Back to Gap Map Infrastructure / Compilers & Model Optimization

oneMath

UXL Foundation
open source / Overall score: 2.0

oneMath is the UXL Foundation's open implementation of the oneMath specification, a cross-vendor math library exposing one interface for BLAS, LAPACK, FFT, RNG and sparse routines and dispatching to a vendor backend - oneMKL, NVIDIA cuBLAS, AMD rocBLAS and others - per target device. It began as oneMKL Interfaces before the UXL Foundation renamed the project.

Openness

5 high confidence
5.0
license
Apache-2.0(OSI)
source
public
core features withheld
no

Apache-2.0 license body confirmed. The repository is public and unarchived and builds the whole product, and the README describes no paid tier, enterprise edition or license-gated build beside it, so source is public and the core ungated.

Adoption

1 low confidence
1.0

oneMath ships as a source build and inside the oneAPI toolkit installers, neither of which publishes a download count, so GitHub stars are the only adoption signal available. A star is not a use.

Capability

3 medium confidence
3.0

oneMath exposes one cross-vendor interface for BLAS, LAPACK, FFT, RNG and sparse routines, dispatched to a backend per device. That routine and vendor breadth is real, but no engine or framework is recorded depending on it, only the backends it calls into - which places it two steps below Apache TVM on the evidence available.

  • https://github.com/uxlfoundation/oneMath/blob/develop/README.md recorded 2026-10-07

    README describes oneMath as the UXL Foundation's open-source implementation of the oneMath specification, dispatching to third-party backend libraries per hardware target, with no paid tier, enterprise edition or license-gated build beside it.

Verified 2026-09-27