/*
Stockfish, a UCI chess playing engine derived from Glaurung 2.1
- Copyright (C) 2004-2023 The Stockfish developers (see AUTHORS file)
+ Copyright (C) 2004-2024 The Stockfish developers (see AUTHORS file)
Stockfish is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
#include "misc.h"
-#ifdef _WIN32
- #if _WIN32_WINNT < 0x0601
- #undef _WIN32_WINNT
- #define _WIN32_WINNT 0x0601 // Force to include needed API prototypes
- #endif
-
- #ifndef NOMINMAX
- #define NOMINMAX
- #endif
-
- #include <windows.h>
-// The needed Windows API for processor groups could be missed from old Windows
-// versions, so instead of calling them directly (forcing the linker to resolve
-// the calls at compile time), try to load them at runtime. To do this we need
-// first to define the corresponding function pointers.
-extern "C" {
-using fun1_t = bool (*)(LOGICAL_PROCESSOR_RELATIONSHIP,
- PSYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX,
- PDWORD);
-using fun2_t = bool (*)(USHORT, PGROUP_AFFINITY);
-using fun3_t = bool (*)(HANDLE, CONST GROUP_AFFINITY*, PGROUP_AFFINITY);
-using fun4_t = bool (*)(USHORT, PGROUP_AFFINITY, USHORT, PUSHORT);
-using fun5_t = WORD (*)();
-using fun6_t = bool (*)(HANDLE, DWORD, PHANDLE);
-using fun7_t = bool (*)(LPCSTR, LPCSTR, PLUID);
-using fun8_t = bool (*)(HANDLE, BOOL, PTOKEN_PRIVILEGES, DWORD, PTOKEN_PRIVILEGES, PDWORD);
-}
-#endif
-
#include <atomic>
+#include <cctype>
#include <cmath>
#include <cstdlib>
#include <fstream>
#include <iomanip>
#include <iostream>
+#include <iterator>
+#include <limits>
#include <mutex>
#include <sstream>
#include <string_view>
#include "types.h"
-#if defined(__linux__) && !defined(__ANDROID__)
- #include <sys/mman.h>
-#endif
-
-#if defined(__APPLE__) || defined(__ANDROID__) || defined(__OpenBSD__) \
- || (defined(__GLIBCXX__) && !defined(_GLIBCXX_HAVE_ALIGNED_ALLOC) && !defined(_WIN32)) \
- || defined(__e2k__)
- #define POSIXALIGNEDALLOC
- #include <stdlib.h>
-#endif
-
namespace Stockfish {
namespace {
} // namespace
-// engine_info() returns the full name of the current Stockfish version.
-// For local dev compiles we try to append the commit sha and commit date
-// from git if that fails only the local compilation date is set and "nogit" is specified:
-// Stockfish dev-YYYYMMDD-SHA
-// or
-// Stockfish dev-YYYYMMDD-nogit
+// Returns the full name of the current Stockfish version.
+//
+// For local dev compiles we try to append the commit SHA and
+// commit date from git. If that fails only the local compilation
+// date is set and "nogit" is specified:
+// Stockfish dev-YYYYMMDD-SHA
+// or
+// Stockfish dev-YYYYMMDD-nogit
//
// For releases (non-dev builds) we only include the version number:
-// Stockfish version
-
+// Stockfish version
std::string engine_info(bool to_uci) {
std::stringstream ss;
ss << "Stockfish " << version << std::setfill('0');
ss << stringify(GIT_DATE);
#else
constexpr std::string_view months("Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec");
- std::string month, day, year;
- std::stringstream date(__DATE__); // From compiler, format is "Sep 21 2008"
+
+ std::string month, day, year;
+ std::stringstream date(__DATE__); // From compiler, format is "Sep 21 2008"
date >> month >> day >> year;
ss << year << std::setw(2) << std::setfill('0') << (1 + months.find(month) / 4)
#else
ss << "nogit";
#endif
+ ss << "-asn";
}
ss << (to_uci ? "\nid author " : " by ") << "the Stockfish developers (see AUTHORS file)";
}
-// compiler_info() returns a string trying to describe the compiler we use
-
+// Returns a string trying to describe the compiler we use
std::string compiler_info() {
#define make_version_string(major, minor, patch) \
