TensoriumCore/Tensorium_lib
An early-stage HPC tensor and grid-kernel library for numerical relativity, focused on a SIMD-optimized (SSE/AVX/AVX2/AVX-512/Arm NEON), parallel implementation with OpenMP of the Z4c formulation of Einstein’s equations.
This is a C++ library designed for researchers and scientists working in numerical relativity, particularly those studying black holes and gravitational waves. It enables high-performance simulations of space-time evolution using the BSSN/Z4c formulation of Einstein's equations. Researchers input initial conditions for gravitational systems and receive detailed data on how space-time and gravitational fields evolve over time, essential for astrophysics and theoretical physics studies.
Use this if you are a numerical relativist needing a high-performance C++ library for simulating single-grid, vacuum BSSN/Z4c space-time evolutions, or if you need robust tensor and linear algebra operations for scientific computing.
Not ideal if you primarily work with GPU-accelerated computing or require a fully integrated MPI-based distributed simulation for large-scale grids, as these features are foundational but not yet fully integrated into the main runtime.
Stars
13
Forks
3
Language
C++
License
MIT
Category
Last pushed
Mar 12, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/TensoriumCore/Tensorium_lib"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
apache/tvm
Open Machine Learning Compiler Framework
uxlfoundation/oneDNN
oneAPI Deep Neural Network Library (oneDNN)
Tencent/ncnn
ncnn is a high-performance neural network inference framework optimized for the mobile platform
OpenMined/TenSEAL
A library for doing homomorphic encryption operations on tensors
iree-org/iree-turbine
IREE's PyTorch Frontend, based on Torch Dynamo.