mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-04-19 22:39:03 +00:00
0ffe956ab1
* [What] Rename the example [Why] Prepare to add unary reduction * Add global oparation to the parameter * Add atomicmax * Fix compile error * Support atomicMax (hip library) * Rename the reduction example * Fix target name * use p_d1_grid as the indicator directly * Prevent performance issue. Let passthrough handle it. * Implement the function template the specialize the float2 * No need to separate into two lines * Remove empty line * add comment * Fix compile error due to merge from develop * make the implementation of atomic_max / atomic_add explicit for each datatype * Refine typo * For future CI test * Fix compiler error in ckProfiler * Merge commit 'de2769e3a6695b38a20529261273ddc5cdaab2fe' * simply use remove_pointer * Rename type and var * Refine example * Modify reducemax example * Fix bug in reduction * Change initialize range * Implement F64 version of atomicMax * Move reduction code together * Add buffer atomic_max * Fix coding style by clang-format * Integrate new api of DeviceGemmReduce_Xdl_CShuffle * Integrate Batch gemm reduction * Fix example * fix example * clean up * Fix batch gemm tensor operation * Fix coding style * Fix template augument * Fix clang format * Keep flexible of different stride for each D tensor * Fix compile error for ckProfiler * Fix typo * [What] Fix naming [Why] Prepare to add out elementop * Add DoutElementOp Co-authored-by: Chao Liu <chao.liu2@amd.com> Co-authored-by: rocking <chunylai@amd.com>
50 lines
1.2 KiB
C++
50 lines
1.2 KiB
C++
#pragma once
|
|
#include "config.hpp"
|
|
#include "array.hpp"
|
|
#include "container_helper.hpp"
|
|
#include "statically_indexed_array.hpp"
|
|
#include "container_element_picker.hpp"
|
|
#include "multi_index.hpp"
|
|
#include "data_type.hpp"
|
|
#include "data_type_enum.hpp"
|
|
#include "data_type_enum_helper.hpp"
|
|
#include "functional.hpp"
|
|
#include "functional2.hpp"
|
|
#include "functional3.hpp"
|
|
#include "functional4.hpp"
|
|
#include "enable_if.hpp"
|
|
#include "ignore.hpp"
|
|
#include "integral_constant.hpp"
|
|
#include "math.hpp"
|
|
#include "number.hpp"
|
|
#include "sequence.hpp"
|
|
#include "sequence_helper.hpp"
|
|
#include "tuple.hpp"
|
|
#include "tuple_helper.hpp"
|
|
#include "type.hpp"
|
|
#include "magic_division.hpp"
|
|
#include "c_style_pointer_cast.hpp"
|
|
#include "is_known_at_compile_time.hpp"
|
|
#include "transpose_vectors.hpp"
|
|
#include "inner_product.hpp"
|
|
#include "element_wise_operation.hpp"
|
|
#include "thread_group.hpp"
|
|
#include "debug.hpp"
|
|
|
|
#include "amd_buffer_addressing.hpp"
|
|
#include "generic_memory_space_atomic.hpp"
|
|
#include "get_id.hpp"
|
|
#include "synchronization.hpp"
|
|
#include "amd_address_space.hpp"
|
|
#include "static_buffer.hpp"
|
|
#include "dynamic_buffer.hpp"
|
|
|
|
// TODO: remove this
|
|
#if CK_USE_AMD_INLINE_ASM
|
|
#include "amd_inline_asm.hpp"
|
|
#endif
|
|
|
|
#ifdef CK_USE_AMD_MFMA
|
|
#include "amd_xdlops.hpp"
|
|
#endif
|