Gokul VG

dblp:429/1704 · DBLP profile ↗
← Back
1ranked-venue papers
0as first author
1since 2021 · last 2026
0009-0005-3278-7762ORCID · reported

Domains — the database's venue-derived domains; a paper can count in several

Systems, architecture and hardware · 1 · 1 since 2021

Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.

Computer architecture, parallel and distributed computing, and storage systems
1 paper
Integrated circuit design · 56% Memory systems · 44%

Topics — the 2 heaviest of 3, each with the papers that count most for it

TopicWeightPapersLastEvidence papers
Memory systems › processing-in-memory
logic-in-memory
1.012026
Self-SHE Pulse-Enabled 2-D Material-Based SOT-MTJ: A Scalable and Energy-Efficient Write Circuit for LiM Architectures · IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. 2026
Integrated circuit design
low-power circuit design
0.312026
Self-SHE Pulse-Enabled 2-D Material-Based SOT-MTJ: A Scalable and Energy-Efficient Write Circuit for LiM Architectures · IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. 2026

Methods — techniques the papers use, named apart from their topics

verilog-a modeling · 1.0monte carlo simulation · 1.0
YearPublicationVenuePosition
2026 Self-SHE Pulse-Enabled 2-D Material-Based SOT-MTJ: A Scalable and Energy-Efficient Write Circuit for LiM Architectures
abstract
Spin-orbit torque magnetic tunnel junction (SOT-MTJ) devices have gained significant attention for energy-efficient computing, particularly in Logic-in-Memory (LiM) architectures. However, conventional SOT-MTJ-based write circuits suffer from excessive power dissipation due to the reliance on externally generated Spin Hall Effect (SHE) pulses, necessitating complex synchronization and additional circuit overhead. This work introduces a novel self-SHE pulse generation technique that eliminates the need for an external SHE pulse, simplifying the circuit design and significantly reducing energy consumption. Furthermore, the proposed design leverages 2D material-based SOT-MTJs, which exhibit superior charge-to-spin conversion efficiency, thereby enhancing write performance. The proposed write circuit is integrated into a 1-bit Arithmetic Logic Unit (ALU), which is further extended to a 4-bit ALU to demonstrate scalability in LiM applications. Simulation results using 45nm CMOS technology and Verilog-A models for 2D SOT-MTJs indicate that the proposed write circuit achieves a 16.049% improvement in area efficiency and a 20.72% reduction in energy consumption compared to conventional SHE-assisted SOT-MTJ write circuits. Additionally, the full adder incorporating the proposed write circuit demonstrates a 25.2% improvement in energy efficiency over existing designs. Monte Carlo simulations validate the robustness of the proposed approach under variations in oxide layer and free layer thickness. By eliminating external SHE pulse requirements and utilizing 2D SOT-MTJ technology, this work presents a significant advancement towards low-power, high-speed, and scalable spintronic computing architectures, making it a strong candidate for next-generation LiM-based processors.
Shashidhara M, Gokul VG, Shobhit Srivatsava, Sourabh Panwar, Abhishek Acharya
IEEE Trans. Comput. Aided Des. Integr. Circuits Syst.2