huangjunying Goto Github PK

-approximate-computing-techniques-for-deep-neural-networks-

Approximate computing technique is very much useful for improving efficiency (approx double) and reducing energy consumption. We will be using different adders and multipliers for this purpose and comparing their energy consumption and accuracy. And we have implemented it on Field Programmable Gate Array (FPGA) and ZEDBoard.

accdnn

A compiler from AI model to RTL (Verilog) accelerator in FPGA hardware with auto design space exploration.

accelergy

Accelergy is an energy estimation infrastructure for accelerator energy estimations

blockchain-demo

A web-based demonstration of blockchain concepts.

bnn

HLS code for a BNN accelerator

clacc

Deep Learning Accelerator (Convolution Neural Networks)

cnn_open

A hardware implementation of CNN, written by Verilog and synthesized on FPGA

combinational-bnn

System Verilog code describing a fully combinational binarized neural network.

cores

Various HDL (Verilog) IP Cores

cryocore

Cryogenic Computer Modeling and Architecture Development

dabnn

dabnn is an accelerated binary neural networks inference framework for mobile platform

debam_decoder_based_approximate_multiplier

DeBAM : Decoder Based Approximate multiplier for Low Power Applications

dfa-aes

C implementation of Differential Fault Analysis on AES

die2sim

Die2Sim is a tool used to aid simulations of large scale superconducting circuits. The main usage of the tool is to create JoSIM files from LEF/DEF files using an existing cell library.

dreamplace

Deep learning toolkit-enabled VLSI placement

finn

Dataflow compiler for QNN inference on FPGAs

finn_matrixvector_rtl

Repository for work on on Xilinx's matrix vector activation unit's RTL implementation. Documentation available at: https://asadalam.github.io/FINN_MatrixVector_RTL/

flush-reload-attacks

freepdk-45nm

ASIC Design Kit for FreePDK45 + Nangate for use with mflowgen

gdscpp

C++ library to create and read GDSII file

graywolf

larq

An Open-Source Library for Training Binarized Neural Networks

mitmojco

MiTMoJCo (Microscopic Tunneling Model for Josephson Contacts) is C and Python code for simulating dynamics of superconducting Josephson junctions using Werthamer's microscopic tunneling theory

mnist_recognition_qt

MLP written on cpp and trained on MNIST dataset.

modeling_of_apuf_compositions

Python Code and Dataset for different PUFs

mult_booth_app

Approximate Booth Multiplier

neta

nextpnr

nextpnr portable FPGA place and route tool

nextpnr-lsp

openabc

OpenABC-D is a large-scale labeled dataset generated by synthesizing open source hardware IPs. This dataset can be used for various graph level prediction problems in chip design.