mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-14 18:17:44 +00:00
f846457a87
* Convolution ND
* Code unification across dimensions for generating tensor descriptors.
* Example
* Instances
* Move convnd f32 instance file to comply with repo structure.
* Conv 1D tensor layouts.
* Formatting and use ReferenceConv
* Reference ConvFwd supporting 1D and 2D convolution.
* Debug printing TensorLayout name.
* Conv fwd 1D instance f32
* Refactor conv ND example.
Needed to support various conv dimensio.
Needed to support various conv dimensions
* Rename conv nd example director to prevent conflicts.
* Refactor some common utility to single file.
Plus some tests.
* Refactor GetHostTensorDescriptor + UT.
* Add 1D test case.
* Test reference convolution 1d/2d
* Remove some leftovers.
* Fix convolution example error for 1D
* Refactor test check errors utility function.
* Test Conv2D Fwd XDL
* More UT for 1D case.
* Parameterize input & weight initializers.
* Rename example to prevent conflicts.
* Split convnd instance into separate files for 1d/2d
* Address review comments.
* Fix data type for flops/gbytes calculations.
* Assign example number 11.
* 3D cases for convolution utility functions.
* 3D reference convolution.
* Add support for 3D convolution.
* Check for inputs bigger than 2GB.
* Formatting
* Support for bf16/f16/f32/i8 - conv instances + UT.
* Use check_err from test_util.hpp.
* Split convnd test into separate files for each dim.
* Fix data generation and use proper instances.
* Formatting
* Skip tensor initialization if not necessary.
* Fix CMakefiles.
* Remove redundant conv2d_fwd test.
* Lower problem size for conv3D UT.
* 3D case for convnd example.
* Remove leftovers after merge.
* Add Conv Specialization string to GetTypeString
* Skip instance causing numerical errors.
* Small fixes.
* Remove redundant includes.
* Fix namespace name error.
* Script for automatic testing and logging convolution fwd UTs
* Comment out numactl cmd.
* Refine weights initalization and relax rtol for fp16
* Move test_util.hpp to check_err.hpp
* Refine weights initalization and relax rtol for fp16
* Refactor common part of test conv utils.
* Move utility function to single common place.
* Add additional common functions to utility.
* Refactor convnd_fwd_xdl examples.
* Remove redundant files.
* Unify structure.
* Add constructor to ConvParams.
* And add input parameters validation.
* Modify conv examples to use single utility file.
* Remove check_error from host_tensor.hpp
* Get rid of check_indices function.
* Remove bf16_to_f32 function overload for scalars.
* Fix namespace.
* Add half_float::half for check_err.
* Fix conv params size in UT.
* Fix weights initialization for int8.
* Fix weights initialization for int8.
* Add type_convert when store output in ref conv 1D.
* Get back old conv2d_fwd_xdl operation.
* Silence conv debug print.
* format
* clean
* clean
* Fix merge.
* Fix namespace for check_err
* Formatting.
* Fix merge artifacts.
* Remove deleted header.
* Fix some includes and use ck::utils::check_err.
* Remove unused check_indices restored by previous merge.
* Fix namespaces after merge.
* Fix compilation error.
* Small fixes.
* Use common functions.
* Fix filename
* Fix namespaces.
* Fix merge artifact - retrieve removed by accident fun.
* Fix ConvForwardSpecialization.
* Adhere to coding style rules.
* Fix merge artifacts.
