And we now have hipcc to go back to AMD. Sweet!

Have fun with that. I burned my hand badly enough on OpenCL that I now know to wait for proof, not promises.

People are doing benchmarks on older rocm's and it is looking pretty good.

https://www.mosaicml.com/blog/amd-mi250

Waiting on the updates.

I'll add that I have learned over time to not discount motivation. If AMD it motivated, they can do it. This has been proven already with their dominance over the server cpu market.

hipcc is a joke, it doesn't handle everything CUDA is capable of, specially not the polyglot capabilities.

What do you mean by polyglot? As in multiple hardware, or mixed-source? HIP is mostly API-compatible with CUDA, so you can just mix host code and device code with it.

That said, ROCm does indeed work with machine code instead of IR. You can compile fat binaries with more than one type of machine code and they'll work on any of the chips you compiled for, at the cost of the binaries becoming, well, basically obese if you want a decent range of hardware supported.