Discrepancy between eager and inductor of CPU AMP when running gt about pytorch HOT 2 CLOSED

cpp_fused_gt_0 = async_compile.cpp_pybinding(['const bfloat16*', 'bool*'], '''
#include "/tmp/torchinductor_leslie/sk/cskh5dx62fglpphcrl6723dnmowdabouerrzy3dmqcngbxwfa7bv.h"
extern "C" void kernel(const bfloat16* in_ptr0,
                       bool* out_ptr0)
{
    {
        #pragma omp simd simdlen(8) 
        for(long x0=static_cast<long>(0L); x0<static_cast<long>(4L); x0+=static_cast<long>(1L))
        {
            auto tmp0 = in_ptr0[static_cast<long>(x0)];
            auto tmp1 = c10::convert<float>(tmp0);
            auto tmp2 = static_cast<float>(0.2);
            auto tmp3 = tmp1 > tmp2;
            out_ptr0[static_cast<long>(x0)] = tmp3;
        }
    }
}
''')