TC-GNN with Pytorch integration

Last update: Dec 01, 2022

Overview

TC-GNN (Running Sparse GNN on Dense Tensor Core on Ampere GPU)

Cite this project and paper.

@inproceedings{TC-GNN,
  title={TC-GNN: Accelerating Sparse Graph Neural Network Computation Via Dense Tensor Core on GPUs},
  author={Yuke Wang and Boyuan Feng and Yufei Ding},
  booktitle={Arxiv},
  year={2022}
}

Clone this project.

git clone [email protected]:YukeWang96/TCGNN-Pytorch.git

OS & Compiler:

Ubuntu 16.04+

gcc >= 7.5

cmake >= 3.14

CUDA >= 11.0 and nvcc >= 11.0

Files and Directories.

config.py: the configuration file for the shape of a TC block.
bench.py: the benchmark file for invoking main_tcgnn.py for various datasets and models.
main_tcgnn.py: the main entry for running TC-GNN.
count_TC_blocks.py: counting the total number of TC blocks without sparse-graph translation.
proc_prof.py: get the detailed GPU kernel metrics from the ncu csv output.
TCGNN_conv/: the directory for core TC-GNN implementations, including TCGNN_kernel.cu and TCGNN.cpp.

Environment Setup.

[Method-1] Install via Docker (Recommended).

Go to Docker/
Run ./build.sh
Run ./launch.sh

[Method-2] Install via Conda.

Install conda on system Toturial.
Create a conda environment:

conda create -n env_name python=3.6

Install Pytorch:

conda install pytorch torchvision torchaudio cudatoolkit=11.1 -c pytorch -c conda-forge

or using pip [Note that make sure the pip you use is the pip from current conda environment. You can check this by which pip]

pip install torch==1.8.0+cu111 torchvision==0.9.0+cu111 torchaudio==0.8.0 -f https://download.pytorch.org/whl/torch_stable.html

Install Deep Graph Library (DGL).

conda install -c dglteam dgl-cuda11.0
pip install torch requests tqdm

Install Pytorch-Geometric (PyG).

pip install torch-scatter -f https://pytorch-geometric.com/whl/torch-1.8.0+cu111.html
pip install torch-sparse -f https://pytorch-geometric.com/whl/torch-1.8.0+cu111.html
pip install torch-cluster -f https://pytorch-geometric.com/whl/torch-1.8.0+cu111.html
pip install torch-spline-conv -f https://pytorch-geometric.com/whl/torch-1.8.0+cu111.html
pip install torch-geometric

Install `TC-GNN`.

Go to TCGNN_conv/, then run

./build.sh

to install the TCGNN_conv modules with Pytorch binding. Note that this step is required for both Docker and Conda setup.

Download graph datasets.

Get the preprocessed datasets in .npy at here, then run

tar -zxvf tcgnn-ae-graphs.tar.gz

Running PyG baseline.

Go to pyg_baseline/ directory;

Pass the --model parameter in pyg_main.py with gcn and gin to profile the example GCN and GIN model, respectively;

./0_bench.py| tee run_pyg.log to run the script and the report 10 epoch runtime for all evaluated datasets.

./1_log2csv.py to convert the run_pyg.log to run_pyg.csv for ease of analysis.

Running DGL baseline.

Go to dgl_baseline/ directory

Pass the --model parameter in dgl_main.py with gcn and gin to profile the example GCN and GIN model, respectively;

./0_bench.py| tee run_dgl.log to run the script and the report 10 epoch runtime for all evaluated datasets.

./1_log2csv.py to convert the run_dgl.log to run_dgl.csv for ease of visualization.

Running TC-GNN.

Under the current project directory

./0_bench.py| tee run_TCGNN.log to run the script and the report 10 epoch runtime for all evaluated datasets.

./1_log2csv.py to convert the run_TCGNN.log to run_TCGNN.csv for ease of analysis.

Comments

Any docs about this project?

Hi I came across this project and found the implementation is quite interesting. Is there any docs/paper that detail this project? Or you have any plan to release these kinds of information in the future?

Thanks

opened by mmmeee1111 1

Releases(v0.2)

v0.2(May 11, 2021)
Add the docker support for environment setup.

Update the path and download link of datasets.

