Thermal-Aware Compilation of Spiking Neural Networks to Neuromorphic Hardware
Twisha Titirsha, Anup Das

TL;DR
This paper introduces a thermal-aware mapping technique for spiking neural networks on neuromorphic hardware, significantly reducing temperature gradients and energy consumption by incorporating a detailed thermal model into the mapping process.
Contribution
It presents a novel thermal model for neuromorphic crossbars and integrates it into a neuron-synapse mapping heuristic to optimize thermal and energy efficiency.
Findings
Average temperature reduction of 11.4K per crossbar
52% decrease in leakage power consumption
11% lower total energy consumption
Abstract
Hardware implementation of neuromorphic computing can significantly improve performance and energy efficiency of machine learning tasks implemented with spiking neural networks (SNNs), making these hardware platforms particularly suitable for embedded systems and other energy-constrained environments. We observe that the long bitlines and wordlines in a crossbar of the hardware create significant current variations when propagating spikes through its synaptic elements, which are typically designed with non-volatile memory (NVM). Such current variations create a thermal gradient within each crossbar of the hardware, depending on the machine learning workload and the mapping of neurons and synapses of the workload to these crossbars. \mr{This thermal gradient becomes significant at scaled technology nodes and it increases the leakage power in the hardware leading to an increase in the…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Memory and Neural Computing · Ferroelectric and Negative Capacitance Devices · Neural Networks and Reservoir Computing
