-
Notifications
You must be signed in to change notification settings - Fork 319
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Add a flag to turn on/off the lowering of scalar broadcasting binary ops to NNPA #2778
Conversation
Signed-off-by: Tung D. Le <tung@jp.ibm.com>
Signed-off-by: Tung D. Le <tung@jp.ibm.com>
Signed-off-by: Tung D. Le <tung@jp.ibm.com>
Signed-off-by: Tung D. Le <tung@jp.ibm.com>
Signed-off-by: Tung D. Le <tung@jp.ibm.com>
I gave this a try today and it looks like this closes the performance gap for roberta-sequence-classification-9 from #2769 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM!
If you pass the option into the pass, the onnx-mlir-opt should work, too.
Signed-off-by: Tung D. Le <tung@jp.ibm.com>
@chentong319 thanks for the comment! I forgot to add a lit test. Since the option is added into |
Jenkins Linux s390x Build #14619 [push] Add a flag to turn on/of... started at 23:57 |
Jenkins Linux amd64 Build #14589 [push] Add a flag to turn on/of... started at 22:57 |
Jenkins Linux ppc64le Build #13614 [push] Add a flag to turn on/of... started at 00:07 |
Jenkins Linux amd64 Build #14589 [push] Add a flag to turn on/of... passed after 1 hr 14 min |
Jenkins Linux s390x Build #14619 [push] Add a flag to turn on/of... passed after 1 hr 36 min |
Jenkins Linux ppc64le Build #13614 [push] Add a flag to turn on/of... passed after 2 hr 2 min |
…ops to NNPA (onnx#2778) * Add a flag to turn on/off scalar broadcasting binary op in NNPA Signed-off-by: Tung D. Le <tung@jp.ibm.com> --------- Signed-off-by: Tung D. Le <tung@jp.ibm.com> Co-authored-by: Alexandre Eichenberger <alexe@us.ibm.com>
…ops to NNPA (#2778) (#2782) * Add a flag to turn on/off scalar broadcasting binary op in NNPA Signed-off-by: Tung D. Le <tung@jp.ibm.com> --------- Signed-off-by: Tung D. Le <tung@jp.ibm.com> Co-authored-by: Alexandre Eichenberger <alexe@us.ibm.com> (cherry picked from commit 08d4fed) Co-authored-by: Tung D. Le <tung@jp.ibm.com>
Add a compile flag,
--nnpa-enable-scalar-bcast-binary
, to turn on/off the lowering of scalar broadcasting binary ops to NNPA, which is flexible for debugging. Default value is off.