@misc{KruseKaoudiQuianeRuizetal.2019,
  author    = {Kruse, Sebastian and Kaoudi, Zoi and Quiane-Ruiz, Jorge-Arnulfo and Chawla, Sanjay and Naumann, Felix and Contreras-Rojas, Bertty},
  title     = {Optimizing Cross-Platform Data Movement},
  series = {2019 IEEE 35th International Conference on Data Engineering (ICDE)},
  journal   = {2019 IEEE 35th International Conference on Data Engineering (ICDE)},
  publisher = {IEEE},
  address   = {New York},
  isbn      = {978-1-5386-7474-1},
  issn      = {1084-4627},
  doi       = {10.1109/ICDE.2019.00162},
  pages     = {1642 -- 1645},
  year      = {2019},
  abstract  = {Data analytics are moving beyond the limits of a single data processing platform. A cross-platform query optimizer is necessary to enable applications to run their tasks over multiple platforms efficiently and in a platform-agnostic manner. For the optimizer to be effective, it must consider data movement costs across different data processing platforms. In this paper, we present the graph-based data movement strategy used by RHEEM, our open-source cross-platform system. In particular, we (i) model the data movement problem as a new graph problem, which we prove to be NP-hard, and (ii) propose a novel graph exploration algorithm, which allows RHEEM to discover multiple hidden opportunities for cross-platform data processing.},
  language  = {en}
}
@misc{KruseKaoudiContrerasRojasetal.2020,
  author    = {Kruse, Sebastian and Kaoudi, Zoi and Contreras-Rojas, Bertty and Chawla, Sanjay and Naumann, Felix and Quian{\´e}-Ruiz, Jorge-Arnulfo},
  title     = {RHEEMix in the data jungle},
  series = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t},
  journal   = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t},
  number    = {6},
  doi       = {10.25932/publishup-51944},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-519443},
  pages     = {26},
  year      = {2020},
  abstract  = {Data analytics are moving beyond the limits of a single platform. In this paper, we present the cost-based optimizer of Rheem, an open-source cross-platform system that copes with these new requirements. The optimizer allocates the subtasks of data analytic tasks to the most suitable platforms. Our main contributions are: (i) a mechanism based on graph transformations to explore alternative execution strategies; (ii) a novel graph-based approach to determine efficient data movement plans among subtasks and platforms; and (iii) an efficient plan enumeration algorithm, based on a novel enumeration algebra. We extensively evaluate our optimizer under diverse real tasks. We show that our optimizer can perform tasks more than one order of magnitude faster when using multiple platforms than when using a single platform.},
  language  = {en}
}
@article{KruseKaoudiContrerasRojasetal.2020,
  author    = {Kruse, Sebastian and Kaoudi, Zoi and Contreras-Rojas, Bertty and Chawla, Sanjay and Naumann, Felix and Quiane-Ruiz, Jorge-Arnulfo},
  title     = {RHEEMix in the data jungle},
  series = {The VLDB Journal},
  volume    = {29},
  journal   = {The VLDB Journal},
  number    = {6},
  publisher = {Springer},
  address   = {Berlin},
  issn      = {1066-8888},
  doi       = {10.1007/s00778-020-00612-x},
  pages     = {1287 -- 1310},
  year      = {2020},
  abstract  = {Data analytics are moving beyond the limits of a single platform. In this paper, we present the cost-based optimizer of Rheem, an open-source cross-platform system that copes with these new requirements. The optimizer allocates the subtasks of data analytic tasks to the most suitable platforms. Our main contributions are: (i) a mechanism based on graph transformations to explore alternative execution strategies; (ii) a novel graph-based approach to determine efficient data movement plans among subtasks and platforms; and (iii) an efficient plan enumeration algorithm, based on a novel enumeration algebra. We extensively evaluate our optimizer under diverse real tasks. We show that our optimizer can perform tasks more than one order of magnitude faster when using multiple platforms than when using a single platform.},
  language  = {en}
}
@article{GevayRablBressetal.2022,
  author    = {Gevay, Gabor E. and Rabl, Tilmann and Bress, Sebastian and Maclai-Tahy, Lorand and Quiane-Ruiz, Jorge-Arnulfo and Markl, Volker},
  title     = {Imperative or Functional Control Flow Handling: Why not the Best of Both Worlds?},
  series = {SIGMOD record},
  volume    = {51},
  journal   = {SIGMOD record},
  number    = {1},
  publisher = {Association for Computing Machinery},
  address   = {New York},
  issn      = {0163-5808},
  doi       = {10.1109/ICDE51399.2021.00127},
  pages     = {60 -- 67},
  year      = {2022},
  abstract  = {Modern data analysis tasks often involve control flow statements, such as the iterations in PageRank and K-means. To achieve scalability, developers usually implement these tasks in distributed dataflow systems, such as Spark and Flink. Designers of such systems have to choose between providing imperative or functional control flow constructs to users. Imperative constructs are easier to use, but functional constructs are easier to compile to an efficient dataflow job. We propose Mitos, a system where control flow is both easy to use and efficient. Mitos relies on an intermediate representation based on the static single assignment form. This allows us to abstract away from specific control flow constructs and treat any imperative control flow uniformly both when building the dataflow job and when coordinating the distributed execution.},
  language  = {en}
}
@article{GevayRablBressetal.2022,
  author    = {G{\´e}vay, G{\´a}bor E. and Rabl, Tilmann and Breß, Sebastian and Madai-Tahy, Lor{\´a}nd and Quian{\´e}-Ruiz, Jorge-Arnulfo and Markl, Volker},
  title     = {Imperative or functional control flow handling},
  series = {SIGMOD record / Association for Computing Machinery, Special Interest Group on Management of Data},
  volume    = {51},
  journal   = {SIGMOD record / Association for Computing Machinery, Special Interest Group on Management of Data},
  number    = {1},
  publisher = {Association for Computing Machinery},
  address   = {New York},
  issn      = {0163-5808},
  doi       = {10.1145/3542700.3542715},
  pages     = {60 -- 67},
  year      = {2022},
  abstract  = {Modern data analysis tasks often involve control flow statements, such as the iterations in PageRank and K-means. To achieve scalability, developers usually implement these tasks in distributed dataflow systems, such as Spark and Flink. Designers of such systems have to choose between providing imperative or functional control flow constructs to users. Imperative constructs are easier to use, but functional constructs are easier to compile to an efficient dataflow job. We propose Mitos, a system where control flow is both easy to use and efficient. Mitos relies on an intermediate representation based on the static single assignment form. This allows us to abstract away from specific control flow constructs and treat any imperative control flow uniformly both when building the dataflow job and when coordinating the distributed execution.},
  language  = {en}
}