struct DebugInfo {
std::atomic<int64_t> data[N] = {0};
- constexpr inline std::atomic<int64_t>& operator[](int index) { return data[index]; }
+ constexpr std::atomic<int64_t>& operator[](int index) { return data[index]; }
+};
+
+struct DebugExtremes: public DebugInfo<3> {
+ DebugExtremes() {
+ data[1] = std::numeric_limits<int64_t>::min();
+ data[2] = std::numeric_limits<int64_t>::max();
+ }
};
-DebugInfo<2> hit[MaxDebugSlots];
-DebugInfo<2> mean[MaxDebugSlots];
-DebugInfo<3> stdev[MaxDebugSlots];
-DebugInfo<6> correl[MaxDebugSlots];
+DebugInfo<2> hit[MaxDebugSlots];
+DebugInfo<2> mean[MaxDebugSlots];
+DebugInfo<3> stdev[MaxDebugSlots];
+DebugInfo<6> correl[MaxDebugSlots];
+DebugExtremes extremes[MaxDebugSlots];
} // namespace
stdev[slot][2] += value * value;
}
+void dbg_extremes_of(int64_t value, int slot) {
+ ++extremes[slot][0];
+
+ int64_t current_max = extremes[slot][1].load();
+ while (current_max < value && !extremes[slot][1].compare_exchange_weak(current_max, value))
+ {}
+
+ int64_t current_min = extremes[slot][2].load();
+ while (current_min > value && !extremes[slot][2].compare_exchange_weak(current_min, value))
+ {}
+}
+
void dbg_correl_of(int64_t value1, int64_t value2, int slot) {
++correl[slot][0];
std::cerr << "Stdev #" << i << ": Total " << n << " Stdev " << r << std::endl;
}
+ for (int i = 0; i < MaxDebugSlots; ++i)
+ if ((n = extremes[i][0]))
+ {
+ std::cerr << "Extremity #" << i << ": Total " << n << " Min " << extremes[i][2]
+ << " Max " << extremes[i][1] << std::endl;
+ }
+
for (int i = 0; i < MaxDebugSlots; ++i)
if ((n = correl[i][0]))
{
}
-// Used to serialize access to std::cout to avoid multiple threads writing at
-// the same time.
-
+// Used to serialize access to std::cout
+// to avoid multiple threads writing at the same time.
std::ostream& operator<<(std::ostream& os, SyncCout sc) {
static std::mutex m;
return os;
}
+void sync_cout_start() { std::cout << IO_LOCK; }
+void sync_cout_end() { std::cout << IO_UNLOCK; }
// Trampoline helper to avoid moving Logger to misc.h
void start_logger(const std::string& fname) { Logger::start(fname); }
-// prefetch() preloads the given address in L1/L2 cache. This is a non-blocking
-// function that doesn't stall the CPU waiting for data to be loaded from memory,
-// which can be quite slow.
#ifdef NO_PREFETCH
-void prefetch(void*) {}
+void prefetch(const void*) {}
#else
-void prefetch(void* addr) {
+void prefetch(const void* addr) {
#if defined(_MSC_VER)
- _mm_prefetch((char*) addr, _MM_HINT_T0);
+ _mm_prefetch((char const*) addr, _MM_HINT_T0);
#else
__builtin_prefetch(addr);
#endif
#endif
-
-// std_aligned_alloc() is our wrapper for systems where the c++17 implementation
-// does not guarantee the availability of aligned_alloc(). Memory allocated with
-// std_aligned_alloc() must be freed with std_aligned_free().
-
-void* std_aligned_alloc(size_t alignment, size_t size) {
-
-#if defined(POSIXALIGNEDALLOC)
- void* mem;
- return posix_memalign(&mem, alignment, size) ? nullptr : mem;
-#elif defined(_WIN32) && !defined(_M_ARM) && !defined(_M_ARM64)
- return _mm_malloc(size, alignment);
-#elif defined(_WIN32)
- return _aligned_malloc(size, alignment);
-#else
- return std::aligned_alloc(alignment, size);
-#endif
-}
-
-void std_aligned_free(void* ptr) {
-
-#if defined(POSIXALIGNEDALLOC)
- free(ptr);
-#elif defined(_WIN32) && !defined(_M_ARM) && !defined(_M_ARM64)
- _mm_free(ptr);
-#elif defined(_WIN32)
- _aligned_free(ptr);
+#ifdef _WIN32
+ #include <direct.h>
+ #define GETCWD _getcwd
#else
- free(ptr);
+ #include <unistd.h>
+ #define GETCWD getcwd
#endif
-}
-
-// aligned_large_pages_alloc() will return suitably aligned memory, if possible using large pages.
