Deepware

antares

Antares: an automatic engine for multi-platform kernel generation and optimization. Supporting CPU, CUDA, ROCm, DirectX12, GraphCore, SYCL for CPU/GPU, OpenCL for AMD/NVIDIA, Android CPU/GPU backends.

awesome-real-time-AI

This is a list of awesome edgeAI inference related papers.

TENNA

TENNA: Tiny Embedded Neural Network Accelerator

xla

A machine learning compiler for GPUs, CPUs, and ML accelerators

acceltran

[TCAD'23] AccelTran: A Sparsity-Aware Accelerator for Transformers

Awesome-Embeded-AI

收集关于嵌入式领域的机器学习算法实现的进展、相关论文和文章、开发库等，帮助初学者快速了解、学习和入门嵌入式领域的机器学习。CC-BY-NC-SA 4.0。

awesome-model-quantization

A list of papers, docs, codes about model quantization. This repo is aimed to provide the info for model quantization research, we are continuously improving the project. Welcome to PR the works (papers, repositories) that are missed by the repo.

BARVINN

BARVINN: A Barrel RISC-V Neural Network Accelerator: https://barvinn.readthedocs.io/en/latest/

BlockMinifloatMAC

Block minifloat MAC unit for single block GEMM

braggHLS

PyTorch model to RTL flow for low latency inference

CHARM

CHARM: Composing Heterogeneous Accelerators for Matrix Multiply on Versal ACAP Architecture (Full Paper accepted to FPGA2023!)

fpga-snntorch-spike

Notebooks and code for Neuromorphic Hardware Workshop at ISFPGA 2024.

FusedGCN4HLS

Systolic Three Matrix Multiplier for Graph Convolutional Networks using High Level Synthesis

gamma

garnet

Next generation CGRA generator

halutmatmul

Hashed Lookup Table based Matrix Multiplication (halutmatmul) - Stella Nera accelerator

HiSparse

High-Performance Sparse Linear Algebra on HBM-Equipped FPGAs Using HLS

iob-versat

Coarse Grained Reconfigurable Array

Magicube

Magicube is a high-performance library for quantized sparse matrix operations (SpMM and SDDMM) of deep learning on Tensor Cores.

neureka

nitta

NITTA - Tool for Hard Real-Time CGRA Processors

nngen

NNgen: A Fully-Customizable Hardware Synthesis Compiler for Deep Neural Network

onnx-simplifier

Simplify your onnx model

qonnx

QONNX: Arbitrary-Precision Quantized Neural Networks in ONNX

redmule

RiscV_CPU_with_Accelerator

A RiscV CPU with an accelerator for accelerating neural networks attached to it

rknn-toolkit

RKNN from Rockchip

Sextans

An FPGA accelerator for general-purpose Sparse-Matrix Dense-Matrix Multiplication (SpMM).

SNN-DSE

Hardware and software implementation of Sparsely-active SNNs

SNNQuantPrune

The Hardware Impact of Quantization and Pruning for Weights in Spiking Neural Networks