Replace blocking cl.launch by asynchronous cl.call. #220
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
cl.launch
, and itsgetindex
-overloading shorthand, are currently blocking. That's pretty bad design when you want to launch as many kernels as possible to saturate the GPU. Besides, most subsequent API calls (likeclEnqueueReadBuffer
when doing acl.read
orcopy!
) are queue-ordered anyway, so I don't see why launches should be blocking.Since this is a pretty subtle change, also rename
launch
tocall
to make sure nobody gets tripped up by this.The goal is to build a high-level
clcall
and then@opencl
on top of this, so the hope is that people won't have to deal with this.