ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-19 04:19:36 +00:00
Code Issues Packages Projects Releases Wiki Activity

Support broadcast for bias in grouped conv fwd (#1081)

Browse Source 
* Support broadcast for bias in grouped conv fwd

* Fix comment

* Comment fixes

* Remove GK layout

[ROCm/composable_kernel commit: f836984891]
This commit is contained in:
Bartłomiej Kocot
2023-12-08 11:07:42 +01:00
committed by GitHub
parent 79814fa5f2
commit 39b25e2d71
15 changed files with 371 additions and 55 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
example/62_conv_fwd_activ/CMakeLists.txt
View File

@@ -42,6 +42,8 @@ foreach(gpu IN LISTS GPU_TARGETS)
# ScaleAdd ScaleAdd Relu
add_example_executable(example_convnd_fwd_xdl_scaleadd_scaleadd_relu_fp16 convnd_fwd_xdl_scaleadd_scaleadd_relu_fp16.cpp)
add_example_dependencies(example_convnd_fwd_activ_xdl example_convnd_fwd_xdl_scaleadd_scaleadd_relu_fp16)
add_example_executable(example_convnd_fwd_xdl_scaleadd_scaleadd_relu_bcasted_bias_fp16 convnd_fwd_xdl_scaleadd_scaleadd_relu_bcasted_bias_fp16.cpp)
add_example_dependencies(example_convnd_fwd_activ_xdl example_convnd_fwd_xdl_scaleadd_scaleadd_relu_bcasted_bias_fp16)
set(target 1)
endif()
endforeach()

294
example/62_conv_fwd_activ/convnd_fwd_xdl_scaleadd_scaleadd_relu_bcasted_bias_fp16.cpp Normal file
View File