Co-authored-by: Adam Osewski <aosewski@amd.com>
Co-authored-by: Chao Liu <chao.liu2@amd.com>
[ROCm/composable_kernel commit: abf4bdb9a9]
155 lines
6.6 KiB
C++
155 lines
6.6 KiB
C++
#include <algorithm>
|
|
#include <cstdlib>
|
|
#include <half.hpp>
|
|
#include <iostream>
|
|
#include <numeric>
|
|
#include <tuple>
|
|
#include <vector>
|
|
|
|
#include "gemm_util.hpp"
|
|
#include "config.hpp"
|
|
#include "print.hpp"
|
|
#include "device.hpp"
|
|
#include "host_tensor.hpp"
|
|
#include "host_tensor_generator.hpp"
|
|
#include "host_gemm.hpp"
|
|
#include "device_tensor.hpp"
|
|
#include "device_gemm_xdl.hpp"
|
|
#include "device_gemm_xdl_c_shuffle.hpp"
|
|
#include "element_wise_operation.hpp"
|
|
#include "reference_gemm.hpp"
|
|
#include "gemm_specialization.hpp"
|
|
|
|
using PassThrough = ck::tensor_operation::element_wise::PassThrough;
|
|
|
|
using DeviceGemmNoOpPtr =
|
|
ck::tensor_operation::device::DeviceGemmPtr<ck::tensor_operation::element_wise::PassThrough,
|
|
ck::tensor_operation::element_wise::PassThrough,
|
|
ck::tensor_operation::element_wise::PassThrough>;
|
|
|
|
namespace ck {
|
|
namespace tensor_operation {
|
|
namespace device {
|
|
namespace device_gemm_instance {
|
|
void add_device_gemm_xdl_f32_f32_f32_km_kn_mn_instances(std::vector<DeviceGemmNoOpPtr>&);
|
|
void add_device_gemm_xdl_f32_f32_f32_km_nk_mn_instances(std::vector<DeviceGemmNoOpPtr>&);
|
|
void add_device_gemm_xdl_f32_f32_f32_mk_nk_mn_instances(std::vector<DeviceGemmNoOpPtr>&);
|
|
void add_device_gemm_xdl_f32_f32_f32_mk_kn_mn_instances(std::vector<DeviceGemmNoOpPtr>&);
|
|
|
|
void add_device_gemm_xdl_splitk_f32_f32_f32_km_kn_mn_instances(std::vector<DeviceGemmNoOpPtr>&);
|
|
void add_device_gemm_xdl_splitk_f32_f32_f32_km_nk_mn_instances(std::vector<DeviceGemmNoOpPtr>&);
|
|
void add_device_gemm_xdl_splitk_f32_f32_f32_mk_nk_mn_instances(std::vector<DeviceGemmNoOpPtr>&);
|
|
void add_device_gemm_xdl_splitk_f32_f32_f32_mk_kn_mn_instances(std::vector<DeviceGemmNoOpPtr>&);
|
|
|
|
void add_device_gemm_xdl_c_shuffle_f32_f32_f32_km_kn_mn_instances(std::vector<DeviceGemmNoOpPtr>&);
|
|
void add_device_gemm_xdl_c_shuffle_f32_f32_f32_km_nk_mn_instances(std::vector<DeviceGemmNoOpPtr>&);
|
|
void add_device_gemm_xdl_c_shuffle_f32_f32_f32_mk_nk_mn_instances(std::vector<DeviceGemmNoOpPtr>&);
|
|
void add_device_gemm_xdl_c_shuffle_f32_f32_f32_mk_kn_mn_instances(std::vector<DeviceGemmNoOpPtr>&);
|
|
|
|
} // namespace device_gemm_instance
|
|
} // namespace device
|
|
} // namespace tensor_operation
|
|
} // namespace ck
|
|
|
|
int main()
|
|
{
|
|
using ADataType = float;
|
|
using BDataType = float;
|
|
using CDataType = float;
|
|
|
|
using RowMajor = ck::tensor_layout::gemm::RowMajor;
|
|
using ColumnMajor = ck::tensor_layout::gemm::ColumnMajor;
|
|
|
|
bool res = true;
|
|
