mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-05 22:22:27 +00:00
Reorganize files, Part 1 (#119)
* delete obselete files * move files * build * update cmake * update cmake * fix build * reorg examples * update cmake for example and test
This commit is contained in:
Chao Liu
2
example/05_conv2d_fwd/CMakeLists.txt
Normal file
2
example/05_conv2d_fwd/CMakeLists.txt
Normal file
@@ -0,0 +1,2 @@
|
||||
add_example_executable(example_conv2d_fwd_xdl_fp16 conv2d_fwd_xdl_fp16.cpp)
|
||||
add_example_executable(example_conv2d_fwd_xdl_int8 conv2d_fwd_xdl_int8.cpp)
|
||||
57
example/05_conv2d_fwd/README.md
Normal file
57
example/05_conv2d_fwd/README.md
Normal file
@@ -0,0 +1,57 @@
|
||||
# Instructions for ```conv2d_fwd_xdl``` Example
|
||||
|
||||
## Docker script
|
||||
```bash
|
||||
docker run \
|
||||
-it \
|
||||
--rm \
|
||||
--privileged \
|
||||
--group-add sudo \
|
||||
-w /root/workspace \
|
||||
-v ${PATH_TO_LOCAL_WORKSPACE}:/root/workspace \
|
||||
rocm/tensorflow:rocm4.3.1-tf2.6-dev \
|
||||
/bin/bash
|
||||
```
|
||||
|
||||
## Build ```conv2d_fwd_xdl```
|
||||
```bash
|
||||
mkdir build && cd build
|
||||
```
|
||||
|
||||
```bash
|
||||
# Need to specify target ID, example below is gfx908
|
||||
cmake \
|
||||
-D BUILD_DEV=OFF \
|
||||
-D CMAKE_BUILD_TYPE=Release \
|
||||
-D CMAKE_CXX_FLAGS="-DCK_AMD_GPU_GFX908 --amdgpu-target=gfx908 -O3 " \
|
||||
-D CMAKE_CXX_COMPILER=/opt/rocm/bin/hipcc \
|
||||
-D CMAKE_PREFIX_PATH=/opt/rocm \
|
||||
..
|
||||
```
|
||||
|
||||
```bash
|
||||
make -j conv2d_fwd_xdl
|
||||
```
|
||||
|
||||
## Run ```conv2d_fwd_xdl```
|
||||
```bash
|
||||
#arg1: verification (0=no, 1=yes)
|
||||
#arg2: initialization (0=no init, 1=integer value, 2=decimal value)
|
||||
#arg3: run kernel # of times (>1)
|
||||
#arg4 to 18: N, K, C, Y, X, Hi, Wi, Sy, Sx, Dy, Dx, LeftPy, LeftPx, RightPy, RightPx
|
||||
./example/conv2d_fwd_xdl 0 1 5
|
||||
```
|
||||
|
||||
Result (MI100 @ 1087Mhz, 133.5TFlops peak FP16)
|
||||
```
|
||||
in_n_c_hi_wi: dim 4, lengths {128, 192, 71, 71}, strides {967872, 1, 13632, 192}
|
||||
wei_k_c_y_x: dim 4, lengths {256, 192, 3, 3}, strides {1728, 1, 576, 192}
|
||||
out_n_k_ho_wo: dim 4, lengths {128, 256, 36, 36}, strides {331776, 1, 9216, 256}
|
||||
arg.a_grid_desc_k0_m_k1_{216, 165888, 8}
|
||||
arg.b_grid_desc_k0_n_k1_{216, 256, 8}
|
||||
arg.c_grid_desc_m_n_{ 165888, 256}
|
||||
launch_and_time_kernel: grid_dim {1296, 1, 1}, block_dim {256, 1, 1}
|
||||
Warm up
|
||||
Start running 5 times...
