[BUG] Model with element-wise select / torch.where() fails to finalize

[mako443]

Describe the bug
If a model contains the QNN ElementWiseSelect operation, equivalent to torch.where(), it converts successfully but the graph fails to finalize on device or in the emulator.

To Reproduce
Steps to reproduce the behavior:

• Compile job is here: https://app.aihub.qualcomm.com/jobs/j0pxk1885/
• You can create an equivalent model in Pytorch with

class Where(nn.Module):
    def __init__(self):
        super(Where, self).__init__()
        self.conv1 = nn.Conv2d(3, 3, kernel_size=3, padding=1)

    def forward(self, x):
        mask = x > 0.5
        y = x - 1.0
        x = torch.where(mask, x, y)
        x = self.conv1(x)
        return x

x = torch.rand(1, 3, 16, 16)
y = Where()(x)

Expected behavior
After conversion, the model should run on the emulator and device as expected.

Stack trace
Output from qnn-net-run:

qnn-net-run pid:21299
WARNING: linker: Warning: unable to normalize "$/data/local/tmp/QNN-2.19" (ignoring)
WARNING: linker: Warning: unable to normalize "$/data/local/tmp/QNN-2.19" (ignoring)
Graph Finalize failure

Host configuration:

• QAI-Hub-Models version: aihub-2024.03.07.0
• QAI-Hub client version: 0.9.0

Additional context
As a heads-up: The operation also fails to finalize when converting through the qnn-pytorch-converter or going creating the model "manually" in C++.

[gustavla]

Thanks for reporting this issue! I have filed an internal bug report for this.

[kory]

This is fixed as of QNN 2.27. Verified today on AI Hub: https://app.aihub.qualcomm.com/jobs/j5mn6loqp/