Deep Mapper: A Multi-Channel Single-Cycle Near-Sensor DNN Accelerator
Document Type
Conference Proceeding
Publication Date
1-1-2023
Abstract
This work proposes the Deep Mapper, as a new near-sensor resistive accelerator architecture for Deep Neural Networks (DNN) inference that co-integrates the sensing and computing phases of resource-constrained edge devices. Deep Mapper is developed to intrinsically realize highly parallelized multi-channel processing of input frames supported by a new dense hardware-friendly mapping methodology. Our circuit-to-application simulation results on the DNN acceleration task show that Deep Mapper reaches an efficiency of 4.71 TOp/s/W outperforming state-of-the-art near-/in-sensor accelerators.
Identifier
85184829382 (Scopus)
ISBN
[9798350382044]
Publication Title
2023 IEEE International Conference on Rebooting Computing Icrc 2023
External Full Text Location
https://doi.org/10.1109/ICRC60800.2023.10386958
Grant
2216772
Fund Ref
National Science Foundation
Recommended Citation
Morsali, Mehrdad; Tabrizchi, Sepehr; Liehr, Maximilian; Cady, Nathaniel; Imani, Mohsen; Roohi, Arman; and Angizi, Shaahin, "Deep Mapper: A Multi-Channel Single-Cycle Near-Sensor DNN Accelerator" (2023). Faculty Publications. 2383.
https://digitalcommons.njit.edu/fac_pubs/2383