Cache-Like Dual-Port SOT-MRAM with Read-while-Write Access Strategy

Spin-orbit torque magnetic random-access memory (SOT-MRAM) attracts considerable attention for its cache-like access speed, low energy consumption, and separated read and write paths. The paper proposes a read-while-write (RWW) scheme for a dual-port SOT-MRAM to enable simultaneous read-write operations. We utilize the write voltage division on the track layer to enable 71-fJ read operation while writing in the identical bit-cell. This approach minimizes the impact of write delays on system performance and significantly enhances throughput. Simulation results conducted on an industrial 40-nm CMOS process, demonstrate a throughput improvement of over $60 \%$ in the operational mode of alternate 5-ns write and 3-ns read functionality. Assisting with write verification, the RWW scheme achieves $39 \%$ energy saving in repeated writing, as well as 98.9% access yield.

Authors

Institutions

Publication Details

Published
2024-10-25
DOI
https://doi.org/10.1109/icta64028.2024.10860292
Citations
1
Primary Topic
Advanced Memory and Neural Computing
Type
article
Field-Weighted Citation Impact
0.21

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Cache-Like Dual-Port SOT-MRAM with Read-while-Write Access Strategy

Keyang Zhang, Hao Cai, Bo Liu
1 citations
Advanced Memory and Neural Computing
0.21
article

Cache-Like Dual-Port SOT-MRAM with Read-while-Write Access Strategy

Keyang Zhang, Hao Cai, Bo Liu
article en
1 citations

Abstract

Spin-orbit torque magnetic random-access memory (SOT-MRAM) attracts considerable attention for its cache-like access speed, low energy consumption, and separated read and write paths. The paper proposes a read-while-write (RWW) scheme for a dual-port SOT-MRAM to enable simultaneous read-write operations. We utilize the write voltage division on the track layer to enable 71-fJ read operation while writing in the identical bit-cell. This approach minimizes the impact of write delays on system performance and significantly enhances throughput. Simulation results conducted on an industrial 40-nm CMOS process, demonstrate a throughput improvement of over $60 \%$ in the operational mode of alternate 5-ns write and 3-ns read functionality. Assisting with write verification, the RWW scheme achieves $39 \%$ energy saving in repeated writing, as well as 98.9% access yield.

Southeast University (CN)
National Natural Science Foundation of China, Natural Science Foundation of Jiangsu Province
Openalex Percentile: Top 44%
Advanced Memory and Neural Computing
0.21
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.

Cache-Like Dual-Port SOT-MRAM with Read-while-Write Access Strategy — Keyang Zhang, Hao Cai, et al. · (2024) | TGRS Research Map | TGRS