mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-03 05:01:25 +00:00
0394f8a713
* port layernorm
* change warp_welford.hpp
* Update warpshuffle
* 1. Add save mean and save std back
2. Move construction of tensor_view and tile_window to operator()
* refine welford max count calculation
* unify layernorm api
* Rename file
* Remove save mean and inv std
* Revert "refine welford max count calculation"
This reverts commit 022365802b.
* Fix order of parameter
* refine welford max count calculation again
* Remove fp32 instances
* Fix bug of padding
* refactor api
* Support bf16
* Extract common function
* Refine arg of operator()
* Add kMThreadPerBlock to template parameter
* clang format
* Refine variable name
* Refine file name
* remove redundant line
* refactor layernorm2d pipeline and add block-per-block utility
* fix name
* rename more
* add more block-per-tile instance
* remove duplicated define
* update instance for 2048, 1024 case
* support up to 2048 now
* opt loading
* add n1536
* Add two pass pipeline
* format
* Fix incorrect type
* parallel compilation
* Use smaller N
* fix 2p pass
* Support Repeat_M in distribution
* Refine nameing
* Add reduce example
---------
Co-authored-by: letaoqin <letaoqin@amd.com>
Co-authored-by: aska-0096 <haocwang@amd.com>
Co-authored-by: rocking <ChunYu.Lai@amd.com>
Co-authored-by: carlushuang <carlus.huang@amd.com>
19 lines
986 B
CMake
19 lines
986 B
CMake
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("adding example ${EXAMPLE_REDUCE}")
|
|
|
|
add_executable(${EXAMPLE_REDUCE} EXCLUDE_FROM_ALL 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})
|
|
|
|
# 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) |