Efficient and Scalable Physics-Informed Deep Learning and Scientific Machine Learning on top of Tensorflow for multi-worker distributed computing

simple ray tracer implemented in Python, capable of rendering 3D scenes with basic shapes, materials, and lighting.

A Taichi component for automatically compiling and launching compute graph.

Introduction to PyCuda GPU programming.

Scripts to manage rocprof tracing of multi-process, multi-node program runs.

Object Tracking of grayscale objects using CUDA

Lesson material for the HIP101 workshop on porting CUDA codes to HIP

PRACE Summer of HPC 2020, Performance of Parallel Python Programs on New HPC Architectures

GPU programming using CUDA & Python

Aixr Tensor is a powerful and flexible deep learning framework designed to optimize neural network training and inference. By leveraging dynamic device management, advanced optimization techniques, and custom functions, Aixr Tensor aims to provide an efficient and user-friendly environment for deep learning practitioners.

Project for the Parallel and Concurrent Programming course 2023/2024

A Bifrost plug-in for the Tensor-Core Correlator.

CUDA accelerated raytracer using PyCUDA in Python

A helper package to easily time Numba CUDA GPU events ⌛

vgg16 inference implementation using tensorflow, numpy and pycuda

bilibili视频【CUDA 12.1 并行编程入门(Python语言版)】配套代码

Fundamentals of heterogeneous parallel programming with CUDA C/C++ at the beginner level.

🌟 Vertex Centric approach for building GNN/TGNNs

pyCUDA implementation of forward propagation for Convolutional Neural Networks

Boilerplate for GPU-Accelerated TensorFlow and PyTorch code on M1 Macbook