Files
composable_kernel/example/CMakeLists.txt
zjing14 716f1c7fb1 Grouped GEMM for fp16 (#126)
* init of grouped_gemm

* 2 gemm test

* perf test

* clean

* wrap desc into a struct

* test cast static_arr to pointer

* add ptr to GemmDesc

* add grouped gemm profiler

* fixed mem issue with unique_ptr

* clean

* clean

* finished ckprofiler

* Update README.md

* readme

* fixed readme

* add example

* improve code

* fixed comments: reserve, seperate ptr and gemm_shapes

* merge group and non-group

* fixed comments: replace push_back with emplace_back to avoid copy constructor

* fixed comments: unified blk2ctile; add test

* ci fix

* fixed ci

* fixed ci

* fixed ci
2022-03-22 18:18:18 -05:00

43 lines
1.8 KiB
CMake

include_directories(BEFORE
${PROJECT_SOURCE_DIR}/include/ck
${PROJECT_SOURCE_DIR}/include/ck/utility
${PROJECT_SOURCE_DIR}/include/ck/tensor_description
${PROJECT_SOURCE_DIR}/include/ck/tensor
${PROJECT_SOURCE_DIR}/include/ck/problem_transform
${PROJECT_SOURCE_DIR}/include/ck/tensor_operation/gpu/device
${PROJECT_SOURCE_DIR}/include/ck/tensor_operation/gpu/grid
${PROJECT_SOURCE_DIR}/include/ck/tensor_operation/gpu/block
${PROJECT_SOURCE_DIR}/include/ck/tensor_operation/gpu/warp
${PROJECT_SOURCE_DIR}/include/ck/tensor_operation/gpu/thread
${PROJECT_SOURCE_DIR}/include/ck/tensor_operation/gpu/element
${PROJECT_SOURCE_DIR}/library/include/ck/library/host_tensor
${PROJECT_SOURCE_DIR}/library/include/ck/library/reference_tensor_operation/cpu
${PROJECT_SOURCE_DIR}/library/include/ck/library/reference_tensor_operation/gpu
${PROJECT_SOURCE_DIR}/external/include/half
)
add_custom_target(examples)
function(add_example_executable EXAMPLE_NAME)
message("adding example ${EXAMPLE_NAME}")
add_executable(${EXAMPLE_NAME} ${ARGN})
target_link_libraries(${EXAMPLE_NAME} PRIVATE host_tensor)
add_dependencies(examples ${EXAMPLE_NAME})
endfunction(add_example_executable EXAMPLE_NAME)
add_subdirectory(01_gemm)
add_subdirectory(02_gemm_alpha_beta)
add_subdirectory(03_gemm_bias_relu)
add_subdirectory(04_gemm_bias_relu_add)
add_subdirectory(05_conv2d_fwd)
add_subdirectory(06_conv2d_fwd_bias_relu)
add_subdirectory(07_conv2d_fwd_bias_relu_add)
add_subdirectory(08_conv3d_fwd)
add_subdirectory(09_convnd_fwd)
add_subdirectory(10_conv2d_bwd_data)
add_subdirectory(11_conv2d_bwd_wgt)
add_subdirectory(12_reduce)
add_subdirectory(13_pool2d_fwd)
add_subdirectory(14_gemm_xdl_requant_relu_requant)
add_subdirectory(15_grouped_gemm)