Merge branch 'develop' into mi300_time_measurement

include/ck_tile/core/utility/unary_element_function.hpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
+
+#pragma once
+
+#include "ck_tile/core.hpp"
+
+namespace ck_tile {
+
+template <typename F, typename... Fs>
+struct composes : private composes<F>
+{
+    template <typename FirstArg, typename... RestArgs>
+    CK_TILE_HOST_DEVICE constexpr explicit composes(FirstArg&& firstArg, RestArgs&&... restArgs)
+        : composes<F>(std::forward<FirstArg>(firstArg)), inner_(std::forward<RestArgs>(restArgs)...)
+    {
+    }
+
+    template <typename Arg>
+    CK_TILE_HOST_DEVICE constexpr auto operator()(Arg&& arg) const
+    {
+        return static_cast<const composes<F>&>(*this)(inner_(std::forward<Arg>(arg)));
+    }
+
+    private:
+    composes<Fs...> inner_;
+};
+
+template <typename F>
+struct composes<F>
+{
+    static_assert(!std::is_reference_v<F>);
+
+    template <typename Arg, typename = std::enable_if_t<std::is_constructible_v<F, Arg>>>
+    CK_TILE_HOST_DEVICE constexpr explicit composes(Arg&& arg) : f_(std::forward<Arg>(arg))
+    {
+    }
+
+    template <typename Arg,
+              typename = std::enable_if_t<std::is_invocable_v<std::add_const_t<F>&, Arg>>>
+    CK_TILE_HOST_DEVICE constexpr auto operator()(Arg&& arg) const
+    {
+        return f_(std::forward<Arg>(arg));
+    }
+
+    private:
+    F f_;
+};
+
+/// FIXME: create macro to replace '__host__ __device__' and nothing more
+template <typename... Ts>
+__host__ __device__ composes(Ts&&...)->composes<remove_cvref_t<Ts>...>;
+
+template <typename To>
+struct saturates
+{
+    template <typename From>
+    CK_TILE_HOST_DEVICE constexpr auto operator()(const From& from) const
+        -> std::enable_if_t<std::is_arithmetic_v<From>, From>
+    {
+        return clamp(from,
+                     type_convert<From>(numeric<To>::lowest()),
+                     type_convert<From>(numeric<To>::max()));
+    }
+};
+
+} // namespace ck_tile

include/ck_tile/host.hpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
+
+#pragma once
+
+#include "ck_tile/host/arg_parser.hpp"
+#include "ck_tile/host/check_err.hpp"
+#include "ck_tile/host/device_memory.hpp"
+#include "ck_tile/host/fill.hpp"
+#include "ck_tile/host/hip_check_error.hpp"
+#include "ck_tile/host/host_tensor.hpp"
+#include "ck_tile/host/kernel_launch.hpp"
+#include "ck_tile/host/ranges.hpp"
+#include "ck_tile/host/reference/reference_batched_elementwise.hpp"
+#include "ck_tile/host/reference/reference_batched_gemm.hpp"
+#include "ck_tile/host/reference/reference_batched_masking.hpp"
+#include "ck_tile/host/reference/reference_batched_softmax.hpp"
+#include "ck_tile/host/reference/reference_gemm.hpp"
+#include "ck_tile/host/reference/reference_im2col.hpp"
+#include "ck_tile/host/reference/reference_reduce.hpp"
+#include "ck_tile/host/reference/reference_softmax.hpp"
+#include "ck_tile/host/stream_config.hpp"

include/ck_tile/host/arg_parser.hpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
+
+#pragma once
+
+#include <string>
+
+#include <iomanip>
+#include <iostream>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string>
+#include <unordered_map>
+#include <vector>
+
+namespace ck_tile {
+/*
+ * a host side utility, arg parser for
+ *  -[key0]=[value0] -[key1]=[value1] ...
+ */
+class ArgParser
+{
+    public:
+    class Arg
+    {
+        public:
+        std::string name;
+        std::string value;
+        std::string help_text;
+    };
+
+    ArgParser() {}
+    ArgParser& insert(const std::string& _name,
+                      const std::string& _default_value,
+                      const std::string& _help_text)
+    {
+        Arg in;
+        in.name      = _name;
+        in.value     = _default_value;
+        in.help_text = _help_text;
+
+        if(input_map.count(_name) != 0)
+        {
+            printf("arg:%s already exist\n", _name.c_str());
+        }
+        else
+        {
+            input_map[_name] = in;
+            keys.push_back(_name);
+        }
+        return *this;
+    }
+    void print()
+    {
+        printf("args:\n");
+        for(auto& key : keys)
+        {
+            auto value = input_map[key];
+            std::vector<std::string> help_text_lines;
+            size_t pos = 0;
+            for(size_t next_pos = value.help_text.find('\n', pos); next_pos != std::string::npos;)
+            {
+                help_text_lines.push_back(std::string(value.help_text.begin() + pos,
+                                                      value.help_text.begin() + next_pos++));
+                pos      = next_pos;
+                next_pos = value.help_text.find('\n', pos);
+            }
+            help_text_lines.push_back(
+                std::string(value.help_text.begin() + pos, value.help_text.end()));
+
+            std::string default_value = std::string("(default:") + value.value + std::string(")");
+
+            std::cout << std::setw(2) << std::setw(12 - value.name.length()) << "-" << key
+                      << std::setw(4) << " " << help_text_lines[0] << " " << default_value
+                      << std::endl;
+
+            for(auto help_next_line = std::next(help_text_lines.begin());
+                help_next_line != help_text_lines.end();
+                ++help_next_line)
+            {
+                std::cout << std::setw(17) << " " << *help_next_line << std::endl;
+            }
+        }
+    }
+    bool parse(int argc, char* argv[], int start_index = 1)
+    {
+        if(argc < start_index)
+        {
+            printf("not enough args\n");
+            return false;
+        }
+        for(int i = start_index; i < argc; i++)
+        {
+            char* cur_arg = argv[i];
+            if(cur_arg[0] != '-')
+            {
+                printf("illegal input\n");
+                print();
+                return false;
+            }
+            else
+            {
+                std::string text(cur_arg + 1);
+                if(text == "?")
+                {
+                    print();
+                    return false;
+                }
+                auto pos = text.find('=');
+                if(pos == std::string::npos)
+                {
+                    printf("arg should be [key]=[value] pair, here:%s\n", text.c_str());
+                    return false;
+                }
+                if(pos >= (text.size() - 1))
+                {
+                    printf("cant find value after \"=\", here:%s\n", text.c_str());
+                    return false;
+                }
+                auto key   = text.substr(0, pos);
+                auto value = text.substr(pos + 1);
+                if(input_map.count(key) == 0)
+                {
+                    printf("no such arg:%s\n", key.c_str());
+                    return false;
+                }
+                input_map[key].value = value;
+            }
+        }
+        return true;
+    }
+
+    std::string get_str(const std::string& name) const
+    {
+        std::string value = input_map.at(name).value;
+        return value;
+    }
+
+    int get_int(const std::string& name) const
+    {
+        int value = atoi(input_map.at(name).value.c_str());
+        return value;
+    }
+
+    uint32_t get_uint32(const std::string& name) const
+    {
+        uint32_t value = strtoul(input_map.at(name).value.c_str(), nullptr, 10);
+        return value;
+    }
+
+    uint64_t get_uint64(const std::string& name) const
+    {
+        uint64_t value = strtoull(input_map.at(name).value.c_str(), nullptr, 10);
+        return value;
+    }
+
+    bool get_bool(const std::string& name) const
+    {
+        auto v = input_map.at(name).value;
+        if(v.compare("t") == 0 || v.compare("true") == 0)
+            return true;
+        if(v.compare("f") == 0 || v.compare("false") == 0)
+            return false;
+        int value = atoi(v.c_str());
+        return value == 0 ? false : true;
+    }
+
+    float get_float(const std::string& name) const
+    {
+        double value = atof(input_map.at(name).value.c_str());
+        return static_cast<float>(value);
+    }
+
+    double get_double(const std::string& name) const
+    {
+        double value = atof(input_map.at(name).value.c_str());
+        return value;
+    }
+
+    private:
+    std::unordered_map<std::string, Arg> input_map;
+    std::vector<std::string> keys;
+};
+} // namespace ck_tile

