Survey of Novel Architectures for Energy Efficient High-Performance Mobile Computing Platforms
There are many real-world applications that require high-performance mobile computing
systems for onboard, real-time processing of gathered data due to latency, reliability …
systems for onboard, real-time processing of gathered data due to latency, reliability …
Toward energy-efficient sparse matrix-vector multiplication with near STT-MRAM computing architecture
Sparse Matrix-Vector Multiplication (SpMV) is one of the vital computational primitives used
in modern workloads. SpMV performs memory access, leading to unnecessary data …
in modern workloads. SpMV performs memory access, leading to unnecessary data …
Computing in-memory with cascaded spintronic devices for AI edge
Spin-transfer-torque magnetic random access memory (STT-MRAM) shows great
advantages for computing in-memory (CIM), which has emerged as a popular research …
advantages for computing in-memory (CIM), which has emerged as a popular research …
A CFMB STT-MRAM-Based Computing-in-Memory Proposal With Cascade Computing Unit for Edge AI Devices
Y Zhou, Z Zhou, Y Wei, Z Yang, X Lin… - … on Circuits and …, 2023 - ieeexplore.ieee.org
The application of non-volatile memory technology is increasingly attractive for Computing-
in-memory (CIM) owing to high integration density and negligible standby power …
in-memory (CIM) owing to high integration density and negligible standby power …
RSACIM: Resistance Summation Analog Computing in Memory With Accuracy Optimization Scheme Based on MRAM
J Wang, Z Gu, B Zhang, Y Chen, Z Wang… - … on Circuits and …, 2023 - ieeexplore.ieee.org
Computing in memory (CIM) has become a promising candidate to address the Von
Neumann bottleneck in processors designed for data-intensive applications. In this article …
Neumann bottleneck in processors designed for data-intensive applications. In this article …
PipeCIM: A High-Throughput Computing-In-Memory Microprocessor With Nested Pipeline and RISC-V Extended Instructions
T Chen, W Wang, J Chen, H Fu, W Yi… - … on Circuits and …, 2024 - ieeexplore.ieee.org
The large number of multiply accumulate (MAC) operations in Convolutional Neural Network
(CNN) leads to substantial data migration and computation. Although computing-in-memory …
(CNN) leads to substantial data migration and computation. Although computing-in-memory …
A reconfigurable spatial architecture for energy-efficient inception neural networks
Convolutional neural networks (CNNs) have been widely utilized in modern artificial
intelligent (AI) systems. In particular, GoogLeNet, one of the most popular CNNs, consisting …
intelligent (AI) systems. In particular, GoogLeNet, one of the most popular CNNs, consisting …
RDCIM: RISC-V Supported Full-Digital Computing-in-Memory Processor With High Energy Efficiency and Low Area Overhead
W Yi, K Mo, W Wang, Y Zhou, Y Zeng… - … on Circuits and …, 2024 - ieeexplore.ieee.org
Digital computing-in-memory (DCIM) that merges computing logic into memory has been
proven to be an efficient architecture for accelerating multiply-and-accumulates (MACs) …
proven to be an efficient architecture for accelerating multiply-and-accumulates (MACs) …
BFP-CIM: Runtime Energy-Accuracy Scalable Computing-in-Memory-Based DNN Accelerator Using Dynamic Block-Floating-Point Arithmetic
Convolutional neural networks (CNNs) are known for their exceptional performance in
various applications; however, their energy consumption during inference can be …
various applications; however, their energy consumption during inference can be …
2-D Analytical Modeling of the Magnetic Tunnel Junctions Including Multidomain Effects: Predictive Insights and Design Optimization
This article presents a comprehensive 2-D analytical model for magnetic tunnel junctions
(MTJs), encompassing the multidomain effect. Utilizing Green's function approach, it derives …
(MTJs), encompassing the multidomain effect. Utilizing Green's function approach, it derives …