[HTML][HTML] 近似计算新范式在深度学习加速系统中的应用及研究进展
龚宇, 王丽萍, 王佑, 刘伟强 - 电子与信息学报, 2023 - jeit.ac.cn
深度学习已经成为当前人工智能技术中最为重要的算法之一. 随着应用场景不断扩展,
深度学习硬件规模越来越大, 计算复杂度呈现数量级提升趋势, 对加速系统提出了极高能效需求 …
深度学习硬件规模越来越大, 计算复杂度呈现数量级提升趋势, 对加速系统提出了极高能效需求 …
Design and Comparison of Low Power Consumption Binary and Quaternary Multipliers
DS Shylu Sam, P Sam Paul… - National Academy …, 2024 - Springer
There is a rapid growth in semiconductor technology as the need for digital application
systems has increased. Arithmetic operations such as addition and multiplication play a …
systems has increased. Arithmetic operations such as addition and multiplication play a …
Design of Low Power Pass Transistor Logic Based Adders for Multiplier in 90nm CMOS Process
The goal of this work is to design a half adder circuit for a multiplier with the considerations
of low power dissipation and area reduction under the supply voltage of 1V. The novelty that …
of low power dissipation and area reduction under the supply voltage of 1V. The novelty that …
Verification of UART using AHB VIP with Maximum Coverage
Universal Asynchronous Receiver Transmitter is a serial communication protocol that helps
in communicating data between devices. The verification of UART is important to eliminate …
in communicating data between devices. The verification of UART is important to eliminate …
Random Pattern Generation and Redundancy Analysis in Memories
KB Anudeep, DJ Jagannath, S Radha… - 2022 IEEE 11th …, 2022 - ieeexplore.ieee.org
Designing a memory is a challenge by itself as the storage and fault occurrence is quite
common in memories. Hence, fault occurrence and fault detection, corrections are major …
common in memories. Hence, fault occurrence and fault detection, corrections are major …
Design techniques in Carry Select Adder using Parallel prefix adder for improved switching energy.
A new architecture of Carry select adder has been proposed with improved switching energy
using parallel prefix adder. The conventional Carry select adder is the use of two Ripple …
using parallel prefix adder. The conventional Carry select adder is the use of two Ripple …
[HTML][HTML] Application and Research Progress of Approximate Computing as a New Computing Paradigm in AI Acceleration Systems
G Yu, W Liping, W You, LIU Weiqiang - 电子与信息学报, 2023 - jeit.ac.cn
Deep learning has emerged as one of the most important algorithms in artificial intelligence.
With the increasing application scenarios, the hardware scales for deep learning are …
With the increasing application scenarios, the hardware scales for deep learning are …
[PDF][PDF] Design techniques in carry select adder using parallel prefix adder for improved switching energy
SAM Shylu, S PAUL, DJ JINGLE, M PAUL… - 2021 - pe.org.pl
A new architecture of Carry select adder has been proposed with improved switching energy
using parallel prefix adder. The conventional Carry select adder is the use of two Ripple …
using parallel prefix adder. The conventional Carry select adder is the use of two Ripple …
An Improved Design of Absolute-value Detector by Using Optimized Ripple Adder
J Yang - Journal of Physics: Conference Series, 2023 - iopscience.iop.org
Absolute-value detector (AVD) is one of the most basic bit-operating devices, which
compares the magnitude of two inputs. However, the traditional 4-bit AVD is not only time …
compares the magnitude of two inputs. However, the traditional 4-bit AVD is not only time …
Approximate Computing for Energy-Constrained DNN-Based Speech Recognition
B Liu, H Cai, Z Wang, J Yang - Approximate Computing, 2012 - Springer
Approximate computing is continuously emerging as an energy-efficient design paradigm in
Internet-of-things scenario. In deep neural network (DNN)-based speech recognition system …
Internet-of-things scenario. In deep neural network (DNN)-based speech recognition system …