(had to close PR into master and open this PR into 3.4)

1. Run OpenCL kernels on 4x less work items as each item computes 4 pixels
2. Use float4 vector arithmetic in NV12->BGR kernel

If applied together with PR19755, performance of the following command

example_tapi_video_acceleration -accel=any -opencl=true -i=input.mp4 -o=null

increases on my iGPU from ~550fps to ~850fps (H264 1080p input video).

Pull Request Readiness Checklist

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

• I agree to contribute to the project under Apache 2 License.
• To the best of my knowledge, the proposed patch is not based on a code under GPL or other license that is incompatible with OpenCV
• The PR is proposed to proper branch
• There is reference to original bug report and related work
• There is accuracy test, performance test and test data in opencv_extra repository, if applicable
  Patch to opencv_extra has the same branch name.
• The feature is well documented and sample code can be built with the project CMake