Source code(tar.gz)
Source code(zip)
v0.1(Apr 16, 2021)

Source code(tar.gz)
Source code(zip)

🐸STT integration examples

🐸 STT 0.9.x Examples These are various examples on how to use or integrate 🐸 STT using our packages. It is a good way to just try out 🐸 STT before

92 Dec 19, 2022

Official repo for AutoInt: Automatic Integration for Fast Neural Volume Rendering in CVPR 2021

AutoInt: Automatic Integration for Fast Neural Volume Rendering CVPR 2021 Project Page | Video | Paper PyTorch implementation of automatic integration

149 Dec 22, 2022

Hand gesture recognition based whiteboard that allows you to write on live webcam. This is the first version and has features like 4 different colors, eraser and a recording option that records your session and saves it in a "recordings" folder. Use index finger to draw and two or more fingers to move around and select items. Future version will contain more functionalities like changeable thickness, color palette, integration with zoom and google meet etc.

hand-write Hand gesture recognition based whiteboard that allows you to write on live webcam. This is the first version and has features like 4 differ

27 Dec 16, 2022

An integration of several popular automatic augmentation methods, including OHL (Online Hyper-Parameter Learning for Auto-Augmentation Strategy) and AWS (Improving Auto Augment via Augmentation Wise Weight Sharing) by Sensetime Research.

45 Dec 8, 2022

Dahua Camera and Doorbell Home Assistant Integration

TC-GNN with Pytorch integration

Related tags

Overview

TC-GNN (Running Sparse GNN on Dense Tensor Core on Ampere GPU)

Files and Directories.

Environment Setup.

[Method-1] Install via Docker (Recommended).

[Method-2] Install via Conda.

Install TC-GNN.

Download graph datasets.

Running PyG baseline.

Running DGL baseline.

Running TC-GNN.

You might also like...

🐸STT integration examples

Official repo for AutoInt: Automatic Integration for Fast Neural Volume Rendering in CVPR 2021

An integration of several popular automatic augmentation methods, including OHL (Online Hyper-Parameter Learning for Auto-Augmentation Strategy) and AWS (Improving Auto Augment via Augmentation Wise Weight Sharing) by Sensetime Research.

Dahua Camera and Doorbell Home Assistant Integration

MaRS - a recursive filtering framework that allows for truly modular multi-sensor integration

ROSITA: Enhancing Vision-and-Language Semantic Alignments via Cross- and Intra-modal Knowledge Integration

Wafer Fault Detection using MlOps Integration

Official code for On Path Integration of Grid Cells: Group Representation and Isotropic Scaling (NeurIPS 2021)

Comments

Any docs about this project?

Releases(v0.2)

v0.2(May 11, 2021)

v0.1(Apr 16, 2021)

Owner

YUKE WANG

A simple pytorch pipeline for semantic segmentation.

[ICML 2021] A fast algorithm for fitting robust decision trees.

JAXDL: JAX (Flax) Deep Learning Library

The source code for CATSETMAT: Cross Attention for Set Matching in Bipartite Hypergraphs

A script depending on VASP output for calculating Fermi-Softness.

Fusion-in-Decoder Distilling Knowledge from Reader to Retriever for Question Answering

TOOD: Task-aligned One-stage Object Detection, ICCV2021 Oral

Posterior predictive distributions quantify uncertainties ignored by point estimates.

automated systems to assist guarding corona Virus precautions for Closed Rooms (e.g. Halls, offices, etc..)

TumorInsight is a Brain Tumor Detection and Classification model built using RESNET50 architecture.

Unconstrained Text Detection with Box Supervisionand Dynamic Self-Training

PyTorch reimplementation of the Smooth ReLU activation function proposed in the paper "Real World Large Scale Recommendation Systems Reproducibility and Smooth Activations" [arXiv 2022].

Monocular Depth Estimation Using Laplacian Pyramid-Based Depth Residuals

DeepLab-ResNet rebuilt in TensorFlow

PyTorch implementation of the ideas presented in the paper Interaction Grounded Learning (IGL)

Code for ICCV 2021 paper "HuMoR: 3D Human Motion Model for Robust Pose Estimation"

PyTorch implementation HoroPCA: Hyperbolic Dimensionality Reduction via Horospherical Projections

Reinforcement learning models in ViZDoom environment

ReConsider is a re-ranking model that re-ranks the top-K (passage, answer-span) predictions of an Open-Domain QA Model like DPR (Karpukhin et al., 2020).

Code to run experiments in SLOE: A Faster Method for Statistical Inference in High-Dimensional Logistic Regression.

Install `TC-GNN`.