10-15 March 2019
Steinmatte conference center
Europe/Zurich timezone

FPGA-accelerated machine learning inference as a solution for particle physics computing challenges

12 Mar 2019, 19:00
20m
Steinmatte Plenary

Steinmatte Plenary

Oral Track 1: Computing Technology for Physics Research Track 1: Computing Technology for Physics Research

Speaker

Jennifer Ngadiuba (CERN)

Description

Resources required for high-throughput computing in large-scale particle physics experiments face challenging demands both now and in the future. The growing exploration of machine learning algorithms in particle physics offers new solutions to simulation, reconstruction, and analysis. These new machine learning solutions often lead to increased parallelization and faster reconstructions times on dedicated hardware, here specifically Field Programmable Gate Arrays. We explore the possibility that applications of machine learning simultaneously also solve the increasing computing challenges. Employing machine learning acceleration as a web service, we demonstrate a heterogeneous compute solution for particle physics experiments that requires minimal modification to the current computing model. First results with Project Brainwave by Microsoft Azure, using the Resnet-50 image classification model as an example, demonstrate inference times of approximately 50 (10) milliseconds with our experimental physics software framework using Brainwave as a cloud (edge) service. We also adapt the image classifier, for example, physics applications using transfer learning: jet identification in the CMS experiment and event classification in the Nova neutrino experiment at Fermilab. Solutions explored here are potentially applicable sooner than may have been initially realized.

Primary authors

Nhan Viet Tran (Fermi National Accelerator Lab. (US)) Maurizio Pierini (CERN) Philip Coleman Harris (Massachusetts Inst. of Technology (US)) Kevin Pedro (Fermi National Accelerator Lab. (US)) Javier Mauricio Duarte (Fermi National Accelerator Lab. (US)) Ben Kreis (Fermi National Accelerator Lab. (US)) Dylan Sheldon Rankin (Massachusetts Inst. of Technology (US)) Sergo Jindariani (Fermi National Accelerator Lab. (US)) Miaoyuan Liu (Fermi National Accelerator Lab. (US)) Aristeidis Tsaris (Fermilab) Jennifer Ngadiuba (CERN) Dr Burt Holzman (Fermi National Accelerator Lab. (US)) Zhenbin Wu (University of Illinois at Chicago (US))

Presentation materials