include/ck_tile/host/check_err.hpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
+
+#pragma once
+
+#include <algorithm>
+#include <cmath>
+#include <cstdlib>
+#include <iostream>
+#include <iomanip>
+#include <iterator>
+#include <limits>
+#include <type_traits>
+#include <vector>
+
+#include "ck_tile/core.hpp"
+#include "ck_tile/host/ranges.hpp"
+
+namespace ck_tile {
+
+template <typename T>
+std::ostream& operator<<(std::ostream& os, const std::vector<T>& v)
+{
+    using size_type = typename std::vector<T>::size_type;
+
+    os << "[";
+    for(size_type idx = 0; idx < v.size(); ++idx)
+    {
+        if(0 < idx)
+        {
+            os << ", ";
+        }
+        os << v[idx];
+    }
+    return os << "]";
+}
+
+template <typename Range, typename RefRange>
+typename std::enable_if<
+    std::is_same_v<ranges::range_value_t<Range>, ranges::range_value_t<RefRange>> &&
+        std::is_floating_point_v<ranges::range_value_t<Range>> &&
+        !std::is_same_v<ranges::range_value_t<Range>, half_t>,
+    bool>::type CK_TILE_HOST
+check_err(const Range& out,
+          const RefRange& ref,
+          const std::string& msg  = "Error: Incorrect results!",
+          double rtol             = 1e-5,
+          double atol             = 3e-6,
+          bool allow_infinity_ref = false)
+{
+    if(out.size() != ref.size())
+    {
+        std::cerr << msg << " out.size() != ref.size(), :" << out.size() << " != " << ref.size()
+                  << std::endl;
+        return false;
+    }
+
+    const auto is_infinity_error = [=](auto o, auto r) {
+        const bool either_not_finite      = !std::isfinite(o) || !std::isfinite(r);
+        const bool both_infinite_and_same = std::isinf(o) && std::isinf(r) && (o == r);
+
+        return either_not_finite && !(allow_infinity_ref && both_infinite_and_same);
+    };
+
+    bool res{true};
+    int err_count  = 0;
+    double err     = 0;
+    double max_err = std::numeric_limits<double>::min();
+    for(std::size_t i = 0; i < ref.size(); ++i)
+    {
+        const double o = *std::next(std::begin(out), i);
+        const double r = *std::next(std::begin(ref), i);
+        err            = std::abs(o - r);
+        if(err > atol + rtol * std::abs(r) || is_infinity_error(o, r))
+        {
+            max_err = err > max_err ? err : max_err;
+            err_count++;
+            if(err_count < 5)
+            {
+                std::cerr << msg << std::setw(12) << std::setprecision(7) << " out[" << i
+                          << "] != ref[" << i << "]: " << o << " != " << r << std::endl;
+            }
+            res = false;
+        }
+    }
+    if(!res)
+    {
+        const float error_percent =
+            static_cast<float>(err_count) / static_cast<float>(out.size()) * 100.f;
+        std::cerr << "max err: " << max_err;
+        std::cerr << ", number of errors: " << err_count;
+        std::cerr << ", " << error_percent << "% wrong values" << std::endl;
+    }
+    return res;
+}
+
+template <typename Range, typename RefRange>
+typename std::enable_if<
+    std::is_same_v<ranges::range_value_t<Range>, ranges::range_value_t<RefRange>> &&
+        std::is_same_v<ranges::range_value_t<Range>, bf16_t>,
+    bool>::type CK_TILE_HOST
+check_err(const Range& out,
+          const RefRange& ref,
+          const std::string& msg  = "Error: Incorrect results!",
+          double rtol             = 1e-3,
+          double atol             = 1e-3,
+          bool allow_infinity_ref = false)
+{
+    if(out.size() != ref.size())
+    {
+        std::cerr << msg << " out.size() != ref.size(), :" << out.size() << " != " << ref.size()
+                  << std::endl;
+        return false;
+    }
+
+    const auto is_infinity_error = [=](auto o, auto r) {
+        const bool either_not_finite      = !std::isfinite(o) || !std::isfinite(r);
+        const bool both_infinite_and_same = std::isinf(o) && std::isinf(r) && (o == r);
+
+        return either_not_finite && !(allow_infinity_ref && both_infinite_and_same);
+    };
+
+    bool res{true};
+    int err_count = 0;
+    double err    = 0;
+    // TODO: This is a hack. We should have proper specialization for bf16_t data type.
+    double max_err = std::numeric_limits<float>::min();
+    for(std::size_t i = 0; i < ref.size(); ++i)
+    {
+        const double o = type_convert<float>(*std::next(std::begin(out), i));
+        const double r = type_convert<float>(*std::next(std::begin(ref), i));
+        err            = std::abs(o - r);
+        if(err > atol + rtol * std::abs(r) || is_infinity_error(o, r))
+        {
+            max_err = err > max_err ? err : max_err;
+            err_count++;
+            if(err_count < 5)
+            {
+                std::cerr << msg << std::setw(12) << std::setprecision(7) << " out[" << i
+                          << "] != ref[" << i << "]: " << o << " != " << r << std::endl;
+            }
+            res = false;
+        }
+    }
+    if(!res)
+    {
+        const float error_percent =
+            static_cast<float>(err_count) / static_cast<float>(out.size()) * 100.f;
+        std::cerr << "max err: " << max_err;
+        std::cerr << ", number of errors: " << err_count;
+        std::cerr << ", " << error_percent << "% wrong values" << std::endl;
+    }
+    return res;
+}
+
+template <typename Range, typename RefRange>
+typename std::enable_if<
+    std::is_same_v<ranges::range_value_t<Range>, ranges::range_value_t<RefRange>> &&
+        std::is_same_v<ranges::range_value_t<Range>, half_t>,
+    bool>::type CK_TILE_HOST
+check_err(const Range& out,
+          const RefRange& ref,
+          const std::string& msg  = "Error: Incorrect results!",
+          double rtol             = 1e-3,
+          double atol             = 1e-3,
+          bool allow_infinity_ref = false)
+{
+    if(out.size() != ref.size())
+    {
+        std::cerr << msg << " out.size() != ref.size(), :" << out.size() << " != " << ref.size()
+                  << std::endl;
+        return false;
+    }
+
+    const auto is_infinity_error = [=](auto o, auto r) {
+        const bool either_not_finite      = !std::isfinite(o) || !std::isfinite(r);
+        const bool both_infinite_and_same = std::isinf(o) && std::isinf(r) && (o == r);
+
+        return either_not_finite && !(allow_infinity_ref && both_infinite_and_same);
+    };
+
+    bool res{true};
+    int err_count  = 0;
+    double err     = 0;
+    double max_err = static_cast<double>(std::numeric_limits<ranges::range_value_t<Range>>::min());
+    for(std::size_t i = 0; i < ref.size(); ++i)
+    {
+        const double o = type_convert<float>(*std::next(std::begin(out), i));
+        const double r = type_convert<float>(*std::next(std::begin(ref), i));
+        err            = std::abs(o - r);
+        if(err > atol + rtol * std::abs(r) || is_infinity_error(o, r))
+        {
+            max_err = err > max_err ? err : max_err;
+            err_count++;
+            if(err_count < 5)
+            {
+                std::cerr << msg << std::setw(12) << std::setprecision(7) << " out[" << i
+                          << "] != ref[" << i << "]: " << o << " != " << r << std::endl;
+            }
+            res = false;
+        }
+    }
+    if(!res)
+    {
+        const float error_percent =
+            static_cast<float>(err_count) / static_cast<float>(out.size()) * 100.f;
+        std::cerr << "max err: " << max_err;
+        std::cerr << ", number of errors: " << err_count;
+        std::cerr << ", " << error_percent << "% wrong values" << std::endl;
+    }
+    return res;
+}
+
+template <typename Range, typename RefRange>
+std::enable_if_t<(std::is_same_v<ranges::range_value_t<Range>, ranges::range_value_t<RefRange>> &&
+                  std::is_integral_v<ranges::range_value_t<Range>> &&
+                  !std::is_same_v<ranges::range_value_t<Range>, bf16_t>)
+#ifdef CK_EXPERIMENTAL_BIT_INT_EXTENSION_INT4
+                     || std::is_same_v<ranges::range_value_t<Range>, int4_t>
+#endif
+                 ,
+                 bool>
+    CK_TILE_HOST check_err(const Range& out,
+                           const RefRange& ref,
+                           const std::string& msg = "Error: Incorrect results!",
+                           double                 = 0,
+                           double atol            = 0)
+{
+    if(out.size() != ref.size())
+    {
+        std::cerr << msg << " out.size() != ref.size(), :" << out.size() << " != " << ref.size()
+                  << std::endl;
+        return false;
+    }
+
+    bool res{true};
+    int err_count   = 0;
+    int64_t err     = 0;
+    int64_t max_err = std::numeric_limits<int64_t>::min();
+    for(std::size_t i = 0; i < ref.size(); ++i)
+    {
+        const int64_t o = *std::next(std::begin(out), i);
+        const int64_t r = *std::next(std::begin(ref), i);
+        err             = std::abs(o - r);
+
+        if(err > atol)
+        {
+            max_err = err > max_err ? err : max_err;
+            err_count++;
+            if(err_count < 5)
+            {
+                std::cerr << msg << " out[" << i << "] != ref[" << i << "]: " << o << " != " << r
+                          << std::endl;
+            }
+            res = false;
+        }
+    }
+    if(!res)
+    {
+        const float error_percent =
+            static_cast<float>(err_count) / static_cast<float>(out.size()) * 100.f;
+        std::cerr << "max err: " << max_err;
+        std::cerr << ", number of errors: " << err_count;
+        std::cerr << ", " << error_percent << "% wrong values" << std::endl;
+    }
+    return res;
+}
+
+template <typename Range, typename RefRange>
+std::enable_if_t<(std::is_same_v<ranges::range_value_t<Range>, ranges::range_value_t<RefRange>> &&
+                  std::is_same_v<ranges::range_value_t<Range>, fp8_t>),
+                 bool>
+    CK_TILE_HOST check_err(const Range& out,
+                           const RefRange& ref,
+                           const std::string& msg               = "Error: Incorrect results!",
+                           unsigned max_rounding_point_distance = 1,
+                           double atol                          = 1e-1,
+                           bool allow_infinity_ref              = false)
+{
+    if(out.size() != ref.size())
+    {
+        std::cerr << msg << " out.size() != ref.size(), :" << out.size() << " != " << ref.size()
+                  << std::endl;
+        return false;
+    }
+
+    const auto is_infinity_error = [=](auto o, auto r) {
+        const bool either_not_finite      = !std::isfinite(o) || !std::isfinite(r);
+        const bool both_infinite_and_same = std::isinf(o) && std::isinf(r) && (o == r);
+
+        return either_not_finite && !(allow_infinity_ref && both_infinite_and_same);
+    };
+
+    static const auto get_rounding_point_distance = [](fp8_t o, fp8_t r) -> unsigned {
+        static const auto get_sign_bit = [](fp8_t v) -> bool {
+            return 0x80 & bit_cast<uint8_t>(v);
+        };
+
+        if(get_sign_bit(o) ^ get_sign_bit(r))
+        {
+            return std::numeric_limits<unsigned>::max();
+        }
+        else
+        {
+            return std::abs(bit_cast<int8_t>(o) - bit_cast<int8_t>(r));
+        }
+    };
+
+    bool res{true};
+    int err_count  = 0;
+    double err     = 0;
+    double max_err = std::numeric_limits<float>::min();
+    for(std::size_t i = 0; i < ref.size(); ++i)
+    {
+        const fp8_t o_fp8   = *std::next(std::begin(out), i);
+        const fp8_t r_fp8   = *std::next(std::begin(ref), i);
+        const double o_fp64 = type_convert<float>(o_fp8);
+        const double r_fp64 = type_convert<float>(r_fp8);
+        err                 = std::abs(o_fp64 - r_fp64);
+        if(!(less_equal<double>{}(err, atol) ||
+             get_rounding_point_distance(o_fp8, r_fp8) <= max_rounding_point_distance) ||
+           is_infinity_error(o_fp64, r_fp64))
+        {
+            max_err = err > max_err ? err : max_err;
+            err_count++;
+            if(err_count < 5)
+            {
+                std::cerr << msg << std::setw(12) << std::setprecision(7) << " out[" << i
+                          << "] != ref[" << i << "]: " << o_fp64 << " != " << r_fp64 << std::endl;
+            }
+            res = false;
+        }
+    }
+    if(!res)
+    {
+        std::cerr << std::setw(12) << std::setprecision(7) << "max err: " << max_err << std::endl;
+    }
+    return res;
+}
+
+template <typename Range, typename RefRange>
+std::enable_if_t<(std::is_same_v<ranges::range_value_t<Range>, ranges::range_value_t<RefRange>> &&
+                  std::is_same_v<ranges::range_value_t<Range>, bf8_t>),
+                 bool>
+    CK_TILE_HOST check_err(const Range& out,
+                           const RefRange& ref,
+                           const std::string& msg  = "Error: Incorrect results!",
+                           double rtol             = 1e-3,
+                           double atol             = 1e-3,
+                           bool allow_infinity_ref = false)
+{
+    if(out.size() != ref.size())
+    {
+        std::cerr << msg << " out.size() != ref.size(), :" << out.size() << " != " << ref.size()
+                  << std::endl;
+        return false;
+    }
+
+    const auto is_infinity_error = [=](auto o, auto r) {
+        const bool either_not_finite      = !std::isfinite(o) || !std::isfinite(r);
+        const bool both_infinite_and_same = std::isinf(o) && std::isinf(r) && (o == r);
+
+        return either_not_finite && !(allow_infinity_ref && both_infinite_and_same);
+    };
+
+    bool res{true};
+    int err_count  = 0;
+    double err     = 0;
+    double max_err = std::numeric_limits<float>::min();
+    for(std::size_t i = 0; i < ref.size(); ++i)
+    {
+        const double o = type_convert<float>(*std::next(std::begin(out), i));
+        const double r = type_convert<float>(*std::next(std::begin(ref), i));
+        err            = std::abs(o - r);
+        if(err > atol + rtol * std::abs(r) || is_infinity_error(o, r))
+        {
+            max_err = err > max_err ? err : max_err;
+            err_count++;
+            if(err_count < 5)
+            {
+                std::cerr << msg << std::setw(12) << std::setprecision(7) << " out[" << i
+                          << "] != ref[" << i << "]: " << o << " != " << r << std::endl;
+            }
+            res = false;
+        }
+    }
+    if(!res)
+    {
+        std::cerr << std::setw(12) << std::setprecision(7) << "max err: " << max_err << std::endl;
+    }
+    return res;
+}
+
+} // namespace ck_tile

