mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-24 14:54:47 +00:00
72b7716744
* initial stub for gemm_gemm_xdl_cshuffle
* set up example code
* compiles
* prevent integer overflow
* harmonize interface between ref_gemm and ref_batched_gemm
* batched_gemm_gemm
* fix example
* host tensor gen: diagonal pattern in lowest two-dimensions only
* make c descriptors containing only integral constants
* clean up
* add BlockwiseGemmXdlops_v2 while exploring an unified approach
* implement proper interface
* tidy up example
* fix compilation warnings
* coarsely controlled 2nd gemm padding
* remove rocm-cmake's hard requirement for certain revision
* clang-format
* resolve merge conflict
* fix compilation error on gfx10
* adds acc0 elementwise op to interface
* attention host validation
* add blockwsie softmax v1
* iteratively update softmax+gemm
* transpose both gemm0 and gemm1 xdl output so as to avoid broadcasting softmax max/sum
* add init method for easier debugging
* do away with manual thread cluster calculation
* generalize blockwise softmax interface
* row-wise softmax sum & max
* format
* rename to DeviceBatchedGemmSoftmaxGemm
* add gemm_softmax_gemm instances and tests
* comment
Co-authored-by: ltqin <letao.qin@amd.com>
Co-authored-by: Chao Liu <chao.liu2@amd.com>
[ROCm/composable_kernel commit: cac014f173]
50 lines
1.8 KiB
CMake
50 lines
1.8 KiB
CMake
include_directories(BEFORE
|
|
${PROJECT_SOURCE_DIR}/include
|
|
${PROJECT_SOURCE_DIR}/library/include
|
|
)
|
|
|
|
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 utility)
|
|
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 utility)
|
|
add_dependencies(examples ${EXAMPLE_NAME})
|
|
endfunction(add_example_executable_no_testing EXAMPLE_NAME)
|
|
|
|
add_subdirectory(01_gemm)
|
|
add_subdirectory(02_gemm_bilinear)
|
|
add_subdirectory(03_gemm_bias_relu)
|
|
add_subdirectory(04_gemm_add_add_fastgelu)
|
|
add_subdirectory(09_convnd_fwd)
|
|
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)
|
|
add_subdirectory(18_batched_gemm_reduce)
|
|
add_subdirectory(19_binary_elementwise)
|
|
add_subdirectory(20_convnd_bwd_weight)
|
|
add_subdirectory(21_gemm_layernorm)
|
|
add_subdirectory(22_cgemm)
|
|
add_subdirectory(23_softmax)
|
|
add_subdirectory(24_batched_gemm_e_permute)
|
|
add_subdirectory(25_gemm_bias_e_permute)
|
|
add_subdirectory(26_contraction)
|
|
add_subdirectory(27_layernorm)
|
|
add_subdirectory(28_grouped_gemm_bias_e_permute)
|
|
add_subdirectory(29_batched_gemm_bias_e_permute)
|
|
add_subdirectory(30_grouped_convnd_fwd_bias_relu)
|
|
add_subdirectory(31_grouped_convnd_fwd_bias_relu_add)
|
|
add_subdirectory(32_batched_gemm_gemm)
|