Top all-time · #12654
SCALE Blog
Company blog · scale-lang.com/posts · on HN as msondprogramminghardware
SCALE Blog is the company blog at scale-lang.com, writing about programming and hardware. Since 2024, 6 different Hacker News readers have linked it 13 times, most often “Scale: Compile unmodified CUDA code for AMD GPUs”. It is still writing: the last post was on 2026-06-12, and you can follow it by feed.
Too few sampled comments (1) to say how often HN recommends it.?
Why HN links it
The only comment describes SCALE, a clang-based CUDA implementation that runs on Nvidia or AMD GPUs, and links its docs. It does not discuss the blog's writing.
Summarised by Claude from a sample of 1 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
(Re)compile and debug CUDA code for a broad range of GPUs to increase performance. Maximize current and future GPU investments with SCALE.
Most-linked posts?
- Scale: Compile unmodified CUDA code for AMD GPUs3 people · 7 mentions · first linked 2024-07-16
What Hacker News says?
We donated one of our MI300x systems to the SCALE team. The moat-less future is coming more quickly than you think. https://scale-lang.com/
Comment linking /
on “AMD now has more compute on the top 500 than Nvidia”Submitted CUDA version of GROMACS is faster on AMD than HIP port as a story · 15 points
HN discussionThere are also interesting efforts like: https://github.com/Zaneham/Booth https://scale-lang.com/
Comment linking /
on “CUDA for AMD on Windows”Submitted A Big Update from Spectral Compute, the Team Behind Scale as a story · 6 points
HN discussionA bit of background. This is directed towards Spectral Compute (Michael) and https://scale-lang.com/ . I know both of these guys personally and consider them both good friends, so you have to understand a bit of the background in order to really dive into this. My take on it is fairly well summed up at the bottom of Elio's post. In essence, Elio is taking the view of "we would never use scale-lang for llms because w…
Comment linking /
on “Why CUDA translation wont unlock AMD”Submitted Scale GPGPU Programming Language as a story · 5 points
HN discussion> CUDA is that level of abstraction, but it only really works for Nvidia cards. There are people actively working on that. https://scale-lang.com/
Comment linking /
on “Ironwood, our latest TPU”Submitted Why GPU compilers are MORE important in the agentic era as a story · 3 points
HN discussionWe actually support NVIDIA hardware, too. In some benchmarks, SCALE beats nvcc, and we have compiler optimizations in the pipeline that will improve those numbers over time. > If all you want is to be able to easily use non-NVidia hardware then high level tools like PyTorch already let you do that Somewhat true, but, CUDA is significantly larger than PyTorch and there's more to Accelerated Computing than just those…
Comment linking /posts/2026-01-19-optimizing-cuda-shuffles
on “Alternative(s) to run CUDA on non-Nvidia hardware”Submitted Scale: August in Review as a story · 2 points
HN discussionSee also: https://scale-lang.com/ Write CUDA code. Run Everywhere. Your CUDA skills are now universal. SCALE compiles your unmodified applications to run natively on any accelerator, ending the nightmare of maintaining multiple codebases.
Comment linking /
on “BarraCUDA Open-source CUDA compiler targeting AMD GPUs”Submitted Scale: Compile unmodified CUDA code for AMD GPUs as a story · 2 points
HN discussionScale is a cuda implementation running on nvidia or amdgpu. Think nvcc semantics with template diagnostics by clang. Nvidia including Spectral in their inception programs seems a big deal to me. It bodes well for the future of the cuda ecosystem. If you'd like to run it, docs and download at https://scale-lang.com/ . It's a clang fork with a bunch of libraries packaged. I'm on the dev team and always happy to hear f…
Comment linking /
on a deleted thread