Lukas Arnold
Loading...
1 results
Filters
Reset filtersSearch Results
Publications 1 - 1 of 1
- Single-Pass Covariance Matrix Calculation on a Hybrid FPGA/CPU PlatformItem type: Conference Paper
EPJ Web of Conferences ~ 24th International Conference on Computing in High Energy and Nuclear Physics (CHEP 2019)Arnold, Lukas; Owaida, Muhsen (2020)Covariance matrices are used for a wide range of applications in particle physics, including Kalman filter for tracking purposes or Primary Component Analysis for dimensionality reduction. Based on a novel decomposition of the covariance matrix, a design that requires only one pass of data for calculating the covariance matrix is presented. Two computation engines are used depending on parallelizability of the necessary computation steps. The design is implemented onto a hybrid FPGA/CPU system and yields speed-up of up to 5 orders of magnitude compared to previous FPGA implementation.
Publications 1 - 1 of 1