A 481pJ/decision 3.4M decision/s Multifunctional Deep In-memory Inference Processor using Standard 6T SRAM Array

10/24/2016
by   Mingu Kang, et al.
0

This paper describes a multi-functional deep in-memory processor for inference applications. Deep in-memory processing is achieved by embedding pitch-matched low-SNR analog processing into a standard 6T 16KB SRAM array in 65 nm CMOS. Four applications are demonstrated. The prototype achieves up to 5.6X (9.7X estimated for multi-bank scenario) energy savings with negligible (<1 conventional architecture.

READ FULL TEXT

page 6

page 12

research
07/22/2016

Novel Graph Processor Architecture, Prototype System, and Results

Graph algorithms are increasingly used in applications that exploit larg...
research
04/13/2021

An Adaptive Synaptic Array using Fowler-Nordheim Dynamic Analog Memory

In this paper we present a synaptic array that uses dynamical states to ...
research
07/16/2022

MAC-DO: Charge Based Multi-Bit Analog In-Memory Accelerator Compatible with DRAM Using Output Stationary Mapping

Deep neural networks (DNN) have been proved for its effectiveness in var...
research
06/02/2020

AnalogNet: Convolutional Neural Network Inference on Analog Focal Plane Sensor Processors

We present a high-speed, energy-efficient Convolutional Neural Network (...
research
03/17/2017

Chaotic-Based Processor for Communication and Multimedia Applications

Chaos is a phenomenon that attracted much attention in the past ten year...
research
09/11/2021

Implementing Parallel Quick Sort Algorithm on OTIS Hyper Hexa-Cell (OHHC) Interconnection Network

This work explores the characteristics of implementing parallel Quick So...
research
03/22/2021

hep_tables: Heterogeneous Array Programming for HEP

Array operations are one of the most concise ways of expressing common f...

Please sign up or login with your details

Forgot password? Click here to reset