Associative clustering with analog content-addressable memory

International Symposium on Memory Systems (MEMSYS), pp. 84–93

Abstract

Similarity search forms the backbone of many clustering algorithms, requiring repeated access to large datasets in memory. In traditional von Neumann architectures, the physical separation between memory and compute units introduces significant data-movement overhead, limiting the scalability of large-scale similarity search. Content Addressable Memories (CAMs) overcome this bottleneck through parallel in-memory search, with analog CAMs further mitigating analog-to-digital conversions overhead by operating directly in the analog domain.

Authors 3

1. Sara Ameli

   Forschungszentrum Jülich

   Affiliation as printed

   Forschungszentrum Jülich GmbH, PGI-14, Jülich, Germany

2. Jiaao Yu

   Forschungszentrum Jülich

   Affiliation as printed

   Forschungszentrum Jülich GmbH, PGI-14, Jülich, Germany

3. John Paul Strachan Aachen

   RWTH Aachen University · Forschungszentrum Jülich

   Affiliation as printed

   Forschungszentrum Jülich GmbH, PGI-14, Jülich, Germany and RWTH Aachen University, Aachen, Germany