include/ck_tile/host/device_memory.hpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
+
+#pragma once
+
+#include <hip/hip_runtime.h>
+#include <stdint.h>
+#include <stdexcept>
+#include "ck_tile/host/hip_check_error.hpp"
+
+namespace ck_tile {
+template <typename T>
+__global__ void set_buffer_value(T* p, T x, uint64_t buffer_element_size)
+{
+    for(uint64_t i = threadIdx.x; i < buffer_element_size; i += blockDim.x)
+    {
+        p[i] = x;
+    }
+}
+
+/**
+ * @brief Container for storing data in GPU device memory
+ *
+ */
+struct DeviceMem
+{
+    DeviceMem() : mpDeviceBuf(nullptr), mMemSize(0) {}
+    DeviceMem(std::size_t mem_size) : mMemSize(mem_size)
+    {
+        HIP_CHECK_ERROR(hipMalloc(static_cast<void**>(&mpDeviceBuf), mMemSize));
+    }
+    void Realloc(std::size_t mem_size)
+    {
+        if(mpDeviceBuf)
+        {
+            HIP_CHECK_ERROR(hipFree(mpDeviceBuf));
+        }
+        mMemSize = mem_size;
+        HIP_CHECK_ERROR(hipMalloc(static_cast<void**>(&mpDeviceBuf), mMemSize));
+    }
+    void* GetDeviceBuffer() const { return mpDeviceBuf; }
+    std::size_t GetBufferSize() const { return mMemSize; }
+    void ToDevice(const void* p) const
+    {
+        if(mpDeviceBuf)
+        {
+            HIP_CHECK_ERROR(
+                hipMemcpy(mpDeviceBuf, const_cast<void*>(p), mMemSize, hipMemcpyHostToDevice));
+        }
+        else
+        {
+            throw std::runtime_error("ToDevice with an empty pointer");
+        }
+    }
+    void ToDevice(const void* p, const std::size_t cpySize) const
+    {
+        HIP_CHECK_ERROR(
+            hipMemcpy(mpDeviceBuf, const_cast<void*>(p), cpySize, hipMemcpyHostToDevice));
+    }
+    void FromDevice(void* p) const
+    {
+        if(mpDeviceBuf)
+        {
+            HIP_CHECK_ERROR(hipMemcpy(p, mpDeviceBuf, mMemSize, hipMemcpyDeviceToHost));
+        }
+        else
+        {
+            throw std::runtime_error("FromDevice with an empty pointer");
+        }
+    }
+    void FromDevice(void* p, const std::size_t cpySize) const
+    {
+        HIP_CHECK_ERROR(hipMemcpy(p, mpDeviceBuf, cpySize, hipMemcpyDeviceToHost));
+    }
+    void SetZero() const
+    {
+        if(mpDeviceBuf)
+        {
+            HIP_CHECK_ERROR(hipMemset(mpDeviceBuf, 0, mMemSize));
+        }
+    }
+    template <typename T>
+    void SetValue(T x) const
+    {
+        if(mMemSize % sizeof(T) != 0)
+        {
+            throw std::runtime_error("wrong! not entire DeviceMem will be set");
+        }
+
+        // TODO: call a gpu kernel to set the value (?)
+        set_buffer_value<T><<<1, 1024>>>(static_cast<T*>(mpDeviceBuf), x, mMemSize / sizeof(T));
+    }
+    ~DeviceMem()
+    {
+        if(mpDeviceBuf)
+        {
+            try
+            {
+                HIP_CHECK_ERROR(hipFree(mpDeviceBuf));
+            }
+            catch(std::runtime_error& re)
+            {
+                std::cerr << re.what() << std::endl;
+            }
+        }
+    }
+
+    void* mpDeviceBuf;
+    std::size_t mMemSize;
+};
+
+} // namespace ck_tile