std::vector<DeviceGemmNoOpPtr> gemmPtrs;
|
|
ck::tensor_operation::device::device_gemm_instance::
|
|
add_device_gemm_xdl_f32_f32_f32_km_kn_mn_instances(gemmPtrs);
|
|
ck::tensor_operation::device::device_gemm_instance::
|
|
add_device_gemm_xdl_splitk_f32_f32_f32_km_kn_mn_instances(gemmPtrs);
|
|
ck::tensor_operation::device::device_gemm_instance::
|
|
add_device_gemm_xdl_c_shuffle_f32_f32_f32_km_kn_mn_instances(gemmPtrs);
|
|
|
|
for(auto& gemmPtr : gemmPtrs)
|
|
{
|
|
res &= ck::gemm_util::TestGemm<DeviceGemmNoOpPtr,
|
|
ADataType,
|
|
BDataType,
|
|
CDataType,
|
|
ColumnMajor,
|
|
RowMajor,
|
|
RowMajor,
|
|
PassThrough,
|
|
PassThrough,
|
|
PassThrough>{}(gemmPtr);
|
|
}
|
|
|
|
gemmPtrs.clear();
|
|
ck::tensor_operation::device::device_gemm_instance::
|
|
add_device_gemm_xdl_f32_f32_f32_km_nk_mn_instances(gemmPtrs);
|
|
ck::tensor_operation::device::device_gemm_instance::
|
|
add_device_gemm_xdl_splitk_f32_f32_f32_km_nk_mn_instances(gemmPtrs);
|
|
ck::tensor_operation::device::device_gemm_instance::
|
|
add_device_gemm_xdl_c_shuffle_f32_f32_f32_km_nk_mn_instances(gemmPtrs);
|
|
|
|
for(auto& gemmPtr : gemmPtrs)
|
|
{
|
|
res &= ck::gemm_util::TestGemm<DeviceGemmNoOpPtr,
|
|
ADataType,
|
|
BDataType,
|
|
CDataType,
|
|
ColumnMajor,
|
|
ColumnMajor,
|
|
RowMajor,
|
|
PassThrough,
|
|
PassThrough,
|
|
PassThrough>{}(gemmPtr);
|
|
}
|
|
|
|
gemmPtrs.clear();
|
|
ck::tensor_operation::device::device_gemm_instance::
|
|
add_device_gemm_xdl_f32_f32_f32_mk_kn_mn_instances(gemmPtrs);
|
|
ck::tensor_operation::device::device_gemm_instance::
|
|
add_device_gemm_xdl_splitk_f32_f32_f32_mk_kn_mn_instances(gemmPtrs);
|
|
ck::tensor_operation::device::device_gemm_instance::
|
|
add_device_gemm_xdl_c_shuffle_f32_f32_f32_mk_kn_mn_instances(gemmPtrs);
|
|
|
|
for(auto& gemmPtr : gemmPtrs)
|
|
{
|
|
res &= ck::gemm_util::TestGemm<DeviceGemmNoOpPtr,
|
|
ADataType,
|
|
BDataType,
|
|
CDataType,
|
|
RowMajor,
|
|
RowMajor,
|
|
RowMajor,
|
|
PassThrough,
|
|
PassThrough,
|
|
PassThrough>{}(gemmPtr);
|
|
}
|
|
|
|
gemmPtrs.clear();
|
|
ck::tensor_operation::device::device_gemm_instance::
|
|
add_device_gemm_xdl_f32_f32_f32_mk_nk_mn_instances(gemmPtrs);
|
|
ck::tensor_operation::device::device_gemm_instance::
|
|
add_device_gemm_xdl_splitk_f32_f32_f32_mk_nk_mn_instances(gemmPtrs);
|
|
ck::tensor_operation::device::device_gemm_instance::
|
|
add_device_gemm_xdl_c_shuffle_f32_f32_f32_mk_nk_mn_instances(gemmPtrs);
|
|
|
|
for(auto& gemmPtr : gemmPtrs)
|
|
{
|
|
res &= ck::gemm_util::TestGemm<DeviceGemmNoOpPtr,
|
|
ADataType,
|
|
BDataType,
|
|
CDataType,
|
|
RowMajor,
|
|
ColumnMajor,
|
|
RowMajor,
|
|
PassThrough,
|
|
PassThrough,
|
|
PassThrough>{}(gemmPtr);
|
|
}
|
|
|
|
std::cout << "TestGemm ..... " << (res ? "SUCCESS" : "FAILURE") << std::endl;
|
|
return res ? 0 : 1;
|
|
}
|