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>

* delete obselete files

* move files

* build

* update cmake

* update cmake

* fix build

* reorg examples

* update cmake for example and test

* start fixing 16bit data packing

* adding StaticTensor

* adding StaticTensor

* adding StaticTensor

* add missing constexpr

* adding static tensor

* adding static tensor

* adding transpose

* add inline asm for transpose 2x2 of half_t

* add general transpose_vectors(), but have unnecessary register initialization using v_mov

* fix unnecessary register initialization in transpose_vector by using more pass-by-reference

* add hardcoded logic for NHWC wrw

* improve asm for v_pack

* make ThreadwiseTensorSliceTransfer_v3r2 support any tensor

* tweak

* reorganize file