X-Git-Url: https://git.sesse.net/?a=blobdiff_plain;f=src%2Fnnue%2Fnnue_feature_transformer.h;h=741d97cf1190c539bdcf2766ae6852bdefc52a12;hb=f193778446acc6e60d7f0f99c6eb01489f89e962;hp=2c0a0c6d3134b61270a9a16a3a1ae199176d9d07;hpb=e8d64af1230fdac65bb0da246df3e7abe82e0838;p=stockfish

diff --git a/src/nnue/nnue_feature_transformer.h b/src/nnue/nnue_feature_transformer.h
index 2c0a0c6d..741d97cf 100644
--- a/src/nnue/nnue_feature_transformer.h
+++ b/src/nnue/nnue_feature_transformer.h
@@ -84,18 +84,18 @@ namespace Stockfish::Eval::NNUE {
 
   #elif USE_MMX
   typedef __m64 vec_t;
-  typedef std::int32_t psqt_vec_t;
+  typedef __m64 psqt_vec_t;
   #define vec_load(a) (*(a))
   #define vec_store(a,b) *(a)=(b)
   #define vec_add_16(a,b) _mm_add_pi16(a,b)
   #define vec_sub_16(a,b) _mm_sub_pi16(a,b)
   #define vec_load_psqt(a) (*(a))
   #define vec_store_psqt(a,b) *(a)=(b)
-  #define vec_add_psqt_32(a,b) a+b
-  #define vec_sub_psqt_32(a,b) a-b
-  #define vec_zero_psqt() 0
+  #define vec_add_psqt_32(a,b) _mm_add_pi32(a,b)
+  #define vec_sub_psqt_32(a,b) _mm_sub_pi32(a,b)
+  #define vec_zero_psqt() _mm_setzero_si64()
   static constexpr IndexType NumRegs = 8;
-  static constexpr IndexType NumPsqtRegs = 8;
+  static constexpr IndexType NumPsqtRegs = 4;
 
   #elif USE_NEON
   typedef int16x8_t vec_t;
@@ -124,8 +124,6 @@ namespace Stockfish::Eval::NNUE {
     // Number of output dimensions for one side
     static constexpr IndexType HalfDimensions = TransformedFeatureDimensions;
 
-    static constexpr int LazyThreshold = 1400;
-
     #ifdef VECTOR
     static constexpr IndexType TileHeight = NumRegs * sizeof(vec_t) / 2;
     static constexpr IndexType PsqtTileHeight = NumPsqtRegs * sizeof(psqt_vec_t) / 4;
@@ -171,7 +169,7 @@ namespace Stockfish::Eval::NNUE {
     }
 
     // Convert input features
-    std::pair<std::int32_t, bool> transform(const Position& pos, OutputType* output, int bucket) const {
+    std::int32_t transform(const Position& pos, OutputType* output, int bucket) const {
       update_accumulator(pos, WHITE);
       update_accumulator(pos, BLACK);
 
@@ -184,9 +182,6 @@ namespace Stockfish::Eval::NNUE {
           - psqtAccumulation[static_cast<int>(perspectives[1])][bucket]
         ) / 2;
 
-      if (abs(psqt) > LazyThreshold * OutputScale)
-        return { psqt, true };
-
   #if defined(USE_AVX512)
       constexpr IndexType NumChunks = HalfDimensions / (SimdWidth * 2);
       static_assert(HalfDimensions % (SimdWidth * 2) == 0);
@@ -293,7 +288,7 @@ namespace Stockfish::Eval::NNUE {
       _mm_empty();
   #endif
 
-      return { psqt, false };
+      return psqt;
     }
 
    private: