HEP/Particle Astrophysics Seminar

Date
Wed, Apr 21, 2021 4:00 pm - 5:00 pm

Description



Accelerating machine learning inference in particle physics with coprocessors
 
Speaker: Kevin Pedro, Fermi National Accelerator Laboratory (FNAL) 
Online Via Zoom:  https://umd.zoom.us/j/96004266225  

New heterogeneous computing paradigms on dedicated hardware with increased parallelization offer exciting solutions with large potential gains. The growing applications of machine learning algorithms in particle physics for simulation, reconstruction, and analysis are naturally deployed on such platforms. The acceleration of machine learning inference as a web service represents a heterogeneous computing solution for particle physics experiments that requires minimal modification to the current computing model. Coprocessors deployed as an edge or cloud service for the particle physics computing model can have a higher duty cycle and are potentially much more cost-effective. Initial results with Microsoft Brainwave FPGAs and Nvidia GPUs show more than an order of magnitude reduction in inference latency and high throughput. The demonstrated performance is suitable to address the computing challenges faced by both energy frontier and intensity frontier experiments, including the HL-LHC detectors and DUNE. 

Upcoming Events

17 May
CMTC Conference
Date Mon, May 17, 2021 10:00 am - 6:00 pm
27 May
Physics and Public Policy
Thu, May 27, 2021 9:00 am - 10:00 am
1 Jun
QuICS - Dissertation Defense
Tue, Jun 1, 2021 10:00 am - 12:00 pm
10 Jun
Physics and Public Policy
Thu, Jun 10, 2021 9:00 am - 10:00 am
24 Jun
Physics and Public Policy: Victor Yakovenko
Thu, Jun 24, 2021 9:00 am - 10:00 am