include/ck_tile/host/fill.hpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
+
+#pragma once
+
+#include <algorithm>
+#include <cmath>
+#include <iterator>
+#include <optional>
+#include <random>
+#include <type_traits>
+#include <utility>
+
+#include "ck_tile/core.hpp"
+
+namespace ck_tile {
+
+template <typename T>
+struct FillUniformDistribution
+{
+    float a_{-5.f};
+    float b_{5.f};
+    std::optional<uint32_t> seed_{11939};
+
+    template <typename ForwardIter>
+    void operator()(ForwardIter first, ForwardIter last) const
+    {
+        std::mt19937 gen(seed_.has_value() ? *seed_ : std::random_device{}());
+        std::uniform_real_distribution<float> dis(a_, b_);
+        std::generate(first, last, [&dis, &gen]() { return ck_tile::type_convert<T>(dis(gen)); });
+    }
+
+    template <typename ForwardRange>
+    auto operator()(ForwardRange&& range) const
+        -> std::void_t<decltype(std::declval<const FillUniformDistribution&>()(
+            std::begin(std::forward<ForwardRange>(range)),
+            std::end(std::forward<ForwardRange>(range))))>
+    {
+        (*this)(std::begin(std::forward<ForwardRange>(range)),
+                std::end(std::forward<ForwardRange>(range)));
+    }
+};
+
+template <typename T>
+struct FillNormalDistribution
+{
+    float mean_{0.f};
+    float variance_{1.f};
+    std::optional<uint32_t> seed_{11939};
+
+    template <typename ForwardIter>
+    void operator()(ForwardIter first, ForwardIter last) const
+    {
+        std::mt19937 gen(seed_.has_value() ? *seed_ : std::random_device{}());
+        std::normal_distribution<float> dis(mean_, std::sqrt(variance_));
+        std::generate(first, last, [&dis, &gen]() { return ck_tile::type_convert<T>(dis(gen)); });
+    }
+
+    template <typename ForwardRange>
+    auto operator()(ForwardRange&& range) const
+        -> std::void_t<decltype(std::declval<const FillNormalDistribution&>()(
+            std::begin(std::forward<ForwardRange>(range)),
+            std::end(std::forward<ForwardRange>(range))))>
+    {
+        (*this)(std::begin(std::forward<ForwardRange>(range)),
+                std::end(std::forward<ForwardRange>(range)));
+    }
+};
+
+// Normally FillUniformDistributionIntegerValue should use std::uniform_int_distribution as below.
+// However this produces segfaults in std::mt19937 which look like inifite loop.
+//      template <typename T>
+//      struct FillUniformDistributionIntegerValue
+//      {
+//          int a_{-5};
+//          int b_{5};
+//
+//          template <typename ForwardIter>
+//          void operator()(ForwardIter first, ForwardIter last) const
+//          {
+//              std::mt19937 gen(11939);
+//              std::uniform_int_distribution<int> dis(a_, b_);
+//              std::generate(
+//                  first, last, [&dis, &gen]() { return ck_tile::type_convert<T>(dis(gen)); });
+//          }
+//      };
+
+// Workaround for uniform_int_distribution not working as expected. See note above.<
+template <typename T>
+struct FillUniformDistributionIntegerValue
+{
+    float a_{-5.f};
+    float b_{5.f};
+    std::optional<uint32_t> seed_{11939};
+
+    template <typename ForwardIter>
+    void operator()(ForwardIter first, ForwardIter last) const
+    {
+        std::mt19937 gen(seed_.has_value() ? *seed_ : std::random_device{}());
+        std::uniform_real_distribution<float> dis(a_, b_);
+        std::generate(
+            first, last, [&dis, &gen]() { return ck_tile::type_convert<T>(std::round(dis(gen))); });
+    }
+
+    template <typename ForwardRange>
+    auto operator()(ForwardRange&& range) const
+        -> std::void_t<decltype(std::declval<const FillUniformDistributionIntegerValue&>()(
+            std::begin(std::forward<ForwardRange>(range)),
+            std::end(std::forward<ForwardRange>(range))))>
+    {
+        (*this)(std::begin(std::forward<ForwardRange>(range)),
+                std::end(std::forward<ForwardRange>(range)));
+    }
+};
+
+template <typename T>
+struct FillNormalDistributionIntegerValue
+{
+    float mean_{0.f};
+    float variance_{1.f};
+    std::optional<uint32_t> seed_{11939};
+
+    template <typename ForwardIter>
+    void operator()(ForwardIter first, ForwardIter last) const
+    {
+        std::mt19937 gen(seed_.has_value() ? *seed_ : std::random_device{}());
+        std::normal_distribution<float> dis(mean_, std::sqrt(variance_));
+        std::generate(
+            first, last, [&dis, &gen]() { return ck_tile::type_convert<T>(std::round(dis(gen))); });
+    }
+
+    template <typename ForwardRange>
+    auto operator()(ForwardRange&& range) const
+        -> std::void_t<decltype(std::declval<const FillNormalDistributionIntegerValue&>()(
+            std::begin(std::forward<ForwardRange>(range)),
+            std::end(std::forward<ForwardRange>(range))))>
+    {
+        (*this)(std::begin(std::forward<ForwardRange>(range)),
+                std::end(std::forward<ForwardRange>(range)));
+    }
+};
+
+template <typename T>
+struct FillMonotonicSeq
+{
+    T init_value_{0};
+    T step_{1};
+
+    template <typename ForwardIter>
+    void operator()(ForwardIter first, ForwardIter last) const
+    {
+        std::generate(first, last, [=, n = init_value_]() mutable {
+            auto tmp = n;
+            n += step_;
+            return tmp;
+        });
+    }
+
+    template <typename ForwardRange>
+    auto operator()(ForwardRange&& range) const
+        -> std::void_t<decltype(std::declval<const FillMonotonicSeq&>()(
+            std::begin(std::forward<ForwardRange>(range)),
+            std::end(std::forward<ForwardRange>(range))))>
+    {
+        (*this)(std::begin(std::forward<ForwardRange>(range)),
+                std::end(std::forward<ForwardRange>(range)));
+    }
+};
+
+template <typename T>
+struct FillConstant
+{
+    T value_{0};
+
+    template <typename ForwardIter>
+    void operator()(ForwardIter first, ForwardIter last) const
+    {
+        std::fill(first, last, value_);
+    }
+
+    template <typename ForwardRange>
+    auto operator()(ForwardRange&& range) const -> std::void_t<
+        decltype(std::declval<const FillConstant&>()(std::begin(std::forward<ForwardRange>(range)),
+                                                     std::end(std::forward<ForwardRange>(range))))>
+    {
+        (*this)(std::begin(std::forward<ForwardRange>(range)),
+                std::end(std::forward<ForwardRange>(range)));
+    }
+};
+
+template <typename T, bool UseCos = true, bool UseAbs = false>
+struct FillTrigValue
+{
+    template <typename T_, bool UseCos_ = true, bool UseAbs_ = false>
+    struct LinearTrigGen
+    {
+        int i{0};
+        auto operator()()
+        {
+            float v = 0;
+            if constexpr(UseCos_)
+            {
+                v = cos(i);
+            }
+            else
+            {
+                v = sin(i);
+            }
+            if constexpr(UseAbs_)
+                v = abs(v);
+            i++;
+            return ck_tile::type_convert<T_>(v);
+        }
+    };
+    template <typename ForwardIter>
+    void operator()(ForwardIter first, ForwardIter last) const
+    {
+        LinearTrigGen<T, UseCos, UseAbs> gen;
+        std::generate(first, last, gen);
+    }
+
+    template <typename ForwardRange>
+    auto operator()(ForwardRange&& range) const -> std::void_t<
+        decltype(std::declval<const FillTrigValue&>()(std::begin(std::forward<ForwardRange>(range)),
+                                                      std::end(std::forward<ForwardRange>(range))))>
+    {
+        (*this)(std::begin(std::forward<ForwardRange>(range)),
+                std::end(std::forward<ForwardRange>(range)));
+    }
+};
+
+} // namespace ck_tile

include/ck_tile/host/hip_check_error.hpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
+
+#pragma once
+
+#include "ck_tile/core/config.hpp"
+#include <sstream>
+#include <stdexcept>
+#include <hip/hip_runtime.h>
+
+namespace ck_tile {
+// To be removed, which really does not tell the location of failed HIP functional call
+CK_TILE_HOST void hip_check_error(hipError_t x)
+{
+    if(x != hipSuccess)
+    {
+        std::ostringstream ss;
+        ss << "HIP runtime error: " << hipGetErrorString(x) << ". " << __FILE__ << ": " << __LINE__
+           << "in function: " << __func__;
+        throw std::runtime_error(ss.str());
+    }
+}
+} // namespace ck_tile
+
+#define HIP_CHECK_ERROR(retval_or_funcall)                                         \
+    do                                                                             \
+    {                                                                              \
+        hipError_t _tmpVal = retval_or_funcall;                                    \
+        if(_tmpVal != hipSuccess)                                                  \
+        {                                                                          \
+            std::ostringstream ostr;                                               \
+            ostr << "HIP Function Failed (" << __FILE__ << "," << __LINE__ << ") " \
+                 << hipGetErrorString(_tmpVal);                                    \
+            throw std::runtime_error(ostr.str());                                  \
+        }                                                                          \
+    } while(0)

