mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-03 05:01:25 +00:00
1acd8e041c
* Fix a typo * Use std::variant to call run_gemm_example_with_layouts with the available layout variant combinations * Use a unified run_gemm_example_prec_type for basic gemm and universal gemm * Factor out run_gemm_example_prec_type * Refactor argument parsing in gemm_splitk_two_stage_reduce.cpp * Parse arguments outside of create_args * Move the gemm operators to separate structs to facilitate their reuse * Move the invokers to separate files to facilitate their reuse * Rename the invoker files for consistency with the examples that use them * Add fp32 support to the elementwise examples, and produce an error message for unsupported types * Get rid of four unused variables * Make two variables const * Add support for different input-output type combinations in elementwise examples * Test support for different input and output types in elementwise examples * Add support for different operations in the elementwise unary tests * Add support for UnaryConvert in the elementwise unary tests * Add support for bf16 in elementwise examples, excluding unsupported type combinations * Make some operator parameters const in ElementWiseKernel * Remove some unnecessary include statements * Implement a two-stage GEMM that does a type conversion in the second stage using the elementwise kernel * Clear workspace instead of output when flushing the cache in SplitKTwoStageInvoker::gemm * Fix formatting issues reported by clang * Add back CK_TILE_USE_WMMA related changes * Use the right prec type for bf16 in the universal GEMM and two stage split K examples * Add some brackets * Add some brackets * Separate the clearing of the GEMM output memory from the cache flushing in the universal GEMM example * Separate the clearing of the GEMM output memory from the cache flushing in the split K two stage example * Fix formatting * No need to call SetZero on ws_m_n_dev_buf here, as clear_gemm_output now does this as part of the kernel preprocessing * Add fp16 data type to splitk two stage example * Add preprocessing with optional cache flushing and clearing of output for k_batch > 1 to the basic GEMM example
21 lines
1.5 KiB
CMake
21 lines
1.5 KiB
CMake
add_executable(tile_example_gemm_basic EXCLUDE_FROM_ALL gemm_basic.cpp)
|
|
add_executable(tile_example_gemm_universal EXCLUDE_FROM_ALL universal_gemm.cpp)
|
|
add_executable(tile_example_gemm_weight_preshuffle EXCLUDE_FROM_ALL gemm_weight_preshuffle.cpp)
|
|
add_executable(tile_example_gemm_reduce EXCLUDE_FROM_ALL gemm_splitk_two_stage_reduce.cpp)
|
|
add_executable(tile_example_gemm_splitk_two_stage EXCLUDE_FROM_ALL gemm_splitk_two_stage.cpp)
|
|
set(EXAMPLE_GEMM_COMPILE_OPTIONS)
|
|
set(EXAMPLE_WEIGHT_PRESHUFFLE_COMPILE_OPTIONS)
|
|
if(CK_USE_OCP_FP8)
|
|
list(APPEND EXAMPLE_GEMM_COMPILE_OPTIONS -DCK_TILE_USE_OCP_FP8)
|
|
endif()
|
|
list(APPEND EXAMPLE_GEMM_COMPILE_OPTIONS -mllvm -enable-noalias-to-md-conversion=0)
|
|
list(APPEND EXAMPLE_WEIGHT_PRESHUFFLE_COMPILE_OPTIONS -Wno-unused-local-typedef)
|
|
list(APPEND EXAMPLE_WEIGHT_PRESHUFFLE_COMPILE_OPTIONS -Wno-gnu-line-marker)
|
|
list(APPEND EXAMPLE_WEIGHT_PRESHUFFLE_COMPILE_OPTIONS --save-temps)
|
|
list(APPEND EXAMPLE_WEIGHT_PRESHUFFLE_COMPILE_OPTIONS "SHELL: -mllvm -greedy-reverse-local-assignment=1 -mllvm -enable-noalias-to-md-conversion=0")
|
|
target_compile_options(tile_example_gemm_basic PRIVATE ${EXAMPLE_GEMM_COMPILE_OPTIONS})
|
|
target_compile_options(tile_example_gemm_universal PRIVATE ${EXAMPLE_GEMM_COMPILE_OPTIONS})
|
|
target_compile_options(tile_example_gemm_weight_preshuffle PRIVATE ${EXAMPLE_WEIGHT_PRESHUFFLE_COMPILE_OPTIONS})
|
|
target_compile_options(tile_example_gemm_reduce PRIVATE ${EXAMPLE_GEMM_COMPILE_OPTIONS})
|
|
target_compile_options(tile_example_gemm_splitk_two_stage PRIVATE ${EXAMPLE_GEMM_COMPILE_OPTIONS})
|