English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Neuromorphic computing systems are embracing memristors to implement highdensity and low power synaptic storage as crossbar arrays in hardware. Thesesystems are energy efficient in executing Spiking Neural Networks (SNNs). Weobserve that long bitlines and wordlines in a memristive crossbar are a majorsource of parasitic voltage drops, which create current asymmetry. Throughcircuit simulations, we show the significant endurance variation that resultsfrom this asymmetry. Therefore, if the critical memristors (ones with lowerendurance) are overutilized, they may lead to a reduction of the crossbar'slifetime. We propose eSpine, a novel technique to improve lifetime byincorporating the endurance variation within each crossbar in mapping machinelearning workloads, ensuring that synapses with higher activation are alwaysimplemented on memristors with higher endurance, and vice versa. eSpine worksin two steps. First, it uses the Kernighan-Lin Graph Partitioning algorithm topartition a workload into clusters of neurons and synapses, where each clustercan fit in a crossbar. Second, it uses an instance of Particle SwarmOptimization (PSO) to map clusters to tiles, where the placement of synapses ofa cluster to memristors of a crossbar is performed by analyzing theiractivation within the workload. We evaluate eSpine for a state-of-the-artneuromorphic hardware model with phase-change memory (PCM)-based memristors.Using 10 SNN workloads, we demonstrate a significant improvement in theeffective lifetime.

Endurance-Aware Mapping of Spiking Neural Networks to Neuromorphic Hardware