Files
composable_kernel/profiler/CMakeLists.txt
ltqin 0180bb825c NHWC conv 2d: bwd fp32/fp16/bfp16/int8, Device level tuning and host API (#92)
* start conv2d bwd api

* kernel running

* add bwd reference

* change to no shuffle

* fix bwd reference

* pass verification

* add Filter1x1Stride1Pad0 and start testing

* change some tuning parameter

* fix test error

* add fp16 tuning parameter

* add bf16 tuning parameter

* add int8 tuning parameters

* change fp32 tuning parameter

* add bwd to profiler

* fix bug for bwd profiler

* fix ckProfiler bug

* change conv2d_bwd_xdl to fp16

* fix bug in comments

* fix precompile id

* fix enum conv name

* chage _bwd_ to _bwd_data_

* change conv2d_bwd example id

* bwd to bwd data

* fix prehead

* fix MakeDefaultBlock2CTileMap ,import form merge develop

* format bwd instance

* bwd to bwd data

* change name bwd to bwd data

* change name bwd to bwd data in example

* formate code

* change conv2d bwd data id in example

* rewrite readme for example

* fix CalculateMagicNumbers about div zero

* add workaround CK_WORKAROUND_SWDEV_325164

* change test_conf2d_bwd_data show info

* format

* fix bug for workaround:CK_WORKAROUND_SWDEV_325164

* formate tuning parameters

* formate tuning parameters again

* formate tuning parameters 3

* formate tuning parameters 4

* remove add function template

* format

* update comment

Co-authored-by: ltqin <letaoqin@amd.com>
Co-authored-by: Chao Liu <chao.liu2@amd.com>

[ROCm/composable_kernel commit: c254e5abd2]
2022-03-04 00:08:26 -06:00

44 lines
1.9 KiB
CMake

include_directories(BEFORE
include
${PROJECT_SOURCE_DIR}/host/host_tensor/include
${PROJECT_SOURCE_DIR}/device/include
${PROJECT_SOURCE_DIR}/device_operation/include
${PROJECT_SOURCE_DIR}/reference_operation/include
${PROJECT_SOURCE_DIR}/profiler/include
${PROJECT_SOURCE_DIR}/composable_kernel/include
${PROJECT_SOURCE_DIR}/composable_kernel/include/utility
${PROJECT_SOURCE_DIR}/composable_kernel/include/tensor_description
${PROJECT_SOURCE_DIR}/composable_kernel/include/tensor_operation
${PROJECT_SOURCE_DIR}/composable_kernel/include/problem_transform
${PROJECT_SOURCE_DIR}/external/rocm/include
)
# ck_profiler
set(PROFILER_SOURCE
src/profiler.cpp
src/profile_gemm.cpp
src/profile_gemm_bias_2d.cpp
src/profile_gemm_bias_relu.cpp
src/profile_gemm_bias_relu_add.cpp
src/profile_conv_fwd.cpp
src/profile_conv_fwd_bias_relu.cpp
src/profile_conv_fwd_bias_relu_add.cpp
src/profile_conv_fwd_bias_relu_atomic_add.cpp
src/profile_batched_gemm.cpp
src/profile_conv_bwd_data.cpp
)
add_executable(ckProfiler ${PROFILER_SOURCE})
target_link_libraries(ckProfiler PRIVATE host_tensor)
target_link_libraries(ckProfiler PRIVATE device_gemm_instance)
target_link_libraries(ckProfiler PRIVATE device_gemm_bias_2d_instance)
target_link_libraries(ckProfiler PRIVATE device_gemm_bias_relu_instance)
target_link_libraries(ckProfiler PRIVATE device_gemm_bias_relu_add_instance)
target_link_libraries(ckProfiler PRIVATE device_conv2d_fwd_instance)
target_link_libraries(ckProfiler PRIVATE device_conv2d_fwd_bias_relu_instance)
target_link_libraries(ckProfiler PRIVATE device_conv2d_fwd_bias_relu_add_instance)
target_link_libraries(ckProfiler PRIVATE device_conv2d_fwd_bias_relu_atomic_add_instance)
target_link_libraries(ckProfiler PRIVATE device_batched_gemm_instance)
target_link_libraries(ckProfiler PRIVATE device_conv2d_bwd_data_instance)