hls4ml: An Open-Source Codesign Workflow to Empower Scientific Low-Power Machine Learning Devices
Year: 2021
Type: preprint
Abstract: Accessible machine learning algorithms, software, and diagnostic tools for energy-efficient devices and systems are extremely valuable across a broad range of application domains. In scientific domains, real-time near-sensor processing can drastically improve experimental design and accelerate scientific discoveries. To support domain scientists, we have developed hls4ml, an open-source software-hardware codesign workflow to interpret and translate machine learning algorithms for implementation with both FPGA and ASIC technologies. We expand on previous hls4ml work by extending capabilities and techniques towards low-power implementations and increased usability: new Python APIs, quantization-aware pruning, end-to-end FPGA workflows, long pipeline kernels for low power, and new device backends include an ASIC workflow. Taken together, these and continued efforts in hls4ml will arm a new generation of domain scientists with accessible, efficient, and powerful tools for machine-learning-accelerated discovery.
Source: arXiv (Cornell University)
Authors: Fahim, Farah, Hawks, Benjamin, Herwig, Christian, Hirschauer, James, Jindariani, Sergo, Tran, Nhan, Carloni, Luca P., Di Guglielmo, Giuseppe, Harris, Philip, Krupa, Jeffrey, Rankin, Dylan, Valentin, Manuel Blanco, Hester, Josiah, Luo, Yingyi, Mamish, John, Orgrenci-Memik, Seda, Aarrestad, Thea, Javed, Hamza, Loncar, Vladimir, Pierini, Maurizio, Pol, Adrian Alan, Summers, Sioni, Duarte, Javier, Hauck, Scott, Hsu, Shih-Chieh, Ngadiuba, Jennifer, Liu, Mia, Hoang, Duc, Kreinar, Edward, Wu, Zhenbin
Institutions: Fermi National Accelerator Laboratory, Columbia University, Massachusetts Institute of Technology, University of Illinois Chicago, Northwestern University, European Organization for Nuclear Research, University of California San Diego, University of Washington, California Institute of Technology, Purdue University West Lafayette, Rhodes College
Language: English
Subfield: Hardware and Architecture
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Awards: G2445786185, G2926102538, G434337789, G4404904460, G4582951547, G498139845, G5616713406, SHF : Medium : Collaborative Research: Decentralized On-Chip Infrastructure for Robustness and Portability in Heterogeneous Multicores, G585908603, G716412294, G7203148941, REAL-TIME ARTIFICIAL INTELLIGENCE FOR PARTICLE RECONSTRUCTION AND HIGGS PHYSICS, REAL-TIME ARTIFICIAL INTELLIGENCE FOR PARTICLE RECONSTRUCTION AND HIGGS PHYSICS, G86560745, G969889393
OpenAlex ID: W3129272413