Are GPUs Still Needed? Maybe Not, HPC Experts Say
The rise of an GPU-less supercomputer called LineShine on the TOP500 list last week has...
Nvidia is primarily known as a hardware company thanks to the wild success of its GPUs. But Nvidia is also a force in the world of software, thanks to its CUDA programming language that has become the defacto standard for AI and HPC developers. Now a group of CUDA experts at Spectral Compute are looking to unhook the language from Nvidia and allow users to run their CUDA code on other chips.
Spectral Compute was formed in 2018 when a group of four engineers, including CEO Michael Søndergaard, CTO Chris Kitching, Software Engineer Nicholas Tomlinson, and Software Engineer Francois Souchay, decided they had had enough with hardware lock-in with their CUDA code. The founders, who had 60 years of combined HPC optimization experience, were working at an AI firm, but grew so frustrated with the cost of Nvidia GPUs and the poor performance of alternative compilers that they decided to build their own.
The founders developed a product called SCALE, which uses CLang and LLVM compiler technology, to function as a drop-in replacement for NVCC, the Nvidia CUDA Compiler. The company’s first target with SCALE were AMD GPUs, but now it’s broadening its goals to enable users to run CUDA on other AI accelerators. The company also supports Nvidia GPUs, on the theory that Nvidia is leaving software-based performance optimization on the table because it wants to sell more hardware.
Spectral is a big fan of CUDA, which it claims represents about 80% of the HPC code in the wild, according to Giulio Malitesta, head of growth for Spectral. “CUDA is basically the de-facto standard of HPC,” Malitesta told HPCwire at the ISC 2026 conference in Hamburg, Germany. “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, but also improve on Nvidia GPUs.”
There are other compilers on the market that can make CUDA code run elsewhere, as Malitesta pointed out. AMD created a tool called HIPIFY to translate Nvidia CUDA code into C++ code that can be run on AMD’s ROCm software stack via HIP (Heterogeneous-compute Interface for Portability). Then there’s SYCLomatic, a open source tool originally developed by Intel to migrate CUDA code to Data Parallel C++ (DPC++). And who could forget ZLUDA, which is a just-in-time compiler once backed by AMD that takes CUDA binaries and runs them on non-Nvidia hardware.
However, most tools have a downside. For instance, HIPIFY–which the Spectral founders worked with previously–essentially ignores Parallel Thread Execution (PTX), the Nvidia assembly language that opens up deep hardware support in CUDA, Malitesta says. SYCLomatic migrates about 90% of code, requiring manual work for the final 10%. And ZLUDA operates on the compiled binary code and acts as a middleware layer, which hurts performance. Legal questions have also dogged various non-Nvidia CUDA compilers.
Malitesta said Spectral Compute is able to surpass the middling performance of these other compilers with SCALE and enable CUDA to take full advantage of the underlying hardware. The company has published benchmarks on its website that show SCALE delivers nearly a 6x performance boost on AMD GPUs compared to using HIPIFY to convert CUDA code to AMD’s own ROCm environment.
Spectral is able to achieve such performance levels because it’s taken a clean-room re-implementation based on a cutting-edge compiler framework, Malitesta said. “We take the approach that’s industry-standard for CPUs, but apply it to GPUs,” he said, adding that it’s “the same approach that enables C++ to run, for example, on AMD and ARM CPUs, where nobody expects a performance gap that isn’t directly caused by differences in the underlying hardware.”
After recompiling the code, Spectral verifies that it’s correct from a numerical perspective. If it matches the normal NVCC output, then the company considers it a successful implementation.
Spectral, which is located in London and raised $6 million last year, is currently working on supporting third-party AI accelerators, which have not yet been named. The company is also working on some proprietary novel compiler optimizations that it says will deliver a major upgrade for customers running CUDA on Nvidia GPUs. Later this month, it’s anticipating releasing support for PyTorch, which will enable its tools to work better with the AI and machine learning framework.
Company employees say what they’re doing is beneficial to the CUDA community, which even Nvidia understands is a good thing at the end of the day. In June, Spectral entered into a formal partnership joined the Nvidia Inception program.
“We’re on the good side of Nvidia and we’re on a good side with AMD,” said Ruben van Dongen, head of academic solutions and business development for Spectral. “Of course, we want to be friends with the entire industry. We are neutral, truly neutral.”
Spectral already supports the core CUDA product, but there are hundreds of specialized CUDA libraries, such as cuDNN, which supports deep neural networks; cuTENSOR, which supports tensors; and cuDF, which supports dataframes like Polars and pandas. The company is actively working to add support for specialized CUDA libraries.
SCALE has been shipping for only about two years, so the company does not have a long track record. However, the company is growing quickly, as it currently has about 30 employees and is looking to expand. Spectra sells access to SCALE to commercial outfits, and it gives the compiler toolkit away to academic institutions and non-profit entities.
Spectral is working with companies, universities, and labs around the world that would like to unlock their CUDA development on additional hardware platforms. SCALE has even run on Frontier, the exascale supercomputer at Oak Ridge National Laboratory.
“The future is looking extremely bright. We are solving a huge problem within the industry,” van Dongen said. “Especially in the field of research, the researchers lack time. Instead of having to rewrite the entire code base or port away from their current existing code base, they can just recompile with our solution and even increase performance benefits.”
As the HPC community comes to terms with the extraordinary events surrounding the AI boom and the rapid popularization of GPU computing, it’s worth taking some time to consider all possible paths forward. Nvidia is an remarkable company that has bootstrapped much of the progress in GPU manufacturing and parallel software development (via CUDA), and it has been duly rewarded by becoming the world’s first $5 trillion company.
Nvidia surely would like to keep all these golden AI eggs in its own basket, but that’s not necessarily in the best interests of HPC and AI customers, nor the computing ecosystem at large. In that respect, Spectral is doing everyone a favor. What is perhaps more surprising is that there are not more companies like Spectral building bridges over the CUDA moat.