CUDA is not C++. CUDA for GPU kernels is its own language. That's the actual problem requiring new languages or abstractions.
You can program CUDA in standard C++20, with CUDA libraries hidding the language extensions.
I love when C and C++ dialects are C and C++ when it matters, and not when it doesn't help to sell the ideas being portrayed.
I'm extremely dubious that such an opaque abstraction can actually solve the (true) problem. "Not having to write CUDA" is not enough - how do you tune performance? Parallelization strategies, memory prefetching and arrangement in on-chip caches, when to fuse kernels vs. not... I don't doubt the compiler can do these things, but I do doubt that it can know at compile time what variants of kernel transformations will optimize performance on any given hardware. That's the real problem: achieving an abstraction that still gives one enough control to achieve peak performance.
Edit: you tell me if I'm wrong, but it seems that std::par can't even use shared memory, let alone let one control its usage? If so, then my point stands: C++ is not remotely relevant. Again, avoiding writing CUDA (etc.) doesn't solve the real problem that high-performance language abstractions aim to address.
Perhaps part of the reason for the bad takes in this thread is due to taking "language" overly literally (perhaps also the fault of the linked blog post itself). I think one thesis of the above tooling is that, when tuning and generating code (CUDA, OpenCL, what have you) at runtime, the best "languages" for these abstractions are, amusingly, scripting languages like Python. Having CUDA/etc. as a back end without having to hand-write/-transform/-optimize it is indeed the point.