|
||||
Perf: 1.43206 ms, 102.486 TFlops, 232.947 GB/s
|
||||
```
|
||||
274
example/05_conv2d_fwd/conv2d_fwd_xdl_fp16.cpp
Normal file
274
example/05_conv2d_fwd/conv2d_fwd_xdl_fp16.cpp
Normal file
@@ -0,0 +1,274 @@
|
||||
#include <iostream>
|
||||
#include <numeric>
|
||||
#include <initializer_list>
|
||||
#include <cstdlib>
|
||||
#include <stdlib.h>
|
||||
#include <half.hpp>
|
||||
#include "config.hpp"
|
||||
#include "print.hpp"
|
||||
#include "device.hpp"
|
||||
#include "host_tensor.hpp"
|
||||
#include "host_tensor_generator.hpp"
|
||||
#include "device_tensor.hpp"
|
||||
#include "tensor_layout.hpp"
|
||||
#include "element_wise_operation.hpp"
|
||||
#include "device_conv2d_fwd_xdl_nhwc_kyxc_nhwk.hpp"
|
||||
#include "device_conv2d_fwd_xdl_c_shuffle_nhwc_kyxc_nhwk.hpp"
|
||||
#include "reference_conv_fwd.hpp"
|
||||
#include "convolution_utility.hpp"
|
||||
|
||||
using InDataType = ck::half_t;
|
||||
using WeiDataType = ck::half_t;
|
||||
using OutDataType = ck::half_t;
|
||||
using AccDataType = float;
|
||||
|
||||
template <ck::index_t... Is>
|
||||
using S = ck::Sequence<Is...>;
|
||||
|
||||
using InLayout = ck::tensor_layout::convolution::NHWC;
|
||||
using WeiLayout = ck::tensor_layout::convolution::KYXC;
|
||||
using OutLayout = ck::tensor_layout::convolution::NHWK;
|
||||
|
||||
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_t::Default;
|
||||
|
||||
using DeviceConvFwdInstance = ck::tensor_operation::device::
|
||||
DeviceConv2dFwdXdl_Input_N_Hi_Wi_C_Weight_K_Y_X_C_Output_N_Ho_Wo_K<
|
||||
InDataType, // InDataType
|
||||
WeiDataType, // WeiDataType
|
||||
OutDataType, // OutDataType
|
||||
AccDataType, // AccDataType
|
||||
InElementOp, // InElementwiseOperation
|
||||
WeiElementOp, // WeiElementwiseOperation
|
||||
OutElementOp, // OutElementwiseOperation
|
||||
ConvFwdDefault, // ConvForwardSpecialization
|
||||
256, // BlockSize
|
||||
128, // MPerBlock
|
||||
256, // NPerBlock
|
||||
4, // K0PerBlock
|
||||
8, // K1
|
||||
32, // MPerXdl
|
||||
32, // NPerXdl
|
||||
2, // MXdlPerWave
|
||||
4, // NXdlPerWave
|
||||
S<4, 64, 1>, // ABlockTransferThreadClusterLengths_K0_M_K1
|
||||
S<1, 0, 2>, // ABlockTransferThreadClusterArrangeOrder
|
||||
S<1, 0, 2>, // ABlockTransferSrcAccessOrder
|
||||
2, // ABlockTransferSrcVectorDim
|
||||
8, // ABlockTransferSrcScalarPerVector
|
||||
8, // ABlockTransferDstScalarPerVector_K1
|
||||
true, // ABlockLdsAddExtraM
|
||||
S<4, 64, 1>, // BBlockTransferThreadClusterLengths_K0_N_K1
|
||||
S<1, 0, 2>, // BBlockTransferThreadClusterArrangeOrder
|
||||
S<1, 0, 2>, // BBlockTransferSrcAccessOrder
|
||||
2, // BBlockTransferSrcVectorDim
|
||||
8, // BBlockTransferSrcScalarPerVector
|
||||
8, // BBlockTransferDstScalarPerVector_K1
|
||||
true, // BBlockLdsAddExtraN
|
||||
7, // CThreadTransferSrcDstVectorDim
|
||||
1>; // CThreadTransferDstScalarPerVector
|
||||
|
||||
using ReferenceConvFwdInstance = ck::tensor_operation::host::
|
||||
ReferenceConvFwd<InDataType, WeiDataType, OutDataType, InElementOp, WeiElementOp, OutElementOp>;
