Implement im2col packing for int8 GEMM #570
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
robertknight
force-pushed
the
im2col-int8
branch
3 times, most recently
from
9b14925 to
49a4679
Compare
robertknight
force-pushed
the
im2col-int8
branch
from
49a4679 to
0c2ba0c
Compare
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Outdated suggestions cannot be applied.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.
Implement a method similar to
Im2Col::pack_blockthat packs the image using the different layout used by int8 kernels.On non-x64 systems there is an unnecessary u8 -> i8 -> u8 double conversion that happens because the
Convoperator will receive the image in u8 format, it will create a copy in i8 format and then the kernel will re-convert back to u8 when packing. When a native u8 x u8 -> i32 GEMM is added in future, this can be avoided.TODO: