Skip to content

Revert "Arm backend: Match fp32->int32 cast between pytorch and TOSA'… #12309

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

Closed
psiddh wants to merge 1 commit into from
Closed

Revert "Arm backend: Match fp32->int32 cast between pytorch and TOSA'… #12309

Show file tree
Hide file tree
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
1 change: 0 additions & 1 deletion backends/arm/_passes/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,7 +51,6 @@
from .decompose_sqrt_pass import DecomposeSqrtPass # noqa
from .decompose_sum_pass import DecomposeSumPass # noqa
from .decompose_var_pass import DecomposeVarPass # noqa
from .decorate_fp32_to_int32_casting_pass import DecorateFp32toInt32CastingPass # noqa
from .fold_qdq_with_annotated_qparams_pass import ( # noqa
FoldAndAnnotateQParamsPass,
QuantizeOperatorArguments,
Expand Down
4 changes: 0 additions & 4 deletions backends/arm/_passes/arm_pass_manager.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,7 +56,6 @@
DecomposeSqrtPass,
DecomposeSumPass,
DecomposeVarPass,
DecorateFp32toInt32CastingPass,
FoldAndAnnotateQParamsPass,
FuseBatchnorm2DPass,
FuseConstantArgsPass,
Expand Down Expand Up @@ -201,9 +200,6 @@ def _tosa_080_MI_pipeline(self, exported_program: ExportedProgram) -> GraphModul
self.add_pass(MatchArgRanksPass(exported_program))
self.add_pass(DecomposeAdaptiveAvgPool2dPass())
self.add_pass(DecomposeAvgPool2d())
self.add_pass(
DecorateFp32toInt32CastingPass()
) # Require that no new fp32->int32 is introduced after this pass
self.add_pass(ComputeConstantOpsAOT(exported_program))

self.add_pass(DecomposeGroupedConv())
Expand Down
78 changes: 0 additions & 78 deletions backends/arm/_passes/decorate_fp32_to_int32_casting_pass.py
View file
Open in desktop

This file was deleted.

80 changes: 0 additions & 80 deletions backends/arm/test/passes/test_decorate_fp32_to_int32_casting_pass.py
View file
Open in desktop

This file was deleted.

Loading