X-Git-Url: https://git.sesse.net/?p=stockfish;a=blobdiff_plain;f=src%2Fnnue%2Fnnue_feature_transformer.h;h=1cfebbe4cbe80425f65aa3e3012594494d615294;hp=f899d7617655cf086274aeee8ecb021434c06bca;hb=651ec3b31ee68db50f38ccd8fcdedbd6673cd9ed;hpb=27b593a94477a821f80a041320683f805114d4a3

diff --git a/src/nnue/nnue_feature_transformer.h b/src/nnue/nnue_feature_transformer.h
index f899d761..1cfebbe4 100644
--- a/src/nnue/nnue_feature_transformer.h
+++ b/src/nnue/nnue_feature_transformer.h
@@ -110,12 +110,36 @@ namespace Eval::NNUE {
         auto out = reinterpret_cast<__m256i*>(&output[offset]);
         for (IndexType j = 0; j < kNumChunks; ++j) {
           __m256i sum0 =
-            _mm256_load_si256(&reinterpret_cast<const __m256i*>(
+
+  #if defined(__MINGW32__) || defined(__MINGW64__)
+            // HACK: Use _mm256_loadu_si256() instead of _mm256_load_si256. Because the binary
+            //       compiled with g++ in MSYS2 crashes here because the output memory is not aligned
+            //       even though alignas is specified.
+            _mm256_loadu_si256
+  #else
+            _mm256_load_si256
+  #endif
+
+            (&reinterpret_cast<const __m256i*>(
               accumulation[perspectives[p]][0])[j * 2 + 0]);
           __m256i sum1 =
-            _mm256_load_si256(&reinterpret_cast<const __m256i*>(
+
+  #if defined(__MINGW32__) || defined(__MINGW64__)
+            _mm256_loadu_si256
+  #else
+            _mm256_load_si256
+  #endif
+
+            (&reinterpret_cast<const __m256i*>(
               accumulation[perspectives[p]][0])[j * 2 + 1]);
-          _mm256_store_si256(&out[j], _mm256_permute4x64_epi64(_mm256_max_epi8(
+
+  #if defined(__MINGW32__) || defined(__MINGW64__)
+          _mm256_storeu_si256
+  #else
+          _mm256_store_si256
+  #endif
+
+          (&out[j], _mm256_permute4x64_epi64(_mm256_max_epi8(
               _mm256_packs_epi16(sum0, sum1), kZero), kControl));
         }
 
@@ -178,7 +202,11 @@ namespace Eval::NNUE {
           auto column = reinterpret_cast<const __m256i*>(&weights_[offset]);
           constexpr IndexType kNumChunks = kHalfDimensions / (kSimdWidth / 2);
           for (IndexType j = 0; j < kNumChunks; ++j) {
+  #if defined(__MINGW32__) || defined(__MINGW64__)
+            _mm256_storeu_si256(&accumulation[j], _mm256_add_epi16(_mm256_loadu_si256(&accumulation[j]), column[j]));
+  #else
             accumulation[j] = _mm256_add_epi16(accumulation[j], column[j]);
+  #endif
           }
 
   #elif defined(USE_SSE2)