HCha/Stockfish
1
0
Fork 0
mirror of https://github.com/HChaZZY/Stockfish.git synced 2025-12-25 03:26:24 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge latest changes from nodchip repo

Browse Source
This commit is contained in:
Dariusz Orzechowski
2020-07-20 13:19:25 +02:00
parent 76d8f6128a c0e1235fef
commit 871e6b8c83
5 changed files with 187 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

89
src/Makefile
View File

@@ -73,6 +73,7 @@ endif
# sse42 = yes/no --- -msse4.2 --- Use Intel Streaming SIMD Extensions 4.2
# avx2 = yes/no --- -mavx2 --- Use Intel Advanced Vector Extensions 2
# pext = yes/no --- -DUSE_PEXT --- Use pext x86_64 asm-instruction
# avx512 = yes/no --- -mavx512vbmi --- Use Intel Advanced Vector Extensions 512
#
# Note that Makefile is space sensitive, so when adding new architectures
# or modifying existing flags, you have to make sure there are no extra spaces
@@ -86,11 +87,13 @@ bits = 64
prefetch = no
popcnt = no
sse = no
sse3 = no
ssse3 = no
sse41 = no
sse42 = no
avx2 = no
pext = no
avx512 = no
### 2.2 Architecture specific
ifeq ($(ARCH),general-32)
@@ -120,13 +123,6 @@ ifeq ($(ARCH),x86-64)
sse = yes
endif
ifeq ($(ARCH),x86-64-ssse3)
arch = x86_64
prefetch = yes
sse = yes
ssse3 = yes
endif
ifeq ($(ARCH),x86-64-modern)
arch = x86_64
prefetch = yes
@@ -134,10 +130,36 @@ ifeq ($(ARCH),x86-64-modern)
sse = yes
endif
ifeq ($(ARCH),x86-64-sse3)
arch = x86_64
prefetch = yes
sse = yes
sse3 = yes
ssse3 = yes
endif
ifeq ($(ARCH),x86-64-sse3-popcnt)
arch = x86_64
prefetch = yes
popcnt = yes
sse = yes
sse3 = yes
ssse3 = yes
endif
ifeq ($(ARCH),x86-64-ssse3)
arch = x86_64
prefetch = yes
sse = yes
sse3 = yes
ssse3 = yes
endif
ifeq ($(ARCH),x86-64-sse41)
arch = x86_64
prefetch = yes
sse = yes
sse3 = yes
ssse3 = yes
sse41 = yes
endif
@@ -147,6 +169,7 @@ ifeq ($(ARCH),x86-64-sse42)
prefetch = yes
popcnt = yes
sse = yes
sse3 = yes
ssse3 = yes
sse41 = yes
sse42 = yes
@@ -158,6 +181,7 @@ ifeq ($(ARCH),x86-64-avx2)
prefetch = yes
popcnt = yes
sse = yes
sse3 = yes
ssse3 = yes
sse41 = yes
sse42 = yes
@@ -169,6 +193,7 @@ ifeq ($(ARCH),x86-64-bmi2)
prefetch = yes
popcnt = yes
sse = yes
sse3 = yes
ssse3 = yes
sse41 = yes
sse42 = yes
@@ -176,6 +201,21 @@ ifeq ($(ARCH),x86-64-bmi2)
pext = yes
endif
ifeq ($(ARCH),x86-64-avx512)
arch = x86_64
bits = 64
prefetch = yes
popcnt = yes
sse = yes
sse3 = yes
ssse3 = yes
sse41 = yes
sse42 = yes
avx2 = yes
pext = yes
avx512 = yes
endif
ifeq ($(ARCH),armv7)
arch = armv7
prefetch = yes
@@ -394,12 +434,11 @@ endif
### 3.6 popcnt
ifeq ($(popcnt),yes)
ifeq ($(arch),$(filter $(arch),ppc64 armv8-a))
CXXFLAGS += -DUSE_POPCNT
else ifeq ($(comp),icc)
CXXFLAGS += -msse3 -DUSE_POPCNT
else
