license: | Licensed to the Apache Software Foundation (ASF) under one or more contributor license agreements. See the NOTICE file distributed with this work for additional information regarding copyright ownership. The ASF licenses this file to You under the Apache License, Version 2.0 (the “License”); you may not use this file except in compliance with the License. You may obtain a copy of the License at

       http://www.apache.org/licenses/LICENSE-2.0

Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on an “AS IS” BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions and limitations under the License. layout: publication title: Publication subtitle: > Optimizing Cross-platform Data Movement link-name: ICDE 2019 img-thumb: assets/img/screenshot/rheem.png authors: Sebastian Kruse, Zoi Kaoudi, Jorge-Arnulfo Quiané-Ruiz, Sanjay Chawla, Felix Naumann and Bertty Contreras-Rojas year: 2019 month: 04 day: 07 link-paper: assets/pdf/paper/icde19.pdf link-external: false

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 RHEEMto discover multiple hidden opportunities for cross-platform data processing