I've missed the stories on this until now. Is it known (and is there an ELI5) how they were able to do it so much more efficiently?
https://en.wikipedia.org/wiki/Standard_Portable_Intermediate...
Or even better in the unified language like SYCL?
https://cdrdv2-public.intel.com/786536/Heidelberg_IWOCL__SYC...
You can do this just fine in CUDA, no PTX required. Of course all the major shops are using inline PTX at the very least to access the Tensor cores effectively.
I'd say the wider industry could learn a thing or two, but as other commentors have joked. The line must go up
Creativity from constrained minds?
Reminds me of Japanese cars and the OPEC boycott in the 1970s...