Raph Levien

> Given MSL's inheritance from C++, I would expect MSL to default to coherent buffers, but I have not tested this. The MSL spec is mostly silent on this issue,...

Re line segmentation, I have no particular ego invested, but it is true as @dhardy points out that xi-unicode has a solution to this problem. It's a very optimized, hand-tuned...

I'll also add that xi-unicode goes to Unicode 10, while uax14_rs seems to be up to date with Unicode 13. That's another consideration, and makes apples-to-apples comparison harder, as Unicode...

If any one runs into this issue, it's likely because the C++ components of the build are leaving stale junk around somewhere in the target/ filter after a failed build,...

I did a bit more digging on this. The corresponding behavior for other atomics like `atomicAdd` seems correct, and the logic is in the `put_atomic_fetch` function, which has explicit case...

This PR is partly for discussion purposes. I'd really appreciate resolution of the following questions: * Is this, in fact, an instance of undefined behavior? I've asked around and haven't...

Thanks for the encouraging reply. Maybe the best thing to do is open a pull request with my prototype (in as rough form as it is), and we can refine...

@xk Code coming soon. I'm a bit busy with other stuff right at the moment, and what I have needs some cleaning up. Yes, part of the parameters I set...

@datajerk Ok, there are two conflicting requirements there: getting code up quickly so that others can experiment and validate its reliability etc, and having the code as a patch against...

I thought I'd update this issue with my latest experimentation and thinking. There are basically three challenges: polarity inversion, 6502 code size, and speed tuning. ## Polarity inversion Based on...