Rod Burns

Can you post the output of the "computecpp_info" tool located in the "bin" folder of the ComputeCpp release you are using?

Can you provide more information about what you are trying to do, what your hardware set up is and steps to reproduce the issue?

The latest guide docs are here https://www.codeplay.com/products/computesuite/computecpp/guides/how-to-setup-tensorflow-with-computecpp and you would be better trying the branch at https://github.com/lukeiwanski/tensorflow.git which has the latest code base.

That is not unexpected at the moment, we are adding vectorization which optimizes the implementation. This is being prepared as a pull request and will be available soon.

The latest OpenCL for TensorFlow work now lives here https://github.com/codeplaysoftware/tensorflow It has not been tested with Windows.

We would like to add support for ComputeCpp on Windows, but currently we don't have firm timescales. I assume this is what you are asking.

Yes we do plan to make a Windows version of ComputeCpp available that should enable you to work with AMD GPU on Windows, but as I say I am not...

The latest OpenCL for TensorFlow work now lives here https://github.com/codeplaysoftware/tensorflow You can follow the guide here https://developer.codeplay.com/products/computecpp/ce/guides/tensorflow-guide/tensorflow-generic-setup

We are just trying to reproduce this at the moment.

The most up to date branch to use is here https://github.com/lukeiwanski/tensorflow-opencl.git with changes being pushed to the main TensorFlow branch. I believe what you are seeing is fixed in that...