|
||||
|
||||
int main(int argc, char* argv[])
|
||||
{
|
||||
bool do_verification = 0;
|
||||
int init_method = 0;
|
||||
int nrepeat = 5;
|
||||
|
||||
// Conv shape
|
||||
ck::index_t N = 128;
|
||||
ck::index_t K = 256;
|
||||
ck::index_t C = 192;
|
||||
ck::index_t Y = 3;
|
||||
ck::index_t X = 3;
|
||||
ck::index_t Hi = 71;
|
||||
ck::index_t Wi = 71;
|
||||
ck::index_t conv_stride_h = 2;
|
||||
ck::index_t conv_stride_w = 2;
|
||||
ck::index_t conv_dilation_h = 1;
|
||||
ck::index_t conv_dilation_w = 1;
|
||||
ck::index_t in_left_pad_h = 1;
|
||||
ck::index_t in_left_pad_w = 1;
|
||||
ck::index_t in_right_pad_h = 1;
|
||||
ck::index_t in_right_pad_w = 1;
|
||||
|
||||
if(argc == 4)
|
||||
{
|
||||
do_verification = std::stoi(argv[1]);
|
||||
init_method = std::stoi(argv[2]);
|
||||
nrepeat = std::stoi(argv[3]);
|
||||
}
|
||||
else if(argc == 19)
|
||||
{
|
||||
do_verification = std::stoi(argv[1]);
|
||||
init_method = std::stoi(argv[2]);
|
||||
nrepeat = std::stoi(argv[3]);
|
||||
|
||||
N = std::stoi(argv[4]);
|
||||
K = std::stoi(argv[5]);
|
||||
C = std::stoi(argv[6]);
|
||||
Y = std::stoi(argv[7]);
|
||||
X = std::stoi(argv[8]);
|
||||
Hi = std::stoi(argv[9]);
|
||||
Wi = std::stoi(argv[10]);
|
||||
conv_stride_h = std::stoi(argv[11]);
|
||||
conv_stride_w = std::stoi(argv[12]);
|
||||
conv_dilation_h = std::stoi(argv[13]);
|
||||
conv_dilation_w = std::stoi(argv[14]);
|
||||
in_left_pad_h = std::stoi(argv[15]);
|
||||
in_left_pad_w = std::stoi(argv[16]);
|
||||
in_right_pad_h = std::stoi(argv[17]);
|
||||
in_right_pad_w = std::stoi(argv[18]);
|
||||
}
|
||||
else
|
||||
{
|
||||
printf("arg1: verification (0=no, 1=yes)\n");
|
||||
printf("arg2: initialization (0=no init, 1=integer value, 2=decimal value)\n");
|
||||
printf("arg3: run kernel # of times (>1)\n");
|
||||
printf("arg4 to 18: N, K, C, Y, X, Hi, Wi, Sy, Sx, Dy, Dx, LeftPy, LeftPx, RightPy, "
|
||||
"RightPx\n");
|
||||
exit(0);
|
||||
}
|
||||
|
||||
const std::vector<ck::index_t> conv_filter_strides{conv_stride_h, conv_stride_w};
|
||||
const std::vector<ck::index_t> conv_filter_dilations{conv_dilation_h, conv_dilation_w};
|
||||
const std::vector<ck::index_t> input_left_pads{in_left_pad_h, in_left_pad_w};
|
||||
const std::vector<ck::index_t> input_right_pads{in_right_pad_h, in_right_pad_w};
|
||||
const auto output_spatial_lengths =
|
||||
ck::tensor_operation::ConvolutionUtility::ComputeOutputSpatialLengths({Hi, Wi},
|
||||
{Y, X},
|
||||
conv_filter_strides,
|
||||
conv_filter_dilations,
|
||||
input_left_pads,
|
||||
input_right_pads);
|
||||
|
||||
const ck::index_t Ho = output_spatial_lengths[0];
|
||||
const ck::index_t Wo = output_spatial_lengths[1];
|
||||
|
||||
// tensor layout
|
||||
auto f_host_tensor_descriptor = [](std::size_t N_,
|
||||
std::size_t C_,
|
||||
std::size_t H,
|
||||
std::size_t W,
|
||||
auto layout) {
|
||||
if constexpr(ck::is_same<decltype(layout), ck::tensor_layout::convolution::NCHW>::value ||
|
||||
ck::is_same<decltype(layout), ck::tensor_layout::convolution::KCYX>::value ||
