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

When arranged in a crossbar configuration, resistive memory devices can beused to execute MVM, the most dominant operation of many ML algorithms, inconstant time complexity. Nonetheless, when performing computations in theanalog domain, novel challenges are introduced in terms of arithmetic precisionand stochasticity, due to non-ideal circuit and device behaviour. Moreover,these non-idealities have a temporal dimension, resulting in a degradingapplication accuracy over time. Facing these challenges, we propose a novelframework, named LionHeart, to obtain hybrid analog-digital mappings to executeDL inference workloads using heterogeneous accelerators. Theaccuracy-constrained mappings derived by LionHeart showcase, across differentDNNs and datasets, high accuracy and potential for speedup. The results of thefull system simulations highlight run-time reductions and energy efficiencygains that exceed 6X, with a user-defined accuracy threshold with respect to afully digital floating point implementation.

LionHeart: A Layer-based Mapping Framework for Heterogeneous Systems with Analog In-Memory Computing Tiles