m-Zephyr: A Digital In-Memory Ising Chip with 240 Spins Featuring Enhanced Connectivity Based on a Modified 3D Zephyr Topology

We present a digital in-memory Ising computing chip with a modified 3D Zephyr topology implemented using a 65nm CMOS technology. This design features cross-dimensional connectivity with 24 interactions per spin for the efficient mapping of complex combinatorial optimization problems to the Ising hardware. The proposed Ising chip with enhanced spin connectivity outperforms prior works in terms of reconfigurability, allowing the Ising chip to solve more difficult problems with complicated topologies and higher dimensions, but minimizing hardware mapping overhead. <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$24\times 7$</tex> -bit precision coefficients are stored in memory and used to compute spin interactions, minimizing energy consumption and computing latency while ensuring accuracy with fully digital and high precision computing. Measured results show <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$&gt; 100\times$</tex> speedup than the baseline algorithm while finding better optimal solutions with lower Mean Ising Hamiltonian values.

Authors

Institutions

Publication Details

Published
2025-06-08
DOI
https://doi.org/10.23919/vlsitechnologyandcir65189.2025.11075071
Citations
1
Primary Topic
Quantum Computing Algorithms and Architecture
Type
article
Field-Weighted Citation Impact
2.48
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

m-Zephyr: A Digital In-Memory Ising Chip with 240 Spins Featuring Enhanced Connectivity Based on a Modified 3D Zephyr Topology

Bongjin Kim, Jooyoung Bae, Yihao Wu, Chaeyun Shim
1 citations
Quantum Computing Algorithms and Architecture
2.48
article

m-Zephyr: A Digital In-Memory Ising Chip with 240 Spins Featuring Enhanced Connectivity Based on a Modified 3D Zephyr Topology

Bongjin Kim, Jooyoung Bae, Yihao Wu, Chaeyun Shim
article en
1 citations

Abstract

We present a digital in-memory Ising computing chip with a modified 3D Zephyr topology implemented using a 65nm CMOS technology. This design features cross-dimensional connectivity with 24 interactions per spin for the efficient mapping of complex combinatorial optimization problems to the Ising hardware. The proposed Ising chip with enhanced spin connectivity outperforms prior works in terms of reconfigurability, allowing the Ising chip to solve more difficult problems with complicated topologies and higher dimensions, but minimizing hardware mapping overhead. <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$24\times 7$</tex> -bit precision coefficients are stored in memory and used to compute spin interactions, minimizing energy consumption and computing latency while ensuring accuracy with fully digital and high precision computing. Measured results show <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$&gt; 100\times$</tex> speedup than the baseline algorithm while finding better optimal solutions with lower Mean Ising Hamiltonian values.

University of California, Santa Barbara (US), Korea Advanced Institute of Science and Technology (KR)
Affordable and clean energy
Openalex Percentile: Top 9%
Quantum Computing Algorithms and Architecture
2.48
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.