- __m256i sum0 =
-
- #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 =
-
- #if defined(__MINGW32__) || defined(__MINGW64__)
- _mm256_loadu_si256
- #else
- _mm256_load_si256
- #endif
-
- (&reinterpret_cast<const __m256i*>(
- accumulation[perspectives[p]][0])[j * 2 + 1]);
-
- #if defined(__MINGW32__) || defined(__MINGW64__)
- _mm256_storeu_si256
- #else
- _mm256_store_si256
- #endif
-
- (&out[j], _mm256_permute4x64_epi64(_mm256_max_epi8(
+ __m256i sum0 = _mm256_loadA_si256(
+ &reinterpret_cast<const __m256i*>(accumulation[perspectives[p]][0])[j * 2 + 0]);
+ __m256i sum1 = _mm256_loadA_si256(
+ &reinterpret_cast<const __m256i*>(accumulation[perspectives[p]][0])[j * 2 + 1]);
+ _mm256_storeA_si256(&out[j], _mm256_permute4x64_epi64(_mm256_max_epi8(