VCMA — Volumetric Compute-Memory Architecture: A Stateful Hierarchical Three-Dimensional Compute-in-Memory Architecture

VCMA (Volumetric Compute-Memory Architecture) is a proposed three-dimensional compute-in-memory architecture in which persistent memory, local computation, hierarchical state representation, and vertical communication are treated as components of a unified computational volume. The work defines the architecture, separates its proposed contributions from existing CIM/PIM and 3D-integration prior art, derives latency, energy, data-movement and thermal models, and specifies falsifiable predictions and a minimal experimental demonstrator. Performance superiority over existing GPU, HBM, or CIM systems is not assumed and remains subject to experimental validation.

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-10-05
DOI
https://doi.org/10.5281/zenodo.23164618
Primary Topic
Parallel Computing and Optimization Techniques
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
preprint

VCMA — Volumetric Compute-Memory Architecture: A Stateful Hierarchical Three-Dimensional Compute-in-Memory Architecture

Oleksandr Kudriavtsev
Zenodo (CERN European Organization for Nuclear Research)
Parallel Computing and Optimization Techniques
preprint

VCMA — Volumetric Compute-Memory Architecture: A Stateful Hierarchical Three-Dimensional Compute-in-Memory Architecture

Oleksandr Kudriavtsev
preprint en

Abstract

VCMA (Volumetric Compute-Memory Architecture) is a proposed three-dimensional compute-in-memory architecture in which persistent memory, local computation, hierarchical state representation, and vertical communication are treated as components of a unified computational volume. The work defines the architecture, separates its proposed contributions from existing CIM/PIM and 3D-integration prior art, derives latency, energy, data-movement and thermal models, and specifies falsifiable predictions and a minimal experimental demonstrator. Performance superiority over existing GPU, HBM, or CIM systems is not assumed and remains subject to experimental validation.

Zenodo (CERN European Organization for Nuclear Research)
Parallel Computing and Optimization Techniques
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.