mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-14 02:02:46 +00:00
65d6442b4c
* replace buffer_atomic with global_atomic
* fixed global_atomic_add
* added bf16 atomic_add
* format
* clang-format-12
* clean
* clean
* add guards
* Update gtest.cmake
* enabled splitk_gemm_multi_d
* format
* add ckProfiler
* format
* fixed naming
* format
* clean
* clean
* add guards
* fix clang format
* format
* add kbatch printout
* clean
* Add rocm6.2 related gemm optimization
* Limit bf16 atomic usage
* remove redundant RCR gemm_universal instance
* Add RRR fp8 gemm universal instance
* Bug fix
* Add GPU_TARGET guard to FP8/BF8 target
* bug fix
* update cmake
* remove all fp8/bf8 example if arch not support
* Enable fp8 RRR support in ckProfiler
* limit greedy-reverse flag to gemm_universal in ckProfiler
---------
Co-authored-by: Jing Zhang <jizhan@fb.com>
Co-authored-by: Jing Zhang <jizhan@meta.com>
Co-authored-by: zjing14 <zhangjing14@gmail.com>
Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>
Co-authored-by: illsilin <Illia.Silin@amd.com>
[ROCm/composable_kernel commit: 3049b5467c]
80 lines
2.4 KiB
CMake
80 lines
2.4 KiB
CMake
cmake_minimum_required(VERSION 3.15)
|
|
project(ck_app)
|
|
add_compile_options(-std=c++17)
|
|
|
|
if (DTYPES)
|
|
add_definitions(-DDTYPES)
|
|
if (DTYPES MATCHES "int8")
|
|
add_definitions(-DCK_ENABLE_INT8)
|
|
set(CK_ENABLE_INT8 "ON")
|
|
endif()
|
|
if (DTYPES MATCHES "fp8")
|
|
add_definitions(-DCK_ENABLE_FP8)
|
|
set(CK_ENABLE_FP8 "ON")
|
|
endif()
|
|
if (DTYPES MATCHES "bf8")
|
|
add_definitions(-DCK_ENABLE_BF8)
|
|
set(CK_ENABLE_BF8 "ON")
|
|
endif()
|
|
if (DTYPES MATCHES "fp16")
|
|
add_definitions(-DCK_ENABLE_FP16)
|
|
set(CK_ENABLE_FP16 "ON")
|
|
endif()
|
|
if (DTYPES MATCHES "fp32")
|
|
add_definitions(-DCK_ENABLE_FP32)
|
|
set(CK_ENABLE_FP32 "ON")
|
|
endif()
|
|
if (DTYPES MATCHES "fp64")
|
|
add_definitions(-DCK_ENABLE_FP64)
|
|
set(CK_ENABLE_FP64 "ON")
|
|
endif()
|
|
if (DTYPES MATCHES "bf16")
|
|
add_definitions(-DCK_ENABLE_BF16)
|
|
set(CK_ENABLE_BF16 "ON")
|
|
endif()
|
|
message("DTYPES macro set to ${DTYPES}")
|
|
else()
|
|
add_definitions(-DCK_ENABLE_INT8 -DCK_ENABLE_FP16 -DCK_ENABLE_FP32 -DCK_ENABLE_FP64 -DCK_ENABLE_BF16)
|
|
set(CK_ENABLE_INT8 "ON")
|
|
set(CK_ENABLE_FP16 "ON")
|
|
set(CK_ENABLE_FP32 "ON")
|
|
set(CK_ENABLE_FP64 "ON")
|
|
set(CK_ENABLE_BF16 "ON")
|
|
if (GPU_TARGETS MATCHES "gfx94")
|
|
add_definitions(-DCK_ENABLE_FP8 -DCK_ENABLE_BF8)
|
|
set(CK_ENABLE_FP8 "ON")
|
|
set(CK_ENABLE_BF8 "ON")
|
|
endif()
|
|
endif()
|
|
|
|
if (GPU_TARGETS)
|
|
if (GPU_TARGETS MATCHES "gfx9")
|
|
add_definitions(-DCK_USE_XDL)
|
|
set(CK_USE_XDL "ON")
|
|
endif()
|
|
if (GPU_TARGETS MATCHES "gfx11")
|
|
add_definitions(-DCK_USE_WMMA)
|
|
set(CK_USE_WMMA "ON")
|
|
endif()
|
|
else()
|
|
add_definitions(-DCK_USE_WMMA -DCK_USE_XDL)
|
|
set(CK_USE_XDL "ON")
|
|
set(CK_USE_WMMA "ON")
|
|
endif()
|
|
|
|
find_package(composable_kernel COMPONENTS device_other_operations device_gemm_operations device_conv_operations device_reduction_operations)
|
|
if(GPU_TARGETS MATCHES "gfx9")
|
|
find_package(composable_kernel COMPONENTS device_contraction_operations)
|
|
endif()
|
|
find_package(hip REQUIRED PATHS /opt/rocm)
|
|
message(STATUS "Build with HIP ${hip_VERSION}")
|
|
|
|
# add all example subdir
|
|
file(GLOB dir_list LIST_DIRECTORIES true *)
|
|
FOREACH(subdir ${dir_list})
|
|
IF(IS_DIRECTORY "${subdir}" AND (NOT "${subdir}" MATCHES "build")
|
|
AND (NOT "${subdir}" MATCHES ".vscode"))
|
|
add_subdirectory(${subdir})
|
|
ENDIF()
|
|
ENDFOREACH()
|