jirayu_sri/stockfish
1
0
Fork 0
mirror of https://github.com/official-stockfish/Stockfish.git synced 2026-07-22 20:57:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add helpers for managing aligned memory

Browse Source 
Previously, we had two type aliases, LargePagePtr and AlignedPtr, which
required manually initializing the aligned memory for the pointer.

The new helpers:

- make_unique_aligned
- make_unique_large_page

are now available for allocating aligned memory (with large pages). They
behave similarly to std::make_unique, ensuring objects allocated with
these functions follow RAII.

The old approach had issues with initializing non-trivial types or
arrays of objects. The evaluation function of the network is now a
unique pointer to an array instead of an array of unique pointers.

Memory related functions have been moved into memory.h

Passed High Hash Pressure Test Non-Regression STC:
https://tests.stockfishchess.org/tests/view/665b2b36586058766677cfd2
LLR: 2.93 (-2.94,2.94) <-1.75,0.25>
Total: 476992 W: 122426 L: 122677 D: 231889
Ptnml(0-2): 1145, 51027, 134419, 50744, 1161

Failed Normal Non-Regression STC:
https://tests.stockfishchess.org/tests/view/665b2997586058766677cfc8
LLR: -2.94 (-2.94,2.94) <-1.75,0.25>
Total: 877312 W: 225233 L: 226395 D: 425684
Ptnml(0-2): 2110, 94642, 246239, 93630, 2035

Probably a fluke since there shouldn't be a real slowndown and it has also
passed the high hash pressure test.

closes https://github.com/official-stockfish/Stockfish/pull/5332

No functional change
This commit is contained in:
Disservin
2024-06-03 23:11:59 +02:00
parent a2a7edf4c8
commit 00a28ae325
11 changed files with 492 additions and 312 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/nnue/network.cpp
+27 -50
View File
@@ -20,7 +20,6 @@
#include <cmath>
#include <cstdlib>
#include <cstring>
#include <fstream>
#include <iostream>
#include <memory>
@@ -30,6 +29,7 @@
#include "../evaluate.h"
#include "../incbin/incbin.h"
#include "../memory.h"
#include "../misc.h"
#include "../position.h"
#include "../types.h"
@@ -86,23 +86,6 @@ namespace Stockfish::Eval::NNUE {
namespace Detail {
// Initialize the evaluation function parameters
template<typename T>
void initialize(AlignedPtr<T>& pointer) {
pointer.reset(reinterpret_cast<T*>(std_aligned_alloc(alignof(T), sizeof(T))));
std::memset(pointer.get(), 0, sizeof(T));
}
template<typename T>
void initialize(LargePagePtr<T>& pointer) {
static_assert(alignof(T) <= 4096,
"aligned_large_pages_alloc() may fail for such a big alignment requirement of T");
pointer.reset(reinterpret_cast<T*>(aligned_large_pages_alloc(sizeof(T))));
std::memset(pointer.get(), 0, sizeof(T));
}
// Read evaluation function parameters
template<typename T>
bool read_parameters(std::istream& stream, T& reference) {
@@ -128,19 +111,17 @@ template<typename Arch, typename Transformer>
Network<Arch, Transformer>::Network(const Network<Arch, Transformer>& other) :
evalFile(other.evalFile),
embeddedType(other.embeddedType) {
if (other.featureTransformer)
{
Detail::initialize(featureTransformer);
*featureTransformer = *other.featureTransformer;
}
featureTransformer = make_unique_large_page<Transformer>(*other.featureTransformer);
network = make_unique_aligned<Arch[]>(LayerStacks);
if (!other.network)
return;
for (std::size_t i = 0; i < LayerStacks; ++i)
{
if (other.network[i])
{
Detail::initialize(network[i]);
*(network[i]) = *(other.network[i]);
}
}
network[i] = other.network[i];
}
template<typename Arch, typename Transformer>
@@ -150,18 +131,15 @@ Network<Arch, Transformer>::operator=(const Network<Arch, Transformer>& other) {
embeddedType = other.embeddedType;
if (other.featureTransformer)
{
Detail::initialize(featureTransformer);
*featureTransformer = *other.featureTransformer;
}
featureTransformer = make_unique_large_page<Transformer>(*other.featureTransformer);
network = make_unique_aligned<Arch[]>(LayerStacks);
if (!other.network)
return *this;
for (std::size_t i = 0; i < LayerStacks; ++i)
{
if (other.network[i])
{
Detail::initialize(network[i]);
*(network[i]) = *(other.network[i]);
}
}
network[i] = other.network[i];
return *this;
}
@@ -253,7 +231,7 @@ Value Network<Arch, Transformer>::evaluate(const Position&
const int bucket = (pos.count<ALL_PIECES>() - 1) / 4;
const auto psqt = featureTransformer->transform(pos, cache, transformedFeatures, bucket);
const auto positional = network[bucket]->propagate(transformedFeatures);
const auto positional = network[bucket].propagate(transformedFeatures);
if (complexity)
*complexity = std::abs(psqt - positional) / OutputScale;
@@ -292,11 +270,11 @@ void Network<Arch, Transformer>::verify(std::string evalfilePath) const {
exit(EXIT_FAILURE);
}
size_t size = sizeof(*featureTransformer) + sizeof(*network) * LayerStacks;
size_t size = sizeof(*featureTransformer) + sizeof(Arch) * LayerStacks;
sync_cout << "info string NNUE evaluation using " << evalfilePath << " ("
<< size / (1024 * 1024) << "MiB, (" << featureTransformer->InputDimensions << ", "
<< network[0]->TransformedFeatureDimensions << ", " << network[0]->FC_0_OUTPUTS
<< ", " << network[0]->FC_1_OUTPUTS << ", 1))" << sync_endl;
<< network[0].TransformedFeatureDimensions << ", " << network[0].FC_0_OUTPUTS << ", "
<< network[0].FC_1_OUTPUTS << ", 1))" << sync_endl;
}
@@ -333,7 +311,7 @@ Network<Arch, Transformer>::trace_evaluate(const Position&
{
const auto materialist =
featureTransformer->transform(pos, cache, transformedFeatures, bucket);
const auto positional = network[bucket]->propagate(transformedFeatures);
const auto positional = network[bucket].propagate(transformedFeatures);
t.psqt[bucket] = static_cast<Value>(materialist / OutputScale);
t.positional[bucket] = static_cast<Value>(positional / OutputScale);
@@ -386,9 +364,8 @@ void Network<Arch, Transformer>::load_internal() {
template<typename Arch, typename Transformer>
void Network<Arch, Transformer>::initialize() {
Detail::initialize(featureTransformer);
for (std::size_t i = 0; i < LayerStacks; ++i)
Detail::initialize(network[i]);
featureTransformer = make_unique_large_page<Transformer>();
network = make_unique_aligned<Arch[]>(LayerStacks);
}
@@ -455,7 +432,7 @@ bool Network<Arch, Transformer>::read_parameters(std::istream& stream,
return false;
for (std::size_t i = 0; i < LayerStacks; ++i)
{
if (!Detail::read_parameters(stream, *(network[i])))
if (!Detail::read_parameters(stream, network[i]))
return false;
}
return stream && stream.peek() == std::ios::traits_type::eof();
@@ -471,7 +448,7 @@ bool Network<Arch, Transformer>::write_parameters(std::ostream& stream,
return false;
for (std::size_t i = 0; i < LayerStacks; ++i)
{
if (!Detail::write_parameters(stream, *(network[i])))
if (!Detail::write_parameters(stream, network[i]))
return false;
}
return bool(stream);