Speaker
Jennifer Ngadiuba
(INFN, Milano)
Description
Machine learning methods are becoming ubiquitous across particle physics. However, the exploration of such techniques in low-latency environments like L1 trigger systems has only just begun. We present here a new software, based on High Level Synthesis (HLS), to generically port several kinds of network models (BDTs, DNNs, CNNs) into FPGA firmware. As a benchmark physics use case, we consider the task of tagging high-pT jets as H->bb candidates using jet substructure. We map out resource usage and latency versus types of machine learning algorithms and their hyper-parameters. We present a set of general practices to efficiently design low-latency machine-learning algorithms on FPGAs.
Authors
Javier Mauricio Duarte
(Fermi National Accelerator Lab. (US))
Song Han
(Stanford University)
Philip Coleman Harris
(Massachusetts Inst. of Technology (US))
Edward Kreinar
(Hawkeye 360)
Ben Kreis
(Fermi National Accelerator Lab. (US))
Jennifer Ngadiuba
(INFN, Milano)
Maurizio Pierini
(CERN)
Nhan Viet Tran
(Fermi National Accelerator Lab. (US))
Zhenbin Wu
(University of Illinois at Chicago (US))
