Tensorium_lang: compiler-visible tensor calculus for numerical relativity
A web version of the Tensorium_lang paper: an experimental MLIR-based DSL for preserving tensor structure through compiler lowering and generated numerical kernels.
I am the creator of the open-source TensoriumCore foundation. My work focuses on Tensorium_lib, Tensorium_lang, MLIR-based compiler infrastructure, high-performance C++ kernels, and numerical relativity workflows for BSSN/Z4-style systems.
Work on tensor-calculus tooling, constraint systems, BSSN/Z4-style formulations, elliptic problems, and numerical infrastructure for general relativity.
TensoriumCore development around tensor and linear-algebra kernels, SIMD-aware layouts, and C++ abstractions for high-performance scientific computing.
A web version of the Tensorium_lang paper: an experimental MLIR-based DSL for preserving tensor structure through compiler lowering and generated numerical kernels.
High-performance C++ tensor, linear algebra, and numerical relativity library with SIMD-oriented kernels and HPC-focused design.
Experimental compiler and DSL infrastructure for tensor calculus, MLIR lowering, generated kernels, and numerical relativity workflows.
Source repository for MLIR tutorial experiments around dialects, lowering pipelines, compiler passes, and backend infrastructure.