Porting the CMS pixel reconstruction to Julia: preliminary results

The Patatrack pixel track reconstruction is a stand-alone project that has been extracted from the CMS reconstruction software. Over the years it has been used to test and evaluate different CPU and GPU technologies, like OpenMP, TBB, CUDA, HIP, SYCL, Kokkos, and Alpaka. In order to evaluate the Julia programming language in the context of a realistic High Energy Physics software project, the Patatrack pixel track reconstruction is now being rewritten in Julia. The project is under active development, and about 30% of the reconstruction algorithms have been documented, rewritten in Julia, and validated. The first results are very encouraging: the Julia version produces correct results, and has a single-threaded performance very close to that of the original C++ version. This contribution will give an overview of the project and its long-term prospects, describe the challenges encountered during the work, along with the solutions chosen to address them, and present the preliminary results in terms of correctness and performance of the Julia implementation.

Institutions

Publication Details

Published
2024-10-01
DOI
https://doi.org/10.17181/gwzzq-56t73
Primary Topic
Geochemistry and Geologic Mapping
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Porting the CMS pixel reconstruction to Julia: preliminary results

Geochemistry and Geologic Mapping
article

Porting the CMS pixel reconstruction to Julia: preliminary results

article en

Abstract

The Patatrack pixel track reconstruction is a stand-alone project that has been extracted from the CMS reconstruction software. Over the years it has been used to test and evaluate different CPU and GPU technologies, like OpenMP, TBB, CUDA, HIP, SYCL, Kokkos, and Alpaka. In order to evaluate the Julia programming language in the context of a realistic High Energy Physics software project, the Patatrack pixel track reconstruction is now being rewritten in Julia. The project is under active development, and about 30% of the reconstruction algorithms have been documented, rewritten in Julia, and validated. The first results are very encouraging: the Julia version produces correct results, and has a single-threaded performance very close to that of the original C++ version. This contribution will give an overview of the project and its long-term prospects, describe the challenges encountered during the work, along with the solutions chosen to address them, and present the preliminary results in terms of correctness and performance of the Julia implementation.

Université Paris-Saclay (FR), European Organization for Nuclear Research (CH), American University of Beirut (LB)
Openalex Percentile: Top 44%
Geochemistry and Geologic Mapping
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.