ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-04 21:51:28 +00:00
Code Issues Packages Projects Releases Wiki Activity

[CK_TILE] Add Flatmm MX FP8 (#3208)

Browse Source 
* Use async for flatmm mxfp4

* Fix preshuffle

* Add flatmm mxfp8

* Thanks, Copilot

* Thanks Copilot again~
This commit is contained in:
Yi DING
2025-11-20 10:35:15 +08:00
committed by GitHub
parent 4e49e0228b
commit 47e2ed838e
17 changed files with 698 additions and 595 deletions
Download Patch File Download Diff File Expand all files Collapse all files

85
example/ck_tile/18_flatmm/mxgemm/mx_flatmm.hpp
View File

@@ -12,4 +12,87 @@
#include "ck_tile/ops/flatmm.hpp"
#include "ck_tile/ops/gemm.hpp"
#include "mxfp4_flatmm.hpp"
// GEMM config with 16x16 warp tile
struct MXfp4_FlatmmConfig16
{
static constexpr ck_tile::index_t M_Tile = 128;
static constexpr ck_tile::index_t N_Tile = 512;
static constexpr ck_tile::index_t K_Tile = 256;
static constexpr ck_tile::index_t M_Warp = 1;
static constexpr ck_tile::index_t N_Warp = 4;
static constexpr ck_tile::index_t K_Warp = 1;
static constexpr ck_tile::index_t M_Warp_Tile = 16;
static constexpr ck_tile::index_t N_Warp_Tile = 16;
static constexpr ck_tile::index_t K_Warp_Tile = 128;
static constexpr bool kPadM = false;
static constexpr bool kPadN = false;
static constexpr bool kPadK = false;
static constexpr bool TransposeC = false;
static constexpr bool UseStructuredSparsity = false;
static constexpr int kBlockPerCu = 1;
static constexpr int TileParitionerGroupNum = 8;
static constexpr int TileParitionerM01 = 4;
static constexpr auto Scheduler = ck_tile::GemmPipelineScheduler::Default;
static constexpr ck_tile::index_t NumWaveGroups = 1;
static constexpr bool DoubleSmemBuffer = false;
static constexpr int N_Repeat = N_Tile / N_Warp_Tile / N_Warp;
static constexpr bool TiledMMAPermuteN = false;
};
struct MXfp8_FlatmmConfig16
{
static constexpr ck_tile::index_t M_Tile = 128;
static constexpr ck_tile::index_t N_Tile = 256;
static constexpr ck_tile::index_t K_Tile = 256;
static constexpr ck_tile::index_t M_Warp = 1;
static constexpr ck_tile::index_t N_Warp = 4;
static constexpr ck_tile::index_t K_Warp = 1;
static constexpr ck_tile::index_t M_Warp_Tile = 16;
static constexpr ck_tile::index_t N_Warp_Tile = 16;
static constexpr ck_tile::index_t K_Warp_Tile = 128;
static constexpr bool kPadM = false;
static constexpr bool kPadN = false;
static constexpr bool kPadK = false;
static constexpr bool TransposeC = false;
static constexpr bool UseStructuredSparsity = false;
static constexpr int kBlockPerCu = 1;
static constexpr int TileParitionerGroupNum = 8;
static constexpr int TileParitionerM01 = 4;
static constexpr auto Scheduler = ck_tile::GemmPipelineScheduler::Default;
static constexpr ck_tile::index_t NumWaveGroups = 1;
static constexpr bool DoubleSmemBuffer = false;
static constexpr int N_Repeat = N_Tile / N_Warp_Tile / N_Warp;
static constexpr bool TiledMMAPermuteN = false;
};
template <typename FlatmmConfig,
typename ADataType,
typename BDataType,
typename DsDatatype,
typename AccDataType,
typename CDataType,
typename ALayout,
typename BLayout,
typename DsLayout,
typename ELayout,
typename ScaleM,
typename ScaleN,
bool persistent,
typename CDEElementWise,
bool Splitk,
bool HasHotLoop,
ck_tile::TailNumber TailNum>
float mx_flatmm_calc(const ck_tile::ScaleFlatmmHostArgs<ScaleM, ScaleN>& args,
const ck_tile::stream_config& s);