Files and links (1)
SubmittedOpen Access (License Unspecified), Open
Conference proceeding
Automated Generation of Integrated Digital and Spiking Neuromorphic Machine Learning Accelerators
2021 IEEE/ACM International Conference On Computer Aided Design (ICCAD), 21545110
01 Nov 2021
Abstract
The growing numbers of application areas for artificial intelligence (AI) methods have led to an explosion in availability of domain-specific accelerators, which struggle to support every new machine learning (ML) algorithm advancement, clearly highlighting the need for a tool to quickly and automatically transition from algorithm definition to hardware implementation and explore the design space along a variety of SWaP (size, weight and Power) metrics. The software defined architectures (SODA) synthesizer implements a modular compiler-based infrastructure for the end-to-end generation of machine learning accelerators, from high-level frameworks to hardware description language. Neuromorphic computing, mimicking how the brain operates, promises to perform artificial intelligence tasks at efficiencies orders-of-magnitude higher than the current conventional tensor-processing based accelerators, as demonstrated by a variety of specialized designs leveraging Spiking Neural Networks (SNNs). Nevertheless, the mapping of an artificial neural network (ANN) to solutions supporting SNNs is still a non-trivial and very device-specific task, and completely lacks the possibility to design hybrid systems that integrate conventional and spiking neural models. In this paper, we discuss the design of such an integrated generator, leveraging the SODA Synthesizer framework and its modular structure. In particular, we present a new MLIR dialect in the SODA frontend that allows expressing spiking neural network concepts (e.g., spiking sequences, transformation, and manipulation) and we discuss how to enable the mapping of spiking neurons to the related specialized hardware (which could be generated through middle-end and backend layers of the SODA Synthesizer). We then discuss the opportunities for further integration offered by the hardware compilation infrastructure, providing a path towards the generation of complex hybrid artificial intelligence systems.
Metrics
Details
- Title
- Automated Generation of Integrated Digital and Spiking Neuromorphic Machine Learning Accelerators
- Creators
- Serena Curzel - Pacific Northwest National LaboratoryNicolas Bohm Agostini - Pacific Northwest National LaboratoryShihao Song - Drexel UniversityIsmet Dagli - Pacific Northwest National LaboratoryAnkur Limaye - Pacific Northwest National LaboratoryCheng Tan - Pacific Northwest National LaboratoryMarco Minutoli - Pacific Northwest National LaboratoryVito Giovanni Castellana - Pacific Northwest National LaboratoryVinay Amatya - Pacific Northwest National LaboratoryJoseph Manzano - Pacific Northwest National LaboratoryAnup Das - Drexel UniversityFabrizio Ferrandi - Politecnico di MilanoAntonino Tumeo - Pacific Northwest National Laboratory
- Publication Details
- 2021 IEEE/ACM International Conference On Computer Aided Design (ICCAD), 21545110
- Conference
- 2021 IEEE/ACM International Conference On Computer Aided Design (ICCAD) (Munich, Germany, 01 Nov 2021–04 Nov 2021)
- Series
- ICCAD-IEEE ACM International Conference on Computer-Aided Design
- Publisher
- IEEE
- Number of pages
- 7
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- Electrical and Computer Engineering
- Web of Science ID
- WOS:000747493600040
- Scopus ID
- 2-s2.0-85117750915
- Other Identifier
- 991019238706504721
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Collaboration types
- Domestic collaboration
- International collaboration
- Web of Science research areas
- Engineering, Manufacturing