Files
composable_kernel/example/CMakeLists.txt
myamlak cb967897e8 Multi-kernel CGEMM (#230)
* Reference CGEMM + test stub

* Format.

* Incomplete simple implementation

* Library instances

* Sketch of tests

* Test fixes.

* Example added

* Cosmetics

* Add elementwise operation kernel and example

* Add comment

* Add template argument of dim . Prepare to support multiple dimension

* Rename example

* Support 1 dimension

* Add static assert

* Add comment

* Second auxiliary buffer added

* Extract pad

* Remove redundant argument

* Support any dimension for elementwise operation

* Remove line

* Let it be the multiple number of CU

* Move thread per block to the parameter of constructor

* Consuming binary ops to do A+B / A-B

* Fix + cosmetics + bf16 test commented out temporarily

* Format

* Enabling bf16 test

* Revert "Enabling bf16 test"

This reverts commit f497e2ba44.

* Fix + test reenabled

* fix build

* Revert "fix build"

This reverts commit d73102384b.

* post PR #235 merge fix

* amend

* Single workspace for cgemm + helper

* Perf calc fix

* Review remarks: static_cast

* Review remarks: binary ops templated

* Cleaning

* Removal of instances and their tests

* Review remarks from aosew addressed

* Review remark: unnecessary attribute

* Post-merge fixes

* Restrict 4gemm to PassThrough + bug fix

* Review remarks

* update licence

* change cgemm example to fp16

Co-authored-by: rocking <chunylai@amd.com>
Co-authored-by: Chao Liu <chao.liu2@amd.com>
Co-authored-by: Anthony Chang <ac.chang@outlook.com>

[ROCm/composable_kernel commit: 7b1e2c379e]
2022-05-31 10:20:55 -05:00

59 lines
2.5 KiB
CMake

include_directories(BEFORE
${PROJECT_SOURCE_DIR}/include/ck
${PROJECT_SOURCE_DIR}/include/ck/utility
${PROJECT_SOURCE_DIR}/include/ck/host_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}/library/include/ck/library/utility
${PROJECT_SOURCE_DIR}/external/include/half
)
add_custom_target(examples)
function(add_example_executable EXAMPLE_NAME FILE_NAME)
message("adding example ${EXAMPLE_NAME}")
add_executable(${EXAMPLE_NAME} ${FILE_NAME})
target_link_libraries(${EXAMPLE_NAME} PRIVATE host_tensor)
add_test(NAME ${EXAMPLE_NAME} COMMAND $<TARGET_FILE:${EXAMPLE_NAME}> ${ARGN})
add_dependencies(examples ${EXAMPLE_NAME})
add_dependencies(check ${EXAMPLE_NAME})
endfunction(add_example_executable EXAMPLE_NAME)
function(add_example_executable_no_testing EXAMPLE_NAME FILE_NAME)
message("adding example ${EXAMPLE_NAME}")
add_executable(${EXAMPLE_NAME} ${FILE_NAME})
target_link_libraries(${EXAMPLE_NAME} PRIVATE host_tensor)
add_dependencies(examples ${EXAMPLE_NAME})
endfunction(add_example_executable_no_testing 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(06_conv2d_fwd_bias_relu)
add_subdirectory(07_conv2d_fwd_bias_relu_add)
add_subdirectory(09_convnd_fwd)
add_subdirectory(10_conv2d_bwd_data)
add_subdirectory(11_conv2d_bwd_weight)
add_subdirectory(12_reduce)
add_subdirectory(13_pool2d_fwd)
add_subdirectory(14_gemm_xdl_requant_relu_requant)
add_subdirectory(15_grouped_gemm)
add_subdirectory(16_gemm_reduce)
add_subdirectory(17_convnd_bwd_data_xdl)
add_subdirectory(18_batched_gemm_reduce)
add_subdirectory(19_binary_elementwise)
add_subdirectory(20_convnd_bwd_weight_xdl)
add_subdirectory(21_gemm_layernorm)
add_subdirectory(22_cgemm)