ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-04 05:31:24 +00:00
Code Issues Packages Projects Releases Wiki Activity

[CK_TILE] Patch for pk_fp4 ref check and buffer load. (#3044)

Browse Source 
* Patch for pk_fp4_raw_t buffer load and ref check
This commit is contained in:
Gino Lu
2025-10-20 14:47:04 +08:00
committed by GitHub
parent af3786fe08
commit fb1d090f3c
2 changed files with 54 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
include/ck_tile/core/arch/amd_buffer_addressing_builtins.hpp
View File

@@ -1405,6 +1405,8 @@ CK_TILE_DEVICE thread_buffer<T, N> amd_buffer_load_impl(int32x4_t src_wave_buffe
(std::is_same<T, fp8_t>::value && (N == 1 || N == 2 || N == 4 || N == 8 || N == 16)) ||
(std::is_same<T, bf8_t>::value && (N == 1 || N == 2 || N == 4 || N == 8 || N == 16)) ||
(std::is_same<T, int8_t>::value && (N == 1 || N == 2 || N == 4 || N == 8 || N == 16)) ||
(std::is_same<T, pk_fp4_raw_t>::value &&
(N == 1 || N == 2 || N == 4 || N == 8 || N == 16)) ||
(std::is_same<T, pk_int4_t>::value &&
(N == 1 || N == 2 || N == 4 || N == 8 || N == 16 || N == 32)),
"wrong! not implemented");