Aditya Bhosale

Add pyopencl-like GenericScanKernel

4

I've tried to keep the kernel source code similar to the scan kernel in `pyopencl` using `pycuda._cluda`. I am listing out the differences between the two: 1. Added a `RESTRICT`...

GenericScanKernel for pycuda

1

I am working on a project for which I need to use a pyopencl-like GenericScanKernel. I have added GenericScanKernel to my fork that is almost identical to the one in...

Use a decorator to register chares

1

Use a decorator to register Chare classes rather than passing them as a list to `charm.start`

The local message optimization stores a reference to entry method arguments in the destination chare's local msg buffer if the source and destination chares lie on the same PE to...

Add `ckDestroy` to delete an array element and `ckLocalBranch` to get the local group object. Also some reformatting to improve PEP8 compliance

Adds an option to enable cProfile. cProfile can measure time spent in local function calls and can also measure overhead from runtime calls in more detail than the current profiling...

GPU build failing on delta

1

Building with MPI and CUDA on Delta fails with the build script because of an error in cmake tests. The buildold script runs fine.

- [ ] Modernize pip infrastructure - Build via cibuildwheel - Package charm++ with charm4py, if possible (so that charm++ does not need to be built when running pip install...