[BYOC][ACL] Depthwise convolution support #7206
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
Added support for depthwise convolution. ACL only supports depth-wise convolution when kernel size is 3x3 and 5x5 and strides are (1, 1) or (2, 2), if this is not the case then fallback to TVM. Also rework tests to remove non-deterministic trials. *Compute Library for the Arm Architecture (ACL). *All credits to Luke Hutton @lhutton1 Change-Id: Ida1f5802a65377b84325edf14a0149242c1af857
d-smirnov
force-pushed
the
depthwise-rebased
branch
from
2948252
to
f02e26e
Compare
lhutton1
reviewed
Jan 8, 2021
|
Thanks @d-smirnov @lhutton1 ! This is now merged. |
tkonolige
pushed a commit
to tkonolige/incubator-tvm
that referenced
this pull request
Jan 11, 2021
* [BYOC][ACL] Depthwise convolution support Added support for depthwise convolution. ACL only supports depth-wise convolution when kernel size is 3x3 and 5x5 and strides are (1, 1) or (2, 2), if this is not the case then fallback to TVM. Also rework tests to remove non-deterministic trials. *Compute Library for the Arm Architecture (ACL). *All credits to Luke Hutton @lhutton1 Change-Id: Ida1f5802a65377b84325edf14a0149242c1af857 * linter * CHECK -> ICHECK Co-authored-by: Luke Hutton <[email protected]>
masahi
pushed a commit
to masahi/tvm
that referenced
this pull request
Jan 14, 2021
* [BYOC][ACL] Depthwise convolution support Added support for depthwise convolution. ACL only supports depth-wise convolution when kernel size is 3x3 and 5x5 and strides are (1, 1) or (2, 2), if this is not the case then fallback to TVM. Also rework tests to remove non-deterministic trials. *Compute Library for the Arm Architecture (ACL). *All credits to Luke Hutton @lhutton1 Change-Id: Ida1f5802a65377b84325edf14a0149242c1af857 * linter * CHECK -> ICHECK Co-authored-by: Luke Hutton <[email protected]>
masahi
pushed a commit
to masahi/tvm
that referenced
this pull request
Jan 18, 2021
* [BYOC][ACL] Depthwise convolution support Added support for depthwise convolution. ACL only supports depth-wise convolution when kernel size is 3x3 and 5x5 and strides are (1, 1) or (2, 2), if this is not the case then fallback to TVM. Also rework tests to remove non-deterministic trials. *Compute Library for the Arm Architecture (ACL). *All credits to Luke Hutton @lhutton1 Change-Id: Ida1f5802a65377b84325edf14a0149242c1af857 * linter * CHECK -> ICHECK Co-authored-by: Luke Hutton <[email protected]>
TusharKanekiDey
pushed a commit
to TusharKanekiDey/tvm
that referenced
this pull request
Jan 20, 2021
* [BYOC][ACL] Depthwise convolution support Added support for depthwise convolution. ACL only supports depth-wise convolution when kernel size is 3x3 and 5x5 and strides are (1, 1) or (2, 2), if this is not the case then fallback to TVM. Also rework tests to remove non-deterministic trials. *Compute Library for the Arm Architecture (ACL). *All credits to Luke Hutton @lhutton1 Change-Id: Ida1f5802a65377b84325edf14a0149242c1af857 * linter * CHECK -> ICHECK Co-authored-by: Luke Hutton <[email protected]>
trevor-m
pushed a commit
to neo-ai/tvm
that referenced
this pull request
Jan 21, 2021
* [BYOC][ACL] Depthwise convolution support Added support for depthwise convolution. ACL only supports depth-wise convolution when kernel size is 3x3 and 5x5 and strides are (1, 1) or (2, 2), if this is not the case then fallback to TVM. Also rework tests to remove non-deterministic trials. *Compute Library for the Arm Architecture (ACL). *All credits to Luke Hutton @lhutton1 Change-Id: Ida1f5802a65377b84325edf14a0149242c1af857 * linter * CHECK -> ICHECK Co-authored-by: Luke Hutton <[email protected]>
electriclilies
pushed a commit
to electriclilies/tvm
that referenced
this pull request
Feb 18, 2021
* [BYOC][ACL] Depthwise convolution support Added support for depthwise convolution. ACL only supports depth-wise convolution when kernel size is 3x3 and 5x5 and strides are (1, 1) or (2, 2), if this is not the case then fallback to TVM. Also rework tests to remove non-deterministic trials. *Compute Library for the Arm Architecture (ACL). *All credits to Luke Hutton @lhutton1 Change-Id: Ida1f5802a65377b84325edf14a0149242c1af857 * linter * CHECK -> ICHECK Co-authored-by: Luke Hutton <[email protected]>
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.
Added support for depthwise convolution. ACL only supports depth-wise convolution when kernel size is 3x3 and 5x5 and strides are (1, 1) or (2, 2), if this is not the case then fallback to TVM.
Also rework tests to remove non-deterministic trials.