X-Git-Url: https://git.sesse.net/?p=stockfish;a=blobdiff_plain;f=src%2Fnnue%2Fnnue_architecture.h;fp=src%2Fnnue%2Fnnue_architecture.h;h=e4c308cb267814c620d6015ba865ab2e7ab3c9b7;hp=65319b14bde9e03f326424e63e0e66929ec46875;hb=bfee35f930bac95b646b1821339f342c70aac2f6;hpb=487c21b1aa64dcc09dd95b845a66f39ae3c3754e

diff --git a/src/nnue/nnue_architecture.h b/src/nnue/nnue_architecture.h
index 65319b14..e4c308cb 100644
--- a/src/nnue/nnue_architecture.h
+++ b/src/nnue/nnue_architecture.h
@@ -21,18 +21,16 @@
 #ifndef NNUE_ARCHITECTURE_H_INCLUDED
 #define NNUE_ARCHITECTURE_H_INCLUDED
 
-#include <memory>
-
-#include "nnue_common.h"
+#include <cstdint>
+#include <cstring>
+#include <iosfwd>
 
 #include "features/half_ka_v2_hm.h"
-
-#include "layers/affine_transform_sparse_input.h"
 #include "layers/affine_transform.h"
+#include "layers/affine_transform_sparse_input.h"
 #include "layers/clipped_relu.h"
 #include "layers/sqr_clipped_relu.h"
-
-#include "../misc.h"
+#include "nnue_common.h"
 
 namespace Stockfish::Eval::NNUE {
 
@@ -40,98 +38,91 @@ namespace Stockfish::Eval::NNUE {
 using FeatureSet = Features::HalfKAv2_hm;
 
