Skip to content

Cortex-M backend: Prerequiste changes to export mv3/mv2 targetting CMSIS-NN backend #16393

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.

Sign up for GitHub

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

Draft
psiddh wants to merge 1 commit into
base: main
Choose a base branch
from
Draft

Cortex-M backend: Prerequiste changes to export mv3/mv2 targetting CMSIS-NN backend #16393

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 7 additions & 5 deletions examples/arm/aot_arm_compiler.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -791,6 +791,8 @@ def to_edge_no_delegate(
return model_quant, edge


from executorch.backends.xnnpack._passes import XNNPACKPass

def transform_for_cortex_m_backend(edge_program_manager, args):
# Let's make sure we are using optimized Cortex M backend
# NB: If we can't find and replace ops those are expected to be replaced,
Expand All @@ -802,11 +804,11 @@ def transform_for_cortex_m_backend(edge_program_manager, args):
passes += [ConvertToCortexMPass, QuantizedOpFusionPass]
current_edge = edge_program_manager
for pass_cls in passes:
transform_pass = (
pass_cls(current_edge.exported_program())
if pass_cls.__name__ == "QuantizedLinearFusionPass"
else pass_cls()
)
# XNNPACKPass and its subclasses require exported_program
if issubclass(pass_cls, XNNPACKPass):
transform_pass = pass_cls(current_edge.exported_program())
else:
transform_pass = pass_cls()
current_edge = current_edge.transform([transform_pass])
return current_edge

Expand Down
Loading