[HTML][HTML] Toolflow for the algorithm-hardware co-design of memristive ANN accelerators
The capabilities of artificial neural networks are rapidly evolving, so are the expectations for
them to solve ever more challenging tasks in numerous everyday situations. Larger, more …
them to solve ever more challenging tasks in numerous everyday situations. Larger, more …
An energy efficient all-digital time-domain compute-in-memory macro optimized for binary neural networks
The deployment of neural networks on edge devices has created a growing need for energy-
efficient computing. In this paper, we propose an all-digital standard cell-based time-domain …
efficient computing. In this paper, we propose an all-digital standard cell-based time-domain …
CLARINET: A quire-enabled RISC-V-based framework for posit arithmetic empiricism
Many applications require high-precision arithmetic. IEEE 754-2019 compliant (floating-
point) arithmetic is the de facto standard for performing these computations. Recently, posit …
point) arithmetic is the de facto standard for performing these computations. Recently, posit …
Scalable time-domain compute-in-memory BNN engine with 2.06 POPS/W energy efficiency for edge-AI devices
Time-domain (TD) computing has attracted attention for its high computing efficiency and
suitability for applications on energy-constrained edge devices. In this paper, we present a …
suitability for applications on energy-constrained edge devices. In this paper, we present a …
Memristive devices for time domain compute-in-memory
Analog compute schemes and compute-in-memory (CIM) have emerged in an effort to
reduce the increasing power hunger of convolutional neural networks (CNNs), which …
reduce the increasing power hunger of convolutional neural networks (CNNs), which …
[PDF][PDF] Memories-Materials, Devices, Circuits and Systems
M Wabnitz, T Gemmeke - publications.rwth-aachen.de
The capabilities of artificial neural networks are rapidly evolving, so are the expectations for
them to solve ever more challenging tasks in numerous everyday situations. Larger, more …
them to solve ever more challenging tasks in numerous everyday situations. Larger, more …
Energy Efficient Time Domain Sram Based Compute In-Memory Architecture Using 8t1c
In this paper, we present an area and energy-efficient TDCIM for BNNs, based on SRAM
memory architecture. The proposed architecture improves the energy efficiency of MAC and …
memory architecture. The proposed architecture improves the energy efficiency of MAC and …
[引用][C] Implementation of Energy Efficient Approximate Computing via Recursive Multiplier in Error Tolerant Applications
M Karthikkumar, R Kalaivani - Journal of Circuits, Systems and …, 2024 - World Scientific
Approximate computing (AC) in arithmetic logic has become a viable option in applications
requiring error tolerance in energy-efficient architectures. AC relied on approximate …
requiring error tolerance in energy-efficient architectures. AC relied on approximate …