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

Rapid advancements in artificial intelligence have given rise totransformative models, profoundly impacting our lives. These models demandmassive volumes of data to operate effectively, exacerbating the data-transferbottleneck inherent in the conventional von-Neumann architecture.Compute-in-memory (CIM), a novel computing paradigm, tackles these issues byseamlessly embedding in-memory search functions, thereby obviating the need fordata transfers. However, existing non-volatile memory (NVM)-based acceleratorsare application specific. During the similarity based associative searchoperation, they only support a single, specific distance metric, such asHamming, Manhattan, or Euclidean distance in measuring the query against thestored data, calling for reconfigurable in-memory solutions adaptable tovarious applications. To overcome such a limitation, in this paper, we presentFeReX, a reconfigurable associative memory (AM) that accommodates variousdistance metrics including Hamming, Manhattan, and Euclidean distances.Leveraging multi-bit ferroelectric field-effect transistors (FeFETs) as theproxy and a hardware-software co-design approach, we introduce a constrainedsatisfaction problem (CSP)-based method to automate AM search input voltage andstored voltage configurations for different distance based search functions.Device-circuit co-simulations first validate the effectiveness of the proposedFeReX methodology for reconfigurable search distance functions. Then, webenchmark FeReX in the context of k-nearest neighbor (KNN) and hyperdimensionalcomputing (HDC), which highlights the robustness of FeReX and demonstrates upto 250x speedup and 10^4 energy savings compared with GPU.

FeReX: A Reconfigurable Design of Multi-bit Ferroelectric Compute-in-Memory for Nearest Neighbor Search