opelly/Stockfish
1
0
Fork 0
mirror of https://github.com/opelly27/Stockfish.git synced 2026-05-20 05:07:46 +00:00
Code Issues Packages Projects Releases Wiki Activity

add clang-format

Browse Source 
This introduces clang-format to enforce a consistent code style for Stockfish.

Having a documented and consistent style across the code will make contributing easier
for new developers, and will make larger changes to the codebase easier to make.

To facilitate formatting, this PR includes a Makefile target (`make format`) to format the code,
this requires clang-format (version 17 currently) to be installed locally.

Installing clang-format is straightforward on most OS and distros
(e.g. with https://apt.llvm.org/, brew install clang-format, etc), as this is part of quite commonly
used suite of tools and compilers (llvm / clang).

Additionally, a CI action is present that will verify if the code requires formatting,
and comment on the PR as needed. Initially, correct formatting is not required, it will be
done by maintainers as part of the merge or in later commits, but obviously this is encouraged.

fixes https://github.com/official-stockfish/Stockfish/issues/3608
closes https://github.com/official-stockfish/Stockfish/pull/4790

Co-Authored-By: Joost VandeVondele <Joost.VandeVondele@gmail.com>
This commit is contained in:
Disservin
2023-10-21 11:40:56 +02:00
committed by Joost VandeVondele
parent 8366ec48ae
commit 2d0237db3f
49 changed files with 6403 additions and 6197 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/nnue/layers/sqr_clipped_relu.h
+43 -48
View File
@@ -29,80 +29,75 @@
namespace Stockfish::Eval::NNUE::Layers {
// Clipped ReLU
template <IndexType InDims>
class SqrClippedReLU {
// Clipped ReLU
template<IndexType InDims>
class SqrClippedReLU {
public:
// Input/output type
using InputType = std::int32_t;
using InputType = std::int32_t;
using OutputType = std::uint8_t;
// Number of input/output dimensions
static constexpr IndexType InputDimensions = InDims;
static constexpr IndexType InputDimensions = InDims;
static constexpr IndexType OutputDimensions = InputDimensions;
static constexpr IndexType PaddedOutputDimensions =
ceil_to_multiple<IndexType>(OutputDimensions, 32);
ceil_to_multiple<IndexType>(OutputDimensions, 32);
using OutputBuffer = OutputType[PaddedOutputDimensions];
// Hash value embedded in the evaluation file
static constexpr std::uint32_t get_hash_value(std::uint32_t prevHash) {
std::uint32_t hashValue = 0x538D24C7u;
hashValue += prevHash;
return hashValue;
std::uint32_t hashValue = 0x538D24C7u;
hashValue += prevHash;
return hashValue;
}
// Read network parameters
bool read_parameters(std::istream&) {
return true;
}
bool read_parameters(std::istream&) { return true; }
// Write network parameters
bool write_parameters(std::ostream&) const {
return true;
}
bool write_parameters(std::ostream&) const { return true; }
// Forward propagation
void propagate(
const InputType* input, OutputType* output) const {
void propagate(const InputType* input, OutputType* output) const {
#if defined(USE_SSE2)
constexpr IndexType NumChunks = InputDimensions / 16;
#if defined(USE_SSE2)
constexpr IndexType NumChunks = InputDimensions / 16;
static_assert(WeightScaleBits == 6);
const auto in = reinterpret_cast<const __m128i*>(input);
const auto out = reinterpret_cast<__m128i*>(output);
for (IndexType i = 0; i < NumChunks; ++i) {
__m128i words0 = _mm_packs_epi32(
_mm_load_si128(&in[i * 4 + 0]),
_mm_load_si128(&in[i * 4 + 1]));
__m128i words1 = _mm_packs_epi32(
_mm_load_si128(&in[i * 4 + 2]),
_mm_load_si128(&in[i * 4 + 3]));
static_assert(WeightScaleBits == 6);
const auto in = reinterpret_cast<const __m128i*>(input);
const auto out = reinterpret_cast<__m128i*>(output);
for (IndexType i = 0; i < NumChunks; ++i)
{
__m128i words0 =
_mm_packs_epi32(_mm_load_si128(&in[i * 4 + 0]), _mm_load_si128(&in[i * 4 + 1]));
__m128i words1 =
_mm_packs_epi32(_mm_load_si128(&in[i * 4 + 2]), _mm_load_si128(&in[i * 4 + 3]));
// We shift by WeightScaleBits * 2 = 12 and divide by 128
// which is an additional shift-right of 7, meaning 19 in total.
// MulHi strips the lower 16 bits so we need to shift out 3 more to match.
words0 = _mm_srli_epi16(_mm_mulhi_epi16(words0, words0), 3);
words1 = _mm_srli_epi16(_mm_mulhi_epi16(words1, words1), 3);
// We shift by WeightScaleBits * 2 = 12 and divide by 128
// which is an additional shift-right of 7, meaning 19 in total.
// MulHi strips the lower 16 bits so we need to shift out 3 more to match.
words0 = _mm_srli_epi16(_mm_mulhi_epi16(words0, words0), 3);
words1 = _mm_srli_epi16(_mm_mulhi_epi16(words1, words1), 3);
_mm_store_si128(&out[i], _mm_packs_epi16(words0, words1));
}
constexpr IndexType Start = NumChunks * 16;
_mm_store_si128(&out[i], _mm_packs_epi16(words0, words1));
}
constexpr IndexType Start = NumChunks * 16;
#else
constexpr IndexType Start = 0;
#endif
#else
constexpr IndexType Start = 0;
#endif
for (IndexType i = Start; i < InputDimensions; ++i) {
output[i] = static_cast<OutputType>(
// Really should be /127 but we need to make it fast so we right shift
// by an extra 7 bits instead. Needs to be accounted for in the trainer.
std::min(127ll, ((long long)input[i] * input[i]) >> (2 * WeightScaleBits + 7)));
}
for (IndexType i = Start; i < InputDimensions; ++i)
{
output[i] = static_cast<OutputType>(
// Really should be /127 but we need to make it fast so we right shift
// by an extra 7 bits instead. Needs to be accounted for in the trainer.
std::min(127ll, ((long long) input[i] * input[i]) >> (2 * WeightScaleBits + 7)));
}
}
};
};
} // namespace Stockfish::Eval::NNUE::Layers
#endif // NNUE_LAYERS_SQR_CLIPPED_RELU_H_INCLUDED
#endif // NNUE_LAYERS_SQR_CLIPPED_RELU_H_INCLUDED