GitLab

* start convert

* using buffer load

* add kernel transfer fun

* using asm for transfer

* add transpose_half_to_bhalf_2x2

* add TypeMap struct

* add LDSDataType to v2r3 and v2r4r2

* change convert fun name

* remove asm in half transfer to bhalf

* fix bug for type_convert

* cshuffle_v1 add LDSDataType

* add ldstype for gridegemm v2r4

* add lds datat ype to v3r1 2 3

* init complete

* fix function name

* remove comments

* format

* fix for merge develop
Co-authored-by: ltqin <letaoqin@amd.com>