Adam Osewski b7659e284a Remove unused lds direct load instruction. (#2573) ...

This functionality is replaced by amd_async_buffer_load

Co-authored-by: Max Podkorytov <4273004+tenpercent@users.noreply.github.com>
Co-authored-by: Aviral Goel <aviral.goel@amd.com>

[ROCm/composable_kernel commit: 2622ff06cb]

2025-08-06 15:16:12 +02:00

..

amd_buffer_addressing_builtins.hpp

Expand the bandwidth of direct_global_to_lds for gfx950 (#2576)

2025-07-28 23:56:53 -07:00

amd_buffer_addressing.hpp

Remove unused lds direct load instruction. (#2573)

2025-08-06 15:16:12 +02:00

amd_transpose_load_encoding.hpp

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

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

arch.hpp

Remove unused lds direct load instruction. (#2573)

2025-08-06 15:16:12 +02:00

generic_memory_space_atomic.hpp

…

utility.hpp

Do not use warpSize as compile time constant as it is removed (#2320)

2025-06-17 11:54:30 -07:00

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