|
||||
ck::is_same<decltype(layout), ck::tensor_layout::convolution::NKHW>::value)
|
||||
{
|
||||
return HostTensorDescriptor(std::vector<std::size_t>({N_, C_, H, W}),
|
||||
std::vector<std::size_t>({C_ * H * W, H * W, W, 1}));
|
||||
}
|
||||
else if constexpr(ck::is_same<decltype(layout),
|
||||
ck::tensor_layout::convolution::NHWC>::value ||
|
||||
ck::is_same<decltype(layout),
|
||||
ck::tensor_layout::convolution::KYXC>::value ||
|
||||
ck::is_same<decltype(layout),
|
||||
ck::tensor_layout::convolution::NHWK>::value)
|
||||
{
|
||||
return HostTensorDescriptor(std::vector<std::size_t>({N_, C_, H, W}),
|
||||
std::vector<std::size_t>({C_ * H * W, 1, W * C_, C_}));
|
||||
}
|
||||
};
|
||||
|
||||
Tensor<InDataType> in_n_c_hi_wi(f_host_tensor_descriptor(N, C, Hi, Wi, InLayout{}));
|
||||
Tensor<WeiDataType> wei_k_c_y_x(f_host_tensor_descriptor(K, C, Y, X, WeiLayout{}));
|
||||
Tensor<OutDataType> out_n_k_ho_wo_host_result(
|
||||
f_host_tensor_descriptor(N, K, Ho, Wo, OutLayout{}));
|
||||
Tensor<OutDataType> out_n_k_ho_wo_device_result(
|
||||
f_host_tensor_descriptor(N, K, Ho, Wo, OutLayout{}));
|
||||
|
||||
std::cout << "in_n_c_hi_wi: " << in_n_c_hi_wi.mDesc << std::endl;
|
||||
std::cout << "wei_k_c_y_x: " << wei_k_c_y_x.mDesc << std::endl;
|
||||
std::cout << "out_n_k_ho_wo: " << out_n_k_ho_wo_host_result.mDesc << std::endl;
|
||||
|
||||
switch(init_method)
|
||||
{
|
||||
case 0: break;
|
||||
case 1:
|
||||
in_n_c_hi_wi.GenerateTensorValue(GeneratorTensor_2<InDataType>{-5, 5});
|
||||
wei_k_c_y_x.GenerateTensorValue(GeneratorTensor_2<WeiDataType>{-5, 5});
|
||||
break;
|
||||
default:
|
||||
in_n_c_hi_wi.GenerateTensorValue(GeneratorTensor_3<InDataType>{0.0, 1.0});
|
||||
wei_k_c_y_x.GenerateTensorValue(GeneratorTensor_3<WeiDataType>{-0.5, 0.5});
|
||||
}
|
||||
|
||||
DeviceMem in_device_buf(sizeof(InDataType) * in_n_c_hi_wi.mDesc.GetElementSpace());
|
||||
DeviceMem wei_device_buf(sizeof(WeiDataType) * wei_k_c_y_x.mDesc.GetElementSpace());
|
||||
DeviceMem out_device_buf(sizeof(OutDataType) *
|
||||
out_n_k_ho_wo_device_result.mDesc.GetElementSpace());
|
||||
|
||||
in_device_buf.ToDevice(in_n_c_hi_wi.mData.data());
|
||||
wei_device_buf.ToDevice(wei_k_c_y_x.mData.data());
|
||||
|
||||
// do GEMM
|
||||
auto conv = DeviceConvFwdInstance{};
|
||||
auto invoker = conv.MakeInvoker();
|
||||
auto argument = conv.MakeArgument(static_cast<InDataType*>(in_device_buf.GetDeviceBuffer()),
|
||||
static_cast<WeiDataType*>(wei_device_buf.GetDeviceBuffer()),
|
||||
static_cast<OutDataType*>(out_device_buf.GetDeviceBuffer()),
|
||||
N,
|
||||
K,
|
||||
C,
|
||||
std::vector<ck::index_t>{Hi, Wi},
|
||||
std::vector<ck::index_t>{Y, X},
|
||||
std::vector<ck::index_t>{Ho, Wo},
|
||||
conv_filter_strides,
|
||||
conv_filter_dilations,
|
||||
input_left_pads,
|
||||
input_right_pads,
|
||||
InElementOp{},
|
||||
WeiElementOp{},
|
||||
OutElementOp{});
|
||||
|
||||
if(!conv.IsSupportedArgument(argument))
|
||||
{
|
||||
throw std::runtime_error(