CXXFLAGS += -msse3 -mpopcnt -DUSE_POPCNT
CXXFLAGS += -DUSE_POPCNT
ifneq ($(arch),$(filter $(arch),ppc64 armv8-a))
ifeq ($(comp),$(filter $(comp),gcc clang mingw msys2))
CXXFLAGS += -mpopcnt
endif
endif
endif
@@ -410,6 +449,13 @@ ifeq ($(avx2),yes)
endif
endif
ifeq ($(avx512),yes)
CXXFLAGS += -DUSE_AVX512
ifeq ($(comp),$(filter $(comp),gcc clang mingw msys2))
CXXFLAGS += -mavx512bw
endif
endif
ifeq ($(sse42),yes)
CXXFLAGS += -DUSE_SSE42
ifeq ($(comp),$(filter $(comp),gcc clang mingw msys2))
@@ -431,6 +477,13 @@ ifeq ($(ssse3),yes)
endif
endif
ifeq ($(sse3),yes)
CXXFLAGS += -DUSE_SSE3
ifeq ($(comp),$(filter $(comp),gcc clang mingw msys2))
CXXFLAGS += -msse3
endif
endif
ifeq ($(arch),x86_64)
CXXFLAGS += -DUSE_SSE2
endif
@@ -485,18 +538,22 @@ help:
@echo "Supported targets:"
@echo ""
@echo "build > Standard build"
@echo "profile-build > PGO build"
@echo "profile-build > Standard build with PGO"
@echo "strip > Strip executable"
@echo "install > Install executable"
@echo "clean > Clean up"
@echo ""
@echo "Supported archs:"
@echo ""
@echo "x86-64-avx512 > x86 64-bit with avx512 support"
@echo "x86-64-bmi2 > x86 64-bit with bmi2 support"
@echo "x86-64-avx2 > x86 64-bit with avx2 support"
@echo "x86-64-sse42 > x86 64-bit with sse42 support"
@echo "x86-64-sse41 > x86 64-bit with sse41 support"
@echo "x86-64-ssse3 > x86 64-bit with ssse3 support"
@echo "x86-64-sse3-popcnt > x86 64-bit with sse3 and popcnt support"
@echo "x86-64-sse3 > x86 64-bit with sse3 support"
@echo "x86-64-modern > x86 64-bit with popcnt support"
@echo "x86-64 > x86 64-bit generic"
@echo "x86-32 > x86 32-bit (also enables SSE)"
@echo "x86-32-old > x86 32-bit fall back for old hardware"
@@ -593,11 +650,13 @@ config-sanity:
@echo "prefetch: '$(prefetch)'"
@echo "popcnt: '$(popcnt)'"
@echo "sse: '$(sse)'"
@echo "sse3: '$(sse3)'"
@echo "ssse3: '$(ssse3)'"
@echo "sse41: '$(sse41)'"
@echo "sse42: '$(sse42)'"
@echo "avx2: '$(avx2)'"
@echo "pext: '$(pext)'"
@echo "avx512: '$(avx512)'"
@echo ""
@echo "Flags:"
@echo "CXX: $(CXX)"
@@ -616,11 +675,13 @@ config-sanity:
@test "$(prefetch)" = "yes" || test "$(prefetch)" = "no"
@test "$(popcnt)" = "yes" || test "$(popcnt)" = "no"
@test "$(sse)" = "yes" || test "$(sse)" = "no"
@test "$(sse3)" = "yes" || test "$(sse3)" = "no"
@test "$(ssse3)" = "yes" || test "$(ssse3)" = "no"
@test "$(sse41)" = "yes" || test "$(sse41)" = "no"
@test "$(sse42)" = "yes" || test "$(sse42)" = "no"
@test "$(avx2)" = "yes" || test "$(avx2)" = "no"
@test "$(pext)" = "yes" || test "$(pext)" = "no"
@test "$(avx512)" = "yes" || test "$(avx512)" = "no"
@test "$(comp)" = "gcc" || test "$(comp)" = "icc" || test "$(comp)" = "mingw" || test "$(comp)" = "clang"
$(EXE): $(OBJS)

