Make PGO builds deterministic again

some environment dependent execution (e.g. pid) were being std::hash'ed, and
net filenames put in unordered maps.  Also uses sprintf instead of
std::to_string.  Depending on precise content, this could lead to different
PGO'ed binaries. This is mitigated by using a basic hash function.

This also fixes a potential issue in net filename generation, in cases where
std::hash would use invocation dependent salt, which is not the cases today for
typical std libraries.

Closes https://github.com/official-stockfish/Stockfish/pull/6562

No functional change
This commit is contained in:
anematode
2026-01-22 19:15:17 +01:00
committed by Joost VandeVondele
parent f61d4317a3
commit c0f245303b
4 changed files with 50 additions and 36 deletions
+28 -13
View File
@@ -34,6 +34,7 @@
#include <memory>
#include <string>
#include <string_view>
#include <type_traits>
#include <vector>
#define stringify2(x) #x
@@ -305,24 +306,38 @@ inline uint64_t mul_hi64(uint64_t a, uint64_t b) {
#endif
}
template<typename T>
inline void hash_combine(std::size_t& seed, const T& v) {
std::hash<T> hasher;
seed ^= hasher(v) + 0x9e3779b9 + (seed << 6) + (seed >> 2);
}
template<>
inline void hash_combine(std::size_t& seed, const std::size_t& v) {
seed ^= v + 0x9e3779b9 + (seed << 6) + (seed >> 2);
inline std::uint64_t hash_bytes(const char* data, std::size_t size) {
// FNV-1a 64-bit
const char* p = data;
std::uint64_t h = 14695981039346656037ull;
for (std::size_t i = 0; i < size; ++i)
h = (h ^ p[i]) * 1099511628211ull;
return h;
}
template<typename T>
inline std::size_t get_raw_data_hash(const T& value) {
return std::hash<std::string_view>{}(
std::string_view(reinterpret_cast<const char*>(&value), sizeof(value)));
// We must have no padding bytes because we're reinterpreting as char
static_assert(std::has_unique_object_representations<T>());
return static_cast<std::size_t>(
hash_bytes(reinterpret_cast<const char*>(&value), sizeof(value)));
}
template<typename T>
inline void hash_combine(std::size_t& seed, const T& v) {
std::size_t x;
// For primitive types we avoid using the default hasher, which may be
// nondeterministic across program invocations
if constexpr (std::is_integral<T>())
x = v;
else
x = std::hash<T>{}(v);
seed ^= x + 0x9e3779b9 + (seed << 6) + (seed >> 2);
}
inline std::uint64_t hash_string(const std::string& sv) { return hash_bytes(sv.data(), sv.size()); }
template<std::size_t Capacity>
class FixedString {
public:
@@ -450,7 +465,7 @@ void move_to_front(std::vector<T>& vec, Predicate pred) {
template<std::size_t N>
struct std::hash<Stockfish::FixedString<N>> {
std::size_t operator()(const Stockfish::FixedString<N>& fstr) const noexcept {
return std::hash<std::string_view>{}((std::string_view) fstr);
return Stockfish::hash_bytes(fstr.data(), fstr.size());
}
};