 // Number of input feature dimensions after conversion
-constexpr IndexType TransformedFeatureDimensions = 2048;
-constexpr IndexType PSQTBuckets = 8;
-constexpr IndexType LayerStacks = 8;
-
-struct Network
-{
-  static constexpr int FC_0_OUTPUTS = 15;
-  static constexpr int FC_1_OUTPUTS = 32;
-
-  Layers::AffineTransformSparseInput<TransformedFeatureDimensions, FC_0_OUTPUTS + 1> fc_0;
-  Layers::SqrClippedReLU<FC_0_OUTPUTS + 1> ac_sqr_0;
-  Layers::ClippedReLU<FC_0_OUTPUTS + 1> ac_0;
-  Layers::AffineTransform<FC_0_OUTPUTS * 2, FC_1_OUTPUTS> fc_1;
-  Layers::ClippedReLU<FC_1_OUTPUTS> ac_1;
-  Layers::AffineTransform<FC_1_OUTPUTS, 1> fc_2;
-
-  // Hash value embedded in the evaluation file
-  static constexpr std::uint32_t get_hash_value() {
-    // input slice hash
-    std::uint32_t hashValue = 0xEC42E90Du;
-    hashValue ^= TransformedFeatureDimensions * 2;
-
-    hashValue = decltype(fc_0)::get_hash_value(hashValue);
-    hashValue = decltype(ac_0)::get_hash_value(hashValue);
-    hashValue = decltype(fc_1)::get_hash_value(hashValue);
-    hashValue = decltype(ac_1)::get_hash_value(hashValue);
-    hashValue = decltype(fc_2)::get_hash_value(hashValue);
-
-    return hashValue;
-  }
-
-  // Read network parameters
-  bool read_parameters(std::istream& stream) {
-    return   fc_0.read_parameters(stream)
-          && ac_0.read_parameters(stream)
-          && fc_1.read_parameters(stream)
-          && ac_1.read_parameters(stream)
-          && fc_2.read_parameters(stream);
-  }
-
-  // Write network parameters
-  bool write_parameters(std::ostream& stream) const {
-    return   fc_0.write_parameters(stream)
-          && ac_0.write_parameters(stream)
-          && fc_1.write_parameters(stream)
-          && ac_1.write_parameters(stream)
-          && fc_2.write_parameters(stream);
-  }
-
-  std::int32_t propagate(const TransformedFeatureType* transformedFeatures)
-  {
-    struct alignas(CacheLineSize) Buffer
-    {
-      alignas(CacheLineSize) decltype(fc_0)::OutputBuffer fc_0_out;
-      alignas(CacheLineSize) decltype(ac_sqr_0)::OutputType ac_sqr_0_out[ceil_to_multiple<IndexType>(FC_0_OUTPUTS * 2, 32)];
-      alignas(CacheLineSize) decltype(ac_0)::OutputBuffer ac_0_out;
-      alignas(CacheLineSize) decltype(fc_1)::OutputBuffer fc_1_out;
-      alignas(CacheLineSize) decltype(ac_1)::OutputBuffer ac_1_out;
-      alignas(CacheLineSize) decltype(fc_2)::OutputBuffer fc_2_out;
-
-      Buffer()
-      {
-          std::memset(this, 0, sizeof(*this));
-      }
-    };
+constexpr IndexType TransformedFeatureDimensions = 2560;
+constexpr IndexType PSQTBuckets                  = 8;
+constexpr IndexType LayerStacks                  = 8;
+
+struct Network {
+    static constexpr int FC_0_OUTPUTS = 15;
+    static constexpr int FC_1_OUTPUTS = 32;
+
+    Layers::AffineTransformSparseInput<TransformedFeatureDimensions, FC_0_OUTPUTS + 1> fc_0;
+    Layers::SqrClippedReLU<FC_0_OUTPUTS + 1>                                           ac_sqr_0;
+    Layers::ClippedReLU<FC_0_OUTPUTS + 1>                                              ac_0;
+    Layers::AffineTransform<FC_0_OUTPUTS * 2, FC_1_OUTPUTS>                            fc_1;
+    Layers::ClippedReLU<FC_1_OUTPUTS>                                                  ac_1;
+    Layers::AffineTransform<FC_1_OUTPUTS, 1>                                           fc_2;
+
+    // Hash value embedded in the evaluation file
+    static constexpr std::uint32_t get_hash_value() {
+        // input slice hash
+        std::uint32_t hashValue = 0xEC42E90Du;
+        hashValue ^= TransformedFeatureDimensions * 2;
+
+        hashValue = decltype(fc_0)::get_hash_value(hashValue);
+        hashValue = decltype(ac_0)::get_hash_value(hashValue);
+        hashValue = decltype(fc_1)::get_hash_value(hashValue);
+        hashValue = decltype(ac_1)::get_hash_value(hashValue);
+        hashValue = decltype(fc_2)::get_hash_value(hashValue);
+
+        return hashValue;
+    }
+
+    // Read network parameters
+    bool read_parameters(std::istream& stream) {
+        return fc_0.read_parameters(stream) && ac_0.read_parameters(stream)
+            && fc_1.read_parameters(stream) && ac_1.read_parameters(stream)
+            && fc_2.read_parameters(stream);
+    }
+
+    // Write network parameters
+    bool write_parameters(std::ostream& stream) const {
+        return fc_0.write_parameters(stream) && ac_0.write_parameters(stream)
+            && fc_1.write_parameters(stream) && ac_1.write_parameters(stream)
+            && fc_2.write_parameters(stream);
+    }
+
+    std::int32_t propagate(const TransformedFeatureType* transformedFeatures) {
+        struct alignas(CacheLineSize) Buffer {
+            alignas(CacheLineSize) decltype(fc_0)::OutputBuffer fc_0_out;
+            alignas(CacheLineSize) decltype(ac_sqr_0)::OutputType
+              ac_sqr_0_out[ceil_to_multiple<IndexType>(FC_0_OUTPUTS * 2, 32)];
+            alignas(CacheLineSize) decltype(ac_0)::OutputBuffer ac_0_out;
+            alignas(CacheLineSize) decltype(fc_1)::OutputBuffer fc_1_out;
+            alignas(CacheLineSize) decltype(ac_1)::OutputBuffer ac_1_out;
+            alignas(CacheLineSize) decltype(fc_2)::OutputBuffer fc_2_out;
+
+            Buffer() { std::memset(this, 0, sizeof(*this)); }
+        };
 
