std::string engine_info(bool to_uci = false);
std::string compiler_info();
+
+// 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.
void prefetch(void* addr);
-void start_logger(const std::string& fname);
+
+void start_logger(const std::string& fname);
void* std_aligned_alloc(size_t alignment, size_t size);
-void std_aligned_free(void* ptr);
-void* aligned_large_pages_alloc(size_t size); // memory aligned by page size, min alignment: 4096 bytes
-void aligned_large_pages_free(void* mem); // nop if mem == nullptr
+void std_aligned_free(void* ptr);
+// memory aligned by page size, min alignment: 4096 bytes
+void* aligned_large_pages_alloc(size_t size);
+// nop if mem == nullptr
+void aligned_large_pages_free(void* mem);
void dbg_hit_on(bool cond, int slot = 0);
void dbg_mean_of(int64_t value, int slot = 0);
void dbg_correl_of(int64_t value1, int64_t value2, int slot = 0);
void dbg_print();
-using TimePoint = std::chrono::milliseconds::rep; // A value in milliseconds
+using TimePoint = std::chrono::milliseconds::rep; // A value in milliseconds
static_assert(sizeof(TimePoint) == sizeof(int64_t), "TimePoint should be 64 bits");
inline TimePoint now() {
- return std::chrono::duration_cast<std::chrono::milliseconds>
- (std::chrono::steady_clock::now().time_since_epoch()).count();
+ return std::chrono::duration_cast<std::chrono::milliseconds>(
+ std::chrono::steady_clock::now().time_since_epoch())
+ .count();
}
-enum SyncCout { IO_LOCK, IO_UNLOCK };
+enum SyncCout {
+ IO_LOCK,
+ IO_UNLOCK
+};
std::ostream& operator<<(std::ostream&, SyncCout);
#define sync_cout std::cout << IO_LOCK
#define sync_endl std::endl << IO_UNLOCK
-// align_ptr_up() : get the first aligned element of an array.
+// Get the first aligned element of an array.
// ptr must point to an array of size at least `sizeof(T) * N + alignment` bytes,
// where N is the number of elements in the array.
-template <uintptr_t Alignment, typename T>
-T* align_ptr_up(T* ptr)
-{
- static_assert(alignof(T) < Alignment);
+template<uintptr_t Alignment, typename T>
+T* align_ptr_up(T* ptr) {
+ static_assert(alignof(T) < Alignment);
- const uintptr_t ptrint = reinterpret_cast<uintptr_t>(reinterpret_cast<char*>(ptr));
- return reinterpret_cast<T*>(reinterpret_cast<char*>((ptrint + (Alignment - 1)) / Alignment * Alignment));
+ const uintptr_t ptrint = reinterpret_cast<uintptr_t>(reinterpret_cast<char*>(ptr));
+ return reinterpret_cast<T*>(
+ reinterpret_cast<char*>((ptrint + (Alignment - 1)) / Alignment * Alignment));
}
-// IsLittleEndian : true if and only if the binary is compiled on a little endian machine
-static inline const union { uint32_t i; char c[4]; } Le = { 0x01020304 };
+// True if and only if the binary is compiled on a little-endian machine
+static inline const union {
+ uint32_t i;
+ char c[4];
+} Le = {0x01020304};
static inline const bool IsLittleEndian = (Le.c[0] == 4);
-template <typename T, std::size_t MaxSize>
+template<typename T, std::size_t MaxSize>
class ValueList {
-public:
- std::size_t size() const { return size_; }
- void push_back(const T& value) { values_[size_++] = value; }
- const T* begin() const { return values_; }
- const T* end() const { return values_ + size_; }
- const T& operator[](int index) const { return values_[index]; }
+ public:
+ std::size_t size() const { return size_; }
+ void push_back(const T& value) { values_[size_++] = value; }
+ const T* begin() const { return values_; }
+ const T* end() const { return values_ + size_; }
+ const T& operator[](int index) const { return values_[index]; }
-private:
- T values_[MaxSize];
- std::size_t size_ = 0;
+ private:
+ T values_[MaxSize];
+ std::size_t size_ = 0;
};
-/// xorshift64star Pseudo-Random Number Generator
-/// This class is based on original code written and dedicated
-/// to the public domain by Sebastiano Vigna (2014).
