FPGA Neural Accelerators ML Frameworks

Hardware implementations and design frameworks for neural network acceleration on FPGAs, including systolic arrays, HLS synthesis tools, and optimization for edge inference. Does NOT include general FPGA design, software ML frameworks, or CPU/GPU-based accelerators.

There are 54 fpga neural accelerators frameworks tracked. 3 score above 50 (established tier). The highest-rated is fastmachinelearning/hls4ml at 64/100 with 1,849 stars. 1 of the top 10 are actively maintained.

Get all 54 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=ml-frameworks&subcategory=fpga-neural-accelerators&limit=20"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

#	Framework	Score	Tier	Stars	Language
1	fastmachinelearning/hls4ml Machine learning on FPGAs using HLS	64	Established	1,849	Python
2	alibaba/TinyNeuralNetwork TinyNeuralNetwork is an efficient and easy-to-use deep learning model...	52	Established	873	Python
3	KULeuven-MICAS/zigzag HW Architecture-Mapping Design Space Exploration Framework for Deep Learning...	51	Established	186	C++
4	fastmachinelearning/hls4ml-tutorial Tutorial notebooks for hls4ml	49	Emerging	416	Jupyter Notebook
5	doonny/PipeCNN An OpenCL-based FPGA Accelerator for Convolutional Neural Networks	44	Emerging	1,367	C
6	es-ude/elastic-ai.creator Design, train and generate neural networks optimized specifically for FPGAs.	43	Emerging	22	Python
7	maestro-project/maestro An analytical cost model evaluating DNN mappings (dataflows and tiling).	42	Emerging	247	MATLAB
8	fengbintu/Neural-Networks-on-Silicon This is originally a collection of papers on neural network accelerators....	41	Emerging	2,068	—
9	embedeep/Free-TPU Free TPU for FPGA with compiler supporting Pytorch/Caffe/Darknet/NCNN. An AI...	41	Emerging	273	Shell
10	hughperkins/VeriGPU OpenSource GPU, in Verilog, loosely based on RISC-V ISA	39	Emerging	1,280	SystemVerilog
11	hunterlew/convolution_network_on_FPGA CNN acceleration on virtex-7 FPGA with verilog HDL	36	Emerging	475	Verilog
12	zssloth/Embedded-Neural-Network collection of works aiming at reducing model sizes or the ASIC/FPGA...	35	Emerging	568	—
13	walkieq/RNN_HLS An LSTM template and a few examples using Vivado HLS	35	Emerging	47	C
14	JunningWu/Learning-NVDLA-Notes NVDLA is an Open source DL/ML accelerator, which is very suitable for...	34	Emerging	232	—
15	yonseicasl/NPUsim NPUsim: Full-Model, Cycle-Level, and Value-Aware Simulator for DNN Accelerators	32	Emerging	50	C++
16	padhi499/Image-Classification-using-CNN-on-FPGA Project is about designing a Trained Neural Network on FPGA to classify an...	30	Emerging	164	Verilog
17	ribesstefano/Mapping-Multiple-LSTM-Models-on-FPGAs Includes the SVD-based approximation algorithms for compressing deep...	30	Emerging	16	Jupyter Notebook
18	IMPETUS-UdeS/rule4ml Resource Utilization and Latency Estimation for ML on FPGA.	30	Emerging	18	Python
19	salehjg/DeepPoint-V2-FPGA The code repository of DGCNN on FPGA: Acceleration of The Point Cloud...	28	Experimental	17	C++
20	hipersys-team/lightning [SIGCOMM 2023] Lightning: A Reconfigurable Photonic-Electronic SmartNIC for...	28	Experimental	44	Verilog
21	Thraetaona/Innervator Innervator: Hardware Acceleration for Neural Networks	27	Experimental	18	VHDL
22	Lumen-Laboratory/Mayoiuta Open-source Neural Processing Unit (NPU) from China ❤	27	Experimental	39	Verilog
23	yonseicasl/NPUWattch NPUWattch: ML-based Power, Area, and Timing Modeling for Neural Accelerators	26	Experimental	5	HCL
24	SalvatoreBarone/CNN-VHDL A library of VHDL components for Neural Networks	26	Experimental	21	C++
25	halalboro/fpga-accelerators Hardware Accelerators on FPGA for Computer Vision Applications	26	Experimental	12	C++
