Parla.py
Parla.py copied to clipboard
ut-parla
A Python based programming system for heterogeneous computing
We've been seeing mysterious segfaults in get_nprocs when threads are used together with VECs. The exact conditions that trigger this aren't known since lots of things still appear to work...
Currently setting attributes on libraries and adding/removing stuff from sys.modules takes up an absolutely awful amount of time when a library lazy-loads its submodules. This is even worse when modules...
Virtual Compute Unit (VCU) sounds like a virtualized environment and is very confusing when compared to VEX (Virtual EXecution environment). We should carefully document VCUs since we are using them...
The spawn decorator currently messes with the closure of the function it's passed to change the scoping semantics. (See https://github.com/ut-parla/Parla.py/blob/d82e6d573a5cd5b1e492a99a0106cd90e632961e/parla/tasks.py#L416.) Though the current commenting calls that a "hack", but it...
It would make a nice user story to be able to auto-generate stub libraries on the fly instead of having to compile them up-front. I'm uncertain of what the infrastructure...
It would be nice if we had some way to test if our virtual layer is complete other than debugging additional demos. Perhaps we could put together a way to...
Rather than write all the shim functions by hand it'd be nice to use some kind of wrapper generator tool. @arthurp has prior work on the Lapis compiler (see their...
Currently one place where resource information can still leak through is in the numbers passed to the CPU_SET interfaces. We should re-map core-numbers within a VEC to avoid confusing any...
I'm occasionally seeing a segmentation fault with the QR factorization app that occurs with Parla (non-VEC related). I haven't been able to reproduce it myself but it's come up before...
In order to load CUDA into a VEC, we added support for faking the PID. (CUDA picks a port to use based off the current PID, so we can't load...