|
||||
"wrong! device_conv with the specified compilation parameters does "
|
||||
"not support this Conv problem");
|
||||
}
|
||||
|
||||
float ave_time = invoker.Run(argument, nrepeat);
|
||||
|
||||
std::size_t flop = std::size_t(2) * N * K * Ho * Wo * C * Y * X;
|
||||
|
||||
std::size_t num_btype = sizeof(InDataType) * (N * C * Hi * Wi) +
|
||||
sizeof(WeiDataType) * (K * C * Y * X) +
|
||||
sizeof(OutDataType) * (N * K * Ho * Wo);
|
||||
|
||||
float tflops = static_cast<float>(flop) / 1.E9 / ave_time;
|
||||
|
||||
float gb_per_sec = num_btype / 1.E6 / ave_time;
|
||||
|
||||
std::cout << "Perf: " << ave_time << " ms, " << tflops << " TFlops, " << gb_per_sec << " GB/s"
|
||||
<< std::endl;
|
||||
|
||||
if(do_verification)
|
||||
{
|
||||
auto ref_conv = ReferenceConvFwdInstance{};
|
||||
auto ref_invoker = ref_conv.MakeInvoker();
|
||||
|
||||
auto ref_argument = ref_conv.MakeArgument(in_n_c_hi_wi,
|
||||
wei_k_c_y_x,
|
||||
out_n_k_ho_wo_host_result,
|
||||
conv_filter_strides,
|
||||
conv_filter_dilations,
|
||||
input_left_pads,
|
||||
input_right_pads,
|
||||
InElementOp{},
|
||||
WeiElementOp{},
|
||||
OutElementOp{});
|
||||
|
||||
ref_invoker.Run(ref_argument);
|
||||
|
||||
out_device_buf.FromDevice(out_n_k_ho_wo_device_result.mData.data());
|
||||
|
||||
check_error(out_n_k_ho_wo_host_result, out_n_k_ho_wo_device_result);
|
||||
}
|
||||
}
|
||||
275
example/05_conv2d_fwd/conv2d_fwd_xdl_int8.cpp
Normal file
275
example/05_conv2d_fwd/conv2d_fwd_xdl_int8.cpp
Normal file
@@ -0,0 +1,275 @@
|
||||
#include <iostream>
|
||||
#include <numeric>
|
||||
#include <initializer_list>
|
||||
#include <cstdlib>
|
||||
#include <stdlib.h>
|
||||
#include <half.hpp>
|
||||
#include "config.hpp"
|
||||
#include "print.hpp"
|
||||
#include "device.hpp"
|
||||
#include "host_tensor.hpp"
|
||||
#include "host_tensor_generator.hpp"
|
||||
#include "device_tensor.hpp"
|
||||
#include "tensor_layout.hpp"
|
||||
#include "device_conv2d_fwd_xdl_nhwc_kyxc_nhwk.hpp"
|
||||
#include "element_wise_operation.hpp"
|
||||
#include "reference_conv_fwd.hpp"
|
||||
#include "convolution_utility.hpp"
|
||||
|
||||
using InDataType = int8_t;
|
||||
using WeiDataType = int8_t;
|
||||
using OutDataType = int8_t;
|
||||
using AccDataType = int32_t;
|
||||
|
||||
template <ck::index_t... Is>
|
||||
using S = ck::Sequence<Is...>;
|
||||
|
||||
using InLayout = ck::tensor_layout::convolution::NHWC;
|
||||
using WeiLayout = ck::tensor_layout::convolution::KYXC;
|
||||
using OutLayout = ck::tensor_layout::convolution::NHWK;
|
||||
|
||||
using InElementOp = ck::tensor_operation::element_wise::PassThrough;
|
||||
using WeiElementOp = ck::tensor_operation::element_wise::PassThrough;
|
||||
using OutElementOp = ck::tensor_operation::element_wise::PassThrough;
|
||||
|
||||
using PassThrough = ck::tensor_operation::element_wise::PassThrough;
|
||||
|
||||
static constexpr auto ConvFwdDefault =
|
||||
ck::tensor_operation::device::ConvolutionForwardSpecialization_t::Default;
|
||||
|
||||
