add conv fwd example

example/01_gemm/gemm_xdl_fp64.cpp

@@ -30,7 +30,6 @@ using Col = ck::tensor_layout::gemm::ColumnMajor;
 
 using PassThrough = ck::tensor_operation::element_wise::PassThrough;
 
-
 using ALayout = ck::tensor_layout::gemm::RowMajor;
 using BLayout = ck::tensor_layout::gemm::ColumnMajor;
 using CLayout = ck::tensor_layout::gemm::RowMajor;
@@ -48,7 +47,7 @@ using DeviceGemmInstance = ck::tensor_operation::device::DeviceGemmXdl
 //##########|      |      |      |        |        |        |        |   Operation|   Operation|   Operation|              |      |      |      |      |   |     |     | Wave| Wave| Lengths_K0_M_K1|   ArrangeOrder|               |               |      PerVector|   PerVector_K1|          | Lengths_K0_N_K1|   ArrangeOrder|               |              |      PerVector|   PerVector_K1|          |                |       PerVector|
 //##########|      |      |      |        |        |        |        |            |            |            |              |      |      |      |      |   |     |     |     |     |                |               |               |               |               |               |          |                |               |               |              |               |               |          |                |                |
 #if 1
-             <  F64,   F64,   F64,     F64,     Row,     Col,     Row, PassThrough, PassThrough, PassThrough,   GemmDefault,   256,   128,   128,     4,  2,   16,   16,    4,    4,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              2,              2,      true,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              2,              2,      true,               7,               1>;
+             <  F64,   F64,   F64,     F64,     Row,     Col,     Row, PassThrough, PassThrough, PassThrough,   GemmDefault,   256,   128,   128,     4,  4,   16,   16,    4,    4,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              4,              4,      true,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              4,              4,      true,               7,               1>;
 using ADataType   = double;
 using BDataType   = double;
 using CDataType   = double;
@@ -144,10 +143,10 @@ int main(int argc, char* argv[])
         b_k_n.GenerateTensorValue(GeneratorTensor_3<BDataType>{-0.5, 0.5});
         break;
     default:
-        //a_m_k.GenerateTensorValue(GeneratorTensor_2<ADataType>{-5, 5}); 
-        b_k_n.GenerateTensorValue(GeneratorTensor_3<BDataType>{-0.5, 0.5});
+        // a_m_k.GenerateTensorValue(GeneratorTensor_2<ADataType>{-5, 5});
+        b_k_n.GenerateTensorValue(GeneratorTensor_2<BDataType>{-5, 5});
         a_m_k.GenerateTensorValue(GeneratorTensor_1<ADataType>{1});
-        //b_k_n.GenerateTensorValue(GeneratorTensor_1<BDataType>{1});
+        // b_k_n.GenerateTensorValue(GeneratorTensor_1<BDataType>{1});
     }
 
     DeviceMem a_m_k_device_buf(sizeof(ADataType) * a_m_k.mDesc.GetElementSpace());
@@ -209,12 +208,12 @@ int main(int argc, char* argv[])
 
         ref_invoker.Run(ref_argument);
 
- #if 1
+#if 0
         {
-            LogRangeAsType<double>(std::cout << "a : ", a_m_k.mData, ",") << std::endl;
-            LogRangeAsType<double>(std::cout << "b: ", b_k_n.mData, ",") << std::endl;
-            LogRangeAsType<double>(std::cout << "c_device: ", c_m_n_device_result.mData, ",") << std::endl;
-            LogRangeAsType<double>(std::cout << "c_host  : ", c_m_n_host_result.mData, ",")
+            LogRangeAsType<AccDataType>(std::cout << "a : ", a_m_k.mData, ",") << std::endl;
+            LogRangeAsType<AccDataType>(std::cout << "b: ", b_k_n.mData, ",") << std::endl;
+            LogRangeAsType<AccDataType>(std::cout << "c_device: ", c_m_n_device_result.mData, ",") << std::endl;
+            LogRangeAsType<AccDataType>(std::cout << "c_host  : ", c_m_n_host_result.mData, ",")
                 << std::endl;
         }
 #endif

example/09_convnd_fwd/CMakeLists.txt

 add_example_executable(example_convnd_fwd_xdl convnd_fwd_xdl.cpp)
 add_example_executable(example_convnd_fwd_xdl_int8 convnd_fwd_xdl_int8.cpp)
 add_example_executable(example_convnd_fwd_xdl_fp16 convnd_fwd_xdl_fp16.cpp)
+add_example_executable(example_convnd_fwd_xdl_fp64 convnd_fwd_xdl_fp64.cpp)

