LLM training in simple, raw C/CUDA

GPU database engine

matrix multiplication in CUDA

@ICCV2017: For exploiting second-order statistics, we propose Matrix Power Normalized Covariance pooling (MPN-COV) ConvNets, different from and outperforming those using global average pooling.

CUDA C implementation of Principal Component Analysis (PCA) through Singular Value Decomposition (SVD) using a highly parallelisable version of the Jacobi eigenvalue algorithm.

CUDA code for Monte Carlo estimation of Pi (see https://www.geeksforgeeks.org/estimating-value-pi-using-monte-carlo/)

Parallel implementation of PCA on Nvidia CUDA

Parallel implementation of Cholesky Decomposition using CUDA APIs

CUDA GPU Cholesky Decomposition

CUDA implementation of the initial steps in plmDCA

Parallel programs using CUDA C++ for Nvidia GPUs supporting cuda.

CUDA GPU Cholesky Decomposition