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

In-memory computing (IMC) with non-volatile memories (NVMs) has emerged as apromising approach to address the rapidly growing computational demands of DeepNeural Networks (DNNs). Mapping DNN layers spatially onto NVM-based IMCaccelerators achieves high degrees of parallelism. However, two challenges thatarise in this approach are the highly non-uniform distribution of layerprocessing times and high area requirements. We propose LRMP, a method tojointly apply layer replication and mixed precision quantization to improve theperformance of DNNs when mapped to area-constrained NVM-based IMC accelerators.LRMP uses a combination of reinforcement learning and integer linearprogramming to search the replication-quantization design space using a modelthat is closely informed by the target hardware architecture. Across five DNNbenchmarks, LRMP achieves 2.8-9$\times$ latency and 11.8-19$\times$ throughputimprovement at iso-accuracy.

LRMP: Layer Replication with Mixed Precision for Spatial In-memory DNN Accelerators