include/ck_tile/host/host_tensor.hpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
+
+#pragma once
+
+#include <algorithm>
+#include <cassert>
+#include <iostream>
+#include <iomanip>
+#include <numeric>
+#include <thread>
+#include <utility>
+#include <vector>
+
+#include "ck_tile/core.hpp"
+#include "ck_tile/host/ranges.hpp"
+
+namespace ck_tile {
+
+template <typename Range>
+CK_TILE_HOST std::ostream& LogRange(std::ostream& os,
+                                    Range&& range,
+                                    std::string delim,
+                                    int precision = std::cout.precision(),
+                                    int width     = 0)
+{
+    bool first = true;
+    for(auto&& v : range)
+    {
+        if(first)
+            first = false;
+        else
+            os << delim;
+        os << std::setw(width) << std::setprecision(precision) << v;
+    }
+    return os;
+}
+
+template <typename T, typename Range>
+CK_TILE_HOST std::ostream& LogRangeAsType(std::ostream& os,
+                                          Range&& range,
+                                          std::string delim,
+                                          int precision = std::cout.precision(),
+                                          int width     = 0)
+{
+    bool first = true;
+    for(auto&& v : range)
+    {
+        if(first)
+            first = false;
+        else
+            os << delim;
+        os << std::setw(width) << std::setprecision(precision) << static_cast<T>(v);
+    }
+    return os;
+}
+
+template <typename F, typename T, std::size_t... Is>
+CK_TILE_HOST auto call_f_unpack_args_impl(F f, T args, std::index_sequence<Is...>)
+{
+    return f(std::get<Is>(args)...);
+}
+
+template <typename F, typename T>
+CK_TILE_HOST auto call_f_unpack_args(F f, T args)
+{
+    constexpr std::size_t N = std::tuple_size<T>{};
+
+    return call_f_unpack_args_impl(f, args, std::make_index_sequence<N>{});
+}
+
+template <typename F, typename T, std::size_t... Is>
+CK_TILE_HOST auto construct_f_unpack_args_impl(T args, std::index_sequence<Is...>)
+{
+    return F(std::get<Is>(args)...);
+}
+
+template <typename F, typename T>
+CK_TILE_HOST auto construct_f_unpack_args(F, T args)
+{
+    constexpr std::size_t N = std::tuple_size<T>{};
+
+    return construct_f_unpack_args_impl<F>(args, std::make_index_sequence<N>{});
+}
+
+struct HostTensorDescriptor
+{
+    HostTensorDescriptor() = default;
+
+    void CalculateStrides()
+    {
+        mStrides.clear();
+        mStrides.resize(mLens.size(), 0);
+        if(mStrides.empty())
+            return;
+
+        mStrides.back() = 1;
+        std::partial_sum(mLens.rbegin(),
+                         mLens.rend() - 1,
+                         mStrides.rbegin() + 1,
+                         std::multiplies<std::size_t>());
+    }
+
+    template <typename X, typename = std::enable_if_t<std::is_convertible_v<X, std::size_t>>>
+    HostTensorDescriptor(const std::initializer_list<X>& lens) : mLens(lens.begin(), lens.end())
+    {
+        this->CalculateStrides();
+    }
+
+    template <typename Lengths,
+              typename = std::enable_if_t<
+                  std::is_convertible_v<ck_tile::ranges::range_value_t<Lengths>, std::size_t>>>
+    HostTensorDescriptor(const Lengths& lens) : mLens(lens.begin(), lens.end())
+    {
+        this->CalculateStrides();
+    }
+
+    template <typename X,
+              typename Y,
+              typename = std::enable_if_t<std::is_convertible_v<X, std::size_t> &&
+                                          std::is_convertible_v<Y, std::size_t>>>
+    HostTensorDescriptor(const std::initializer_list<X>& lens,
+                         const std::initializer_list<Y>& strides)
+        : mLens(lens.begin(), lens.end()), mStrides(strides.begin(), strides.end())
+    {
+    }
+
+    template <typename Lengths,
+              typename Strides,
+              typename = std::enable_if_t<
+                  std::is_convertible_v<ck_tile::ranges::range_value_t<Lengths>, std::size_t> &&
+                  std::is_convertible_v<ck_tile::ranges::range_value_t<Strides>, std::size_t>>>
+    HostTensorDescriptor(const Lengths& lens, const Strides& strides)
+        : mLens(lens.begin(), lens.end()), mStrides(strides.begin(), strides.end())
+    {
+    }
+
+    std::size_t get_num_of_dimension() const { return mLens.size(); }
+    std::size_t get_element_size() const
+    {
+        assert(mLens.size() == mStrides.size());
+        return std::accumulate(
+            mLens.begin(), mLens.end(), std::size_t{1}, std::multiplies<std::size_t>());
+    }
+    std::size_t get_element_space_size() const
+    {
+        std::size_t space = 1;
+        for(std::size_t i = 0; i < mLens.size(); ++i)
+        {
+            if(mLens[i] == 0)
+                continue;
+
+            space += (mLens[i] - 1) * mStrides[i];
+        }
+        return space;
+    }
+
+    const std::vector<std::size_t>& get_lengths() const { return mLens; }
+    const std::vector<std::size_t>& GetStrides() const { return mStrides; }
+
+    template <typename... Is>
+    std::size_t GetOffsetFromMultiIndex(Is... is) const
+    {
+        assert(sizeof...(Is) == this->get_num_of_dimension());
+        std::initializer_list<std::size_t> iss{static_cast<std::size_t>(is)...};
+        return std::inner_product(iss.begin(), iss.end(), mStrides.begin(), std::size_t{0});
+    }
+
+    std::size_t GetOffsetFromMultiIndex(std::vector<std::size_t> iss) const
+    {
+        return std::inner_product(iss.begin(), iss.end(), mStrides.begin(), std::size_t{0});
+    }
+
+    friend std::ostream& operator<<(std::ostream& os, const HostTensorDescriptor& desc);
+
+    private:
+    std::vector<std::size_t> mLens;
+    std::vector<std::size_t> mStrides;
+};
+
+template <typename New2Old>
+CK_TILE_HOST HostTensorDescriptor transpose_host_tensor_descriptor_given_new2old(
+    const HostTensorDescriptor& a, const New2Old& new2old)
+{
+    std::vector<std::size_t> new_lengths(a.get_num_of_dimension());
+    std::vector<std::size_t> new_strides(a.get_num_of_dimension());
+
+    for(std::size_t i = 0; i < a.get_num_of_dimension(); i++)
+    {
+        new_lengths[i] = a.get_lengths()[new2old[i]];
+        new_strides[i] = a.GetStrides()[new2old[i]];
+    }
+
+    return HostTensorDescriptor(new_lengths, new_strides);
+}
+
+struct joinable_thread : std::thread
+{
+    template <typename... Xs>
+    joinable_thread(Xs&&... xs) : std::thread(std::forward<Xs>(xs)...)
+    {
+    }
+
+    joinable_thread(joinable_thread&&) = default;
+    joinable_thread& operator=(joinable_thread&&) = default;
+
+    ~joinable_thread()
+    {
+        if(this->joinable())
+            this->join();
+    }
+};
+
+template <typename F, typename... Xs>
+struct ParallelTensorFunctor
+{
+    F mF;
+    static constexpr std::size_t NDIM = sizeof...(Xs);
+    std::array<std::size_t, NDIM> mLens;
+    std::array<std::size_t, NDIM> mStrides;
+    std::size_t mN1d;
+
+    ParallelTensorFunctor(F f, Xs... xs) : mF(f), mLens({static_cast<std::size_t>(xs)...})
+    {
+        mStrides.back() = 1;
+        std::partial_sum(mLens.rbegin(),
+                         mLens.rend() - 1,
+                         mStrides.rbegin() + 1,
+                         std::multiplies<std::size_t>());
+        mN1d = mStrides[0] * mLens[0];
+    }
+
+    std::array<std::size_t, NDIM> GetNdIndices(std::size_t i) const
+    {
+        std::array<std::size_t, NDIM> indices;
+
+        for(std::size_t idim = 0; idim < NDIM; ++idim)
+        {
+            indices[idim] = i / mStrides[idim];
+            i -= indices[idim] * mStrides[idim];
+        }
+
+        return indices;
+    }
+
+    void operator()(std::size_t num_thread = 1) const
+    {
+        std::size_t work_per_thread = (mN1d + num_thread - 1) / num_thread;
+
+        std::vector<joinable_thread> threads(num_thread);
+
+        for(std::size_t it = 0; it < num_thread; ++it)
+        {
+            std::size_t iw_begin = it * work_per_thread;
+            std::size_t iw_end   = std::min((it + 1) * work_per_thread, mN1d);
+
+            auto f = [this, iw_begin, iw_end] {
+                for(std::size_t iw = iw_begin; iw < iw_end; ++iw)
+                {
+                    call_f_unpack_args(this->mF, this->GetNdIndices(iw));
+                }
+            };
+            threads[it] = joinable_thread(f);
+        }
+    }
+};
+
+template <typename F, typename... Xs>
+CK_TILE_HOST auto make_ParallelTensorFunctor(F f, Xs... xs)
+{
+    return ParallelTensorFunctor<F, Xs...>(f, xs...);
+}
+
+template <typename T>
+struct HostTensor
+{
+    using Descriptor = HostTensorDescriptor;
+    using Data       = std::vector<T>;
+
+    template <typename X>
+    HostTensor(std::initializer_list<X> lens) : mDesc(lens), mData(mDesc.get_element_space_size())
+    {
+    }
+
+    template <typename X, typename Y>
+    HostTensor(std::initializer_list<X> lens, std::initializer_list<Y> strides)
+        : mDesc(lens, strides), mData(mDesc.get_element_space_size())
+    {
+    }
+
+    template <typename Lengths>
+    HostTensor(const Lengths& lens) : mDesc(lens), mData(mDesc.get_element_space_size())
+    {
+    }
+
+    template <typename Lengths, typename Strides>
+    HostTensor(const Lengths& lens, const Strides& strides)
+        : mDesc(lens, strides), mData(get_element_space_size())
+    {
+    }
+
+    HostTensor(const Descriptor& desc) : mDesc(desc), mData(mDesc.get_element_space_size()) {}
+
+    template <typename OutT>
+    HostTensor<OutT> CopyAsType() const
+    {
+        HostTensor<OutT> ret(mDesc);
+        std::transform(mData.cbegin(), mData.cend(), ret.mData.begin(), [](auto value) {
+            return ck_tile::type_convert<OutT>(value);
+        });
+        return ret;
+    }
+
+    HostTensor()                  = delete;
+    HostTensor(const HostTensor&) = default;
+    HostTensor(HostTensor&&)      = default;
+
+    ~HostTensor() = default;
+
+    HostTensor& operator=(const HostTensor&) = default;
+    HostTensor& operator=(HostTensor&&) = default;
+
+    template <typename FromT>
+    explicit HostTensor(const HostTensor<FromT>& other) : HostTensor(other.template CopyAsType<T>())
+    {
+    }
+
+    decltype(auto) get_lengths() const { return mDesc.get_lengths(); }
+
+    decltype(auto) GetStrides() const { return mDesc.GetStrides(); }
+
+    std::size_t get_num_of_dimension() const { return mDesc.get_num_of_dimension(); }
+
+    std::size_t get_element_size() const { return mDesc.get_element_size(); }
+
+    std::size_t get_element_space_size() const { return mDesc.get_element_space_size(); }
+
+    std::size_t get_element_space_size_in_bytes() const
+    {
+        return sizeof(T) * get_element_space_size();
+    }
+
+    // void SetZero() { ck_tile::ranges::fill<T>(mData, 0); }
+    void SetZero() { std::fill(mData.begin(), mData.end(), 0); }
+
+    template <typename F>
+    void ForEach_impl(F&& f, std::vector<size_t>& idx, size_t rank)
+    {
+        if(rank == mDesc.get_num_of_dimension())
+        {
+            f(*this, idx);
+            return;
+        }
+        // else
+        for(size_t i = 0; i < mDesc.get_lengths()[rank]; i++)
+        {
+            idx[rank] = i;
+            ForEach_impl(std::forward<F>(f), idx, rank + 1);
+        }
+    }
+
+    template <typename F>
+    void ForEach(F&& f)
+    {
+        std::vector<size_t> idx(mDesc.get_num_of_dimension(), 0);
+        ForEach_impl(std::forward<F>(f), idx, size_t(0));
+    }
+
+    template <typename F>
+    void ForEach_impl(const F&& f, std::vector<size_t>& idx, size_t rank) const
+    {
+        if(rank == mDesc.get_num_of_dimension())
+        {
+            f(*this, idx);
+            return;
+        }
+        // else
+        for(size_t i = 0; i < mDesc.get_lengths()[rank]; i++)
+        {
+            idx[rank] = i;
+            ForEach_impl(std::forward<const F>(f), idx, rank + 1);
+        }
+    }
+
+    template <typename F>
+    void ForEach(const F&& f) const
+    {
+        std::vector<size_t> idx(mDesc.get_num_of_dimension(), 0);
+        ForEach_impl(std::forward<const F>(f), idx, size_t(0));
+    }
+
+    template <typename G>
+    void GenerateTensorValue(G g, std::size_t num_thread = 1)
+    {
+        switch(mDesc.get_num_of_dimension())
+        {
+        case 1: {
+            auto f = [&](auto i) { (*this)(i) = g(i); };
+            make_ParallelTensorFunctor(f, mDesc.get_lengths()[0])(num_thread);
+            break;
+        }
+        case 2: {
+            auto f = [&](auto i0, auto i1) { (*this)(i0, i1) = g(i0, i1); };
+            make_ParallelTensorFunctor(f, mDesc.get_lengths()[0], mDesc.get_lengths()[1])(
+                num_thread);
+            break;
+        }
+        case 3: {
+            auto f = [&](auto i0, auto i1, auto i2) { (*this)(i0, i1, i2) = g(i0, i1, i2); };
+            make_ParallelTensorFunctor(f,
+                                       mDesc.get_lengths()[0],
+                                       mDesc.get_lengths()[1],
+                                       mDesc.get_lengths()[2])(num_thread);
+            break;
+        }
+        case 4: {
+            auto f = [&](auto i0, auto i1, auto i2, auto i3) {
+                (*this)(i0, i1, i2, i3) = g(i0, i1, i2, i3);
+            };
+            make_ParallelTensorFunctor(f,
+                                       mDesc.get_lengths()[0],
+                                       mDesc.get_lengths()[1],
+                                       mDesc.get_lengths()[2],
+                                       mDesc.get_lengths()[3])(num_thread);
+            break;
+        }
+        case 5: {
+            auto f = [&](auto i0, auto i1, auto i2, auto i3, auto i4) {
+                (*this)(i0, i1, i2, i3, i4) = g(i0, i1, i2, i3, i4);
+            };
+            make_ParallelTensorFunctor(f,
+                                       mDesc.get_lengths()[0],
+                                       mDesc.get_lengths()[1],
+                                       mDesc.get_lengths()[2],
+                                       mDesc.get_lengths()[3],
+                                       mDesc.get_lengths()[4])(num_thread);
+            break;
+        }
+        case 6: {
+            auto f = [&](auto i0, auto i1, auto i2, auto i3, auto i4, auto i5) {
+                (*this)(i0, i1, i2, i3, i4, i5) = g(i0, i1, i2, i3, i4, i5);
+            };
+            make_ParallelTensorFunctor(f,
+                                       mDesc.get_lengths()[0],
+                                       mDesc.get_lengths()[1],
+                                       mDesc.get_lengths()[2],
+                                       mDesc.get_lengths()[3],
+                                       mDesc.get_lengths()[4],
+                                       mDesc.get_lengths()[5])(num_thread);
+            break;
+        }
+        default: throw std::runtime_error("unspported dimension");
+        }
+    }
+
+    template <typename... Is>
+    std::size_t GetOffsetFromMultiIndex(Is... is) const
+    {
+        return mDesc.GetOffsetFromMultiIndex(is...);
+    }
+
+    template <typename... Is>
+    T& operator()(Is... is)
+    {
+        return mData[mDesc.GetOffsetFromMultiIndex(is...)];
+    }
+
+    template <typename... Is>
+    const T& operator()(Is... is) const
+    {
+        return mData[mDesc.GetOffsetFromMultiIndex(is...)];
+    }
+
+    T& operator()(std::vector<std::size_t> idx)
+    {
+        return mData[mDesc.GetOffsetFromMultiIndex(idx)];
+    }
+
+    const T& operator()(std::vector<std::size_t> idx) const
+    {
+        return mData[mDesc.GetOffsetFromMultiIndex(idx)];
+    }
+
+    typename Data::iterator begin() { return mData.begin(); }
+
+    typename Data::iterator end() { return mData.end(); }
+
+    typename Data::pointer data() { return mData.data(); }
+
+    typename Data::const_iterator begin() const { return mData.begin(); }
+
+    typename Data::const_iterator end() const { return mData.end(); }
+
+    typename Data::const_pointer data() const { return mData.data(); }
+
+    typename Data::size_type size() const { return mData.size(); }
+
+    template <typename U = T>
+    auto AsSpan() const
+    {
+        constexpr std::size_t FromSize = sizeof(T);
+        constexpr std::size_t ToSize   = sizeof(U);
+
+        using Element = std::add_const_t<std::remove_reference_t<U>>;
+        return ck_tile::span<Element>{reinterpret_cast<Element*>(data()),
+                                      size() * FromSize / ToSize};
+    }
+
+    template <typename U = T>
+    auto AsSpan()
+    {
+        constexpr std::size_t FromSize = sizeof(T);
+        constexpr std::size_t ToSize   = sizeof(U);
+
+        using Element = std::remove_reference_t<U>;
+        return ck_tile::span<Element>{reinterpret_cast<Element*>(data()),
+                                      size() * FromSize / ToSize};
+    }
+
+    Descriptor mDesc;
+    Data mData;
+};
+} // namespace ck_tile

