Seth R. Johnson
Seth R. Johnson
One thing I notice (not to do with your work or in scope for this PR) is that we have `join(and, [join(and, [..]), ...])` which should probably be "canonicalized" into...
We've decided to suspend work on this for now: if AMD hints at having experimental support for automatic offloading (or something like it) then it will definitely be worth reopening...
Hey @AlexVlx that's great! Our team is a little overloaded at the moment, but this would be a great project for an intern to implement? We're going to try to...
Thanks @mcolg ! Since the time that we first explored this, we did some substantial refactoring of how we launch kernels (see #743 and #783) to fix various odd behaviors...
Supersedes #1067
Well, the GPU performance (even when not using involutes) seems to take a substantial hit (~40% longer for testem3 without involutes!) from this branch. It's easy to see why from...
@VHLM2001 Great work this summer! As we discussed last Friday, it's disappointing but unsurprising that this ends up being a burden on the GPU. Next week (?) I can see...
I just ran before and after this branch; it seems the runtime "not reachable" is doing its job, but the CPU still suffers a runtime hit; not sure why since...
OK with the latest update all is well at runtime! 
Question for @paulromano : on-the-fly sense evaluation works for "point in volume" but might be difficult for "distance to boundary" in the case with internal surface crossings. To do that...