics

load PDF 

Runtime-Optimized Analytics
Anastasia Ailamaki1,2
1
    Ecole Polytechnique Federale de Lausanne (EPFL), Switzerland
2
    RAW Labs SA, Switzerland


                                         Abstract
                                         The ever-increasing demand for diverse real-time analysis on exponentially growing data has brought a
                                         series of new system design challenges: First, we can no longer afford to pre-load the data in a database
                                         in order to support interactive analytics. Second, with the semiconductor advancement predicted by the
                                         end of Dennard scaling, hardware in servers becomes increasingly heterogeneous. Third, the need for
                                         throughput is increased as a function of the number of concurrent queries issued by applications and
                                         users, but current work sharing techniques do not scale. Fourth, data pipelines are made of heterogeneous
                                         tools, each optimized for each processing step, but cross-tool communication introduces high overheads.
                                         Finally, we need real-time processing over fresh data (aka Hybrid Transactional Analytical Processing
                                         or HTAP), but interference between heterogeneous workloads results in suboptimal performance. The
                                         common theme is increasing heterogeneity which is impossible to address efficiently with system design
                                         decision made ahead of time, as at design time we know too little too early. Runtime decisions about
                                         both mechanisms and heuristics, on the other hand, always lead to efficient processing because optimal
                                         processing depends on the use case properties (dat, workload, hardware, concurrency). I will discuss
                                         novel just-in-time (JIT) systems which make and actuate decisions at runtime, and explain how the
                                         individual JIT solutions synthesise a real-time intelligence paradigm that helps resolve most system
                                         performance challenges.




SEBD 2022: The 30th Italian Symposium on Advanced Database Systems, June 19-22, 2022, Tirrenia (PI), Italy
                                       © 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
    CEUR
    Workshop
    Proceedings
                  http://ceur-ws.org
                  ISSN 1613-0073
                                       CEUR Workshop Proceedings (CEUR-WS.org)
�
Retrieved from "http://ceur-ws.bitplan.com/index.php?title=Vol-3194/invited1&oldid=1600"