mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-04-19 22:39:03 +00:00
500fa99512
* convnd_fwd fp16 example * update example * update example * update instance * updating refernce conv * update reference conv * update conv fwd profiler * update conv 1d and 3d instance * update include path * clean * update profiler for conv bwd data and weight * update conv bwd weight * clean * update conv example * update profiler for conv bwd weight * update ckprofiler for conv bwd data * fix reference conv bwd data bug; update conv bwd data test * update examples * fix initialization issue * update test for conv fwd * clean * clean * remove test case too sensitive to error threshhold * fix test * clean * fix build * adding conv multiple d * adding conv multiple D * add matrix padder * add gemm padding to convnd * adding group conv * update gemm multi-d * refactor * refactor * refactor * clean * clean * refactor * refactor * reorg * add ds * add bias * clean * add G * adding group * adding group * adding group * update Tensor * clean * update example * update DeviceGemmMultipleD_Xdl_CShuffle * update conv bwd-data and bwd-weight * upate contraction example * update gemm and batch gemm with e permute * fix example build * instance for grouped conv1d * update example * adding group conv instance * update gemm bilinear instance * update gemm+add+add+fastgelu instance * update profiler * update profiler * update test * update test and client example * clean * add grouped conv into profiler * update profiler * clean * add test grouped conv, update all conv test to gtest * update test
75 lines
2.0 KiB
C++
75 lines
2.0 KiB
C++
// SPDX-License-Identifier: MIT
|
|
// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
|
|
|
|
#pragma once
|
|
|
|
#include <hip/hip_runtime.h>
|
|
|
|
#include "ck/ck.hpp"
|
|
#include "ck/stream_config.hpp"
|
|
#include "ck/host_utility/hip_check_error.hpp"
|
|
|
|
template <typename... Args, typename F>
|
|
float launch_and_time_kernel(const StreamConfig& stream_config,
|
|
F kernel,
|
|
dim3 grid_dim,
|
|
dim3 block_dim,
|
|
std::size_t lds_byte,
|
|
Args... args)
|
|
{
|
|
#if CK_TIME_KERNEL
|
|
if(stream_config.time_kernel_)
|
|
{
|
|
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);
|
|
|
|
const int nrepeat = 10;
|
|
|
|
printf("Warm up 1 time\n");
|
|
|
|
// warm up
|
|
kernel<<<grid_dim, block_dim, lds_byte, stream_config.stream_id_>>>(args...);
|
|
|
|
printf("Start running %d times...\n", nrepeat);
|
|
|
|
hipEvent_t start, stop;
|
|
|
|
hip_check_error(hipEventCreate(&start));
|
|
hip_check_error(hipEventCreate(&stop));
|
|
|
|
hip_check_error(hipDeviceSynchronize());
|
|
hip_check_error(hipEventRecord(start, stream_config.stream_id_));
|
|
|
|
for(int i = 0; i < nrepeat; ++i)
|
|
{
|
|
kernel<<<grid_dim, block_dim, lds_byte, stream_config.stream_id_>>>(args...);
|
|
}
|
|
|
|
hip_check_error(hipEventRecord(stop, stream_config.stream_id_));
|
|
hip_check_error(hipEventSynchronize(stop));
|
|
|
|
float total_time = 0;
|
|
|
|
hip_check_error(hipEventElapsedTime(&total_time, start, stop));
|
|
|
|
return total_time / nrepeat;
|
|
}
|
|
else
|
|
{
|
|
kernel<<<grid_dim, block_dim, lds_byte, stream_config.stream_id_>>>(args...);
|
|
|
|
return 0;
|
|
}
|
|
#else
|
|
kernel<<<grid_dim, block_dim, lds_byte, stream_config.stream_id_>>>(args...);
|
|
|
|
return 0;
|
|
#endif
|
|
}
|