onnxruntime

Improve performance of BiasGelu on oneDNN execution provider (#11935)

Improve performance of BiasGelu on OneDNN execution provider

This modifies how BiasGelu is handled by the OneDNN execution provider
by executing the gelu_erf primitive as a postop of the binary_add primitive.

Also fixes extra data copies made when running on GPU.

Signed-off-by: George Nash <george.nash@intel.com>