include/ck_tile/host/kernel_launch.hpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
+
+#pragma once
+
+#include "ck_tile/core/config.hpp"
+#include "ck_tile/host/stream_config.hpp"
+#include "ck_tile/host/hip_check_error.hpp"
+#include <hip/hip_runtime.h>
+#include <cstddef>
+
+namespace ck_tile {
+template <int MaxThreadPerBlock, int MinBlockPerCu, typename Kernel, typename... Args>
+#if CK_TILE_USE_LAUNCH_BOUNDS
+__launch_bounds__(MaxThreadPerBlock, MinBlockPerCu)
+#endif
+    __global__ void kentry(Kernel f, Args... args)
+{
+    f(args...);
+}
+
+template <typename... Args, typename F>
+CK_TILE_HOST float launch_and_time_kernel(const stream_config& s,
+                                          F kernel,
+                                          dim3 grid_dim,
+                                          dim3 block_dim,
+                                          std::size_t lds_byte,
+                                          Args... args)
+{
+#if CK_TILE_TIME_KERNEL
+    if(s.time_kernel_)
+    {
+        // warm up
+        for(int i = 0; i < s.cold_niters_; ++i)
+        {
+            kernel<<<grid_dim, block_dim, lds_byte, s.stream_id_>>>(args...);
+            hip_check_error(hipGetLastError());
+        }
+
+        const int nrepeat = s.nrepeat_;
+        hipEvent_t start, stop;
+
+        HIP_CHECK_ERROR(hipEventCreate(&start));
+        HIP_CHECK_ERROR(hipEventCreate(&stop));
+
+        HIP_CHECK_ERROR(hipDeviceSynchronize());
+        HIP_CHECK_ERROR(hipEventRecord(start, s.stream_id_));
+
+        for(int i = 0; i < nrepeat; ++i)
+        {
+            kernel<<<grid_dim, block_dim, lds_byte, s.stream_id_>>>(args...);
+            hip_check_error(hipGetLastError());
+        }
+
+        HIP_CHECK_ERROR(hipEventRecord(stop, s.stream_id_));
+        HIP_CHECK_ERROR(hipEventSynchronize(stop));
+
+        float total_time = 0;
+
+        HIP_CHECK_ERROR(hipEventElapsedTime(&total_time, start, stop));
+
+        return total_time / nrepeat;
+    }
+    else
+    {
+        kernel<<<grid_dim, block_dim, lds_byte, s.stream_id_>>>(args...);
+        hip_check_error(hipGetLastError());
+        return 0;
+    }
+#else
+    kernel<<<grid_dim, block_dim, lds_byte, s.stream_id_>>>(args...);
+    hip_check_error(hipGetLastError());
+    return 0;
+#endif
+}
+
+template <typename... Args, typename F, typename PreProcessFunc>
+CK_TILE_HOST float launch_and_time_kernel_with_preprocess(const stream_config& s,
+                                                          PreProcessFunc preprocess,
+                                                          F kernel,
+                                                          dim3 grid_dim,
+                                                          dim3 block_dim,
+                                                          std::size_t lds_byte,
+                                                          Args... args)
+{
+#if CK_TILE_TIME_KERNEL
+    if(s.time_kernel_)
+    {
+#if CK_TILE_DEBUG_LOG
+        printf("%s: grid_dim {%d, %d, %d}, block_dim {%d, %d, %d} \n",
+               __func__,
+               grid_dim.x,
+               grid_dim.y,
+               grid_dim.z,
+               block_dim.x,
+               block_dim.y,
+               block_dim.z);
+
+        printf("Warm up 1 time\n");
+#endif
+        // warm up
+        preprocess();
+        kernel<<<grid_dim, block_dim, lds_byte, s.stream_id_>>>(args...);
+        hip_check_error(hipGetLastError());
+
+        const int nrepeat = 10;
+#if CK_TILE_DEBUG_LOG
+        printf("Start running %d times...\n", nrepeat);
+#endif
+        hipEvent_t start, stop;
+
+        HIP_CHECK_ERROR(hipEventCreate(&start));
+        HIP_CHECK_ERROR(hipEventCreate(&stop));
+
+        HIP_CHECK_ERROR(hipDeviceSynchronize());
+        HIP_CHECK_ERROR(hipEventRecord(start, s.stream_id_));
+
+        for(int i = 0; i < nrepeat; ++i)
+        {
+            preprocess();
+            kernel<<<grid_dim, block_dim, lds_byte, s.stream_id_>>>(args...);
+            hip_check_error(hipGetLastError());
+        }
+
+        HIP_CHECK_ERROR(hipEventRecord(stop, s.stream_id_));
+        HIP_CHECK_ERROR(hipEventSynchronize(stop));
+
+        float total_time = 0;
+
+        HIP_CHECK_ERROR(hipEventElapsedTime(&total_time, start, stop));
+
+        return total_time / nrepeat;
+    }
+    else
+    {
+        preprocess();
+        kernel<<<grid_dim, block_dim, lds_byte, s.stream_id_>>>(args...);
+        hip_check_error(hipGetLastError());
+
+        return 0;
+    }
+#else
+    kernel<<<grid_dim, block_dim, lds_byte, s.stream_id_>>>(args...);
+    hip_check_error(hipGetLastError());
+
+    return 0;
+#endif
+}
+
+template <int MaxThreadPerBlock = CK_TILE_MAX_THREAD_PER_BLOCK,
+          int MinBlockPerCu     = CK_TILE_MIN_BLOCK_PER_CU,
+          typename KernelImpl,
+          typename... Args>
+CK_TILE_HOST float launch_kernel(const stream_config& s,
+                                 KernelImpl kernel_impl,
+                                 dim3 grid_dim,
+                                 dim3 block_dim,
+                                 std::size_t dynamic_smem_byte,
+                                 Args... args)
+{
+    const auto kernel = kentry<MaxThreadPerBlock, MinBlockPerCu, KernelImpl, Args...>;
+
+    return launch_and_time_kernel(
+        s, kernel, grid_dim, block_dim, dynamic_smem_byte, kernel_impl, args...);
+}
+} // namespace ck_tile

