MathsAI By Tuqa Alzahra AR
All repos
C++ MIT 10 1

mgorshkov/np

⚡ NumPy-style arrays in C++ | CUDA GPU + SIMD (AVX2/AVX512/AMX) CPU | Tikhonov Regularized EVD, LSQR, MRRR, SVD, QR eigenvalue solvers

Open on GitHub

Why it is useful

np is a recent open-source project in Education. It is included because it has recent repository activity and can support mathematical learning, research, modelling, software development, or AI workflows.

Repository at a glance

  • Owner: mgorshkov
  • Primary language: C++
  • Latest update: 2026-07-18
  • Stars / forks: 10 / 1
  • License: MIT
  • Links: Official project site

Good starting points

  1. Read the project README and installation instructions.
  2. Try the smallest example before changing parameters or datasets.
  3. Check tests, issues, and release notes before relying on results in teaching or research.
  4. Cite the repository and its license when reusing code or figures.

README snapshot

⚡ NumPy-style arrays in C++ | CUDA GPU + SIMD (AVX2/AVX512/AMX) CPU | Tikhonov Regularized EVD, LSQR, MRRR, SVD, QR, eigenvalue solvers High-performance N-dimensional arrays with CPU/GPU/Multithreading acceleration and built-in ML algorithms (Tikhonov Regularized EVD, LSQR, MRRR, SVD, QR, eigenvalue solvers) C++20-compatible compiler: * gcc 13 or higher * clang 14 or higher * Visual Studio 2019 or higher * CUDA development environment (NVIDIA CUDA Toolkit, and compatible NVIDIA drivers installed) to use CUDA optimizations (nvcc 12 or higher) Open np/build/doc/html/index.html in