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.