[ARCHIVED] The C++ parallel algorithms library. See https://github.com/NVIDIA/cccl

Fast inference engine for Transformer models

Header only framework for data analysis in massively parallel platforms.

Thrust, CUB, TBB, AVX2, AVX-512, CUDA, OpenCL, OpenMP, Metal - all it takes to sum a lot of numbers fast!

CUDA tool set for non-C++ languages that provides similar functionality like Thrust, with NVRTC at its core.

CPU and GPU point cloud plane segmentation

simple GPU ransac fitting of multiple lines on 2d/3d point cloud

A performance-portable geodesic ray tracing library.

Thrust, voltage, amperage, and RPM sensing designed to replace the internal electronics in the Turnigy Thrust stand or a custom built stand, running on a Tiva C Launchpad with the IO Booster Pack.

Hardware & Software Interface for a Thrust Vector Control System for the Arduino

CUDA C/C++ programs

CURandRTC is a GPU random number generation module based on ThrustRTC.

Experimental

Maniuplate time series data in parallel using modern hardware (CPU, GPU). Course project for UCSC AMS 250

Material for a training on portable GPU programming

Aero 405 Thrust Stand Project

Lunar lander game (for linux), was inspired by the 1970's Atari vector graphics CRT coin arcade game. Features high quality line rendition which minimizes jaggies.

Parallel Programming courses exercises (Moscow Aviation Institute 7th semester)

Multi-Core Programming / searching for prime numbers with OpenMP and Thrust