Explore projects

Simple programs for testing and debugging MPI + cuda issues on various hardware and software stacks.

Strong scaling CPU+GPU parallelized tools.

This project contains an implementation of a CUDA Tensor Core-based complex matrix multiplication (CGEMM).

MPI benchmarks for performance measurements

Minimal 'hello world' example with scikit-build and pybind11

SOAP descriptor and related tools

A tool for performing many 3D FFTs on large three-dimensional stacks of images using CPUs (and GPUs).

Cosmic-ray propagation package

clean FASTQ files for low quality reads and PCR duplicates