using DeviceConvFwdInstance = ck::tensor_operation::device::
|
||||
DeviceConv2dFwdXdl_Input_N_Hi_Wi_C_Weight_K_Y_X_C_Output_N_Ho_Wo_K<
|
||||
int8_t, // InDataType
|
||||
int8_t, // WeiDataType
|
||||
int8_t, // OutDataType
|
||||
int32_t, // AccDataType
|
||||
PassThrough, // InElementwiseOperation
|
||||
PassThrough, // WeiElementwiseOperation
|
||||
PassThrough, // OutElementwiseOperation
|
||||
ConvFwdDefault, // ConvForwardSpecialization
|
||||
256, // BlockSize
|
||||
128, // MPerBlock
|
||||
256, // NPerBlock
|
||||
4, // K0PerBlock
|
||||
16, // K1
|
||||
32, // MPerXdl
|
||||
32, // NPerXdl
|
||||
2, // MXdlPerWave
|
||||
4, // NXdlPerWave
|
||||
S<4, 64, 1>, // ABlockTransferThreadClusterLengths_K0_M_K1
|
||||
S<1, 0, 2>, // ABlockTransferThreadClusterArrangeOrder
|
||||
S<1, 0, 2>, // ABlockTransferSrcAccessOrder
|
||||
2, // ABlockTransferSrcVectorDim
|
||||
16, // ABlockTransferSrcScalarPerVector
|
||||
16, // ABlockTransferDstScalarPerVector_K1
|
||||
true, // ABlockLdsAddExtraM
|
||||
S<4, 64, 1>, // BBlockTransferThreadClusterLengths_K0_N_K1
|
||||
S<1, 0, 2>, // BBlockTransferThreadClusterArrangeOrder
|
||||
S<1, 0, 2>, // BBlockTransferSrcAccessOrder
|
||||
2, // BBlockTransferSrcVectorDim
|
||||
16, // BBlockTransferSrcScalarPerVector
|
||||
16, // BBlockTransferDstScalarPerVector_K1
|
||||
true, // BBlockLdsAddExtraN
|
||||
7, // CThreadTransferSrcDstVectorDim
|
||||
1>; // CThreadTransferDstScalarPerVector
|
||||
|
||||
using ReferenceConvFwdInstance = ck::tensor_operation::host::
|
||||
ReferenceConvFwd<InDataType, WeiDataType, OutDataType, InElementOp, WeiElementOp, OutElementOp>;
|
||||
|
||||
int main(int argc, char* argv[])
|
||||
{
|
||||
bool do_verification = 0;
|
||||
int init_method = 0;
|
||||
int nrepeat = 5;
|
||||
|
||||
// Conv shape
|
||||
ck::index_t N = 128;
|
||||
ck::index_t K = 256;
|
||||
ck::index_t C = 192;
|
||||
ck::index_t Y = 3;
|
||||
ck::index_t X = 3;
|
||||
ck::index_t Hi = 71;
|
||||
ck::index_t Wi = 71;
|
||||
ck::index_t conv_stride_h = 2;
|
||||
ck::index_t conv_stride_w = 2;
|
||||
ck::index_t conv_dilation_h = 1;
|
||||
ck::index_t conv_dilation_w = 1;
|
||||
ck::index_t in_left_pad_h = 1;
|
||||
ck::index_t in_left_pad_w = 1;
|
||||
ck::index_t in_right_pad_h = 1;
|
||||
ck::index_t in_right_pad_w = 1;
|
||||
|
||||
if(argc == 4)
|
||||
{
|
||||
do_verification = std::stoi(argv[1]);
|
||||
init_method = std::stoi(argv[2]);
|
||||
nrepeat = std::stoi(argv[3]);
|
||||
}
|
||||
else if(argc == 19)
|
||||
{
|
||||
do_verification = std::stoi(argv[1]);
|
||||
init_method = std::stoi(argv[2]);
|
||||
nrepeat = std::stoi(argv[3]);
|
||||
|
||||
N = std::stoi(argv[4]);
|
||||
K = std::stoi(argv[5]);
|
||||
C = std::stoi(argv[6]);
|
||||
Y = std::stoi(argv[7]);
|
||||
X = std::stoi(argv[8]);
|
||||
Hi = std::stoi(argv[9]);
|
||||
Wi = std::stoi(argv[10]);
|
||||
conv_stride_h = std::stoi(argv[11]);
|
||||
conv_stride_w = std::stoi(argv[12]);
|
||||
conv_dilation_h = std::stoi(argv[13]);
|
||||
conv_dilation_w = std::stoi(argv[14]);
