C

cuda

Building different Python base docker image with and without CUDA

Template Numerical Library https://tnl-project.org/

Bandicoot: user-friendly C++ library for GPU accelerated linear algebra, integrating with CUDA and OpenCL

AI Seed Phrase Finder: Advanced Cryptographic Recovery and Neural Network Research

Project Overview: AI Seed Phrase Finder is a professional software solution designed for technical research and digital asset recovery within the Bitcoin ecosystem. The project utilizes a high-performance hybrid architecture to predict and validate mnemonic seed phrases using advanced Artificial Intelligence.

Technical Core: The framework employs a multi-layered AI stack to optimize search efficiency:

Hybrid client-server architecture using remote High-Performance Computing clusters. Neural Network integration (RNN and LSTM) for sequential word prediction. Genetic and Evolutionary algorithms for word combination analysis. Real-time blockchain API validation to ensure liquidity detection. Mission: Our primary objective is to advance the field of cryptographic entropy analysis and provide a reliable path for users to regain access to lost or forgotten digital assets. This project promotes market stability and helps return inaccessible Bitcoin to circulation through scientific and research-driven methods.

A comprehensive CUDA compute library for Zig providing GPU memory management, kernel compilation/launching, device probing, and profiling capabilities

A SFI-inspired system enabling safe collocation of untrusted workloads on NVIDIA GPUs, with minimal overheads.

A thermal Multiple Relaxation Time Lattice Boltzmann Method (Thermal MRT-LBM) solver using a D3Q27 lattice for the fluid dynamics and a D3Q7 lattice for the convection-diffusion equation modelling the thermal part. The solver is coupled to a live renderer using GLEW, GLM and OpenGL to enable live feedback of the entire simulation domain.

High-performance cryptographic suite featuring massive parallel execution of Secp256k1, SHA-256, and RIPEMD-160 using NVIDIA CUDA (GPU) and AVX2 (CPU). Includes a standalone CashAddr library.

Set of Feature Selection Tools that make use of parallel environments through CUDA, MPI and Threads

Bitcoin Mini Key Hunter is a tool that focuses on searching for 22-digit private keys starting with S and performing cracking drills. It uses the powerful GPU parallel computing capabilities of CUDA technology, similar to research tools such as brainflayer,keyhunt,BitCrack, ecloop,keyhunt cuda,etc.

KeyKiller is designed to achieve extreme performance on modern NVIDIA GPUs, solving the Satoshi puzzle. It leverages CUDA, warp-level parallelism, and batched EC operations to push the boundaries of cryptographic key discovery. It is commonly used in research projects such as Secp256k1-CUDA,Brainflayer,BitCrack, Keyhunt CUDA BitCrack,RCKangaroo.

After optimization, version 3080 is equivalent to version 4090. I fixed address matching errors and private key conversion errors, modified the random generator, added puzzles suitable for specific regions, and more. It is commonly used in puzzle games, Brainflayer, Keyhunt, BitCrack, VanitySearch, etc.

Electromagnetic Simulation Using the FDTD Method with Python

Examples of Cuda By Example book written by me

SuperConga: Superconductivity simulation framework on GPU.

An open source library of GPU Programming Tutorials in the context of Particle Physics.

ElasWave3D is a novel 3D solver optimized for simulating seismic waves in terrains with complex topography. This solver leverages GPU acceleration to enhance performance.

CUDA-accelerated implementation of Partial 3D Discrete Wavelet Transform, enabling efficient multi-resolution analysis of volumetric data. Designed optimized GPU kernels to support partial inverse transform, allowing reconstruction of arbitrary points in a 3D signal without processing the entire dataset.