 #if defined(__clang__) && (__APPLE__)
-    // workaround for a bug reported with xcode 12
-    static thread_local auto tlsBuffer = std::make_unique<Buffer>();
-    // Access TLS only once, cache result.
-    Buffer& buffer = *tlsBuffer;
+        // workaround for a bug reported with xcode 12
+        static thread_local auto tlsBuffer = std::make_unique<Buffer>();
+        // Access TLS only once, cache result.
+        Buffer& buffer = *tlsBuffer;
 #else
-    alignas(CacheLineSize) static thread_local Buffer buffer;
+        alignas(CacheLineSize) static thread_local Buffer buffer;
 #endif
 
-    fc_0.propagate(transformedFeatures, buffer.fc_0_out);
-    ac_sqr_0.propagate(buffer.fc_0_out, buffer.ac_sqr_0_out);
-    ac_0.propagate(buffer.fc_0_out, buffer.ac_0_out);
-    std::memcpy(buffer.ac_sqr_0_out + FC_0_OUTPUTS, buffer.ac_0_out, FC_0_OUTPUTS * sizeof(decltype(ac_0)::OutputType));
-    fc_1.propagate(buffer.ac_sqr_0_out, buffer.fc_1_out);
-    ac_1.propagate(buffer.fc_1_out, buffer.ac_1_out);
-    fc_2.propagate(buffer.ac_1_out, buffer.fc_2_out);
-
-    // buffer.fc_0_out[FC_0_OUTPUTS] is such that 1.0 is equal to 127*(1<<WeightScaleBits) in quantized form
-    // but we want 1.0 to be equal to 600*OutputScale
-    std::int32_t fwdOut = int(buffer.fc_0_out[FC_0_OUTPUTS]) * (600*OutputScale) / (127*(1<<WeightScaleBits));
-    std::int32_t outputValue = buffer.fc_2_out[0] + fwdOut;
-
-    return outputValue;
-  }
+        fc_0.propagate(transformedFeatures, buffer.fc_0_out);
+        ac_sqr_0.propagate(buffer.fc_0_out, buffer.ac_sqr_0_out);
+        ac_0.propagate(buffer.fc_0_out, buffer.ac_0_out);
+        std::memcpy(buffer.ac_sqr_0_out + FC_0_OUTPUTS, buffer.ac_0_out,
+                    FC_0_OUTPUTS * sizeof(decltype(ac_0)::OutputType));
+        fc_1.propagate(buffer.ac_sqr_0_out, buffer.fc_1_out);
+        ac_1.propagate(buffer.fc_1_out, buffer.ac_1_out);
+        fc_2.propagate(buffer.ac_1_out, buffer.fc_2_out);
+
+        // buffer.fc_0_out[FC_0_OUTPUTS] is such that 1.0 is equal to 127*(1<<WeightScaleBits) in
+        // quantized form, but we want 1.0 to be equal to 600*OutputScale
+        std::int32_t fwdOut =
+          int(buffer.fc_0_out[FC_0_OUTPUTS]) * (600 * OutputScale) / (127 * (1 << WeightScaleBits));
+        std::int32_t outputValue = buffer.fc_2_out[0] + fwdOut;
+
+        return outputValue;
+    }
 };
 
 }  // namespace Stockfish::Eval::NNUE
 
-#endif // #ifndef NNUE_ARCHITECTURE_H_INCLUDED
+#endif  // #ifndef NNUE_ARCHITECTURE_H_INCLUDED