ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-04-20 14:59:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

MX GEMM - FP6 Example (#2419)

Browse Source 
Adds support for MX FP6 data type in MX GEMM block pipeline version v1.
Provides an example of MX FP6 GEMM algorithm.

---------

Co-authored-by: OscarXu <huaiguxu@amd.com>
Co-authored-by: aska-0096 <haocwang@amd.com>
Co-authored-by: mtgu0705 <mtgu@amd.com>
Co-authored-by: Your Name <you@example.com>
Co-authored-by: lalala-sh <Jiaxing.Wen@amd.com>
Co-authored-by: valarLip <340077269@qq.com>
Co-authored-by: Ding, Yi <yi.ding@amd.com>
Co-authored-by: feifei14119 <feiw@amd.com>
Co-authored-by: Lin, Qun <qlin@amd.com>
Co-authored-by: joye <joye@amd.com>
This commit is contained in:
Andriy Roshchenko
2025-07-07 10:33:26 -06:00
committed by GitHub
parent bfe573d3ba
commit 054f85ab7c
18 changed files with 578 additions and 95 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
include/ck/utility/dynamic_buffer.hpp
View File

@@ -34,6 +34,10 @@ struct DynamicBuffer
ElementSpaceSize element_space_size_;
T invalid_element_value_ = T{0};
// XXX: PackedSize semantics for pk_i4_t is different from the other packed types.
// Objects of f4x2_pk_t and f6_pk_t are counted as 1 element, while
// objects of pk_i4_t are counted as 2 elements. Therefore, element_space_size_ for pk_i4_t must
// be divided by 2 to correctly represent the number of addressable elements.
static constexpr index_t PackedSize = []() {
if constexpr(is_same_v<remove_cvref_t<T>, pk_i4_t>)
return 2;