Graham Markall

I listed a simpler workaround until this is resolved in https://github.com/numba/numba/issues/9340#issuecomment-1849833085 - the workaround is essentially the same as above, but now linking CUDA C/C++ directly is possible in Numba,...

Thanks for the request! I'm marking this for triage for now, so it can be discussed at the next triage meeting.

@esc does this still need triage? It seems to clearly be a bug.

@sklam is the avoidance of casts to `float64` the reason there were originally signed?

So far comparing PTX before and after this patch (with a subset of the test suite) I haven't seen any instances where typing is casting to floats, but I suspect...

BTW @sklam - could you do a buildfarm run of this please, in case it turns up any other latent issues? This feels like the sort of thing that will...

I've broken out the straightforward parts of this PR (everything but changing the signedness of indices) into a separate PR so that they can be reviewed / merged independently: #6127.

In the meantime for this PR, I'm looking into an acceptable way to avoid casting to floats for the signed / unsigned comparison that occurs when comparing a value based...

> NOTE: To reviewers, this is dropping CUDA Toolkit 8.0 support. I split that out into #6127, but I left all that's in #6127 in here because it's needed for...

Following discussion in the triage meeting, I'll look into replacing the unsigned types for these indices with an index type to see if that alleviates some of the complication of...