|
||||
in_left_pad_h = std::stoi(argv[15]);
|
||||
in_left_pad_w = std::stoi(argv[16]);
|
||||
in_right_pad_h = std::stoi(argv[17]);
|
||||
in_right_pad_w = std::stoi(argv[18]);
|
||||
}
|
||||
else
|
||||
{
|
||||
printf("arg1: verification (0=no, 1=yes)\n");
|
||||
printf("arg2: initialization (0=no init, 1=integer value, 2=decimal value)\n");
|
||||
printf("arg3: run kernel # of times (>1)\n");
|
||||
printf("arg4 to 18: N, K, C, Y, X, Hi, Wi, Sy, Sx, Dy, Dx, LeftPy, LeftPx, RightPy, "
|
||||
"RightPx\n");
|
||||
exit(0);
|
||||
}
|
||||
|
||||
const std::vector<ck::index_t> conv_filter_strides{conv_stride_h, conv_stride_w};
|
||||
const std::vector<ck::index_t> conv_filter_dilations{conv_dilation_h, conv_dilation_w};
|
||||
const std::vector<ck::index_t> input_left_pads{in_left_pad_h, in_left_pad_w};
|
||||
const std::vector<ck::index_t> input_right_pads{in_right_pad_h, in_right_pad_w};
|
||||
const auto output_spatial_lengths =
|
||||
ck::tensor_operation::ConvolutionUtility::ComputeOutputSpatialLengths({Hi, Wi},
|
||||
{Y, X},
|
||||
conv_filter_strides,
|
||||
conv_filter_dilations,
|
||||
input_left_pads,
|
||||
input_right_pads);
|
||||
|
||||
const ck::index_t Ho = output_spatial_lengths[0];
|
||||
const ck::index_t Wo = output_spatial_lengths[1];
|
||||
|
||||
// tensor layout
|
||||
auto f_host_tensor_descriptor = [](std::size_t N_,
|
||||
std::size_t C_,
|
||||
std::size_t H,
|
||||
std::size_t W,
|
||||
auto layout) {
|
||||
if constexpr(ck::is_same<decltype(layout), ck::tensor_layout::convolution::NCHW>::value ||
|
||||
ck::is_same<decltype(layout), ck::tensor_layout::convolution::KCYX>::value ||
|
||||
ck::is_same<decltype(layout), ck::tensor_layout::convolution::NKHW>::value)
|
||||
{
|
||||
return HostTensorDescriptor(std::vector<std::size_t>({N_, C_, H, W}),
|
||||
std::vector<std::size_t>({C_ * H * W, H * W, W, 1}));
|
||||
}
|
||||
else if constexpr(ck::is_same<decltype(layout),
|
||||
ck::tensor_layout::convolution::NHWC>::value ||
|
||||
ck::is_same<decltype(layout),
|
||||
ck::tensor_layout::convolution::KYXC>::value ||
|
||||
ck::is_same<decltype(layout),
|
||||
ck::tensor_layout::convolution::NHWK>::value)
|
||||
{
|
||||
return HostTensorDescriptor(std::vector<std::size_t>({N_, C_, H, W}),
|
||||
std::vector<std::size_t>({C_ * H * W, 1, W * C_, C_}));
|
||||
}
|
||||
};
|
||||
|
||||
Tensor<InDataType> in_n_c_hi_wi(f_host_tensor_descriptor(N, C, Hi, Wi, InLayout{}));
|
||||
Tensor<WeiDataType> wei_k_c_y_x(f_host_tensor_descriptor(K, C, Y, X, WeiLayout{}));
|
||||
Tensor<OutDataType> out_n_k_ho_wo_host_result(
|
||||
f_host_tensor_descriptor(N, K, Ho, Wo, OutLayout{}));
|
||||
Tensor<OutDataType> out_n_k_ho_wo_device_result(
|
||||
f_host_tensor_descriptor(N, K, Ho, Wo, OutLayout{}));
|
||||
|
||||
std::cout << "in_n_c_hi_wi: " << in_n_c_hi_wi.mDesc << std::endl;
|
||||
std::cout << "wei_k_c_y_x: " << wei_k_c_y_x.mDesc << std::endl;
|
||||
std::cout << "out_n_k_ho_wo: " << out_n_k_ho_wo_host_result.mDesc << std::endl;
|
||||
|
||||