-/// It has the following characteristics:
-///
-/// - Outputs 64-bit numbers
-/// - Passes Dieharder and SmallCrush test batteries
-/// - Does not require warm-up, no zeroland to escape
-/// - Internal state is a single 64-bit integer
-/// - Period is 2^64 - 1
-/// - Speed: 1.60 ns/call (Core i7 @3.40GHz)
-///
-/// For further analysis see
-/// <http://vigna.di.unimi.it/ftp/papers/xorshift.pdf>
+// xorshift64star Pseudo-Random Number Generator
+// This class is based on original code written and dedicated
+// to the public domain by Sebastiano Vigna (2014).
+// It has the following characteristics:
+//
+// - Outputs 64-bit numbers
+// - Passes Dieharder and SmallCrush test batteries
+// - Does not require warm-up, no zeroland to escape
+// - Internal state is a single 64-bit integer
+// - Period is 2^64 - 1
+// - Speed: 1.60 ns/call (Core i7 @3.40GHz)
+//
+// For further analysis see
+// <http://vigna.di.unimi.it/ftp/papers/xorshift.pdf>
class PRNG {
- uint64_t s;
+ uint64_t s;
- uint64_t rand64() {
+ uint64_t rand64() {
- s ^= s >> 12, s ^= s << 25, s ^= s >> 27;
- return s * 2685821657736338717LL;
- }
+ s ^= s >> 12, s ^= s << 25, s ^= s >> 27;
+ return s * 2685821657736338717LL;
+ }
-public:
- PRNG(uint64_t seed) : s(seed) { assert(seed); }
+ public:
+ PRNG(uint64_t seed) :
+ s(seed) {
+ assert(seed);
+ }
- template<typename T> T rand() { return T(rand64()); }
+ template<typename T>
+ T rand() {
+ return T(rand64());
+ }
- /// Special generator used to fast init magic numbers.
- /// Output values only have 1/8th of their bits set on average.
- template<typename T> T sparse_rand()
- { return T(rand64() & rand64() & rand64()); }
+ // Special generator used to fast init magic numbers.
+ // Output values only have 1/8th of their bits set on average.
+ template<typename T>
+ T sparse_rand() {
+ return T(rand64() & rand64() & rand64());
+ }
};
inline uint64_t mul_hi64(uint64_t a, uint64_t b) {
#endif
}
-/// Under Windows it is not possible for a process to run on more than one
-/// logical processor group. This usually means to be limited to use max 64
-/// cores. To overcome this, some special platform specific API should be
-/// called to set group affinity for each thread. Original code from Texel by
-/// Peter Ă–sterlund.
-
+// Under Windows it is not possible for a process to run on more than one
+// logical processor group. This usually means being limited to using max 64
+// cores. To overcome this, some special platform-specific API should be
+// called to set group affinity for each thread. Original code from Texel by
+// Peter Ă–sterlund.
namespace WinProcGroup {
- void bindThisThread(size_t idx);
+void bindThisThread(size_t idx);
}
namespace CommandLine {
- void init(int argc, char* argv[]);
+void init(int argc, char* argv[]);
- extern std::string binaryDirectory; // path of the executable directory
- extern std::string workingDirectory; // path of the working directory
+extern std::string binaryDirectory; // path of the executable directory
+extern std::string workingDirectory; // path of the working directory
}
-} // namespace Stockfish
+} // namespace Stockfish
-#endif // #ifndef MISC_H_INCLUDED
+#endif // #ifndef MISC_H_INCLUDED