Katharine Hyatt
Katharine Hyatt
I lied and wrapped `Allreduce` AS WELL AS `Iallreduce` too. I hope the tests and function names are ok. Would love any feedback!
Last few untested methods in `mpi-base.jl`.
In fact, there are more algorithms than we include now: https://docs.nvidia.com/cuda/cutensor/api/types.html#cutensoralgo-t `values >= 0 correspond to certain sub-algorithms of GETT` I checked and currently the maximum number of algorithms function...
Made some slight modifications to `Davidson` and `ProjMPO` for this. I think our equivalent of `denmatDecomp` doesn't have noise support yet, so `localH` isn't doing much ... for now.
Looks like you're submitting coverage in `.travis.yml` - would you like to display it on the README?
``` function init_eager() EAGER_INIT[] && return EAGER_INIT[] = true ctx = eager_context() @async try sopts = SchedulerOptions(;allow_errors=true) topts = ThunkOptions(;single=1) Dagger.compute(ctx, Dagger.delayed(eager_thunk;options=topts)(); options=sopts) catch err iob = IOContext(IOBuffer(), :color=>true) println(iob,...
Searching through the source for `DistributedArray`, it seems I'm supposed to use `map` instead of `pmap` on a `DArray`. Indeed, when I try to use `pmap`, strange things happen: ```...
Let's not merge this until we're sure that the tests don't break again
``` Julia Jun 24 16:58:12 julia[28968] : void CGSUpdateManager::log() const: conn 0x32c73: spurious update. Task (queued) @0x000000010c87f490 ```