tensorflow: TfLiteGpuDelegateV2Create() causes segmentation fault with tflite-gpu2.8 on native side in Android

Please make sure that this is a bug. As per our GitHub Policy, we only address code/doc bugs, performance issues, feature requests and build/installation issues on GitHub. tag:bug_template

System information

• Have I written custom code (as opposed to using a stock example script provided in TensorFlow):Yes
• OS Platform and Distribution (e.g., Linux Ubuntu 16.04):Android 10, API 29
• Mobile device (e.g. iPhone 8, Pixel 2, Samsung Galaxy) if the issue happens on mobile device: Galaxy S9
• TensorFlow installed from (source or binary): binary
• TensorFlow version (use command below): 2.8
• Python version: N/A
• Bazel version (if compiling from source): N/A
• GCC/Compiler version (if compiling from source): N/A
• CUDA/cuDNN version: N/A
• GPU model and memory: Qualcomm Adreno 630

You can collect some of this information using our environment capture script You can also obtain the TensorFlow version with:

1. TF 1.0: python -c "import tensorflow as tf; print(tf.GIT_VERSION, tf.VERSION)"
2. TF 2.0: python -c "import tensorflow as tf; print(tf.version.GIT_VERSION, tf.version.VERSION)"

Describe the current behavior

1. On Native side. auto* delegate = TfLiteGpuDelegateV2Create(/*default options=*/nullptr); results in following error with tensorflow-lite 2.8 A/libc: Fatal signal 11 (SIGSEGV), code 1 (SEGV_MAPERR), fault addr 0x18 in tid 23129 (com.example.gpu), pid 23129 (com.example.gpu)

2. In Java. GPU delegation works fine with tensorflow-lite 2.8, following code works well. GpuDelegate.Options delegateOptions = compatList.getBestOptionsForThisDevice(); delegate = new GpuDelegate(delegateOptions); options.addDelegate(delegate);

Describe the expected behavior No segmentation fault in 1.

Contributing

• Do you want to contribute a PR? (yes/no): Not at the moment
• Briefly describe your candidate solution(if contributing):

Standalone code to reproduce the issue Provide a reproducible test case that is the bare minimum necessary to generate the problem. If possible, please share a link to Colab/Jupyter/any notebook. I downloaded the tflite-2.8 and tflite-gpu-2.8 from the maven repository(https://search.maven.org/) and added them to a new C++ Android project. And in the default native-lib.cpp added the above code, which throws the error.

Other info / logs Include any logs or source code that would be helpful to diagnose the problem. If including tracebacks, please include the full traceback. Large logs and files should be attached.