mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-19 04:19:36 +00:00
58d8d793b1
* WIP
* Add Unit tests for the Multi Reduction Kernel
* clang format
* Rename multiblock to threadwise
* Multiblock WIP
* Fix multi reduce multi block unit tests
* Multi Reduce Tile Engine: WIP
* refactoring + try addressing precision error
* Fix multiops examples
* Cleanup
* Clean up tile engine's reduce op
* Update changelog
* Fix remod/clang
* Fix dates
* Fix documentation & missing file
* Fix comments
* Use the update_tile api in the multi-block kernel
* Unify threadwise/multiblock into a single kernel + default multiblock output to float in tests
* Add TileParitioner
* Cleanup
* Add warning when no data to process, in the example
* Refactoring Reduce kernel Tile Partioner + cleanup
* Move the tile partioner to its own file
* Add missing includes
* Fix copyright header with update_amd_copyright_headers.py
* Fix change of interface in Reduce2dProblem
---------
Co-authored-by: Damien Lejeune <damien.lejeune@amd.com>
Co-authored-by: Adam Osewski <19374865+aosewski@users.noreply.github.com>
[ROCm/composable_kernel commit: 4216d43da8]
39 lines
2.1 KiB
CMake
39 lines
2.1 KiB
CMake
# Copyright (c) Advanced Micro Devices, Inc., or its affiliates.
|
|
# SPDX-License-Identifier: MIT
|
|
|
|
set(EXAMPLE_REDUCE "tile_example_reduce")
|
|
# not using add_example_executable() to add this target, since we don't want this to have
|
|
# to be included in "make all/install/check"
|
|
message(DEBUG "adding example ${EXAMPLE_REDUCE}")
|
|
|
|
add_executable(${EXAMPLE_REDUCE} reduce.cpp)
|
|
target_include_directories(${EXAMPLE_REDUCE} PRIVATE ${CMAKE_CURRENT_LIST_DIR})
|
|
set(EXAMPLE_REDUCE_COMPILE_OPTIONS)
|
|
|
|
# NOTE: we turn off undefined-func-template to let source compile without explicit declare function specializations
|
|
list(APPEND EXAMPLE_REDUCE_COMPILE_OPTIONS -Wno-undefined-func-template -Wno-float-equal)
|
|
|
|
target_compile_options(${EXAMPLE_REDUCE} PRIVATE ${EXAMPLE_REDUCE_COMPILE_OPTIONS})
|
|
|
|
# Multi Reduce Threadwise Example
|
|
set(EXAMPLE_MULTI_REDUCE "tile_example_multi_reduce_threadwise")
|
|
add_executable(${EXAMPLE_MULTI_REDUCE} EXCLUDE_FROM_ALL multiple_reduce_threadwise.cpp)
|
|
target_include_directories(${EXAMPLE_MULTI_REDUCE} PRIVATE ${CMAKE_CURRENT_LIST_DIR})
|
|
set(EXAMPLE_MULTI_REDUCE_COMPILE_OPTIONS)
|
|
list(APPEND EXAMPLE_MULTI_REDUCE_COMPILE_OPTIONS -Wno-undefined-func-template -Wno-float-equal)
|
|
target_compile_options(${EXAMPLE_MULTI_REDUCE} PRIVATE ${EXAMPLE_MULTI_REDUCE_COMPILE_OPTIONS})
|
|
|
|
# Multi Reduce Blockwise Example
|
|
set(EXAMPLE_MULTI_REDUCE_BLOCKWISE "tile_example_multi_reduce_multiblock")
|
|
add_executable(${EXAMPLE_MULTI_REDUCE_BLOCKWISE} EXCLUDE_FROM_ALL multiple_reduce_multiblock.cpp)
|
|
target_include_directories(${EXAMPLE_MULTI_REDUCE_BLOCKWISE} PRIVATE ${CMAKE_CURRENT_LIST_DIR})
|
|
set(EXAMPLE_MULTI_REDUCE_BLOCKWISE_COMPILE_OPTIONS)
|
|
list(APPEND EXAMPLE_MULTI_REDUCE_BLOCKWISE_COMPILE_OPTIONS -Wno-undefined-func-template -Wno-float-equal)
|
|
target_compile_options(${EXAMPLE_MULTI_REDUCE_BLOCKWISE} PRIVATE ${EXAMPLE_MULTI_REDUCE_BLOCKWISE_COMPILE_OPTIONS})
|
|
|
|
# TODO: we have to turn off this global prop, otherwise the progress bar generated
|
|
# by cmake will print too many files, execvp: /bin/sh: Argument list too long
|
|
# however, this property may affect global
|
|
# TODO: consider codegen a makefile by us
|
|
set_property(GLOBAL PROPERTY RULE_MESSAGES OFF)
|