Andreas Klöckner
Andreas Klöckner
Made https://github.com/inducer/pytential/issues/213 to discuss the unbounded memory growth.
Please don't remove the `sorted()` calls, FWIW.
:+1: I'd like a fix for this, too.
@ThomasLecocq Just had this happen in Chrome. (Chromium 31.0)
> Is `get_info(BINARIES)` doing something inefficient? It sure looks that way. It might require duplicate compilation in pocl? (I'm not sure where, but your second graph is enough for me.)...
Thanks for doing more digging here, @matthiasdiener! While we didn't decode that a "generic" kernel was being built, we did track down `pocl_driver_build_poclbinary` and concluded that it would likely trigger...
Thanks for the tip! Though it seems that setting `recv_mprobe = False` does not avoid this particular issue.
Exciting news: while I don't know *what* exactly the issue is, OpenMPI 4.1.5-1 seems to include a fix that makes it work properly with the previously-offending version of libfabric1.
That's where the documentation would be if it were written. Sorry!
Contributions welcome!