SQL Query Processing Using an Integrated FPGA-based Near-Data Accelerator in ReProVide

In this demo, we explain the working of ReProVide, a framework that integrates an on-the-fly reconfigurable FPGA-based SoC architecture with a DBMS for accelerated query processing. For this, a capability-aware optimization that can optimize and partition the queries is demonstrated. This optimization for the hardware is based on its capabilities. Our hardware can also generate statistics of the data while executing a query. In contrast to the existing approaches, this does not have any additional costs in terms of execution time. We will demonstrate how these statistics are later used by the DBMS to select the best plan from the search space using accurate cost values.

[1]  Wolfgang Lehner,et al.  Adaptive Work Placement for Query Processing on Heterogeneous Computing Resources , 2017, Proc. VLDB Endow..

[2]  Jürgen Teich,et al.  A co-design approach for accelerated SQL query processing via FPGA-based data filtering , 2015, 2015 International Conference on Field Programmable Technology (FPT).

[3]  Jürgen Teich,et al.  In situ Statistics Generation within partially reconfigurable Hardware Accelerators for Query Processing , 2019, DaMoN.

[4]  Gustavo Alonso,et al.  Centaur: A Framework for Hybrid CPU-FPGA Databases , 2017, 2017 IEEE 25th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM).

[5]  Jürgen Teich,et al.  Integration of FPGAs in Database Management Systems: Challenges and Opportunities , 2018, Datenbank-Spektrum.

[6]  Hans-Arno Jacobsen,et al.  Flexible Query Processor on FPGAs , 2013, Proc. VLDB Endow..

[7]  Jürgen Teich,et al.  ReProVide: Towards Utilizing Heterogeneous Partially Reconfigurable Architectures for Near-Memory Data Processing , 2019, BTW.

[8]  Wolfgang Lehner,et al.  Local vs. Global Optimization: Operator Placement Strategies in Heterogeneous Environments , 2015, EDBT/ICDT Workshops.

[9]  Gustavo Alonso,et al.  Histograms as a side effect of data movement for big data , 2014, SIGMOD Conference.

[10]  Jürgen Teich,et al.  FPGA-Based Dynamically Reconfigurable SQL Query Processing , 2016, ACM Trans. Reconfigurable Technol. Syst..

[11]  Gustavo Alonso,et al.  Accelerating Pattern Matching Queries in Hybrid CPU-FPGA Architectures , 2017, SIGMOD Conference.

[12]  Gunter Saake,et al.  Ocelot/HyPE: Optimized Data Processing on Heterogeneous Hardware , 2014, Proc. VLDB Endow..

[13]  Daniel Lemire,et al.  Apache Calcite: A Foundational Framework for Optimized Query Processing Over Heterogeneous Data Sources , 2018, SIGMOD Conference.

[14]  Gustavo Alonso,et al.  Ibex - An Intelligent Storage Engine with Support for Advanced SQL Off-loading , 2014, Proc. VLDB Endow..

[15]  Wolfgang Lehner,et al.  Heterogeneity-Aware Operator Placement in Column-Store DBMS , 2014, Datenbank-Spektrum.