-
-#if defined(_WIN32)
-
-static void* aligned_large_pages_alloc_windows([[maybe_unused]] size_t allocSize) {
-
- #if !defined(_WIN64)
- return nullptr;
- #else
-
- HANDLE hProcessToken{};
- LUID luid{};
- void* mem = nullptr;
-
- const size_t largePageSize = GetLargePageMinimum();
- if (!largePageSize)
- return nullptr;
-
- // Dynamically link OpenProcessToken, LookupPrivilegeValue and AdjustTokenPrivileges
-
- HMODULE hAdvapi32 = GetModuleHandle(TEXT("advapi32.dll"));
-
- if (!hAdvapi32)
- hAdvapi32 = LoadLibrary(TEXT("advapi32.dll"));
-
- auto fun6 = fun6_t((void (*)()) GetProcAddress(hAdvapi32, "OpenProcessToken"));
- if (!fun6)
- return nullptr;
- auto fun7 = fun7_t((void (*)()) GetProcAddress(hAdvapi32, "LookupPrivilegeValueA"));
- if (!fun7)
- return nullptr;
- auto fun8 = fun8_t((void (*)()) GetProcAddress(hAdvapi32, "AdjustTokenPrivileges"));
- if (!fun8)
- return nullptr;
-
- // We need SeLockMemoryPrivilege, so try to enable it for the process
- if (!fun6( // OpenProcessToken()
- GetCurrentProcess(), TOKEN_ADJUST_PRIVILEGES | TOKEN_QUERY, &hProcessToken))
- return nullptr;
-
- if (fun7( // LookupPrivilegeValue(nullptr, SE_LOCK_MEMORY_NAME, &luid)
- nullptr, "SeLockMemoryPrivilege", &luid))
- {
- TOKEN_PRIVILEGES tp{};
- TOKEN_PRIVILEGES prevTp{};
- DWORD prevTpLen = 0;
-
- tp.PrivilegeCount = 1;
- tp.Privileges[0].Luid = luid;
- tp.Privileges[0].Attributes = SE_PRIVILEGE_ENABLED;
-
- // Try to enable SeLockMemoryPrivilege. Note that even if AdjustTokenPrivileges() succeeds,
- // we still need to query GetLastError() to ensure that the privileges were actually obtained.
- if (fun8( // AdjustTokenPrivileges()
- hProcessToken, FALSE, &tp, sizeof(TOKEN_PRIVILEGES), &prevTp, &prevTpLen)
- && GetLastError() == ERROR_SUCCESS)
- {
- // Round up size to full pages and allocate
- allocSize = (allocSize + largePageSize - 1) & ~size_t(largePageSize - 1);
- mem = VirtualAlloc(nullptr, allocSize, MEM_RESERVE | MEM_COMMIT | MEM_LARGE_PAGES,
- PAGE_READWRITE);
-
- // Privilege no longer needed, restore previous state
- fun8( // AdjustTokenPrivileges ()
- hProcessToken, FALSE, &prevTp, 0, nullptr, nullptr);
- }
- }
-
- CloseHandle(hProcessToken);
-
- return mem;
-
- #endif
-}
-
-void* aligned_large_pages_alloc(size_t allocSize) {
-
- // Try to allocate large pages
- void* mem = aligned_large_pages_alloc_windows(allocSize);
-
- // Fall back to regular, page-aligned, allocation if necessary
- if (!mem)
- mem = VirtualAlloc(nullptr, allocSize, MEM_RESERVE | MEM_COMMIT, PAGE_READWRITE);
-
- return mem;
-}
-
-#else
-
-void* aligned_large_pages_alloc(size_t allocSize) {
-
- #if defined(__linux__)
- constexpr size_t alignment = 2 * 1024 * 1024; // assumed 2MB page size
- #else
- constexpr size_t alignment = 4096; // assumed small page size
- #endif
- // round up to multiples of alignment
- size_t size = ((allocSize + alignment - 1) / alignment) * alignment;
- void* mem = std_aligned_alloc(alignment, size);
- #if defined(MADV_HUGEPAGE)
- madvise(mem, size, MADV_HUGEPAGE);
- #endif
- return mem;
+size_t str_to_size_t(const std::string& s) {
+ unsigned long long value = std::stoull(s);