@@ -0,0 +1,294 @@
// SPDX-License-Identifier: MIT
// Copyright (c) 2023, Advanced Micro Devices, Inc. All rights reserved.
#include <algorithm>
#include <cstdlib>
#include <iostream>
#include <numeric>
#include <type_traits>
#include "ck/ck.hpp"
#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
#include "ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_abd_xdl_cshuffle.hpp"
#include "ck/library/utility/algorithm.hpp"
#include "ck/library/utility/check_err.hpp"
#include "ck/library/utility/device_memory.hpp"
#include "ck/library/utility/host_tensor.hpp"
#include "ck/library/utility/host_tensor_generator.hpp"
#include "ck/library/utility/convolution_parameter.hpp"
#include "ck/library/utility/convolution_host_tensor_descriptor_helper.hpp"
#include "ck/library/reference_tensor_operation/cpu/reference_conv_fwd.hpp"
#include "ck/library/utility/convolution_host_tensor_descriptor_helper.hpp"
constexpr ck::index_t NDimSpatial = 3;
using InDataType = ck::half_t;
using WeiDataType = ck::half_t;
using AccDataType = float;
using CShuffleDataType = ck::half_t;
using OutDataType = ck::half_t;
template <ck::index_t... Is>
using S = ck::Sequence<Is...>;
using InLayout = ck::tensor_layout::convolution::NDHWGC;
using WeiLayout = ck::tensor_layout::convolution::GKZYXC;
using OutLayout = ck::tensor_layout::convolution::NDHWGK;
using BiasLayout = ck::tensor_layout::convolution::G_K;
using InElementOp = ck::tensor_operation::element_wise::PassThrough;
using WeiElementOp = ck::tensor_operation::element_wise::PassThrough;
using OutElementOp = ck::tensor_operation::element_wise::ScaleAddScaleAddRelu;
static constexpr auto ConvSpec =
ck::tensor_operation::device::ConvolutionForwardSpecialization::Default;
static constexpr auto GemmSpec = ck::tensor_operation::device::GemmSpecialization::MNKPadding;
template <typename OutElementOp>
using DeviceGroupedConvNDFwdInstance =
ck::tensor_operation::device::DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<
NDimSpatial,
InLayout,
WeiLayout,
ck::Tuple<OutLayout, BiasLayout>,
OutLayout,
InDataType,
WeiDataType,
AccDataType,
CShuffleDataType,
ck::Tuple<OutDataType, OutDataType>,
OutDataType,
InElementOp,
WeiElementOp,
OutElementOp,
ConvSpec, // ConvForwardSpecialization
GemmSpec, // GemmSpecialization
1, //
256, // BlockSize
128, // MPerBlock
256, // NPerBlock
32, // KPerBlock
8, // AK1
8, // BK1
32, // MPerXdl
32, // NPerXdl
2, // MXdlPerWave
4, // NXdlPerWave
S<4, 64, 1>, // ABlockTransferThreadClusterLengths_AK0_M_AK1
S<1, 0, 2>, // ABlockTransferThreadClusterArrangeOrder
S<1, 0, 2>, // ABlockTransferSrcAccessOrder
2, // ABlockTransferSrcVectorDim
8, // ABlockTransferSrcScalarPerVector
8, // ABlockTransferDstScalarPerVector_AK1
1, // ABlockLdsExtraM
S<4, 64, 1>, // BBlockTransferThreadClusterLengths_BK0_N_BK1
S<1, 0, 2>, // BBlockTransferThreadClusterArrangeOrder
S<1, 0, 2>, // BBlockTransferSrcAccessOrder
2, // BBlockTransferSrcVectorDim
8, // BBlockTransferSrcScalarPerVector
8, // BBlockTransferDstScalarPerVector_BK1
1, // BBlockLdsExtraN
1,
1,
S<1, 32, 1, 8>,
8>;
using DeviceGroupedConvNDFwdActivInstance = DeviceGroupedConvNDFwdInstance<OutElementOp>;
namespace {
// Use custom implementation to pass two more tensors for post op
template <ck::index_t NDimSpatial,
typename InDataType,
typename WeiDataType,
typename OutDataType,
typename InElementOp,
typename WeiElementOp,
typename OutElementOp,
typename DeviceConvNDFwdInstance>
bool run_grouped_conv_fwd(bool do_verification,
int init_method,
bool time_kernel,
const ck::utils::conv::ConvParam& conv_param,
