Common Implemenatation for MatMul and MatMulTran for both aligned and unaligned arrays #1218
Conversation
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
Before
After
// update with changes |
|
@tannergooding are the performance tests fine ? |
test/Microsoft.ML.CpuMath.PerformanceTests/AvxPerformanceTests.cs
Outdated
Show resolved
Hide resolved
test/Microsoft.ML.CpuMath.PerformanceTests/SsePerformanceTests.cs
Outdated
Show resolved
Hide resolved
|
@eerhardt @tannergooding can you take another look ? |
eerhardt
reviewed
Oct 15, 2018
eerhardt
reviewed
Oct 15, 2018
|
@tannergooding @eerhardt cany more feedback ? |
ghost
locked as resolved and limited conversation to collaborators
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Outdated suggestions cannot be applied.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.
Fixes #1245
For inputs that are not naturally aligned (the alignment is not a multiple of 4), it does exclusively unaligned loads
For all other inputs, it will do at most two unaligned loads (one each for any leading/trailing unaligned elements) and all other loads will be aligned.
cc @tannergooding @eerhardt @danmosemsft @TomFinley