switch(init_method)
|
||||
{
|
||||
case 0: break;
|
||||
case 1:
|
||||
in_n_c_hi_wi.GenerateTensorValue(GeneratorTensor_2<InDataType>{-1, 1});
|
||||
wei_k_c_y_x.GenerateTensorValue(GeneratorTensor_2<WeiDataType>{-1, 1});
|
||||
break;
|
||||
default:
|
||||
in_n_c_hi_wi.GenerateTensorValue(GeneratorTensor_3<InDataType>{0, 1});
|
||||
wei_k_c_y_x.GenerateTensorValue(GeneratorTensor_3<WeiDataType>{-1, 1});
|
||||
}
|
||||
|
||||
DeviceMem in_device_buf(sizeof(InDataType) * in_n_c_hi_wi.mDesc.GetElementSpace());
|
||||
DeviceMem wei_device_buf(sizeof(WeiDataType) * wei_k_c_y_x.mDesc.GetElementSpace());
|
||||
DeviceMem out_device_buf(sizeof(OutDataType) *
|
||||
out_n_k_ho_wo_device_result.mDesc.GetElementSpace());
|
||||
|
||||
in_device_buf.ToDevice(in_n_c_hi_wi.mData.data());
|
||||
wei_device_buf.ToDevice(wei_k_c_y_x.mData.data());
|
||||
|
||||
// do GEMM
|
||||
auto conv = DeviceConvFwdInstance{};
|
||||
auto invoker = conv.MakeInvoker();
|
||||
auto argument = conv.MakeArgument(static_cast<InDataType*>(in_device_buf.GetDeviceBuffer()),
|
||||
static_cast<WeiDataType*>(wei_device_buf.GetDeviceBuffer()),
|
||||
static_cast<OutDataType*>(out_device_buf.GetDeviceBuffer()),
|
||||
N,
|
||||
K,
|
||||
C,
|
||||
std::vector<ck::index_t>{Hi, Wi},
|
||||
std::vector<ck::index_t>{Y, X},
|
||||
std::vector<ck::index_t>{Ho, Wo},
|
||||
conv_filter_strides,
|
||||
conv_filter_dilations,
|
||||
input_left_pads,
|
||||
input_right_pads,
|
||||
InElementOp{},
|
||||
WeiElementOp{},
|
||||
OutElementOp{});
|
||||
|
||||
if(!conv.IsSupportedArgument(argument))
|
||||
{
|
||||
throw std::runtime_error(
|
||||
"wrong! device_conv with the specified compilation parameters does "
|
||||
"not support this Conv problem");
|
||||
}
|
||||
|
||||
float ave_time = invoker.Run(argument, nrepeat);
|
||||
|
||||
std::size_t flop = std::size_t(2) * N * K * Ho * Wo * C * Y * X;
|
||||
|
||||
std::size_t num_btype = sizeof(InDataType) * (N * C * Hi * Wi) +
|
||||
sizeof(WeiDataType) * (K * C * Y * X) +
|
||||
sizeof(OutDataType) * (N * K * Ho * Wo);
|
||||
|
||||
float tflops = static_cast<float>(flop) / 1.E9 / ave_time;
|
||||
|
||||
float gb_per_sec = num_btype / 1.E6 / ave_time;
|
||||
|
||||
std::cout << "Perf: " << ave_time << " ms, " << tflops << " TFlops, " << gb_per_sec << " GB/s"
|
||||
<< std::endl;
|
||||
|
||||
if(do_verification)
|
||||
{
|
||||
auto ref_conv = ReferenceConvFwdInstance{};
|
||||
auto ref_invoker = ref_conv.MakeInvoker();
|
||||
|
||||
auto ref_argument = ref_conv.MakeArgument(in_n_c_hi_wi,
|
||||
wei_k_c_y_x,
|
||||
out_n_k_ho_wo_host_result,
|
||||
conv_filter_strides,
|
||||
conv_filter_dilations,
|
||||
input_left_pads,
|
||||
input_right_pads,
|
||||
InElementOp{},
|
||||
WeiElementOp{},
|
||||
OutElementOp{});
|
||||
|
||||
ref_invoker.Run(ref_argument);
|
||||
|
||||
out_device_buf.FromDevice(out_n_k_ho_wo_device_result.mData.data());
|
||||
|
||||
check_error(out_n_k_ho_wo_host_result, out_n_k_ho_wo_device_result);
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user