Parallelizing the Unpacking and Clustering of Detector Data for Reconstruction of Charged Particle Tracks on Multi-core CPUs and Many-core GPUs

TL;DR

This paper introduces a parallelized approach for unpacking and clustering detector data to reconstruct charged particle tracks efficiently on multi-core CPUs and GPUs, significantly improving processing throughput.

Contribution

It presents a novel parallel implementation of data unpacking, clustering, and the Kalman filter algorithm for charged particle track reconstruction on modern hardware.

Findings

Achieved high throughput on Intel Xeon and NVIDIA GPU architectures.

Enabled efficient global event reconstruction using parallel processing.

Demonstrated the effectiveness of nested parallelism and CUDA streams.

Abstract

We present results from parallelizing the unpacking and clustering steps of the raw data from the silicon strip modules for reconstruction of charged particle tracks. Throughput is further improved by concurrently processing multiple events using nested OpenMP parallelism on CPU or CUDA streams on GPU. The new implementation along with earlier work in developing a parallelized and vectorized implementation of the combinatoric Kalman filter algorithm has enabled efficient global reconstruction of the entire event on modern computer architectures. We demonstrate the performance of the new implementation on Intel Xeon and NVIDIA GPU architectures.