Evolution of the ROOT Tree I/O
The ROOT TTree data format encodes hundreds of petabytes of High Energy and Nuclear Physics events. Its columnar layout drives rapid analyses, as only those parts (“branches”) that are really used in a given analysis need to be read from storage. Its unique feature is the seamless C++ integration, w...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EDP Sciences
2020-01-01
|
| Series: | EPJ Web of Conferences |
| Online Access: | https://www.epj-conferences.org/articles/epjconf/pdf/2020/21/epjconf_chep2020_02030.pdf |
| _version_ | 1818891205311725568 |
|---|---|
| author | Blomer Jakob Canal Philippe Naumann Axel Piparo Danilo |
| author_facet | Blomer Jakob Canal Philippe Naumann Axel Piparo Danilo |
| author_sort | Blomer Jakob |
| collection | DOAJ |
| description | The ROOT TTree data format encodes hundreds of petabytes of High Energy and Nuclear Physics events. Its columnar layout drives rapid analyses, as only those parts (“branches”) that are really used in a given analysis need to be read from storage. Its unique feature is the seamless C++ integration, which allows users to directly store their event classes without explicitly defining data schemas. In this contribution, we present the status and plans of the future ROOT 7 event I/O. Along with the ROOT 7 interface modernization, we aim for robust, where possible compile-time safe C++ interfaces to read and write event data. On the performance side, we show first benchmarks using ROOT’s new experimental I/O subsystem that combines the best of TTrees with recent advances in columnar data formats. A core ingredient is a strong separation of the high-level logical data layout (C++ classes) from the low-level physical data layout (storage backed nested vectors of simple types). We show how the new, optimized physical data layout speeds up serialization and deserialization and facilitates parallel, vectorized and bulk operations. This lets ROOT I/O run optimally on the upcoming ultra-fast NVRAM storage devices, as well as file-less storage systems such as object stores. |
| first_indexed | 2024-12-19T17:37:06Z |
| format | Article |
| id | doaj.art-fe3ffdf8a5154600abedf34d52124d18 |
| institution | Directory Open Access Journal |
| issn | 2100-014X |
| language | English |
| last_indexed | 2024-12-19T17:37:06Z |
| publishDate | 2020-01-01 |
| publisher | EDP Sciences |
| record_format | Article |
| series | EPJ Web of Conferences |
| spelling | doaj.art-fe3ffdf8a5154600abedf34d52124d182022-12-21T20:12:19ZengEDP SciencesEPJ Web of Conferences2100-014X2020-01-012450203010.1051/epjconf/202024502030epjconf_chep2020_02030Evolution of the ROOT Tree I/OBlomer Jakob0Canal Philippe1Naumann Axel2Piparo Danilo3CERNFermilabCERNCERNThe ROOT TTree data format encodes hundreds of petabytes of High Energy and Nuclear Physics events. Its columnar layout drives rapid analyses, as only those parts (“branches”) that are really used in a given analysis need to be read from storage. Its unique feature is the seamless C++ integration, which allows users to directly store their event classes without explicitly defining data schemas. In this contribution, we present the status and plans of the future ROOT 7 event I/O. Along with the ROOT 7 interface modernization, we aim for robust, where possible compile-time safe C++ interfaces to read and write event data. On the performance side, we show first benchmarks using ROOT’s new experimental I/O subsystem that combines the best of TTrees with recent advances in columnar data formats. A core ingredient is a strong separation of the high-level logical data layout (C++ classes) from the low-level physical data layout (storage backed nested vectors of simple types). We show how the new, optimized physical data layout speeds up serialization and deserialization and facilitates parallel, vectorized and bulk operations. This lets ROOT I/O run optimally on the upcoming ultra-fast NVRAM storage devices, as well as file-less storage systems such as object stores.https://www.epj-conferences.org/articles/epjconf/pdf/2020/21/epjconf_chep2020_02030.pdf |
| spellingShingle | Blomer Jakob Canal Philippe Naumann Axel Piparo Danilo Evolution of the ROOT Tree I/O EPJ Web of Conferences |
| title | Evolution of the ROOT Tree I/O |
| title_full | Evolution of the ROOT Tree I/O |
| title_fullStr | Evolution of the ROOT Tree I/O |
| title_full_unstemmed | Evolution of the ROOT Tree I/O |
| title_short | Evolution of the ROOT Tree I/O |
| title_sort | evolution of the root tree i o |
| url | https://www.epj-conferences.org/articles/epjconf/pdf/2020/21/epjconf_chep2020_02030.pdf |
| work_keys_str_mv | AT blomerjakob evolutionoftheroottreeio AT canalphilippe evolutionoftheroottreeio AT naumannaxel evolutionoftheroottreeio AT piparodanilo evolutionoftheroottreeio |