Automated HW/SW co-design for edge AI: State, challenges and steps ahead

O Bringmann, W Ecker, I Feldner… - Proceedings of the …, 2021 - dl.acm.org
Gigantic rates of data production in the era of Big Data, Internet of Thing (IoT), and Smart
Cyber Physical Systems (CPS) pose incessantly escalating demands for massive data …

New Systolic Array Algorithms and VLSI Architectures for 1-D MDST

DF Chiper, A Cracan - Sensors, 2023 - mdpi.com
In this paper, we present two systolic array algorithms for efficient Very-Large-Scale
Integration (VLSI) implementations of the 1-D Modified Discrete Sine Transform (MDST) …

Parameterized computing module generator based on a systolic array

VV Zunin, II Romanova - 2022 IEEE International Conference …, 2022 - ieeexplore.ieee.org
In this paper, the use of systolic arrays for data processing in the training or executing neural
networks is explored. Two types of systolic arrays were developed, and a comparison on …

FPGA-based optical character recognition for handwritten mathematical expressions

BW Yogatama, J Lee, S Harimurti… - 2018 International SoC …, 2018 - ieeexplore.ieee.org
This paper presents the hardware design of optical character recognition for handwritten
mathematical expressions using field programmable gate array (FPGA). The OCR is based …

Design of Quantized Deep Neural Network Hardware Inference Accelerator Using Systolic Architecture

DM Rifqie, YA Djawad, FA Samman… - Journal of Applied …, 2024 - qemsjournal.org
This paper presents a hardware inference accelerator architecture of quantized deep neural
networks (DNN). The proposed accelerator implements all computation in a quantize …

HW-Acceleration for Edge-AI

SS Prebeck - 2024 - mediatum.ub.tum.de
This thesis addresses the platform gap between embedded microcontroller and cloud
computing for neural network inferences on the Edge with a combined HW-SW-AI solution. A …