Gcc misoptimises sse function

I'm converting a project to compile with gcc from clang and I've ran into a issue with a function that uses sse functions:

void dodgy_function(      const short* lows,      const short* highs,      short* mins,      short* maxs,      int its  )  {      __m128i v00[2] = { _mm_setzero_si128(), _mm_setzero_si128() };       __m128i v10[2] = { _mm_setzero_si128(), _mm_setzero_si128() };        for (int i = 0; i < its; ++i) {          reinterpret_cast<short*>(v00)[i] = lows[i];          reinterpret_cast<short*>(v10)[i] = highs[i];      }        reinterpret_cast<short*>(v00)[its] = reinterpret_cast<short*>(v00)[its - 1];      reinterpret_cast<short*>(v10)[its] = reinterpret_cast<short*>(v10)[its - 1];        __m128i v01[2] = {_mm_setzero_si128(), _mm_setzero_si128()};      __m128i v11[2] = {_mm_setzero_si128(), _mm_setzero_si128()};        __m128i min[2];      __m128i max[2];        min[0] = _mm_min_epi16(_mm_max_epi16(v11[0], v01[0]), _mm_min_epi16(v10[0], v00[0]));      max[0] = _mm_max_epi16(_mm_max_epi16(v11[0], v01[0]), _mm_max_epi16(v10[0], v00[0]));        min[1] = _mm_min_epi16(_mm_min_epi16(v11[1], v01[1]), _mm_min_epi16(v10[1], v00[1]));       max[1] = _mm_max_epi16(_mm_max_epi16(v11[1], v01[1]), _mm_max_epi16(v10[1], v00[1]));        reinterpret_cast<__m128i*>(mins)[0] = _mm_min_epi16(reinterpret_cast<__m128i*>(mins)[0], min[0]);      reinterpret_cast<__m128i*>(maxs)[0] = _mm_max_epi16(reinterpret_cast<__m128i*>(maxs)[0], max[0]);        reinterpret_cast<__m128i*>(mins)[1] = _mm_min_epi16(reinterpret_cast<__m128i*>(mins)[1], min[1]);      reinterpret_cast<__m128i*>(maxs)[1] = _mm_max_epi16(reinterpret_cast<__m128i*>(maxs)[1], max[1]);  }  

Now with clang it gives it gives me the expected output but in gcc it prints all zeros: godbolt link

Playing around I discovered that gcc gives me the right results when I compile with -O1 but goes wrong with -O2 and -O3, suggesting the optimiser is going awry. Is there something particularly wrong I'm doing that would cause this behavior?

As a workaround I can wrap things up in a union and gcc will then give me the right result, but that feels a little icky: godbolt link 2

Any ideas?

https://stackoverflow.com/questions/66606202/gcc-misoptimises-sse-function March 13, 2021 at 03:39AM