MLBEDSW-7316: Fix crash for networks with resource variables

- The problem was that networks with resource variables have
not been thought of. The major problem was the graph traversal
where these ops were not visited resulting in an empty subgraph
that resulted in the crash.
- Fixed the problem by attaching virtual tensors to the ops simulating
subgraph output. These tensors are only used to get the graph
traversal to work.
- Fixed serializing of attribute container and shared_name
- Fixed subgraph index for operator CallOnce
- All resource variable ops are pushed to the CPU

Change-Id: I815f9c81baf7a3fbb686e895980b462f58208b6e
Signed-off-by: Johan Alfven <johan.alfven@arm.com>

1 files changed, 3 insertions, 1 deletions

diff --git a/ethosu/vela/mark_tensors.py b/ethosu/vela/mark_tensors.py
index 64cc7883..4b5bf1dc 100644
--- a/ethosu/vela/mark_tensors.py
+++ b/ethosu/vela/mark_tensors.py
@@ -1,4 +1,4 @@
-# SPDX-FileCopyrightText: Copyright 2020-2021 Arm Limited and/or its affiliates <open-source-office@arm.com>
+# SPDX-FileCopyrightText: Copyright 2020-2023 Arm Limited and/or its affiliates <open-source-office@arm.com>
 #
 # SPDX-License-Identifier: Apache-2.0
 #
@@ -41,6 +41,8 @@ def mark_purpose(tens, arch, purpose):
     # Sets tensor's purpose, format, mem_area and mem_type
     if tens.purpose == TensorPurpose.Unknown:
         tens.purpose = purpose
+    elif tens.purpose == TensorPurpose.Virtual:
+        return
     elif tens.purpose not in (purpose, TensorPurpose.LUT):
         assert 0, "Cannot resolve tensor purpose {} and {} for tensor {}".format(tens.purpose, purpose, tens)