+ if (value > std::numeric_limits<size_t>::max())
+ std::exit(EXIT_FAILURE);
+ return static_cast<size_t>(value);
}
-#endif
-
-
-// aligned_large_pages_free() will free the previously allocated ttmem
-
-#if defined(_WIN32)
-
-void aligned_large_pages_free(void* mem) {
-
- if (mem && !VirtualFree(mem, 0, MEM_RELEASE))
- {
- DWORD err = GetLastError();
- std::cerr << "Failed to free large page memory. Error code: 0x" << std::hex << err
- << std::dec << std::endl;
- exit(EXIT_FAILURE);
- }
+std::optional<std::string> read_file_to_string(const std::string& path) {
+ std::ifstream f(path, std::ios_base::binary);
+ if (!f)
+ return std::nullopt;
+ return std::string(std::istreambuf_iterator<char>(f), std::istreambuf_iterator<char>());
}
-#else
-
-void aligned_large_pages_free(void* mem) { std_aligned_free(mem); }
-
-#endif
-
-
-namespace WinProcGroup {
-
-#ifndef _WIN32
-
-void bindThisThread(size_t) {}
-
-#else
-
-// best_node() retrieves logical processor information using Windows specific
-// API and returns the best node id for the thread with index idx. Original
-// code from Texel by Peter Ă–sterlund.
-
-static int best_node(size_t idx) {
-
- int threads = 0;
- int nodes = 0;
- int cores = 0;
- DWORD returnLength = 0;
- DWORD byteOffset = 0;
-
- // Early exit if the needed API is not available at runtime
- HMODULE k32 = GetModuleHandle(TEXT("Kernel32.dll"));
- auto fun1 = (fun1_t) (void (*)()) GetProcAddress(k32, "GetLogicalProcessorInformationEx");
- if (!fun1)
- return -1;
-
- // First call to GetLogicalProcessorInformationEx() to get returnLength.
- // We expect the call to fail due to null buffer.
- if (fun1(RelationAll, nullptr, &returnLength))
- return -1;
-
- // Once we know returnLength, allocate the buffer
- SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX *buffer, *ptr;
- ptr = buffer = (SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX*) malloc(returnLength);
-
- // Second call to GetLogicalProcessorInformationEx(), now we expect to succeed
- if (!fun1(RelationAll, buffer, &returnLength))
- {
- free(buffer);
- return -1;
- }
-
- while (byteOffset < returnLength)
- {
- if (ptr->Relationship == RelationNumaNode)
- nodes++;
-
- else if (ptr->Relationship == RelationProcessorCore)
- {
- cores++;
- threads += (ptr->Processor.Flags == LTP_PC_SMT) ? 2 : 1;
- }
-
- assert(ptr->Size);
- byteOffset += ptr->Size;
- ptr = (SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX*) (((char*) ptr) + ptr->Size);
- }
-
- free(buffer);
-
- std::vector<int> groups;
-
- // Run as many threads as possible on the same node until the core limit is
- // reached, then move on to filling the next node.
- for (int n = 0; n < nodes; n++)
- for (int i = 0; i < cores / nodes; i++)
- groups.push_back(n);
-
- // In case a core has more than one logical processor (we assume 2) and we
- // have still threads to allocate, then spread them evenly across available
- // nodes.
- for (int t = 0; t < threads - cores; t++)
- groups.push_back(t % nodes);
-
- // If we still have more threads than the total number of logical processors
- // then return -1 and let the OS to decide what to do.