example/09_convnd_fwd/convnd_fwd_xdl_fp64.cpp

+#include <cstdlib>
+#include <iostream>
+#include <numeric>
+#include <type_traits>
+
+#include "check_err.hpp"
+#include "config.hpp"
+#include "conv_fwd_util.hpp"
+#include "device.hpp"
+#include "device_tensor.hpp"
+#include "device_convnd_fwd_xdl_nhwc_kyxc_nhwk.hpp"
+#include "element_wise_operation.hpp"
+#include "host_tensor.hpp"
+#include "host_tensor_generator.hpp"
+#include "reference_conv_fwd.hpp"
+#include "tensor_layout.hpp"
+
+namespace {
+
+using InDataType  = double;
+using WeiDataType = double;
+using OutDataType = double;
+using AccDataType = double;
+
+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;
+
+using DeviceConvFwdBasePtr =
+    ck::tensor_operation::device::DeviceConvFwdPtr<InElementOp, WeiElementOp, OutElementOp>;
+
+template <ck::index_t NumDimSpatial>
+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,        //
+        AccDataType,        // 
+        InElementOp,        // Input Elementwise Operation
+        WeiElementOp,       // Weights Elementwise Operation
+        OutElementOp,       // Output Elementwise Operation
+        ConvFwdDefault,     // ConvForwardSpecialization
+        NumDimSpatial,      // NumDimSpatial
+        256,                // BlockSize
+        128,                // MPerBlock
+        128,                // NPerBlock
+        4,                  // K0PerBlock
+        2,                  // K1
+        16,                 // MPerXDL
+        16,                 // NPerXDL
+        4,                  // MXdlPerWave
+        4,                  // NXdlPerWave
+        S<4, 64, 1>,        // ABlockTransferThreadClusterLengths_K0_M_K1
+        S<1, 0, 2>,         // ABlockTransferThreadClusterArrangeOrder
+        S<1, 0, 2>,         // ABlockTransferSrcAccessOrder
+        2,                  // ABlockTransferSrcVectorDim
+        2,                  // ABlockTransferSrcScalarPerVector
+        2,                  // ABlockTransferDstScalarPerVector_K1
+        true,               // ABlockLdsAddExtraM
+        S<4, 64, 1>,        // BBlockTransferThreadClusterLengths_K0_N_K1
+        S<1, 0, 2>,         // BBlockTransferThreadClusterArrangeOrder
+        S<1, 0, 2>,         // BBlockTransferSrcAccessOrder
+        2,                  // BBlockTransferSrcVectorDim
+        2,                  // BBlockTransferSrcScalarPerVector
+        2,                  // BBlockTransferDstScalarPerVector_K1
+        true,               // BBlockTransferAddExtraN
+        7,                  // CThreadTransferSrcDstVectorDim
+        1>;                 // CThreadTransferDstScalarPerVector
+// clang-format on
+
+template <ck::index_t NumDimSpatial>
+using ReferenceConvNDFwdInstance = ck::tensor_operation::host::ReferenceConvFwd<InDataType,
+                                                                                WeiDataType,
+                                                                                OutDataType,
+                                                                                InElementOp,
+                                                                                WeiElementOp,
+                                                                                OutElementOp,
+                                                                                NumDimSpatial>;
+
+DeviceConvFwdBasePtr get_conv_instance(int num_dim_spatial)
+{
+    switch(num_dim_spatial)
+    {
+    case 3: {
+        return std::make_unique<DeviceConvNDFwdInstance<3>>();
+    }
+    case 2: {
+        return std::make_unique<DeviceConvNDFwdInstance<2>>();
+    }
+    case 1: {
+        return std::make_unique<DeviceConvNDFwdInstance<1>>();
+    }
+    default: {
+        throw std::runtime_error("Unsupported number of spatial dimensions provided!");
+    }
+    }
+}
+
+void print_use_msg()
+{
+    std::cout << "arg1: verification (0=no, 1=yes)\n"
+              << "arg2: initialization (0=no init, 1=integer value, 2=decimal value)\n"
+              << "arg3: run kernel # of times (>1)\n"
+              << "arg4: N spatial dimensions (default 2)\n"
+              << "Following arguments (depending on number of spatial dims):\n"
+              << " N, K, C, \n"
+              << " <filter spatial dimensions>, (ie Y, X for 2D)\n"
+              << " <input image spatial dimensions>, (ie Hi, Wi for 2D)\n"
+              << " <strides>, (ie Sy, Sx for 2D)\n"
+              << " <dilations>, (ie Dy, Dx for 2D)\n"
+              << " <left padding>, (ie LeftPy, LeftPx for 2D)\n"
+              << " <right padding>, (ie RightPy, RightPx for 2D)\n"
