This repository has been archived by the owner on May 27, 2021. It is now read-only.
-
-
Notifications
You must be signed in to change notification settings - Fork 55
WIP: Support custom allocators, implement a bump allocator #422
Open
jonathanvdc
wants to merge
10
commits into
JuliaGPU:master
Choose a base branch
from
jonathanvdc:bump-allocator
base: master
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Add a pass that rewrites calls to 'managed_malloc'
The 'init' kwarg to '@cuda' allows users to define custom kernel initialization logic, which is run just prior to the kernel. The main use case for this kwarg right now is setting up globals.
Change how bump allocators are initialized Define 'cuda_global_ptr' in runtime library
Great, thanks! This will be a good starting point to get a more complex GC merged. |
tryBuild failed |
bors try |
Yikes. I see what happened there. The call to |
tryBuild failed |
EDIT: I made some tweaks. Let's see if this works. |
bors try |
tryBuild failed |
The pairwise test has been flaky before, so this looks like it is working. I'm going to leave this open until I have some time to give it a proper look, which might be a while. |
Alright, thanks! I can't reproduce the pairwise test failure either. |
maleadt
changed the title
Support custom allocators, implement a bump allocator
WIP: Support custom allocators, implement a bump allocator
Jul 12, 2019
maleadt
force-pushed
the
master
branch
4 times, most recently
from
January 22, 2020 15:17
17dfd92
to
3c9b279
Compare
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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.
This PR allows
@cuda
callers to pick a custom allocation function and implements a bump allocator, as per your request, @maleadt, in #419. I also threw in an example program that doubles as a test.