Spectral Compute Aims to Run CUDA on Non-Nvidia Hardware

Alternative(s) to run CUDA on non-Nvidia hardware

Frustrated by hardware lock-in and high costs, we founded Spectral Compute to free CUDA from Nvidia GPUs. Our SCALE compiler uses LLVM technology to run CUDA code on AMD and other accelerators with near-native performance. Unlike existing tools that require manual migration or suffer performance losses, we offer a drop-in replacement that preserves the de-facto standard for HPC developers while supporting the entire industry.

"CUDA is basically the de-facto standard of HPC, and we need to accept that as a fact and just do the work as compiler engineers to make it available on different platforms that are not necessarily Nvidia."