zjing14 7ecdba878f add vector load 16/32 for bf16/fp16 (#2779) ...

* add vector load 16/32 for bf16/fp16

* comment addressed

* clang format

---------

Co-authored-by: Jing Zhang <jizhan@fb.com>
Co-authored-by: ThomasNing <thomas.ning@amd.com>

2025-09-09 23:15:19 -07:00

..

amd_buffer_addressing_builtins.hpp

add vector load 16/32 for bf16/fp16 (#2779)

2025-09-09 23:15:19 -07:00

amd_buffer_addressing.hpp

[CK_TILE] FMHA avoid unnecessary vmcnt0 (#2715)

2025-08-25 20:55:12 +08:00

amd_transpose_load_encoding.hpp

[CK_TILE] Use read_tr in universal gemm (#2436)

2025-07-16 23:56:22 -07:00

arch.hpp

[CK_TILE] Allow switching between SGPR/VGPR get_warp_id() return values (#2669)

2025-08-22 10:17:05 +08:00

generic_memory_space_atomic.hpp

[CK_TILE] CK_TILE GEMM WMMA Support for GFX11/GFX12 (#2466)

2025-08-15 16:22:27 -07:00

utility.hpp

Re-enable optimization for gfx950 fmha fwd (#2671)

2025-08-13 14:57:43 +08:00

workgroup_barrier.hpp

[CK_TILE] optimize moe sorting kernel, boost large context case up to 20x (#2153)

2025-05-06 17:32:07 +08:00