include/ck_tile/host/ranges.hpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
+
+#pragma once
+
+#include <iterator>
+#include <type_traits>
+#include <utility>
+
+// ranges implementation are not intented to be used by user
+// TODO: do we need this?
+namespace ck_tile {
+
+template <typename T>
+using iter_value_t = typename std::iterator_traits<remove_cvref_t<T>>::value_type;
+
+template <typename T>
+using iter_reference_t = decltype(*std::declval<T&>());
+
+template <typename T>
+using iter_difference_t = typename std::iterator_traits<remove_cvref_t<T>>::difference_type;
+
+namespace ranges {
+template <typename R>
+using iterator_t = decltype(std::begin(std::declval<R&>()));
+
+template <typename R>
+using sentinel_t = decltype(std::end(std::declval<R&>()));
+
+template <typename R>
+using range_size_t = decltype(std::size(std::declval<R&>()));
+
+template <typename R>
+using range_difference_t = ck_tile::iter_difference_t<ranges::iterator_t<R>>;
+
+template <typename R>
+using range_value_t = iter_value_t<ranges::iterator_t<R>>;
+
+template <typename R>
+using range_reference_t = iter_reference_t<ranges::iterator_t<R>>;
+
+template <typename T, typename = void>
+struct is_range : std::false_type
+{
+};
+
+template <typename T>
+struct is_range<
+    T,
+    std::void_t<decltype(std::begin(std::declval<T&>())), decltype(std::end(std::declval<T&>()))>>
+    : std::true_type
+{
+};
+
+template <typename T>
+inline constexpr bool is_range_v = is_range<T>::value;
+
+template <typename T, typename = void>
+struct is_sized_range : std::false_type
+{
+};
+
+template <typename T>
+struct is_sized_range<T, std::void_t<decltype(std::size(std::declval<T&>()))>>
+    : std::bool_constant<is_range_v<T>>
+{
+};
+} // namespace ranges
+} // namespace ck_tile

include/ck_tile/host/reference/reference_batched_elementwise.hpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
+
+#pragma once
+
+#include "ck_tile/core.hpp"
+#include "ck_tile/host/host_tensor.hpp"
+#include <thread>
+
+namespace ck_tile {
+
+template <typename ADataType,
+          typename BDataType,
+          typename AccDataType,
+          typename CDataType,
+          typename AElementOp      = ck_tile::identity,
+          typename BElementOp      = ck_tile::identity,
+          typename BinaryElementOp = ck_tile::plus<AccDataType>>
+CK_TILE_HOST void reference_batched_elementwise(const HostTensor<ADataType>& a_b_m_n,
+                                                const HostTensor<BDataType>& b_b_m_n,
+                                                HostTensor<CDataType>& c_b_m_n,
+                                                const AElementOp& a_element_op           = {},
+                                                const BElementOp& b_element_op           = {},
+                                                const BinaryElementOp& binary_element_op = {})
+{
+    const ck_tile::index_t N = c_b_m_n.mDesc.get_lengths()[2];
+
+    const bool broadcast_a_dim_b = (a_b_m_n.get_lengths()[0] == 1);
+    const bool broadcast_a_dim_m = (a_b_m_n.get_lengths()[1] == 1);
+    const bool broadcast_a_dim_n = (a_b_m_n.get_lengths()[2] == 1);
+
+    const bool broadcast_b_dim_b = (b_b_m_n.get_lengths()[0] == 1);
+    const bool broadcast_b_dim_m = (b_b_m_n.get_lengths()[1] == 1);
+    const bool broadcast_b_dim_n = (b_b_m_n.get_lengths()[2] == 1);
+
+    auto f = [&](auto batch, auto m) {
+        for(ck_tile::index_t n = 0; n < N; ++n)
+        {
+            AccDataType v_a{};
+            {
+                ck_tile::index_t i_b = (broadcast_a_dim_b ? 0 : batch);
+                ck_tile::index_t i_m = (broadcast_a_dim_m ? 0 : m);
+                ck_tile::index_t i_n = (broadcast_a_dim_n ? 0 : n);
+
+                v_a = ck_tile::type_convert<AccDataType>(a_element_op(a_b_m_n(i_b, i_m, i_n)));
+            }
+
+            AccDataType v_b{};
+            {
+                ck_tile::index_t i_b = (broadcast_b_dim_b ? 0 : batch);
+                ck_tile::index_t i_m = (broadcast_b_dim_m ? 0 : m);
+                ck_tile::index_t i_n = (broadcast_b_dim_n ? 0 : n);
+
+                v_b = ck_tile::type_convert<AccDataType>(b_element_op(b_b_m_n(i_b, i_m, i_n)));
+            }
+
+            c_b_m_n(batch, m, n) = ck_tile::type_convert<CDataType>(binary_element_op(v_a, v_b));
+        }
+    };
+
+    make_ParallelTensorFunctor(f, c_b_m_n.mDesc.get_lengths()[0], c_b_m_n.mDesc.get_lengths()[1])(
+        std::thread::hardware_concurrency());
+}
+} // namespace ck_tile

include/ck_tile/host/reference/reference_batched_gemm.hpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
+
+#pragma once
+
+#include "ck_tile/core.hpp"
+#include "ck_tile/host/host_tensor.hpp"
+#include <thread>
+
+namespace ck_tile {
+
+template <typename ADataType,
+          typename BDataType,
+          typename AccDataType,
+          typename CDataType,
+          typename AElementOp   = ck_tile::identity,
+          typename BElementOp   = ck_tile::identity,
+          typename ACCElementOp = ck_tile::identity>
+CK_TILE_HOST void reference_batched_gemm(const HostTensor<ADataType>& a_b_m_k,
+                                         const HostTensor<BDataType>& b_b_n_k,
+                                         HostTensor<CDataType>& c_b_m_n,
+                                         const AElementOp& a_element_op     = {},
+                                         const BElementOp& b_element_op     = {},
+                                         const ACCElementOp& acc_element_op = {})
+{
+    const int N = b_b_n_k.mDesc.get_lengths()[1];
+    const int K = b_b_n_k.mDesc.get_lengths()[2];
+
+    auto f = [&](auto batch, auto m) {
+        for(int n = 0; n < N; ++n)
+        {
+            AccDataType v_acc = 0;
+
+            for(int k = 0; k < K; ++k)
+            {
+                ADataType v_a = a_element_op(a_b_m_k(batch, m, k));
+                BDataType v_b = b_element_op(b_b_n_k(batch, n, k));
+
+                v_acc += ck_tile::type_convert<AccDataType>(v_a) *
+                         ck_tile::type_convert<AccDataType>(v_b);
+            }
+
+            c_b_m_n(batch, m, n) = ck_tile::type_convert<CDataType>(acc_element_op(v_acc));
+        }
+    };
+
+    make_ParallelTensorFunctor(f, c_b_m_n.mDesc.get_lengths()[0], c_b_m_n.mDesc.get_lengths()[1])(
+        std::thread::hardware_concurrency());
+}
+} // namespace ck_tile

include/ck_tile/host/reference/reference_batched_masking.hpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
+
+#pragma once
+
+#include "ck_tile/core.hpp"
+#include "ck_tile/host/host_tensor.hpp"
+#include <thread>
+
+namespace ck_tile {
+
+template <typename CDataType, typename MaskingType>
+CK_TILE_HOST void reference_batched_masking(HostTensor<CDataType>& c_b_m_n, const MaskingType& mask)
+{
+    const int M = c_b_m_n.mDesc.get_lengths()[1];
+    const int N = c_b_m_n.mDesc.get_lengths()[2];
+
+    auto f = [&](auto batch) {
+        for(int n = 0; n < N; ++n)
+        {
+            for(int m = 0; m < M; ++m)
+            {
+                if(mask.IsOutOfBound(m, n))
+                    c_b_m_n(batch, m, n) = -ck_tile::numeric<CDataType>::infinity();
+            }
+        }
+    };
+
+    make_ParallelTensorFunctor(f,
+                               c_b_m_n.mDesc.get_lengths()[0])(std::thread::hardware_concurrency());
+}
+} // namespace ck_tile

