> sometimes performance is a critical feature, yet you have no time or inclination to write (say) low-level GPU code by hand
I also have no time or inclination to integrate an entirely new tool into my build chain, complicate and lengthen the build process, and increase the cognitive load required to begin working on the project.
Sure, that's a fine judgment for most applications. That's exactly why high-performance languages (of any kind) necessarily must remain somewhat niche.
Although I will point out that the point of this post is exactly to try to minimise the build system complication and cognitive load as much as possible, so Futhark will be useful to just slightly more projects.
Futhark is an offer for people that need high performance code, but could spend their time on better things than writing CUDA/OpenCL code by hand.
Clearly that's not everyone. Maybe you don't need high performance code. Maybe you need to squeeze every last bit of performance out of your GPUs, so you actually need to spend time writing your own CUDA/OpenCL code.
So while it might not be worth it for you, it might be worth it for people trying to solve other kinds of problems :)
That's probably why they focussed on making the compiler as simple and straightforward to use as possible, so it does not significantly increase the complexity of your build process.
You would still need to wrap it in some form for it to be useable from most other build systems except make. For build systems such as bazel this is quite some work for little immediate benefit.
I also have no time or inclination to integrate an entirely new tool into my build chain, complicate and lengthen the build process, and increase the cognitive load required to begin working on the project.