A high-performance hybrid memory architecture for embedded CMPs using a convex optimization model

Series

Abstract

In this article, we present a convex optimization model to design a stacked hybrid memory system for 3D embedded chip-multiprocessors (eCMP). Our convex model optimizes numbers and placement of SRAM and STT-RAM memories on the memory layer, and maps applications/threads on cores in the core layer effectively. The detailed proposed model satisfies the power constraint which is the main challenge of dark-silicon era. Experimental results show that the proposed architecture considerably improves the energy-delay product (EDP) and performance of the 3D eCMP compared to the Baseline memory design. © 2015 IEEE.

Source Title

ISOCC 2015 - International SoC Design Conference: SoC for Internet of Everything (IoE)

Publisher

IEEE

Course

Other identifiers

Book Title

Keywords

Convex-optimization, Embedded chip-multiprocessor (eCMP), Hybrid memory architecture, Non-volatile memory (NVM), Adaptive systems, Convex optimization, Data storage equipment, Design, Digital storage, Multiprocessing systems, Optimization, Product design, Programmable logic controllers, Random access storage, Static random access storage, Convex modeling, Embedded chips, Energy delay product, Memory design, Memory layers, Non-volatile memory, Power constraints, Proposed architectures, Memory architecture

Degree Discipline

Degree Level

Degree Name

Citation

Published Version (Please cite this version)

Language

English