+              << std::endl;
+}
+
+ck::utils::conv::ConvParams parse_conv_params(int num_dim_spatial, int argc, char* argv[])
+{
+    // (N, K, C) + num_dim_spatial * 6 (filter, input, strides, dilations, pad left, pad right)
+    int conv_args     = 3 + num_dim_spatial * 6;
+    int cmdline_nargs = conv_args + 5;
+    if(cmdline_nargs != argc)
+    {
+        print_use_msg();
+        exit(0);
+    }
+
+    ck::utils::conv::ConvParams params;
+    int arg_idx = 5;
+
+    params.num_dim_spatial = num_dim_spatial;
+    params.N               = std::stoi(argv[arg_idx++]);
+    params.K               = std::stoi(argv[arg_idx++]);
+    params.C               = std::stoi(argv[arg_idx++]);
+
+    params.filter_spatial_lengths.resize(num_dim_spatial);
+    for(int i = 0; i < num_dim_spatial; ++i)
+    {
+        params.filter_spatial_lengths[i] = std::stoi(argv[arg_idx++]);
+    }
+    params.input_spatial_lengths.resize(num_dim_spatial);
+    for(int i = 0; i < num_dim_spatial; ++i)
+    {
+        params.input_spatial_lengths[i] = std::stoi(argv[arg_idx++]);
+    }
+    params.conv_filter_strides.resize(num_dim_spatial);
+    for(int i = 0; i < num_dim_spatial; ++i)
+    {
+        params.conv_filter_strides[i] = std::stoi(argv[arg_idx++]);
+    }
+    params.conv_filter_dilations.resize(num_dim_spatial);
+    for(int i = 0; i < num_dim_spatial; ++i)
+    {
+        params.conv_filter_dilations[i] = std::stoi(argv[arg_idx++]);
+    }
+    params.input_left_pads.resize(num_dim_spatial);
+    for(int i = 0; i < num_dim_spatial; ++i)
+    {
+        params.input_left_pads[i] = std::stoi(argv[arg_idx++]);
+    }
+    params.input_right_pads.resize(num_dim_spatial);
+    for(int i = 0; i < num_dim_spatial; ++i)
+    {
+        params.input_right_pads[i] = std::stoi(argv[arg_idx++]);
+    }
+
+    return params;
+}
+
+} // anonymous namespace
+
+int main(int argc, char* argv[])
+{
+    using namespace ck::utils::conv;
+
+    bool do_verification = 0;
+    int init_method      = 0;
+    int nrepeat          = 5;
+    int num_dim_spatial  = 2;
+
+    ck::utils::conv::ConvParams params;
+
+    if(argc >= 5)
+    {
+        do_verification = std::stoi(argv[1]);
+        init_method     = std::stoi(argv[2]);
+        nrepeat         = std::stoi(argv[3]);
+        num_dim_spatial = std::stoi(argv[4]);
+    }
+
+    if(argc >= 6)
+    {
+        params = parse_conv_params(num_dim_spatial, argc, argv);
+    }
+
+    std::vector<std::size_t> input_dims{static_cast<std::size_t>(params.N),
+                                        static_cast<std::size_t>(params.C)};
+    input_dims.insert(std::end(input_dims),
+                      std::begin(params.input_spatial_lengths),
+                      std::end(params.input_spatial_lengths));
+
+    std::vector<std::size_t> filter_dims{static_cast<std::size_t>(params.K),
+                                         static_cast<std::size_t>(params.C)};
+    filter_dims.insert(std::end(filter_dims),
+                       std::begin(params.filter_spatial_lengths),
+                       std::end(params.filter_spatial_lengths));
+
+    const std::vector<ck::index_t>& output_spatial_lengths = params.GetOutputSpatialLengths();
+    std::vector<std::size_t> output_dims{static_cast<std::size_t>(params.N),
+                                         static_cast<std::size_t>(params.K)};
+    output_dims.insert(std::end(output_dims),
+                       std::begin(output_spatial_lengths),
+                       std::end(output_spatial_lengths));
+
+    Tensor<InDataType> input(get_input_host_tensor_descriptor(input_dims, num_dim_spatial));
+    Tensor<WeiDataType> weights(get_filters_host_tensor_descriptor(filter_dims, num_dim_spatial));
+    Tensor<OutDataType> host_output(
+        get_output_host_tensor_descriptor(output_dims, num_dim_spatial));
+    Tensor<OutDataType> device_output(
+        get_output_host_tensor_descriptor(output_dims, num_dim_spatial));
+
+    std::cout << "input: " << input.mDesc << std::endl;
+    std::cout << "weights: " << weights.mDesc << std::endl;
+    std::cout << "output: " << host_output.mDesc << std::endl;
+
+    switch(init_method)
+    {
+    case 0: break;
+    case 1:
+        input.GenerateTensorValue(GeneratorTensor_2<InDataType>{-5, 5});
+        weights.GenerateTensorValue(GeneratorTensor_2<WeiDataType>{-5, 5});
+        break;
+    case 2:
+        input.GenerateTensorValue(GeneratorTensor_3<InDataType>{0.0, 1.0});
+        weights.GenerateTensorValue(GeneratorTensor_3<WeiDataType>{-0.5, 0.5});
+        break;
+    default:
