mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-04 13:41:24 +00:00
[CK Tile] Spatially local GEMM tile partitioner. (#1843)
* Add spatially local tile partitioner
* Use 1D Grid size & create partitioner object.
* Docs & use 1D partitioner in example.
* Clang format.
* Change kernel grid size
Now: X is the # of output C-tiles,
Y is the batch count
Z is the splitK
* Formatting & more doc.
* Clang format.
* Fix batched gemm test. Use 1d partitioner.
* Move condition.
* FIx ctor.
* clang-format.
This commit is contained in:
@@ -50,7 +50,9 @@ float gemm_calc(const ck_tile::GemmHostArgs& args, const ck_tile::stream_config&
|
||||
|
||||
constexpr bool TransposeC = false;
|
||||
|
||||
constexpr int kBlockPerCu = 1;
|
||||
constexpr int kBlockPerCu = 1;
|
||||
constexpr ck_tile::index_t TileParitionerGroupNum = 8;
|
||||
constexpr ck_tile::index_t TileParitionerM01 = 4;
|
||||
|
||||
// ===============================================
|
||||
|
||||
@@ -58,7 +60,8 @@ float gemm_calc(const ck_tile::GemmHostArgs& args, const ck_tile::stream_config&
|
||||
ck_tile::TileGemmShape<ck_tile::sequence<M_Tile, N_Tile, K_Tile>,
|
||||
ck_tile::sequence<M_Warp, N_Warp, K_Warp>,
|
||||
ck_tile::sequence<M_Warp_Tile, N_Warp_Tile, K_Warp_Tile>>;
|
||||
using TilePartitioner = ck_tile::GemmTile2DPartitioner<GemmShape>;
|
||||
using TilePartitioner = ck_tile::
|
||||
GemmSpatiallyLocalTilePartitioner<GemmShape, TileParitionerGroupNum, TileParitionerM01>;
|
||||
|
||||
using Traits = ck_tile::TileGemmTraits<kPadM, kPadN, kPadK, ALayout, BLayout, CLayout>;
|
||||
using GemmUniversalTraits = ck_tile::
|
||||
|
||||
Reference in New Issue
Block a user