26	hftsoi/sparse-pixels Efficient convolution for sparse data on FPGAs	25	Experimental	4	C++
27	EngineeringSoftware/hdlp Code and data for "On the Naturalness of Hardware Descriptions" in ESEC/FSE'20	24	Experimental	2	Java
28	anupam-io/ES203-COA-CNN ES-203 Computer Organization & Architecture CNN on FPGA board	24	Experimental	17	Verilog
29	yifeng-ethz/mu3e-ip-cores Mu3e experiment (PSI) IP-core Library	24	Experimental	6	Smarty
30	GSTL-ITU/HORNET-RV32IMF-For-AI-Applications A custom RISC-V (RV32IMF) soft-core, "Hornet", implemented on Artix-7 FPGA...	24	Experimental	2	C
31	jainamnahar14surat/Deep-Learning-Accelerator-Transformer-FPGA FPGA-based hardware accelerator for Transformer neural networks enabling...	23	Experimental	5	Verilog
32	Nokia-Bell-Labs/data-channel-extension [NeurIPS'24] DEX: Data Channel Extension for Efficient CNN Inference on Tiny...	22	Experimental	9	Jupyter Notebook
33	rigoorozco/m2-artix7-accelerator-card M.2 PCIe Artix 7 FPGA Accelerator Card	22	Experimental	21	C
34	certainly-param/garuda-accelerator Garuda: CVXIF coprocessor optimizing batch-1 attention microkernels with...	22	Experimental	3	SystemVerilog
35	PanosZin/fpga-lstm-ecg-accelerator FPGA implementation of a quantized LSTM accelerator for ECG waveform...	22	Experimental	—	C++
36	Devanik21/A-Machine-Learning-Approach-for-Optimal-Low-Power-VLSI The project uses an ML surrogate model (e.g., Random Forest) to instantly...	22	Experimental	—	Python
37	EzraWolf/TinyMOA-IHP26a IHP26a TinyTapeout implementation of a RISC-V CPU with an integrated...	22	Experimental	—	Python
38	fastmachinelearning/ml4fg Machine Learning on frame grabbers for ultra-low latency in situ inference	20	Experimental	6	Jupyter Notebook
39	PCov3r/FPGA_Handwritten_digit_recognition A Verilog implementation of a hand-written digit recognition Neural Network	19	Experimental	10	Jupyter Notebook
40	LorenzoValente3/Autoencoder-for-FPGA Autoencoder model for FPGA implementation using hls4ml. Repository for...	18	Experimental	7	Jupyter Notebook
41	TadejMurovic/BNN_Deployment Part of paper: Massively Parallel Combinational Binary Neural Networks for...	17	Experimental	12	MATLAB
42	ngenehub/deepltk_fpga_examples Set of examples for DeepLTK FPGA Add-On	16	Experimental	4	LabVIEW
43	marcelwa/ls4ai Hack4Her: Logic Synthesis for AI	16	Experimental	10	Jupyter Notebook
44	angeliaplutus/ipcoredesign Design & Verification of IP Cores and ICs, Artificial Intelligence	15	Experimental	1	VHDL
45	mertz1999/CNN_ON_FPGA implement convolution neural network on FPGA based on VHDL design	15	Experimental	27	Jupyter Notebook
46	BrosnanYuen/tt07-Neuromorphic-ASIC-with-96-Neurons Neuromorphic ASIC with 96 neurons on Tiny Tapeout 7	14	Experimental	11	Verilog
47	JochiSt/AI_FPGA running ANN on an FPGA	13	Experimental	5	SystemVerilog
48	Monish-KS/DL_and_ML_On_FPGA This repository contains implementations of various machine learning (ML)...	12	Experimental	—	VHDL
49	mriosrivas/Pynq-Neural-Network Complete Implementation of a Integer Neural Network using SystemVerilog...	12	Experimental	4	HTML
50	josipnigojevic/VerilogMineDetectingANN Neural Network implemented in Verilog used for distinguishing if the wave...	12	Experimental	4	C
51	DYGV/FPGA-Based-EdgeAI-Prototypes Xilinx DPU(Vitis AI)を用いたエッジAI実現に向けたサンプルプログラム	12	Experimental	3	C++
52	Deverne-labs/TinyML-Zybo This repository is a collection of designs invloving FPGAs and AI technologies.	12	Experimental	14	VHDL
53	ahmed-ramsey-shahin/deep-learning-accelerator A hardware implementation of a deep learning accelerator using...	11	Experimental	6	SystemVerilog
54	mcastiglia/Graph2Gates Area and delay optimization for parallel prefix adder circuits using...	11	Experimental	6	Python

Comparisons in this category

hls4ml and hls4ml-tutorial (64 vs 49) hls4ml and rule4ml (64 vs 30)