Fix benchmarks and gpu crash#20
Open
bgreni wants to merge 2 commits into
Open
Conversation
bgreni
force-pushed
the
improve-gpu-performance
branch
from
5aa1a5a to
622335c
Compare
Contributor
Author
|
Putting this into a draft as I am trying to write a gpu kernel for the sobel operation and it is not going well so far |
bgreni
force-pushed
the
improve-gpu-performance
branch
2 times, most recently
from
04663a3 to
390badf
Compare
Contributor
Author
|
Looks like my gpu implementation is now correct, but actually still a bit slower than the |
bgreni
force-pushed
the
improve-gpu-performance
branch
2 times, most recently
from
a6570cd to
a884c33
Compare
Contributor
Author
|
looks like simdifying things got me a little bit across the finish line on my rtx 3080. Performance difference on my mac M3 pro seems negligible. |
bgreni
force-pushed
the
improve-gpu-performance
branch
from
a884c33 to
22fdd20
Compare
Add better gpu kernel for sobel oeprator
bgreni
force-pushed
the
improve-gpu-performance
branch
from
22fdd20 to
b94ec59
Compare
bgreni
force-pushed
the
improve-gpu-performance
branch
from
281cce9 to
0b82e8f
Compare
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fix crash caused by
converted_intensitybeing ref captured and color tensor begin read by thee cpu now before gpu kernel execution.Also apparently
foreachis async now on gpu (or maybe just because I was only running them on mac until now?) so explicit sync is required. Also stride value in bench tensor spec was wrong.