File size: 13,962 Bytes
b024d42 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 | // 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 <unordered_set>
#include "ck_tile/core.hpp"
#include "ck_tile/host/joinable_thread.hpp"
namespace ck_tile {
template <typename T>
struct FillUniformDistribution
{
float a_{-5.f};
float b_{5.f};
std::optional<uint32_t> seed_{11939};
// ATTENTION: threaded does not guarantee the distribution between thread
bool threaded = false;
template <typename ForwardIter>
void operator()(ForwardIter first, ForwardIter last) const
{
if(threaded)
{
uint32_t num_thread = std::thread::hardware_concurrency();
auto total = static_cast<std::size_t>(std::distance(first, last));
auto work_per_thread = static_cast<std::size_t>((total + 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, total);
auto thread_f = [this, total, iw_begin, iw_end, &first] {
if(iw_begin > total || iw_end > total)
return;
// need to make each thread unique, add an offset to current seed
std::mt19937 gen(seed_.has_value() ? (*seed_ + iw_begin)
: std::random_device{}());
std::uniform_real_distribution<float> dis(a_, b_);
std::generate(first + iw_begin, first + iw_end, [&dis, &gen]() {
return ck_tile::type_convert<T>(dis(gen));
});
};
threads[it] = joinable_thread(thread_f);
}
}
else
{
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)));
}
};
namespace impl {
// clang-format off
template<index_t bytes> struct RawIntegerType_ {};
template<> struct RawIntegerType_<1> { using type = uint8_t;};
template<> struct RawIntegerType_<2> { using type = uint16_t;};
template<> struct RawIntegerType_<4> { using type = uint32_t;};
template<> struct RawIntegerType_<8> { using type = uint64_t;};
// clang-format on
template <typename T>
using RawIntegerType = typename RawIntegerType_<sizeof(T)>::type;
} // namespace impl
// Note: this struct will have no const-ness will generate random
template <typename T>
struct FillUniformDistribution_Unique
{
float a_{-5.f};
float b_{5.f};
std::optional<uint32_t> seed_{11939};
std::mt19937 gen_{};
std::unordered_set<impl::RawIntegerType<T>> set_{};
FillUniformDistribution_Unique(float a = -5.f,
float b = 5.f,
std::optional<uint32_t> seed = {11939})
: a_(a),
b_(b),
seed_(seed),
gen_{seed_.has_value() ? *seed_ : std::random_device{}()},
set_{}
{
}
template <typename ForwardIter>
void operator()(ForwardIter first, ForwardIter last)
{
std::mt19937& gen = gen_;
std::uniform_real_distribution<float> dis(a_, b_);
auto& set = set_;
std::generate(first, last, [&dis, &gen, &set]() {
T v = static_cast<T>(0);
do
{
v = ck_tile::type_convert<T>(dis(gen));
} while(set.count(bit_cast<impl::RawIntegerType<T>>(v)) == 1);
set.insert(bit_cast<impl::RawIntegerType<T>>(v));
return v;
});
}
template <typename ForwardRange>
auto operator()(ForwardRange&& range)
-> std::void_t<decltype(std::declval<FillUniformDistribution_Unique&>()(
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)));
}
void clear() { set_.clear(); }
};
template <typename T>
struct FillNormalDistribution
{
float mean_{0.f};
float variance_{1.f};
std::optional<uint32_t> seed_{11939};
// ATTENTION: threaded does not guarantee the distribution between thread
bool threaded = false;
template <typename ForwardIter>
void operator()(ForwardIter first, ForwardIter last) const
{
if(threaded)
{
uint32_t num_thread = std::thread::hardware_concurrency();
auto total = static_cast<std::size_t>(std::distance(first, last));
auto work_per_thread = static_cast<std::size_t>((total + 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, total);
auto thread_f = [this, total, iw_begin, iw_end, &first] {
if(iw_begin > total || iw_end > total)
return;
// need to make each thread unique, add an offset to current seed
std::mt19937 gen(seed_.has_value() ? (*seed_ + iw_begin)
: std::random_device{}());
std::normal_distribution<float> dis(mean_, std::sqrt(variance_));
std::generate(first + iw_begin, first + iw_end, [&dis, &gen]() {
return ck_tile::type_convert<T>(dis(gen));
});
};
threads[it] = joinable_thread(thread_f);
}
}
else
{
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, bool IsAscending = true>
struct FillStepRange
{
float start_value_{0};
float end_value_{3};
float step_{1};
template <typename ForwardIter>
void operator()(ForwardIter first, ForwardIter last) const
{
std::generate(first, last, [=, n = start_value_]() mutable {
auto tmp = n;
n += step_;
if constexpr(IsAscending)
{
if(n > end_value_)
n = start_value_;
}
else
{
if(n < end_value_)
n = start_value_;
}
return type_convert<T>(tmp);
});
}
template <typename ForwardRange>
auto operator()(ForwardRange&& range) const -> std::void_t<
decltype(std::declval<const FillStepRange&>()(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
|