vosen/ZLUDA

CUDA on non-NVIDIA GPUs

What it solves

It removes the hardware lock-in of NVIDIA GPUs for software written in CUDA. It allows users to run unmodified CUDA applications on non-NVIDIA GPUs without needing to rewrite the same code for other platforms.

How it works

ZLUDA acts as a drop-in replacement for the CUDA platform, translating the CUDA calls to be compatible with non-NVIDIA hardware, achieving performance levels close to those of native execution.

Who it’s for

Developers and users who want to run CUDA-based software on GPUs from other manufacturers.

Highlights

  • Drop-in replacement for CUDA
  • Supports unmodified CUDA applications
  • Near-native performance on non-NVIDIA GPUs

Related

  • Dispatch
    ZLUDA 6 Release: Running Unmodified CUDA Applications on Non-NVIDIA GPUs

    ZLUDA 6 introduces support for 32-bit PhysX, basic texture support for Blender, and significantly improved Windows usability for running CUDA applications on non-NVIDIA hardware.

  • Dispatch
    cuda-oxide: Bringing Rust's Safety and Expressiveness to CUDA

    NVIDIA introduces cuda-oxide, an experimental Rust-to-CUDA compiler that allows developers to write GPU kernels in idiomatic Rust without relying on DSLs or foreign language bindings.

  • Project
    NVIDIA/cuda-quantum

    A platform for hybrid quantum-classical computing that integrates QPUs, GPUs, and CPUs into a single programmable system.

  • Project
    kunzmi/managedCuda

    A .NET wrapper for NVIDIA's CUDA Driver API and libraries, enabling C# and Visual Basic developers to integrate GPU acceleration into their applications.

  • Project
    JuliaGPU/CUDA.jl

    A programming interface for NVIDIA CUDA GPUs in Julia, featuring a compiler for Julia-native kernels and wrappers for various CUDA libraries.