+        // input.GenerateTensorValue(GeneratorTensor_2<InDataType>{-5, 5});
+        weights.GenerateTensorValue(GeneratorTensor_2<WeiDataType>{-5, 5});
+        input.GenerateTensorValue(GeneratorTensor_1<InDataType>{1});
+        // weights.GenerateTensorValue(GeneratorTensor_1<WeiDataType>{1});
+    }
+
+    DeviceMem in_device_buf(sizeof(InDataType) * input.mDesc.GetElementSpace());
+    DeviceMem wei_device_buf(sizeof(WeiDataType) * weights.mDesc.GetElementSpace());
+    DeviceMem out_device_buf(sizeof(OutDataType) * device_output.mDesc.GetElementSpace());
+
+    in_device_buf.ToDevice(input.mData.data());
+    wei_device_buf.ToDevice(weights.mData.data());
+
+    // do GEMM
+    auto conv    = get_conv_instance(num_dim_spatial);
+    auto invoker = conv->MakeInvokerPointer();
+    auto argument =
+        conv->MakeArgumentPointer(static_cast<InDataType*>(in_device_buf.GetDeviceBuffer()),
+                                  static_cast<WeiDataType*>(wei_device_buf.GetDeviceBuffer()),
+                                  static_cast<OutDataType*>(out_device_buf.GetDeviceBuffer()),
+                                  params.N,
+                                  params.K,
+                                  params.C,
+                                  params.input_spatial_lengths,
+                                  params.filter_spatial_lengths,
+                                  output_spatial_lengths,
+                                  params.conv_filter_strides,
+                                  params.conv_filter_dilations,
+                                  params.input_left_pads,
+                                  params.input_right_pads,
+                                  InElementOp{},
+                                  WeiElementOp{},
+                                  OutElementOp{});
+
+    if(!conv->IsSupportedArgument(argument.get()))
+    {
+        throw std::runtime_error(
+            "wrong! device_conv with the specified compilation parameters does "
+            "not support this Conv problem");
+    }
+
+    float ave_time = invoker->Run(argument.get(), nrepeat);
+
+    std::size_t flop = get_flops(
+        params.N, params.C, params.K, params.filter_spatial_lengths, output_spatial_lengths);
+    std::size_t num_btype =
+        get_btype<InDataType, WeiDataType, OutDataType>(params.N,
+                                                        params.C,
+                                                        params.K,
+                                                        params.input_spatial_lengths,
+                                                        params.filter_spatial_lengths,
+                                                        output_spatial_lengths);
+
+    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 verify_f = [&input, &weights, &host_output, &params, &out_device_buf, &device_output](
+                            const auto& ref_conv) {
+            auto ref_invoker  = ref_conv.MakeInvoker();
+            auto ref_argument = ref_conv.MakeArgument(input,
+                                                      weights,
+                                                      host_output,
+                                                      params.conv_filter_strides,
+                                                      params.conv_filter_dilations,
+                                                      params.input_left_pads,
+                                                      params.input_right_pads,
+                                                      InElementOp{},
+                                                      WeiElementOp{},
+                                                      OutElementOp{});
+
+            ref_invoker.Run(ref_argument);
+            out_device_buf.FromDevice(device_output.mData.data());
+            ck::utils::check_err(
+                host_output.mData, device_output.mData, "Error: incorrect results!", 1e-5f, 1e-4f);
+        };
+
+        switch(num_dim_spatial)
+        {
+        case 3: {
+            auto ref_conv = ReferenceConvNDFwdInstance<3>();
+            verify_f(ref_conv);
+            break;
+        }
+        case 2: {
+            auto ref_conv = ReferenceConvNDFwdInstance<2>();
+            verify_f(ref_conv);
+            break;
+        }
+        case 1: {
+            auto ref_conv = ReferenceConvNDFwdInstance<1>();
+            verify_f(ref_conv);
+            break;
+        }
+        default: {
+            throw std::runtime_error("Unsupported number of spatial dimensions provided!");
+        }
+        }
+    }
+}