BEGIN:VCALENDAR
VERSION:2.0
PRODID:www.dresden-science-calendar.de
METHOD:PUBLISH
CALSCALE:GREGORIAN
X-MICROSOFT-CALSCALE:GREGORIAN
X-WR-TIMEZONE:Europe/Berlin
BEGIN:VTIMEZONE
TZID:Europe/Berlin
X-LIC-LOCATION:Europe/Berlin
BEGIN:DAYLIGHT
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
DTSTART:19810329T030000
RRULE:FREQ=YEARLY;INTERVAL=1;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
DTSTART:19961027T030000
RRULE:FREQ=YEARLY;INTERVAL=1;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:DSC-12421
DTSTART;TZID=Europe/Berlin:20170203T150000
SEQUENCE:1486107835
TRANSP:OPAQUE
DTEND;TZID=Europe/Berlin:20170203T160000
URL:https://dresden-science-calendar.de/calendar/en/detail/12421
LOCATION:TUD Andreas-Pfitzmann-Bau\, Nöthnitzer Straße 4601069 Dresden
SUMMARY:Paradies: Graph Processing in Main-Memory Column Stores
CLASS:PUBLIC
DESCRIPTION:Speaker: Dipl.-Inf. Marcus Paradies\nInstitute of Speaker: Inst
 itut für Systemarchitektur\, Professur Datenbanken\nTopics:\nInformatik\n
  Location:\n  Name: TUD Andreas-Pfitzmann-Bau (APB 1004 (Ratssaal))\n  Str
 eet: Nöthnitzer Straße 46\n  City: 01069 Dresden\n  Phone: \n  Fax: \nDe
 scription: Evermore\, novel and traditional business applications leverage
  the advantages of a graph data model\, such as the offered schema flexibi
 lity and an explicit representation of relationships between entities. As 
 a consequence\, companies are confronted with the challenge of storing\, m
 anipulating\, and querying terabytes of graph data for enterprise-critical
  applications. Although these business applications operate on graph-struc
 tured data\, they still require direct access to the relational data and t
 ypically rely on an RDBMS to keep a single source of truth and access. Exi
 sting solutions performing graph operations on business-critical data eith
 er use a combination of SQL and application logic or employ a graph data m
 anagement system. For the first approach\, relying solely on SQL results i
 n poor execution performance caused by the functional mismatch between typ
 ical graph operations and the relational algebra. To the worse\, graph alg
 orithms expose a tremendous variety in structure and functionality caused 
 by their often domain-specific implementations and therefore can be hardly
  integrated into a database management system other than with custom codin
 g. Since the majority of these enterprise-critical applications exclusivel
 y run on relational DBMSs\, employing a specialized system for storing and
  processing graph data is typically not sensible. Besides the maintenance 
 overhead for keeping the systems in sync\, combining graph and relational 
 operations is hard to realize as it requires data transfer across system b
 oundaries. A basic ingredient of graph queries and algorithms are traversa
 l operations and are a fundamental component of any database management sy
 stem that aims at storing\, manipulating\, and querying graph data. Well-e
 stablished graph traversal algorithms are standalone implementations relyi
 ng on optimized data structures. The integration of graph traversals as an
  operator into a database management system requires a tight integration i
 nto the existing database environment and a development of new components\
 , such as a graph topology-aware optimizer and accompanying graph statisti
 cs\, graph-specific secondary index structures to speedup traversals\, and
  an accompanying graph query language. In this thesis\, we introduce and d
 escribe Graphite\, a hybrid graph-relational data management system. Graph
 ite is a performance-oriented graph data management system as part of an R
 DBMS allowing to seamlessly combine processing of graph data with relation
 al data in the same system. We propose a columnar storage representation f
 or graph data to leverage the already existing and mature data management 
 and query processing infrastructure of relational database management syst
 ems. At the core of Graphite we propose an execution engine solely based o
 n set operations and graph traversals. Our design is driven by the observa
 tion that different graph topologies expose different algorithmic requirem
 ents to the design of a graph traversal operator. We derive two graph trav
 ersal implementations targeting the most common graph topologies and demon
 strate how graph-specific statistics can be leveraged to select the optima
 l physical traversal operator. To accelerate graph traversals\, we devise 
 a set of graph-specific\, updateable secondary index structures to improve
  the performance of vertex neighborhood expansion. Finally\, we introduce 
 a domain-specific language with an intuitive programming model to extend g
 raph traversals with custom application logic at runtime. We use the LLVM 
 compiler framework to generate efficient code that tightly integrates the 
 user-specified application logic with our highly optimized built-in graph 
 traversal operators. Our experimental evaluation shows that Graphite can o
 utperform native graph management systems by several orders of magnitude w
 hile providing all the features of an RDBMS\, such as transaction support\
 , backup and recovery\, security and user management\, effectively providi
 ng a promising alternative to specialized graph management systems that la
 ck many of these features and require expensive data replication and maint
 enance processes.
DTSTAMP:20260602T131320Z
CREATED:20170121T075347Z
LAST-MODIFIED:20170203T074355Z
END:VEVENT
END:VCALENDAR