P331 - BTW2023- Datenbanksysteme für Business, Technologie und Web

Permanent URI for this collectionhttps://dl.gi.de/handle/20.500.12116/40312

Authors with most Documents  

König-Ries, Birgitta
6
Habich, Dirk
5
Lehner, Wolfgang
4
Binnig, Carsten
3
Hartmann, Claudio
3

Browse

Author: search.filters.author.Lehner, Wolfgang

Search Results

1 - 4 of 4
  • Conference Paper
    Improving GPU Matrix Multiplication by Leveraging Bit Level Granularity and Compression
    (Gesellschaft für Informatik e.V., 2023) Fett, Johannes; Schwarz, Christian; Kober, Urs; Habich, Dirk; Lehner, Wolfgang; König-Ries, Birgitta; Scherzinger, Stefanie; Lehner, Wolfgang; Vossen, Gottfried
    In this paper we introduce BEAM as a novel approach to perform GPU based matrix multiplication on compressed elements. BEAM allows flexible handling of bit sizes for both input and output elements. First evaluations show promising speedups compared to an uncompressed state-of-the-art matrix multiplication algorithm provided by nvidia.
  • Conference Paper
    Working with Disaggregated Systems. What are the Challenges and Opportunities of RDMA and CXL?
    (Gesellschaft für Informatik e.V., 2023) Geyer, Andreas; Ritter, Daniel; Lee, Dong Hun; Ahn, Minseon; Pietrzyk, Johannes; Krause, Alexander; Habich, Dirk; Lehner, Wolfgang; König-Ries, Birgitta; Scherzinger, Stefanie; Lehner, Wolfgang; Vossen, Gottfried
    The usage of disaggregated systems in large scale data-centers offers a lot of flexibility and easy scalability in comparison to the traditional statically configured scale-up and scaleout systems. Disaggregated architectures allow for the creation of software composable systems in order to create a virtual machine by software out of the pool of available hardware resources. In this paper, we propose a memory disaggregation classification and applicable use cases. We would be delighted to present our ideas and the memory disaggregation classification at the workshop and discuss the presented ideas. The valuable feedback of the attendees will help us to further refine our classification both in terms of preciseness and applicability.
  • Conference Paper
    JumpXClass: Explainable AI for Jump Classification in Trampoline Sports
    (Gesellschaft für Informatik e.V., 2023) Woltmann, Lucas; Ferger, Katja; Hartmann, Claudio; Lehner, Wolfgang; König-Ries, Birgitta; Scherzinger, Stefanie; Lehner, Wolfgang; Vossen, Gottfried
    Movement patterns in trampoline gymnastics have become faster and more complex with the increase in the athletes’ capabilities. This makes the assessment of jump type, pose, and quality during training or competitions by humans very difficult or even impossible. To counteract this development, data-driven solutions are thought to be a solution to improve training. In recent work, sensor measurements and machine learning is used to automatically predict jumps and give feedback to the athletes and trainers. However, machine learning models, and especially neural networks, are black boxes most of the time. Therefore, the athletes and trainers cannot gain any insights about the jump from the machine learning-based jump classification. To better understand the jump execution during training, we propose JumpXClass: a tool for automatic machine learning-based jump classification with explainable artificial intelligence. Using elements of explainable artificial intelligence can improve the training experience for athletes and trainers. This work will demonstrate a live system capable to classify and explain jumps from trampoline athletes.
  • Conference Paper
    PostBOUND: PostgreSQL with Upper Bound SPJ Query Optimization
    (Gesellschaft für Informatik e.V., 2023) Bergmann, Rico; Hertzschuch, Axel; Hartmann, Claudio; Habich, Dirk; Lehner, Wolfgang; König-Ries, Birgitta; Scherzinger, Stefanie; Lehner, Wolfgang; Vossen, Gottfried
    A variety of query optimization papers have shown the disastrous effect of poor cardinality estimates on the overall run time for arbitrary select-project-join (SPJ) queries.Especially, underestimating join cardinalities for multi-joins can lead to catastrophic join orderings. A promising solution to overcome this problem is query optimization based on upper bounds for the join cardinalities. In this domain, our proposed UES concept is presently the most efficient technique featuring a simple, yet effective upper bound for an arbitrary number of joins. To foster research in that direction, we introduce PostBOUND, our generalized framework making upper bound SPJ query optimization a first class citizen in PostgreSQL.PostBOUND provides abstractions to calculate arbitrary upper bounds, to model joins required by an SPJ query and to iteratively construct an optimized join order.To highlight the extensibility of PostBOUND and to show the research potential, we additionally present two tighter upper bound UES variants using top-k statistics in this paper.In our evaluation, we show the efficiency and applicability of PostBOUND on different workloads as well as using different PostgreSQL versions. Additionally, we evaluate both presented tighter upper bound variant ideas.
Load citations