when i was a baby my dad was driving me late at night and a drunk driver asleep at the wheel hit us head-on. my dad was in a coma for weeks. i needed hundreds of stitches. i still have a massive scar.
many years later, i got to work at waymo during the first few years we were testing, launching, and scaling in sf. there was a huge amount to do, but it all felt pretty fucking amazing when we got to see logs like this. superhuman moments.
it's easy to write off these things as just another expensive uber competitor for techies who don't want to talk to people. but humans behind the wheel are one of the top causes of death and injury globally. and one day not long from now self driving cars will make the kinds of accidents that happened to me a thing of the past.
@steeve@IronRedSandHive@CatGodSandHive@RealTjDunham I would very much like to see this. Splitting up monolithic NVCC invocations into separate & more granular cubin + host code compilations would be a huge improvement to the ergonomics of CUDA in Bazel.
@corentinanjuna@bazelbuild@buildbuddy This is cool to see. I've spent a bunch of time thinking about this since it seems so close to being possible to stitch together just from the provided NVCC commands, i.e. some combination of per CUDA arch --fatbin actions and one --cuda for the host side + kernel inclusion.
fun start to my week: setuptools published 82.0.0 yesterday and finally dropped pkg_resources entirely, breaking wheel builds for a bunch of packages that had setuptools in setup_requires with no upper version bound (which they tell you not to do anyway)
@JRROwens@toxictiramisu This book seems to be somewhere in the vicinity of conspiracy theory or creative fiction. I can't find any other works discussing the events as described but I can find reviews trashing this book for its lack of primary sources and shoddy history.
@__phantomderp I had a shower thought and figured you were the most likely person to know the answer: Has C converged on the C++11 memory model for atomics?