How to force memory generated in clusters to be implemented in MLAB in FPGA OpenCL v19.1

There is new feature in FPGA OpenCL v19.1 that one could force memory blocks to be implemented in MLAB or M20K as described in the guide:

But it only works on variables that are explicitly defined in the code. Some time the compiler will generate lots of memory in the clusters like follows:

When I use multiple kernels, it became very costly in M20K.

So is there any way that one could force such memory to be implemented in MLAB rather than M20K ?