mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-12 01:10:17 +00:00
ae57e5938e
* parse examples inside the add_example_executable function * fix the example 64 cmake file * add xdl flag to the gemm_bias_softmax_gemm_permute example * add filtering of tests based on architecture type * enable test_grouped_gemm for gfx9 only * enable test_transpose only for gfx9 * only linnk test_transpose if it gets built * split the gemm instances by architectures * split gemm_bilinear,grouped_conv_bwd_weight instances by targets * split instances by architecture * split grouped_conv instances by architecture * fix clang format * fix the if-else logic in group_conv headers * small fix for grouped convolution instances * fix the grouped conv bwd weight dl instances * fix client examples * only enable client examples 3 and 4 on gfx9 * set the gfx9 macro * make sure the architecture macros are set by cmake * use separate set of xdl/wmma flags for host code * sinmplify the main cmake file * add conv_fwd_bf8 instance declaration
50 lines
1.4 KiB
C++
50 lines
1.4 KiB
C++
// SPDX-License-Identifier: MIT
|
|
// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
|
|
|
|
#include <iostream>
|
|
|
|
#include "profiler/profile_gemm_reduce_impl.hpp"
|
|
|
|
int main()
|
|
{
|
|
using Row = ck::tensor_layout::gemm::RowMajor;
|
|
using Col = ck::tensor_layout::gemm::ColumnMajor;
|
|
|
|
int M = 512;
|
|
int N = 256;
|
|
int K = 128;
|
|
|
|
bool pass = true;
|
|
|
|
pass = pass &&
|
|
ck::profiler::
|
|
profile_gemm_reduce_impl<ck::half_t, ck::half_t, ck::half_t, float, Row, Row, Row>(
|
|
true, 1, false, false, M, N, K, K, N, N);
|
|
|
|
pass = pass &&
|
|
ck::profiler::
|
|
profile_gemm_reduce_impl<ck::half_t, ck::half_t, ck::half_t, float, Row, Col, Row>(
|
|
true, 1, false, false, M, N, K, K, K, N);
|
|
|
|
pass = pass &&
|
|
ck::profiler::
|
|
profile_gemm_reduce_impl<ck::half_t, ck::half_t, ck::half_t, float, Col, Row, Row>(
|
|
true, 1, false, false, M, N, K, M, N, N);
|
|
|
|
pass = pass &&
|
|
ck::profiler::
|
|
profile_gemm_reduce_impl<ck::half_t, ck::half_t, ck::half_t, float, Col, Col, Row>(
|
|
true, 1, false, false, M, N, K, M, K, N);
|
|
|
|
if(pass)
|
|
{
|
|
std::cout << "test GEMM+Reduce fp16: Pass" << std::endl;
|
|
return 0;
|
|
}
|
|
else
|
|
{
|
|
std::cout << "test GEMM+Reduce fp16: Fail" << std::endl;
|
|
return -1;
|
|
}
|
|
}
|