Dear IPP user,
We have scale 12 bits image into 16 bits with 4-bit zero and 16bits pack to 12bits in IPP, while hasn't the API to convert 10bit Image to 16it or 8it currently, . But you can raise the feature request through Intel online service center https://supporttickets.intel.com/servicecenter?lang=en-US
For the SSE/AVX intrinsic, there isn't only one instruction to convert 10bit Image to 16it or 8it directly, you need to use several instructions to meet your goal.
This issue is closing and we will no longer respond to this thread. If you require additional assistance from Intel, please start a new thread. Any further interaction in this thread will be considered community only.