52
src/nnue/layers/affine_transform.h
View File

@@ -67,7 +67,12 @@ namespace Eval::NNUE::Layers {
transformed_features, buffer + kSelfBufferSize);
const auto output = reinterpret_cast<OutputType*>(buffer);
#if defined(USE_AVX2)
#if defined(USE_AVX512)
constexpr IndexType kNumChunks = kPaddedInputDimensions / (kSimdWidth * 2);
const __m512i kOnes = _mm512_set1_epi16(1);
const auto input_vector = reinterpret_cast<const __m512i*>(input);
#elif defined(USE_AVX2)
constexpr IndexType kNumChunks = kPaddedInputDimensions / kSimdWidth;
const __m256i kOnes = _mm256_set1_epi16(1);
const auto input_vector = reinterpret_cast<const __m256i*>(input);
@@ -85,8 +90,47 @@ namespace Eval::NNUE::Layers {
for (IndexType i = 0; i < kOutputDimensions; ++i) {
const IndexType offset = i * kPaddedInputDimensions;
#if defined(USE_AVX2)
__m256i sum = _mm256_set_epi32(0, 0, 0, 0, 0, 0, 0, biases_[i]);
#if defined(USE_AVX512)
__m512i sum = _mm512_setzero_si512();
const auto row = reinterpret_cast<const __m512i*>(&weights_[offset]);
for (IndexType j = 0; j < kNumChunks; ++j) {
#if defined(__MINGW32__) || defined(__MINGW64__)
__m512i product = _mm512_maddubs_epi16(_mm512_loadu_si512(&input_vector[j]), _mm512_load_si512(&row[j]));
#else
__m512i product = _mm512_maddubs_epi16(_mm512_load_si512(&input_vector[j]), _mm512_load_si512(&row[j]));
#endif
product = _mm512_madd_epi16(product, kOnes);
sum = _mm512_add_epi32(sum, product);
}
output[i] = _mm512_reduce_add_epi32(sum) + biases_[i];
// Note: Changing kMaxSimdWidth from 32 to 64 breaks loading existing networks.
// As a result kPaddedInputDimensions may not be an even multiple of 64(512bit)
// and we have to do one more 256bit chunk.
if (kPaddedInputDimensions != kNumChunks * kSimdWidth * 2)
{
const auto iv_256 = reinterpret_cast<const __m256i*>(input);
const auto row_256 = reinterpret_cast<const __m256i*>(&weights_[offset]);
int j = kNumChunks * 2;
#if defined(__MINGW32__) || defined(__MINGW64__) // See HACK comment below in AVX2.
__m256i sum256 = _mm256_maddubs_epi16(_mm256_loadu_si256(&iv_256[j]), _mm256_load_si256(&row_256[j]));
#else
__m256i sum256 = _mm256_maddubs_epi16(_mm256_load_si256(&iv_256[j]), _mm256_load_si256(&row_256[j]));
#endif
sum256 = _mm256_madd_epi16(sum256, _mm256_set1_epi16(1));
sum256 = _mm256_hadd_epi32(sum256, sum256);
sum256 = _mm256_hadd_epi32(sum256, sum256);
const __m128i lo = _mm256_extracti128_si256(sum256, 0);
const __m128i hi = _mm256_extracti128_si256(sum256, 1);
output[i] += _mm_cvtsi128_si32(lo) + _mm_cvtsi128_si32(hi);
}
#elif defined(USE_AVX2)
__m256i sum = _mm256_setzero_si256();
const auto row = reinterpret_cast<const __m256i*>(&weights_[offset]);
for (IndexType j = 0; j < kNumChunks; ++j) {
__m256i product = _mm256_maddubs_epi16(
@@ -108,7 +152,7 @@ namespace Eval::NNUE::Layers {
sum = _mm256_hadd_epi32(sum, sum);
const __m128i lo = _mm256_extracti128_si256(sum, 0);
const __m128i hi = _mm256_extracti128_si256(sum, 1);
output[i] = _mm_cvtsi128_si32(lo) + _mm_cvtsi128_si32(hi);
output[i] = _mm_cvtsi128_si32(lo) + _mm_cvtsi128_si32(hi) + biases_[i];
#elif defined(USE_SSSE3)
__m128i sum = _mm_cvtsi32_si128(biases_[i]);

2
src/ucioption.cpp
View File

@@ -95,7 +95,7 @@ void init(OptionsMap& o) {
o["Syzygy50MoveRule"] << Option(true);
o["SyzygyProbeLimit"] << Option(7, 0, 7);
o["Use NNUE"] << Option(false, on_use_nnue);
o["EvalFile"] << Option("nn.bin", on_eval_file);
o["EvalFile"] << Option("./eval/nn.bin", on_eval_file);
}