const HostTensorDescriptor& in_g_n_c_wis_desc,
const HostTensorDescriptor& wei_g_k_c_xs_desc,
const HostTensorDescriptor& out_g_n_k_wos_desc,
const InElementOp& in_element_op,
const WeiElementOp& wei_element_op,
const OutElementOp& out_element_op)
{
constexpr ck::index_t NumDs = 2;
const ck::index_t G = out_g_n_k_wos_desc.GetLengths()[0];
const ck::index_t K = out_g_n_k_wos_desc.GetLengths()[2];
// Logical broadcast bias (we have to pass bias lengths in the same format as output - GNKDHW)
std::array<ck::index_t, NDimSpatial + 3> bias_g_k_lengths;
std::array<ck::index_t, NDimSpatial + 3> bias_g_k_strides;
// Fill other lenghts than G,K with 1 and strides with 0
bias_g_k_lengths.fill(1);
bias_g_k_strides.fill(0);
bias_g_k_lengths[0] = G;
bias_g_k_lengths[2] = K;
bias_g_k_strides[0] = K; // stride to G
bias_g_k_strides[2] = 1; // stride to K
const auto broadcasted_bias_desc = HostTensorDescriptor(bias_g_k_lengths, bias_g_k_strides);
// y = relu ( alpha1 * conv(x) + alpha2 * z + bias )
Tensor<InDataType> in(in_g_n_c_wis_desc);
Tensor<WeiDataType> wei(wei_g_k_c_xs_desc);
Tensor<OutDataType> out_host(out_g_n_k_wos_desc);
Tensor<OutDataType> out_device(out_g_n_k_wos_desc);
std::array<Tensor<OutDataType>, NumDs> d_tensors = {Tensor<OutDataType>(out_g_n_k_wos_desc),
Tensor<OutDataType>(broadcasted_bias_desc)};
std::cout << "in: " << in.mDesc << std::endl;
std::cout << "wei: " << wei.mDesc << std::endl;
std::cout << "out: " << out_host.mDesc << std::endl;
std::cout << "z_tensor: " << d_tensors[0].mDesc << std::endl;
std::cout << "bias_tensor: " << d_tensors[1].mDesc << std::endl;
// Make sure that we allocated only G * K values for bias
assert(static_cast<ck::index_t>(d_tensors[1].mData.size()) == G * K);
switch(init_method)
{
case 0: break;
case 1:
in.GenerateTensorValue(GeneratorTensor_2<InDataType>{-2, 2});
wei.GenerateTensorValue(GeneratorTensor_2<WeiDataType>{-2, 2});
d_tensors[0].GenerateTensorValue(GeneratorTensor_2<OutDataType>{-2, 2});
d_tensors[1].GenerateTensorValue(GeneratorTensor_2<OutDataType>{-2, 2});
break;
default:
in.GenerateTensorValue(GeneratorTensor_3<InDataType>{-1.0, 1.0});
wei.GenerateTensorValue(GeneratorTensor_3<WeiDataType>{-0.05, 0.05});
d_tensors[0].GenerateTensorValue(GeneratorTensor_3<OutDataType>{-0.05, 0.05});
d_tensors[1].GenerateTensorValue(GeneratorTensor_3<OutDataType>{-0.05, 0.05});
}
DeviceMem in_device_buf(sizeof(InDataType) * in.mDesc.GetElementSpaceSize());
DeviceMem wei_device_buf(sizeof(WeiDataType) * wei.mDesc.GetElementSpaceSize());
DeviceMem z_buf(sizeof(OutDataType) * d_tensors[0].mDesc.GetElementSpaceSize());
DeviceMem bias_buf(sizeof(OutDataType) * d_tensors[1].mDesc.GetElementSpaceSize());
DeviceMem out_device_buf(sizeof(OutDataType) * out_device.mDesc.GetElementSpaceSize());
in_device_buf.ToDevice(in.mData.data());
wei_device_buf.ToDevice(wei.mData.data());
z_buf.ToDevice(d_tensors[0].mData.data());
bias_buf.ToDevice(d_tensors[1].mData.data());
std::array<ck::index_t, NDimSpatial + 3> a_g_n_c_wis_lengths{};
std::array<ck::index_t, NDimSpatial + 3> a_g_n_c_wis_strides{};
std::array<ck::index_t, NDimSpatial + 3> b_g_k_c_xs_lengths{};
std::array<ck::index_t, NDimSpatial + 3> b_g_k_c_xs_strides{};
std::array<ck::index_t, NDimSpatial + 3> e_g_n_k_wos_lengths{};
std::array<ck::index_t, NDimSpatial + 3> e_g_n_k_wos_strides{};
std::array<ck::index_t, NDimSpatial> conv_filter_strides{};
std::array<ck::index_t, NDimSpatial> conv_filter_dilations{};
std::array<ck::index_t, NDimSpatial> input_left_pads{};
std::array<ck::index_t, NDimSpatial> input_right_pads{};
