mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-13 01:36:06 +00:00
e17c0d8008
* Initial adding of generic reduction * Initial adding of generic reduction ... * Updates to make compiling done * clang-format all files * clang-format some files again * Renaming in profiler/include/profile_reduce.hpp * Updates and make BlockWise cases passed * Updates and make ThreadWise and MultiBlockTwoCall cases passed * Remove the support for MUL and NORM1 reduceOp from the profiler and the device instances * Change to replace the dim0_max_vector_size/dim1_max_vector_size template argument in the device reduce classes * format * adding pooling * added max and average pooling * comment out cout and kernel timing * Tiny simplification in profiler/reduce_profiler.cpp * Add example for reduce_blockwise * Tiny updates * Change to pass the ElementWiseOp from device layer to kernel * Fix the vectorDim and vectorSize in Device layer * Enable vector load on both dim0 and dim1 for Threadwise method * Tiny updates * Change to let the user to pass the preUnaryOp and posUnaryOp * Make pooling example work * split device_reduce_instance into two libraries * Tiny update * Replace nanPropaOpt enum by boolean propagate_nan * Simplification in DeviceReduce layer codes * update build * Change to clarify the difference between ck::half_t and half_float::half * Renaming in all the reduction codes * Add VectorSize as template parameter for device layer * Add BetaIsZero as kernel template and as AccDataType for alpha * print * Small updates for pooling * Updates for host_generic_reduction for reference * Update to make AVG pooling pass * Update to make MAX pooling with indices output pass * fix * add OutDst vector store to threadwise reduction and pooling * tweak * turn off check_indices that caused build issue * refactor pooling * clean up * turn off check_indices for building issue for php-compiler * add more tile size for odd C * tweak conv for odd C * update script * clean up elementwise op * add hack in reduction_operator.hpp to avoid compile error. To fix it, need to use element_wise_op in reduction op * Add OutVectorSize as device and kernel tunable, also update to Elementwise Operations * Move reduce operator mapping to host layer file reduction_operator_mapping.hpp from reduction_operator.hpp * Change to the unary operators * Move the definitions of unary operations to element_wise_operation.hpp * re-org files * Refine in device interfaces and multiblock kernels * Split the reduction configurations into instances for specific methods * Update in getTypeString() of device pool2d * Renaming in host and kernel * Tiny update in profiler/src/profiler.cpp * Uncomment in device_operation/CMakeLists.txt to enable the building of all operations * Make check_indices a templated function to remove some linking issue * Renaming in the profiler reduce module * Add support for double Reduction (but disable MultiblockAtomicAdd for double) * Tiny correction of literal string * Rename DevicePoolFwd to DevicePool2dFwd * Split device_reduce_instance_xxx.cpp files according to the data types to speed up compiling * Add comments for lists of configurations, lists of instances and references of add_reduce_instances_xxx * Remove un-used header file gridwise_generic_reduction_wrapper_common.hpp * Renaming and refining in the Reduction codes * Tiny change in the unary operators * Renaming symbols and files * Renaming symbols in the kernels * Move kernel kernel_set_buffer_value to separate file * Add IndexDataType template parameter for kernels and use int32_t as index data type in device layer * Tiny update in the kernels * Remove definition of sqrtf()/isnan()/abs() for half_t due to some ADL issue * Simplify a helper function in device layer * Tiny adjustment in testing data initialization * Renaming in kernel/device/host * Add two testing scripts for reduction * Refine the Unary operators in element_wise_operation.hpp * Update in the reduce profiler module * Update to the reduction testing scripts * reduce compile parallelism * change CI docker to rocm5.0 * remove unused variables * fix build Co-authored-by: Chao Liu <chao.liu2@amd.com>
91 lines
1.9 KiB
C++
91 lines
1.9 KiB
C++
#ifndef DEVICE_HPP
|
|
#define DEVICE_HPP
|
|
|
|
#include <memory>
|
|
#include <functional>
|
|
#include <thread>
|
|
#include <chrono>
|
|
#include "hip/hip_runtime.h"
|
|
#include "hip/hip_fp16.h"
|
|
|
|
struct DeviceMem
|
|
{
|
|
DeviceMem() = delete;
|
|
DeviceMem(std::size_t mem_size);
|
|
void* GetDeviceBuffer();
|
|
void ToDevice(const void* p);
|
|
void FromDevice(void* p);
|
|
~DeviceMem();
|
|
|
|
void* mpDeviceBuf;
|
|
std::size_t mMemSize;
|
|
};
|
|
|
|
struct KernelTimerImpl;
|
|
|
|
struct KernelTimer
|
|
{
|
|
KernelTimer();
|
|
~KernelTimer();
|
|
void Start();
|
|
void End();
|
|
float GetElapsedTime() const;
|
|
|
|
std::unique_ptr<KernelTimerImpl> impl;
|
|
};
|
|
|
|
using device_stream_t = hipStream_t;
|
|
|
|
template <typename... Args, typename F>
|
|
void launch_kernel(F kernel, dim3 grid_dim, dim3 block_dim, std::size_t lds_byte, Args... args)
|
|
{
|
|
hipStream_t stream_id = nullptr;
|
|
|
|
hipLaunchKernelGGL(kernel, grid_dim, block_dim, lds_byte, stream_id, args...);
|
|
}
|
|
|
|
template <typename... Args, typename F>
|
|
float launch_and_time_kernel(
|
|
F kernel, int nrepeat, dim3 grid_dim, dim3 block_dim, std::size_t lds_byte, Args... args)
|
|
{
|
|
#if 1
|
|
KernelTimer timer;
|
|
|
|
printf("%s: grid_dim {%d, %d, %d}, block_dim {%d, %d, %d} \n",
|
|
__func__,
|
|
grid_dim.x,
|
|
grid_dim.y,
|
|
grid_dim.z,
|
|
block_dim.x,
|
|
block_dim.y,
|
|
block_dim.z);
|
|
|
|
printf("Warm up\n");
|
|
|
|
hipStream_t stream_id = nullptr;
|
|
|
|
// warm up
|
|
hipLaunchKernelGGL(kernel, grid_dim, block_dim, lds_byte, stream_id, args...);
|
|
|
|
printf("Start running %d times...\n", nrepeat);
|
|
|
|
timer.Start();
|
|
|
|
for(int i = 0; i < nrepeat; ++i)
|
|
{
|
|
hipLaunchKernelGGL(kernel, grid_dim, block_dim, lds_byte, stream_id, args...);
|
|
}
|
|
|
|
timer.End();
|
|
|
|
// std::this_thread::sleep_for (std::chrono::microseconds(10));
|
|
|
|
return timer.GetElapsedTime() / nrepeat;
|
|
#else
|
|
launch_kernel(kernel, grid_dim, block_dim, lds_byte, args...);
|
|
|
|
return 0;
|
|
#endif
|
|
}
|
|
#endif
|