- return idx < groups.size() ? groups[idx] : -1;
+void remove_whitespace(std::string& s) {
+ s.erase(std::remove_if(s.begin(), s.end(), [](char c) { return std::isspace(c); }), s.end());
}
-
-// bindThisThread() sets the group affinity of the current thread
-
-void bindThisThread(size_t idx) {
-
- // Use only local variables to be thread-safe
- int node = best_node(idx);
-
- if (node == -1)
- return;
-
- // Early exit if the needed API are not available at runtime
- HMODULE k32 = GetModuleHandle(TEXT("Kernel32.dll"));
- auto fun2 = fun2_t((void (*)()) GetProcAddress(k32, "GetNumaNodeProcessorMaskEx"));
- auto fun3 = fun3_t((void (*)()) GetProcAddress(k32, "SetThreadGroupAffinity"));
- auto fun4 = fun4_t((void (*)()) GetProcAddress(k32, "GetNumaNodeProcessorMask2"));
- auto fun5 = fun5_t((void (*)()) GetProcAddress(k32, "GetMaximumProcessorGroupCount"));
-
- if (!fun2 || !fun3)
- return;
-
- if (!fun4 || !fun5)
- {
- GROUP_AFFINITY affinity;
- if (fun2(node, &affinity)) // GetNumaNodeProcessorMaskEx
- fun3(GetCurrentThread(), &affinity, nullptr); // SetThreadGroupAffinity
- }
- else
- {
- // If a numa node has more than one processor group, we assume they are
- // sized equal and we spread threads evenly across the groups.
- USHORT elements, returnedElements;
- elements = fun5(); // GetMaximumProcessorGroupCount
- GROUP_AFFINITY* affinity = (GROUP_AFFINITY*) malloc(elements * sizeof(GROUP_AFFINITY));
- if (fun4(node, affinity, elements, &returnedElements)) // GetNumaNodeProcessorMask2
- fun3(GetCurrentThread(), &affinity[idx % returnedElements],
- nullptr); // SetThreadGroupAffinity
- free(affinity);
- }
+bool is_whitespace(const std::string& s) {
+ return std::all_of(s.begin(), s.end(), [](char c) { return std::isspace(c); });
}
-#endif
-
-} // namespace WinProcGroup
-
-#ifdef _WIN32
- #include <direct.h>
- #define GETCWD _getcwd
-#else
- #include <unistd.h>
- #define GETCWD getcwd
-#endif
-
-namespace CommandLine {
-
-std::string argv0; // path+name of the executable binary, as given by argv[0]
-std::string binaryDirectory; // path of the executable directory
-std::string workingDirectory; // path of the working directory
-
-void init([[maybe_unused]] int argc, char* argv[]) {
+std::string CommandLine::get_binary_directory(std::string argv0) {
std::string pathSeparator;
- // extract the path+name of the executable binary
- argv0 = argv[0];
-
#ifdef _WIN32
pathSeparator = "\\";
#ifdef _MSC_VER
pathSeparator = "/";
#endif
- // extract the working directory
- workingDirectory = "";
- char buff[40000];
- char* cwd = GETCWD(buff, 40000);
- if (cwd)
- workingDirectory = cwd;
+ // Extract the working directory
+ auto workingDirectory = CommandLine::get_working_directory();
- // extract the binary directory path from argv0
- binaryDirectory = argv0;
- size_t pos = binaryDirectory.find_last_of("\\/");
+ // Extract the binary directory path from argv0
+ auto binaryDirectory = argv0;
+ size_t pos = binaryDirectory.find_last_of("\\/");
if (pos == std::string::npos)
binaryDirectory = "." + pathSeparator;
else
binaryDirectory.resize(pos + 1);
- // pattern replacement: "./" at the start of path is replaced by the working directory
+ // Pattern replacement: "./" at the start of path is replaced by the working directory
if (binaryDirectory.find("." + pathSeparator) == 0)
binaryDirectory.replace(0, 1, workingDirectory);
+
+ return binaryDirectory;
}
+std::string CommandLine::get_working_directory() {
+ std::string workingDirectory = "";
+ char buff[40000];
+ char* cwd = GETCWD(buff, 40000);
+ if (cwd)
+ workingDirectory = cwd;
+
+ return workingDirectory;
+}
-} // namespace CommandLine
} // namespace Stockfish