auto copy = [](const auto& x, auto& y) { ck::ranges::copy(x, y.begin()); };
copy(in_g_n_c_wis_desc.GetLengths(), a_g_n_c_wis_lengths);
copy(in_g_n_c_wis_desc.GetStrides(), a_g_n_c_wis_strides);
copy(wei_g_k_c_xs_desc.GetLengths(), b_g_k_c_xs_lengths);
copy(wei_g_k_c_xs_desc.GetStrides(), b_g_k_c_xs_strides);
copy(out_g_n_k_wos_desc.GetLengths(), e_g_n_k_wos_lengths);
copy(out_g_n_k_wos_desc.GetStrides(), e_g_n_k_wos_strides);
copy(conv_param.conv_filter_strides_, conv_filter_strides);
copy(conv_param.conv_filter_dilations_, conv_filter_dilations);
copy(conv_param.input_left_pads_, input_left_pads);
copy(conv_param.input_right_pads_, input_right_pads);
const std::array<const void*, NumDs> ds = {z_buf.GetDeviceBuffer(), bias_buf.GetDeviceBuffer()};
auto conv = DeviceConvNDFwdInstance{};
auto invoker = conv.MakeInvoker();
auto argument = conv.MakeArgument(in_device_buf.GetDeviceBuffer(),
wei_device_buf.GetDeviceBuffer(),
ds,
out_device_buf.GetDeviceBuffer(),
a_g_n_c_wis_lengths,
a_g_n_c_wis_strides,
b_g_k_c_xs_lengths,
b_g_k_c_xs_strides,
std::array<std::array<ck::index_t, NDimSpatial + 3>, NumDs>{
e_g_n_k_wos_lengths, bias_g_k_lengths},
std::array<std::array<ck::index_t, NDimSpatial + 3>, NumDs>{
e_g_n_k_wos_strides, bias_g_k_strides},
e_g_n_k_wos_lengths,
e_g_n_k_wos_strides,
conv_filter_strides,
conv_filter_dilations,
input_left_pads,
input_right_pads,
in_element_op,
wei_element_op,
out_element_op);
if(!conv.IsSupportedArgument(argument))
{
throw std::runtime_error("The device op with the specified compilation parameters does "
"not support this convolution problem.");
}
float avg_time = invoker.Run(argument, StreamConfig{nullptr, time_kernel});
std::size_t flop = conv_param.GetFlops() + G * K +
conv_param.GetOutputByte<OutDataType>() / sizeof(OutDataType);
std::size_t num_btype = conv_param.GetByte<InDataType, WeiDataType, OutDataType>() +
G * K * sizeof(OutDataType) + conv_param.GetOutputByte<OutDataType>();
float tflops = static_cast<float>(flop) / 1.E9 / avg_time;
float gb_per_sec = num_btype / 1.E6 / avg_time;
std::cout << "Perf: " << avg_time << " ms, " << tflops << " TFlops, " << gb_per_sec << " GB/s, "
<< conv.GetTypeString() << std::endl;
if(do_verification)
{
auto ref_conv =
ck::tensor_operation::host::ReferenceConvFwd<NDimSpatial,
InDataType,
WeiDataType,
OutDataType,
InElementOp,
WeiElementOp,
OutElementOp,
0, /*Num A Elementwise Tensors*/
0, /*Num B Elementwise Tensors*/
NumDs>();
auto ref_invoker = ref_conv.MakeInvoker();
auto ref_argument = ref_conv.MakeArgument(in,
wei,
out_host,
conv_param.conv_filter_strides_,
conv_param.conv_filter_dilations_,
conv_param.input_left_pads_,
conv_param.input_right_pads_,
in_element_op,
wei_element_op,
out_element_op,
{},
{},
d_tensors);
ref_invoker.Run(ref_argument);
out_device_buf.FromDevice(out_device.mData.data());
return ck::utils::check_err(out_device, out_host, "Error: incorrect results!");
}
return true;
}
} // namespace
#include "run_convnd_fwd_activ_example.inc"
int main(int argc, char* argv[]) { return !run_convnd_fwd_example(argc, argv); }

2
example/62_conv_fwd_activ/run_convnd_fwd_activ_example.inc
View File

@@ -24,7 +24,7 @@ bool run_convnd_fwd_example(int argc, char* argv[])
// Following shapes are selected to avoid overflow. Expect inf in case of
// size increase for some elementwise ops.
ck::utils::conv::ConvParam conv_param{
3, 1, 16, 128, 8, {3, 3, 3}, {17, 17, 17}, {2, 2, 2}, {1, 1, 1}, {1, 1, 1}, {1, 1, 1}};
3, 2, 16, 128, 8, {3, 3, 3}, {17, 17, 17}, {2, 2, 2}, {1, 1, 1}, {1, 1, 1}, {1, 1, 1}};
if(argc == 1)
{