mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-27 00:14:35 +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]
91 lines
3.5 KiB
C++
91 lines
3.5 KiB
C++
#ifndef TEST_CONV_UTIL_HPP
|
|
#define TEST_CONV_UTIL_HPP
|
|
|
|
#include <tuple>
|
|
|
|
#include "config.hpp"
|
|
#include "conv_fwd_util.hpp"
|
|
#include "device_convnd_fwd_xdl_nhwc_kyxc_nhwk.hpp"
|
|
#include "element_wise_operation.hpp"
|
|
#include "host_tensor.hpp"
|
|
#include "sequence.hpp"
|
|
|
|
namespace {
|
|
|
|
template <ck::index_t... Is>
|
|
using S = ck::Sequence<Is...>;
|
|
|
|
using InElementOp = ck::tensor_operation::element_wise::PassThrough;
|
|
using WeiElementOp = ck::tensor_operation::element_wise::PassThrough;
|
|
using OutElementOp = ck::tensor_operation::element_wise::PassThrough;
|
|
|
|
static constexpr auto ConvFwdDefault =
|
|
ck::tensor_operation::device::ConvolutionForwardSpecialization::Default;
|
|
|
|
template <ck::index_t SpatialDims, typename InDataType, typename WeiDataType, typename OutDataType>
|
|
using DeviceConvNDFwdInstance = ck::tensor_operation::device::
|
|
DeviceConvNDFwdXdl_Input_N_Hi_Wi_C_Weight_K_Y_X_C_Output_N_Ho_Wo_K<
|
|
// clang-format off
|
|
InDataType, //
|
|
WeiDataType, //
|
|
OutDataType, //
|
|
InDataType, //
|
|
InElementOp, // Input Elementwise Operation
|
|
WeiElementOp, // Weights Elementwise Operation
|
|
OutElementOp, // Output Elementwise Operation
|
|
ConvFwdDefault, // ConvForwardSpecialization
|
|
SpatialDims, // SptialDims
|
|
64, // BlockSize
|
|
16, // MPerBlock
|
|
16, // NPerBlock
|
|
4, // K0PerBlock
|
|
1, // K1
|
|
16, // MPerXDL
|
|
16, // NPerXDL
|
|
1, // MXdlPerWave
|
|
1, // NXdlPerWave
|
|
S<1, 16, 1>, // ABlockTransferThreadClusterLengths_K0_M_K1
|
|
S<1, 0, 2>, // ABlockTransferThreadClusterArrangeOrder
|
|
S<1, 0, 2>, // ABlockTransferSrcAccessOrder
|
|
2, // ABlockTransferSrcVectorDim
|
|
1, // ABlockTransferSrcScalarPerVector
|
|
1, // ABlockTransferDstScalarPerVector_K1
|
|
true, // ABlockLdsAddExtraM
|
|
S<1, 16, 1>, // BBlockTransferThreadClusterLengths_K0_N_K1
|
|
S<1, 0, 2>, // BBlockTransferThreadClusterArrangeOrder
|
|
S<1, 0, 2>, // BBlockTransferSrcAccessOrder
|
|
2, // BBlockTransferSrcVectorDim
|
|
1, // BBlockTransferSrcScalarPerVector
|
|
1, // BBlockTransferDstScalarPerVector_K1
|
|
true, // BBlockTransferAddExtraN
|
|
7, // CThreadTransferSrcDstVectorDim
|
|
1>; // CThreadTransferDstScalarPerVector
|
|
// clang-format on
|
|
|
|
} // namespace
|
|
|
|
namespace test {
|
|
namespace conv {
|
|
|
|
template <ck::index_t NDim,
|
|
typename InDataType = float,
|
|
typename WeiDataType = float,
|
|
typename OutDataType = float>
|
|
void RunConv(const ck::utils::conv::ConvParams& params,
|
|
const Tensor<InDataType>& input,
|
|
const Tensor<WeiDataType>& weights,
|
|
Tensor<OutDataType>& output)
|
|
{
|
|
ck::utils::conv::run_convolution_forward<NDim,
|
|
InDataType,
|
|
WeiDataType,
|
|
OutDataType,
|
|
DeviceConvNDFwdInstance>(
|
|
params, input, weights, output);
|
|
}
|
|
|
|
} // namespace conv
|
|
} // namespace test
|
|
|
|
#endif
|