Skip to content

Qualcomm AI Engine Direct - Test int64 get_attr cast order in the rework suite #24046

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

Open
msluszniak wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Qualcomm AI Engine Direct - Test int64 get_attr cast order in the rework suite #24046

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
18 changes: 18 additions & 0 deletions backends/qualcomm/tests/rework/src/pattern.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4209,9 +4209,15 @@ def forward(self, x, y):
squeeze_out = view_out.squeeze(-1)
return squeeze_out, conv_out

class _RemainderByScalar(torch.nn.Module):
# DecomposeRemainder turns the scalar into an int64 get_attr at the graph head
def forward(self, x, idx):
return x + (idx % 80).float()

@staticmethod
@unpack_pass_fixtures
def test(
subtests,
quantizer,
compile_spec,
backend_type: QnnExecuTorchBackendType,
Expand All @@ -4237,6 +4243,18 @@ def test(
gm, exir_ops.edge.aten._to_copy.default, expected_casts
)

# The int32 cast of a constant must still follow it once the constant is lifted
with subtests.test(msg="constant_cast_order"):
gm = pass_pipeline.lower_edge_ep(
module=I64toI32._RemainderByScalar(),
sample_input=(torch.randn(1, 3), torch.tensor([[3, 170, 85]])),
backend_type=backend_type,
compile_spec=compile_spec,
target_pass=target_pass,
quantizer=quantizer,
).graph_module
gm.graph.lint()


class InsertIOQDQ:
class _Basic(torch.nn.Module):
Expand Down
Loading