ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-03 05:01:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

Stream-K Tile Partitioner Base Class with Tests

Browse Source 
To better align with the original Stream-K paper, this change implements
a new Stream-K tile partitioner base class. This class will handle the
Stream-K setup that is common to both a persistent and non-persistent DP
section. A later change will implement derived classes to handle the
differences between persistent and non-persistent DP.

This change also includes unit tests for the base tile partitioner.
This commit is contained in:
Emily Martins
2025-10-08 15:53:19 +00:00
committed by Emily Martins
parent 2d1c9e28e2
commit f87f768d16
6 changed files with 1073 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
test/ck_tile/gemm_streamk/CMakeLists.txt
View File

@@ -4,7 +4,7 @@ if(GPU_TARGETS MATCHES "gfx9")
include_directories(BEFORE ${CMAKE_CURRENT_SOURCE_DIR})
#TODO: support all arches
#TODO: current stream-k c-shuffle only supports C layout as R
#TODO: current c-shuffle only supports C layout as R
add_gtest_executable(test_ck_tile_streamk_smoke
${CMAKE_CURRENT_SOURCE_DIR}/smoke_tests/f16_rrr_compv3_256x256x32_2x2x1_32x32x16_NonPersistent.cpp
#${CMAKE_CURRENT_SOURCE_DIR}/smoke_tests/f16_rrc_compv3_256x256x32_2x2x1_32x32x16_NonPersistent.cpp
@@ -116,6 +116,7 @@ if(GPU_TARGETS MATCHES "gfx9")
# ${CMAKE_CURRENT_SOURCE_DIR}/extended_tests/mem/bf16_ccr_mem_128x128x32_2x2x1_32x32x16_NonPersistent.cpp
# #${CMAKE_CURRENT_SOURCE_DIR}/extended_tests/mem/bf16_ccc_mem_128x128x32_2x2x1_32x32x16_NonPersistent.cpp
# )
add_gtest_executable(test_ck_tile_streamk_tile_partitioner test_streamk_tile_partitioner.cpp)
else()
message(DEBUG "Skipping test_ck_tile_streamk tests for current target")
endif()