|
|
Distributed Graph Query Engine Improvements for Big Data Graphs
Faltín, Tomáš ; Yaghob, Jakub (advisor) ; Tommasini, Riccardo (referee) ; Vora, Keval (referee)
Graph pattern matching queries enable flexible graph exploration, similar to what SQL provides for relational databases. In this thesis, we design and improve key compo- nents of a distributed in-memory graph querying engine. First, we optimize a distributed depth-first search (DFS) asynchronous pattern matching algorithm by combining it with breadth-first search (BFS), thus improving the overall engine performance by leveraging strengths of both approaches: ability to strictly bound the consumed memory of DFS and better parallelization, locality, and load balancing of BFS. Second, we further ex- tend the distributed pattern matching with a novel solution for reachability regular path queries (RPQs) that supports variable-length patterns based on regular expressions. Our design retains the underlying runtime characteristics, allowing for efficient memory con- trol during path exploration with great performance and scalability. Third, we improve query planning, which is one of the most crucial aspects impacting the performance of any querying system. Choosing the "best" query plan is challenging due to the many aspects influencing the performance, especially in a distributed system. We present a lightweight mechanism for gathering runtime information, which can be used to select the most effective query plan...
|
|
|
Interactive disassembler for Intel 64 processors
Faltín, Tomáš ; Yaghob, Jakub (advisor) ; Kofroň, Jan (referee)
The aim of this thesis is to create disassembler-debugger for Intel64 processors. Disassembler loads instructions and instruction's format from XML files which implies future extensibility for new instructions and architecture. After inserting of a program disassembler converts its instructions to assembly language. Debugger is able to run and control the program's instruction flow by stepping over single instruction or by setting some breakpoints that stops the program. Debugger can also show program's threads and find some basic programming structures like if statements and loops. Powered by TCPDF (www.tcpdf.org)
|
|
|
Improvement of data aggregation in query engine for graph databases
Gora, Martin ; Faltín, Tomáš (advisor) ; Nečaský, Martin (referee)
Streaming systems have an advantage over query engines for graph databases with regard to data aggregation (clauses Group by and Order by), because they reduce the set of stored elements only to the aggregated values. However, streaming systems cannot perform pattern matching, unlike query engines. In this work, we created a static graph database with the Labeled-property graph model and a query engine that performs data aggregation using the classical approach of aggregating data after pattern matching was finished. Subsequently, we adjusted query processing in the query engine by applying streaming systems methods. As the result, the query engine was able to perform data aggregation during pattern matching. The goal of this work was to test whether the above-mentioned adjustments can improve performance of query processing. We designed and implemented a certain number of single-thread and parallel solutions for both the adjusted and the classical approach. Afterwards, we conducted experiments on real graphs with artificially generated property values in order to test performance of the created solutions. The experiments showed that there were situations where the adjusted approach had better performance. Specifically, it happened in the case of parallel solutions of Order by when sorting by property...
|
|
|
An intelligent search aggregator and trip planner for accommodation web sites
Deckert, František ; Faltín, Tomáš (advisor) ; Parízek, Pavel (referee)
There are a lot of different accommodation aggregators available. However, none of them offer the possibilities of more advanced adjustments. Instead, all searches are done for one place and two specific range dates only. My work aims to bring the advanced types of search into the accommodation world. It gives users the possibility of splitting any stay at one place between multiple accommodations' stays. It is also able to plan a trip around multiple cities with a flexible time range based on user specified sorting criteria. 1
|
|
|
Streaming system scheduling for Xeon Phi
Faltín, Tomáš ; Yaghob, Jakub (advisor) ; Kruliš, Martin (referee)
Task scheduling in operating system area is a well-known problem on traditional system architectures (NUMA, SMP). Unfortunately, it does not perform well on emerging many-core architectures, especially on Intel Xeon Phi. We collected all publicly available information about the architecture of Xeon Phi. After that, we benchmarked the Xeon Phi in order to find the missing information about its architecture. We focused especially on the information about cores and memory controllers. These are the most important parts when designing a scheduler. Based on the results, we proposed improvements for scheduling algorithm in the Bobox (an experimental streaming system). However, we found that the biggest problem is not in the scheduling algorithm, but in the design of operators' parallelization. Therefore, we proposed improvements to the parallelization and tested one of the proposals.
|
|
|
Streaming system scheduling for Xeon Phi
Faltín, Tomáš ; Yaghob, Jakub (advisor) ; Kruliš, Martin (referee)
Task scheduling in operating system area is well known problem on traditional system architectures (NUMA, SMP). However, it does not perform well on emerging many-core architectures, especially on Intel Xeon Phi. We have collected all publicly available information about the Xeon Phi's architecture. After that we have benchmarked the Xeon Phi to find missing information about its architecture. We were especially curious in architecture of cores and memory controllers. These parts are most important while designing scheduler. Based on the measured results we have proposed improvements to scheduling algorithm in the Bobox - experimental streaming system. Powered by TCPDF (www.tcpdf.org)
|
|
|
Interactive disassembler for Intel 64 processors
Faltín, Tomáš ; Yaghob, Jakub (advisor) ; Kofroň, Jan (referee)
The aim of this thesis is to create disassembler-debugger for Intel64 processors. Disassembler loads instructions and instruction's format from XML files which implies future extensibility for new instructions and architecture. After inserting of a program disassembler converts its instructions to assembly language. Debugger is able to run and control the program's instruction flow by stepping over single instruction or by setting some breakpoints that stops the program. Debugger can also show program's threads and find some basic programming structures like if statements and loops. Powered by TCPDF (www.tcpdf.org)
|
guest ::
