Citations per year

20202021202220232024138
Abstract: (EDP Sciences)
The Awkward Array library has been an important tool for physics analysis in Python since September 2018. However, some interface and implementation issues have been raised in Awkward Array’s first year that argue for a reimplementation in C++ and Numba. We describe those issues, the new architecture, and present some examples of how the new interface will look to users. Of particular importance is the separation of kernel functions from data structure management, which allows a C++ implementation and a Numba implementation to share kernel functions, and the algorithm that transforms recordoriented data into columnar Awkward Arrays.
Note:
  • To be published in CHEP 2019 proceedings, EPJ Web of Conferences; post-review update
  • interface
  • programming
  • data management
  • retrieved Feb 25
    • R. Brun
      ,
    • N. Buncic
      ,
    • F. Rademakers
  • Dremel: Interactive Analysis of Web-Scale Datasets

    • S. Melnik
      ,
    • A. Gubarev
      ,
    • J.J. Long
      ,
    • G. Romer
      ,
    • S. Shivakumar
    et al.
  • Apache Parquet. In: Practical Hadoop Ecosystem. Apress, Berkeley, CA
    • D. Vohra
  • retrieved Feb 20
  • retrieved Oct 16
  • Columnar Objects: Improving the Performance of Analytical Applications

    • T. Mattis
      ,
    • J. Henning
      ,
    • P. Rein
      ,
    • R. Hirschfeld
      ,
    • M. Appeltauer
  • retrieved Aug 16
  • Vectorized processing of nested data

    • J. Pivarski
  • Nested data structures in array and SIMD frameworks

    • J. Pivarski
      ,
    • P. Elmer
  • Numba: a LLVM-based Python JIT compiler

    • S.K. Lam
      ,
    • A. Pitrou
      ,
    • S. Seibert
  • retrieved Jun 26
  • pybind11 - Seamless operability between C++11 and Python

    • W. Jakob
      ,
    • J. Rhinelander
      ,
    • D. Moldovan