added triangular matrix multiplication kernel #214
Merged
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
|
Wow, you really had a lot of fun with the TriMatlon 😂 😂 😂 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Companion to #213, adding a file specifically for the development of this matmul.
Also shows different intermediate kernels on the way towards efficiency.
To give a break from all the maths and indexing in the code, the development of these is described as a story.
Some of the metaphors are stretched quite a bit, so feel free to make adjustments, but I hope that overall, this might be easier to follow than just "indexing with this formula to achieve coalesced access".
Currently, the reads in the inner loop still cause 2-way bank conflicts, so there is still room for improvement.
Timings on my machine:
Given that we're doing only half the work, that leaves us still 20% less efficient than cuBLAS.