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

Analog computing has been recognized as a promising low-power alternative todigital counterparts for neural network acceleration. However, conventionalanalog computing is mainly in a mixed-signal manner. Tedious analog/digital(A/D) conversion cost significantly limits the overall system's energyefficiency. In this work, we devise an efficient analog activation unit withmagnetic tunnel junction (MTJ)-based analog content-addressable memory (MACAM),simultaneously realizing nonlinear activation and A/D conversion in a fusedfashion. To compensate for the nascent and therefore currently limitedrepresentation capability of MACAM, we propose to mix our analog activationunit with digital activation dataflow. A fully differential framework,SuperMixer, is developed to search for an optimized activation workloadassignment, adaptive to various activation energy constraints. Theeffectiveness of our proposed methods is evaluated on a silicon photonicaccelerator. Compared to standard activation implementation, our mixedactivation system with the searched assignment can achieve competitive accuracywith $>$60% energy saving on A/D conversion and activation.

Fuse and Mix: MACAM-Enabled Analog Activation for Energy-Efficient Neural Acceleration