Add preliminary support for the xcore target. #585
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
|
Ideally we'd be able to have separate MLIR tests for the different targets, but I'm not sure our setup currently supports doing that? |
AdamHillier
force-pushed
the
xcore-target
branch
3 times, most recently
from
922bb6c
to
5b5423e
Compare
AdamHillier
force-pushed
the
xcore-target
branch
from
5b5423e
to
8ac16e2
Compare
AdamHillier
commented
Jan 28, 2021
Tombana
reviewed
Jan 28, 2021
Tombana
approved these changes
Jan 28, 2021
AdamHillier
force-pushed
the
xcore-target
branch
from
8ac16e2
to
133609c
Compare
lgeiger
reviewed
Jan 28, 2021
AdamHillier
force-pushed
the
xcore-target
branch
from
133609c
to
fb76a73
Compare
lgeiger
reviewed
Jan 28, 2021
AdamHillier
force-pushed
the
xcore-target
branch
from
fb76a73
to
6df009d
Compare
lgeiger
approved these changes
Jan 28, 2021
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Outdated suggestions cannot be applied.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.
What do these changes do?
This PR adds support for a 'target' flag to the LCE converter, with two values: "arm" (the default), and "xcore" (the XMOS xcore.ai board). For the time being, the only difference between the two is that the "arm" target supports 'same zero' padding, and the binary maxpool op, but the "xcore" target does not.
How Has This Been Tested?
I added a small test case to the Python converter test, but it's not possible to use the end2end tests with the xcore target because the converted models are not compatible with the LCE interpreter (and indeed are not meant to be). Need to work out what to do here.
Benchmark Results
N/A.
Related issue number
N/A.