include/ck_tile/host/reference/reference_batched_softmax.hpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
+
+#pragma once
+
+#include "ck_tile/core.hpp"
+#include "ck_tile/host/host_tensor.hpp"
+#include <thread>
+
+namespace ck_tile {
+
+template <typename ADataType,
+          typename CompDataType,
+          typename BDataType,
+          typename CompElementOp = ck_tile::identity>
+CK_TILE_HOST void reference_batched_softmax(
+    const HostTensor<ADataType>& a_b_m_n,
+    HostTensor<BDataType>& b_b_m_n,
+    const CompElementOp& comp_element_op                                    = {},
+    std::optional<std::reference_wrapper<HostTensor<CompDataType>>> lse_b_m = std::nullopt)
+{
+    const int N = a_b_m_n.mDesc.get_lengths()[2];
+
+    auto f = [&](auto batch, auto m) {
+        CompDataType v_max = -ck_tile::numeric<CompDataType>::infinity();
+
+        // max
+        for(int n = 0; n < N; ++n)
+        {
+            const CompDataType v_a = ck_tile::type_convert<CompDataType>(a_b_m_n(batch, m, n));
+
+            v_max = v_max < v_a ? v_a : v_max;
+        }
+
+        CompDataType v_exp_sum = 0;
+        // validate v_max if all the elements within a row are -INF
+        if(std::isinf(v_max) && v_max < 0)
+        {
+            v_max = ck_tile::type_convert<CompDataType>(0.f);
+        }
+
+        // sum
+        for(int n = 0; n < N; ++n)
+        {
+            const CompDataType v_a = ck_tile::type_convert<CompDataType>(a_b_m_n(batch, m, n));
+
+            v_exp_sum += ck_tile::exp(v_a - v_max);
+        }
+
+        // if sum is zero(masked), or nan/inf(other computation error), don't do divide
+        CompDataType inv_sum = (v_exp_sum == 0.f ? 1.f : 1.f / v_exp_sum);
+
+        // elementwise
+        for(int n = 0; n < N; ++n)
+        {
+            const CompDataType v_a = ck_tile::type_convert<CompDataType>(a_b_m_n(batch, m, n));
+            const CompDataType v_b = ck_tile::exp(v_a - v_max) * inv_sum;
+
+            b_b_m_n(batch, m, n) = ck_tile::type_convert<BDataType>(comp_element_op(v_b));
+        }
+        // lse
+        if(lse_b_m)
+        {
+            lse_b_m->get()(batch, m) = v_max + ck_tile::log(v_exp_sum);
+        }
+    };
+
+    make_ParallelTensorFunctor(f, b_b_m_n.mDesc.get_lengths()[0], b_b_m_n.mDesc.get_lengths()[1])(
+        std::thread::hardware_concurrency());
+}
+} // namespace ck_tile

include/ck_tile/host/reference/reference_gemm.hpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
+
+#pragma once
+
+#include "ck_tile/core.hpp"
+#include "ck_tile/host/host_tensor.hpp"
+#include <thread>
+
+namespace ck_tile {
+
+template <typename ADataType,
+          typename BDataType,
+          typename AccDataType,
+          typename CDataType,
+          typename AElementOp   = ck_tile::identity,
+          typename BElementOp   = ck_tile::identity,
+          typename ACCElementOp = ck_tile::identity>
+CK_TILE_HOST void reference_gemm(const HostTensor<ADataType>& a_m_k,
+                                 const HostTensor<BDataType>& b_n_k,
+                                 HostTensor<CDataType>& c_m_n,
+                                 const AElementOp& a_element_op     = {},
+                                 const BElementOp& b_element_op     = {},
+                                 const ACCElementOp& acc_element_op = {})
+{
+    const int N = b_n_k.mDesc.get_lengths()[0];
+    const int K = b_n_k.mDesc.get_lengths()[1];
+
+    auto f = [&](auto m) {
+        for(int n = 0; n < N; ++n)
+        {
+            AccDataType v_acc = 0;
+
+            for(int k = 0; k < K; ++k)
+            {
+                ADataType v_a = a_element_op(a_m_k(m, k));
+                BDataType v_b = b_element_op(b_n_k(n, k));
+
+                v_acc += ck_tile::type_convert<AccDataType>(v_a) *
+                         ck_tile::type_convert<AccDataType>(v_b);
+            }
+
+            c_m_n(m, n) = ck_tile::type_convert<CDataType>(acc_element_op(v_acc));
+        }
+    };
+
+    make_ParallelTensorFunctor(f,
+                               c_m_n.mDesc.get_lengths()[0])(std::thread::hardware_concurrency());
+}
+} // namespace ck_tile

include/ck_tile/host/reference/reference_im2col.hpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
+
+#pragma once
+
+#include "ck_tile/core.hpp"
+#include "ck_tile/host/host_tensor.hpp"
+#include <thread>
+
+namespace ck_tile {
+
+template <typename T>
+CK_TILE_HOST void reference_im2col(HostTensor<T>& in_mtx_host_ref,
+                                   const HostTensor<T>& in_host,
+                                   int /*N*/,
+                                   int /*K*/,
+                                   int C,
+                                   int /*Y*/,
+                                   int X,
+                                   int Hi,
+                                   int Wi,
+                                   int Ho,
+                                   int Wo,
+                                   int ConvStrideH,
+                                   int ConvStrideW,
+                                   int ConvDilationH,
+                                   int ConvDilationW,
+                                   int InLeftPadH,
+                                   int InLeftPadW,
+                                   int /*InRightPadH*/,
+                                   int /*InRightPadW*/)
+{
+    int GemmM = in_mtx_host_ref.get_lengths()[0];
+    int GemmK = in_mtx_host_ref.get_lengths()[1];
+
+    for(int gemm_m = 0; gemm_m < GemmM; ++gemm_m)
+    {
+        int mtmp = gemm_m;
+        int n    = mtmp / (Ho * Wo);
+        mtmp -= n * Ho * Wo;
+        int ho = mtmp / Wo;
+        int wo = mtmp - ho * Wo;
+
+        for(int gemm_k = 0; gemm_k < GemmK; ++gemm_k)
+        {
+            int ktmp = gemm_k;
+            int y    = ktmp / (X * C);
+            ktmp -= y * X * C;
+            int x = ktmp / C;
+            int c = ktmp - x * C;
+
+            int hi = y * ConvDilationH + ho * ConvStrideH - InLeftPadH;
+            int wi = x * ConvDilationW + wo * ConvStrideW - InLeftPadW;
+
+            bool inbound = (hi >= 0 && hi < Hi && wi >= 0 && wi < Wi);
+
+            in_mtx_host_ref(gemm_m, gemm_k) = inbound ? in_host(n, hi, wi, c) : 0;
+        }
+    }
+}
+} // namespace ck_tile

include/ck_tile/host/reference/reference_reduce.hpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
+
+#pragma once
+
+#include "ck_tile/core.hpp"
+#include "ck_tile/host/host_tensor.hpp"
+#include <thread>
+
+namespace ck_tile {
+
+template <typename ADataType, typename AccDataType, typename BDataType>
+CK_TILE_HOST void reference_reduce(const HostTensor<ADataType>& a_m_n, HostTensor<BDataType>& b_m)
+{
+    auto f = [&](auto m) {
+        const int N = a_m_n.mDesc.get_lengths()[1];
+
+        AccDataType v_acc = 0;
+
+        for(int n = 0; n < N; ++n)
+        {
+            const ADataType v_a = a_m_n(m, n);
+
+            v_acc += v_a;
+        }
+
+        b_m(m) = ck_tile::type_convert<BDataType>(v_acc);
+    };
+
+    make_ParallelTensorFunctor(f, b_m.mDesc.get_lengths()[0])(std::thread::hardware_concurrency());
+}
+} // namespace ck_tile

include/ck_tile/host/reference/reference_softmax.hpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
+
+#pragma once
+
+#include "ck_tile/core.hpp"
+#include "ck_tile/host/host_tensor.hpp"
+#include <thread>
+
+namespace ck_tile {
+
+template <typename ADataType, typename AccDataType, typename BDataType>
+CK_TILE_HOST void reference_softmax(const HostTensor<ADataType>& a_m_n,
+                                    HostTensor<BDataType>& b_m_n)
+{
+    auto f = [&](auto m) {
+        const int N = a_m_n.mDesc.get_lengths()[1];
+
+        AccDataType v_max = ck_tile::numeric<ADataType>::Lowest();
+
+        // max
+        for(int n = 0; n < N; ++n)
+        {
+            const ADataType v_a = a_m_n(m, n);
+
+            v_max = v_max < v_a ? v_a : v_max;
+        }
+
+        AccDataType v_exp_sum = 0;
+
+        // sum
+        for(int n = 0; n < N; ++n)
+        {
+            const ADataType v_a = a_m_n(m, n);
+
+            v_exp_sum += ck_tile::exp(v_a - v_max);
+        }
+
+        // elementwise
+        for(int n = 0; n < N; ++n)
+        {
+            const ADataType v_a = a_m_n(m, n);
+
+            b_m_n(m, n) = ck_tile::exp(v_a - v_max) / v_exp_sum;
+        }
+    };
+
+    make_ParallelTensorFunctor(f,
+                               b_m_n.mDesc.get_lengths()[0])(std::thread::hardware_concurrency());
+}
+} // namespace ck_tile

include/ck_tile/host/stream_config.hpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
+
+#pragma once
+
+#include <hip/hip_runtime.h>
+
+namespace ck_tile {
+struct stream_config
+{
+    hipStream_t stream_id_ = nullptr;
+    bool time_kernel_      = false;
+    int log_level_         = 0;
+    int cold_niters_       = 3;
+    int nrepeat_           = 10;
+};
+} // namespace ck_tile

include/ck_tile/ops/common.hpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
+
+#pragma once
+
+#include "ck_tile/ops/common/tensor_layout.hpp"